In brief: A clinical decision support system (CDSS) is software that matches information about an individual patient with a clinical knowledge base or model and offers the clinician a patient-specific assessment or recommendation at the moment a decision is made (Berner & La Lande, 2016; Main et al., 2010). Example: when a physician prescribes a drug that interacts with one the patient already takes, a warning appears in the order screen and proposes a safer alternative. Four decades of trials show that such systems change clinicians’ actions more reliably than they change patients’ health outcomes (Biffi et al., 2026; Garg et al., 2005).
Clinical decision support systems: an introduction (101)
This guide introduces clinical decision support systems for students and practitioners of health management, nursing, medicine and pharmacy: what a CDSS is and is not, how systems are classified and studied, what the evidence says about their effects, why many are ignored, and what managers can do today. It is built on 1,067 records (723 research articles and 344 reviews) from the Web of Science Core Collection, published between 1990 and 2027, and every empirical statement is traced to one of those records. Readers who need the data layer first may start with our guide to electronic health records.
Try it yourself: Decide whether eight short scenarios describe a CDSS or not, redesign a noisy alert using the CDS Five Rights, and rate an organisation on ten readiness questions to get a profile with suggested next steps.
Open the interactive module: CDSS Lab
Learning objectives
After working through this guide, you should be able to:
- Define a CDSS and state the elements most definitions share.
- Distinguish a CDSS from order entry, the EHR, paper decision rules, patient decision aids and stand-alone AI models.
- Classify a system by knowledge source, delivery mode, autonomy and architecture.
- Appraise CDSS evidence by separating process from patient outcomes and spotting measurement problems such as reliance on override rates.
- Plan a CDSS implementation and its evaluation with a roadmap and indicators.
Key concepts
- Clinical decision support system (CDSS). A computer system intended to influence clinicians’ decisions about individual patients when those decisions are made (Berner & La Lande, 2016).
- Knowledge-based and non-knowledge-based CDSS. The first apply explicit rules and are transparent but costly to maintain; the second learn from data and can act as a black box (Kim et al., 2024).
- Active (push) and passive (pull) support. Active support appears automatically, for example as an alert; passive support waits until the user asks for it (Raynaud et al., 2023).
- Alert and override. An override is the decision to proceed without following an alert; override rates are high, and many overrides are appropriate (Nanji et al., 2014).
- Alert fatigue. Dismissal of alerts because they are excessive or irrelevant; rarely defined in a measurable way (Ancker et al., 2017; Ray et al., 2026).
- CDS Five Rights. A design principle asking whether the right information reaches the right person, in the right format, through the right channel, at the right time; used as the core principle of a pharmacogenomic CDS design guide (Wake et al., 2022).
- Sociotechnical fit. Success depends on the fit between human, organisational and technological factors, as in the HOT-fit framework (Kilsdonk et al., 2017).
- Human-in-the-loop. Keeping human expertise in the design, use and monitoring of AI-based support (Bakker et al., 2026).
Contents
- How this guide was produced
- Introduction: why CDSS matters
- History and development
- Definitions and conceptual scheme
- Distinguishing CDSS from neighbouring concepts
- Types and classifications
- Theoretical frameworks and models
- Themes and bibliometric profile
- CDSS in Türkiye
- Debates and contradictions in the literature
- Measurement problems
- Research gaps and agenda
- Implications for practice today
- Summary, discussion questions, further reading and glossary
- Frequently asked questions and references
How this guide was produced
Database and date. Web of Science Core Collection, Advanced Search, all editions, searched on 17 November 2026. No language or publication year limits were applied; document types were limited to articles and reviews.
Query (title search, verbatim). (TI=("clinical decision support*" OR CDSS OR CDSSs) OR (TI=("decision support system*" OR "computerized decision support*" OR "computerised decision support*" OR "computer-based decision support*") AND TS=(clinical OR patient* OR health* OR hospital* OR medic* OR nurs* OR physician*))) AND TI=(defin* OR concept* OR framework* OR taxonom* OR typolog* OR histor* OR evolution OR "state of the art" OR overview OR review OR adoption OR implement* OR acceptance OR usability OR "alert fatigue" OR override* OR effectiveness OR barrier* OR facilitator*) NOT TI=("deep learning" OR "neural network*" OR "prediction model*" OR algorithm*) AND DT=("Article" OR "Review")
Inclusion criteria. Studies that treat a CDSS as a system, intervention, policy object or concept: definitions, types, history, effectiveness, alerts, usability and acceptance, implementation, ethics and law, AI-based CDSS evaluation, economics and low-resource settings.
Exclusion criteria. Decision support outside health care; algorithm or model development without evaluation in practice; studies in which a CDSS stays in the background; off-topic or patient-facing tools; editorials, letters, meeting abstracts and retracted publications.
Flow. 1,260 records identified; 1 duplicate removed (1,259); 1 retracted publication removed, leaving 1,258 records screened on title and abstract; 191 excluded (128 model or algorithm development without evaluation in practice, 26 decision support outside health care, 21 off-topic or patient-facing tools, 16 CDSS only in the background); 1,067 included (723 articles, 344 reviews), published from 1990 to 2027 (2027 refers to issue dates of early-access papers).
Screening and extraction. Titles and abstracts were screened by three AI-assisted screeners working in parallel under a common protocol; 19 records marked as unsure were resolved by the lead reviewer. Evidence was then extracted from abstracts into a structured template, with the record identifier kept on every row.
Limitations. A single database was searched. The title search missed papers that mention CDSS only in the abstract or full text, and its conceptual terms favoured implementation papers. Evidence was read at abstract level, so effect sizes are reported as abstracts state them and study quality was not appraised independently. Screening was AI-assisted; the lead reviewer resolved unclear cases but did not re-screen every record.
Introduction: why CDSS matters
Picture a ward round: within an hour a physician adjusts a dose for falling kidney function, orders tests, chooses an antibiotic and reviews a frail patient’s sedative, each time drawing on scattered data and changing guidelines. CDSS were designed for this gap between what is known and what is done at the point of care. After the Institute of Medicine report To Err Is Human, CDSS became central to patient safety strategies and a requirement for meaningful use of electronic health records in the United States (Berner & La Lande, 2016), and decision support is now commonly delivered through the electronic medical record (Sutton et al., 2020).
The stakes are concrete. Inappropriate laboratory test ordering has been estimated at up to 30% (Delvaux et al., 2017). In hospitals, decision support for antibiotic prescribing improved the adequacy of antibiotic coverage (odds ratio 2.11, 13 studies) and was associated with marginally lower mortality (odds ratio 0.85, 20 studies) in a review of 81 studies (Curtis et al., 2017). Decision support also reaches beyond physicians, into community pharmacies for more than 40 years (Moon et al., 2024) and into nursing (Lopez et al., 2017).
Yet the literature records a persistent puzzle. Practitioner performance improved in 64% of controlled trials by 2004 (Garg et al., 2005), but many systems are little used despite demonstrated benefits (Kaplan, 2001), strong evidence has not led to wide use outside a few sites (Wright & Sittig, 2008), and pooled provider uptake across 55 studies was only 34.2% (Kouri et al., 2022).
History and development
Early systems. Sources disagree on when CDSS began because they count different things. One review dates their use for medication orders, documentation and adherence to the 1970s (Wingfield et al., 2024); computer-aided support for acute abdominal pain was widely tested in the 1970s and 1980s, but bulky, slow hardware held back uptake (Cooper et al., 2011); a clinical overview dates first use to the 1980s (Sutton et al., 2020). Looking at architecture, an influential model traces four phases from 1959: stand-alone systems, integration into clinical information systems, standards for sharing knowledge, and service-based models (Wright & Sittig, 2008).
A growing trial base. By March 1998 reviewers had identified 68 controlled trials, with quality improving over time (Hunt et al., 1998); by September 2004 there were 100 (Garg et al., 2005). The McMaster series added 41 drug therapy trials up to January 2010 (Hemens et al., 2011), and a 2026 update of a 2014 review of EHR-linked CDSS added 29 randomised trials from searches up to January 2023 (Biffi et al., 2026).
The EHR era. As records went digital, decision support moved into order entry. In one health system, imaging order entry with decision support was phased in between 2000 and 2010, and adoption rose from 0.5% to 94.6% (Ip et al., 2012). In paediatric care, decision support evolved from static to dynamic alerts as electronic data accumulated (Wang et al., 2020), and the smartphone, introduced in 2007, opened a channel for decision-support apps (Watson et al., 2019).
The data-driven turn. Machine learning renewed interest in CDSS (Mahadevaiah et al., 2020). Mental health and addiction systems shifted from knowledge-based models before 2017 to data-driven models after 2017 (Tai et al., 2024), and drug decision support moved from rule-based engines towards probabilistic and neural hybrids (Bello et al., 2026). The turn is partial: 78.6% of 220 cancer symptom systems were still rule-based (Chi et al., 2026). In Türkiye, a nationwide Disease Management Platform with CDS services has operated in family medicine since January 2020 (Ulgu et al., 2024).
Definitions and conceptual scheme
There is no single agreed definition. The table paraphrases ten definitions from different disciplines and decades; the last column names the dimension each puts in the foreground.
| Source | Year | Discipline | Definition (paraphrased) | Emphasised dimension |
|---|---|---|---|---|
| Main et al., 2010 | 2010 | Health technology assessment | Information systems that match an individual patient’s characteristics to a computerised knowledge base, with algorithms that generate patient-specific recommendations | Patient-specific recommendation |
| Haynes & Wilczynski, 2010 | 2010 | Clinical epidemiology | Information technology systems designed to improve clinical decision-making, which should be rigorously evaluated before widespread use | Decision improvement, with evaluation built in |
| Kesselheim et al., 2011 | 2011 | Health law and policy | Interactive computer systems that help doctors make clinical choices, such as real-time alerts about possible adverse drug reactions | Real-time alerting |
| Berner & La Lande, 2016 | 2016 | Medical informatics | Computer systems intended to influence clinicians’ decisions about individual patients at the moment those decisions are made | Point-of-decision timing |
| Sutton et al., 2020 | 2020 | Clinical informatics | Computerised systems that augment clinicians in complex decisions, now delivered mostly through electronic medical records and workflows | Augmentation of clinicians |
| Papadopoulos et al., 2022 | 2022 | Health informatics and software engineering | A technology platform that combines medical knowledge with clinical data to produce tailored advice for one patient, using rules and inference engines | Knowledge representation and rule inference |
| Chien et al., 2022 | 2022 | Medical informatics and bibliometrics | A system that informs or generates medical recommendations for practitioners, most often through alerts | Delivery through alerts |
| Khan et al., 2023 | 2023 | Diagnostic informatics | Systems that simulate human cognitive reasoning to reach valid diagnostic conclusions and improve care | Simulation of clinical reasoning |
| He et al., 2024 | 2024 | Primary care | Interventions that support clinical decisions by combining targeted medical knowledge with information about the patient | Knowledge plus patient data |
| Nielsen et al., 2026 | 2026 | Infectious disease and public health | Computerised tools that analyse data to guide action and inform decisions, including early warning, detection and prevention | Action at clinical, population and system levels |
The common core. Read side by side, the definitions share five elements: a CDSS is (1) computer-based, (2) takes data about a specific patient, (3) applies clinical knowledge or a model, (4) returns an assessment or recommendation rather than raw information, and (5) addresses a clinician close to the moment of decision. These elements echo the four features that predicted improved practice in 70 randomised trials: automatic provision in the workflow, recommendations rather than assessments alone, support at the time and place of decision, and computer-based delivery (Kawamoto et al., 2005).
Points of divergence. Definitions differ on the role of the system, supporting the clinician (Sutton et al., 2020) or simulating clinical reasoning (Khan et al., 2023); on the channel, with some treating alerts as the typical form (Kesselheim et al., 2011) although alerts are only one of many intervention types (Standiford et al., 2022); on the unit, a software platform (Papadopoulos et al., 2022) or a complex intervention (Reese et al., 2022); on the level of action, individual patients or whole populations and systems (Nielsen et al., 2026); and, for AI, on the place of human oversight (Bakker et al., 2026). Figure 3 summarises the scheme.
Distinguishing CDSS from neighbouring concepts
The key test is simple: does the tool apply clinical knowledge or a model to data about a specific patient and return patient-specific advice to the person deciding? The table compares CDSS with seven neighbours.
| Concept | What it is | Relation to CDSS |
|---|---|---|
| Computerised provider order entry (CPOE) | Electronic entry of prescriptions, tests and other orders by clinicians | Medication CDS is often delivered within CPOE. Basic checks cover drug allergies, basic dosing, formulary, duplicate therapy and drug interactions; advanced checks cover renal and geriatric dosing, laboratory monitoring, pregnancy and drug-disease contraindications (Kuperman et al., 2007). Order entry without rules is not a CDSS, and reviews analyse the two separately (Kaushal et al., 2003). |
| Electronic health record (EHR) | The longitudinal record of a patient’s care | The EHR supplies data and is the main delivery platform, yet among 45 primary care CDSSs only 63% were partially or fully EHR-integrated and 44% required double data entry (Raynaud et al., 2023). |
| Clinical guidelines and decision rules | Recommendations or scores that clinicians apply themselves, on paper or from memory | They provide the knowledge content; layered frameworks turn narrative guideline text into executable, portable rules (Boxwala et al., 2011), yet the scientific basis of CDSS recommendations is often not stated (Newroz et al., 2026). |
| Patient decision aids | Tools that help patients weigh options in line with their values | The user is the patient, so patient-facing tools were excluded from this corpus; among knee osteoarthritis decision aids, fewer than half included personalised information about non-surgical alternatives (Cochrane et al., 2026). |
| AI diagnostic or prediction models | Algorithms that estimate a diagnosis or risk from data | A model becomes a CDSS only when it is embedded in care and used by clinicians. Reviewers argue that the supported human decision, not the model output alone, should be the end point (Vasey et al., 2021); only 2.9% of explainable AI CDSS studies reported real-world deployment (Zandkarimi & Ghorbanzadeh, 2027). |
| Health information exchange (HIE) | Infrastructure that moves patient data between organisations | HIE feeds CDSS with data but gives no advice; fragmented patient data and terminology problems have long limited CDS (Wright & Sittig, 2008). |
| Medical consultation platforms | Services that answer general medical questions | They offer general medical information, whereas CDSS give recommendations integrated into the clinical workflow (Rosati et al., 2026). |
Types and classifications
CDSS can be sorted along several independent axes, so one sepsis alert can be knowledge-based, active, interruptive, assistive and EHR-integrated at once.
| Axis | Main categories | What the corpus shows |
|---|---|---|
| Knowledge source | Knowledge-based (rules, ontologies, guidelines); non-knowledge-based (machine learning); hybrid; explainable AI-based | Knowledge-based systems still dominate: 76% of 58 diabetes systems (Huang et al., 2023) and 72% of implemented inpatient algorithms (Varghese et al., 2018) were rule-based or knowledge-based. |
| Initiation and mode | Active (push, system-initiated) or passive (pull, user-initiated); interruptive or non-interruptive | Among 45 primary care systems, 64% were passive, 75% non-interruptive and 98% worked in pull mode (Raynaud et al., 2023). |
| Style of advice | Critiquing (comments on a decision already made) or consultative (advises before the decision) | In trials, an impact was found in 71% of studies of critiquing systems and 47% of studies of consultative systems (Sintchenko et al., 2007). |
| Intervention type | Alerts and reminders, order sets, documentation templates, data displays, guideline and protocol support, reference information | A Delphi study listed 53 front-end CDS tools; all appeared in at least one EHR but only 8 in all, with medication dosing support and order facilitators most common (Wright et al., 2011). |
| Function | Alert, monitoring, recommendation, prediction; detection or prediction; diagnosis or treatment | In sepsis, 62% of articles addressed detection and 33% prediction (Wulff et al., 2019). |
| Degree of autonomy | Assistive (clinician confirms) to autonomous; stages of automation | A three-level classification is based on how tasks are divided between clinician and system (Susanto et al., 2023). |
| Architecture | Stand-alone; integrated (for example best practice alerts); service-oriented (SMART, CDS Hooks) | Malfunctions occur across all three architectures; a review added organisational policy, hardware error and data source as new causes (Thayer et al., 2024). |
| Data acquisition | Manual, hybrid, automated | Manual systems impose high data-entry burden; hybrid systems balance efficiency and oversight; automated systems give real-time support through EHR integration (Castellano et al., 2026). |
Knowledge-based versus data-driven systems. This is the most debated axis. Knowledge acquisition has long been the bottleneck for knowledge-based CDSS (Zolhavarieh et al., 2017), and ontologies have not been used to manage or reuse CDSS rules (Jing et al., 2023). Data-driven systems avoid hand-coding but raise problems of opacity and validation, discussed below. In practice the categories blur: cancer symptom systems were 78.6% rule-based, 15.0% machine learning and 3.2% hybrid (Chi et al., 2026).
Theoretical frameworks and models
Four families of theory appear in the corpus, each answering a different question.
| Family | Frameworks | Typical question | Example from the corpus |
|---|---|---|---|
| Individual acceptance | Technology Acceptance Model (TAM), Unified Theory of Acceptance and Use of Technology (UTAUT), task-technology fit | Will clinicians intend to use the system? | A meta-analysis of 17 studies supported UTAUT for intention to use AI-CDSS, with trust among the strongest predictors (Dingel et al., 2024). |
| Sociotechnical fit | HOT-fit, NASSS, DeLone and McLean information systems success model | Do people, organisation and technology fit, and what counts as success? | NASSS mapping of 227 barriers and 130 facilitators found none in the domain of embedding and adaptation over time (Abell et al., 2023). |
| Implementation science | CFIR, Theoretical Domains Framework, Behaviour Change Wheel, ERIC strategies, Proctor outcomes, RE-AIM | Which determinants and strategies matter, and how is implementation success judged? | Antimicrobial stewardship CDSS studies used a median of 11 of 73 ERIC strategies (Giordano et al., 2026). |
| Design principles | Critical success features, CDS Five Rights, interface-information-interaction framework, MINDSPACE | How should advice be built and delivered? | Systems with all four critical features improved practice in 30 of 32 cases (94%) (Kawamoto et al., 2005). |
Acceptance models. TAM was the most frequent baseline among 15 frameworks in one synthesis (Khong et al., 2015). Performance and effort expectancy predicted intention to use in one field study (Chang et al., 2007), and interviews with general practitioners pointed to usefulness, facilitating conditions, ease of use and trust (Shibl et al., 2013); but social influence did not matter in one study (Jeng & Tzeng, 2012), and perceived threat to professional autonomy predicted adoption intention among Malaysian physicians (Esmaeilzadeh et al., 2015).
Sociotechnical frameworks. HOT-fit mapping of 421 factors showed that research concentrated on human and technology factors and neglected organisational ones (Kilsdonk et al., 2017); in primary care, human and organisational factors acted against use, technology was neutral and net benefits supported use (Meunier et al., 2023). The DeLone and McLean model showed that “net benefit” dominated CDSS success measures while other dimensions were rarely measured (Ji et al., 2021).
Implementation science. CFIR has organised pre-implementation determinants in hospitals (Bonakdeh et al., 2025), and in real-world AI-CDSS studies barriers clustered in the inner setting, the innovation and individuals (Bogner et al., 2026). Integrative frameworks such as BEAR, which merges TDF, CFIR, HOT-fit and UTAUT into 22 domains (Camacho et al., 2020), and GUIDE-CDSS, with 8 determinants and 38 elements from 23 reviews (Janssen et al., 2026), try to bridge behaviour change and technology acceptance.
How much theory is actually used? Less than these lists suggest. Only 1 of 33 home blood pressure CDSS studies used a theoretical framework (Moosa et al., 2025), no comparative effectiveness trials of CDS used causal pathways (Reese et al., 2022), and 86% of studies applying implementation theories did not report the limitations of their chosen approach (Fernando et al., 2023).
Themes and bibliometric profile
Growth and sources. Only 24 of the 1,067 records appeared up to 2004; output passed 100 a year in 2023 and reached 140 in 2026 (Figure 5). The leading journals are the Journal of the American Medical Informatics Association (71 records), BMC Medical Informatics and Decision Making (54), Applied Clinical Informatics (49), the International Journal of Medical Informatics (48), the Journal of Medical Internet Research (34), JMIR Medical Informatics (27) and Implementation Science (26). By author affiliation, the United States leads with 440 records, followed by England (117), Australia (98), Canada (83), the Netherlands (70), Germany (62) and China (55). AI arrived late: no record mentioned AI, machine learning or large language models up to 2009, against 90 of 437 in 2020 to 2024 and 122 of 264 in 2025 to 2027.
Themes. Figure 6 shows the primary theme of each record; diagnosis, chronic disease and nursing are more common as secondary themes.
Effectiveness: processes move, outcomes rarely do. The most stable finding in four decades of reviews is a gap between process and patient outcomes.
| Review | Domain | Process or practitioner performance improved | Patient outcomes improved |
|---|---|---|---|
| Hunt et al., 1998 | All controlled trials to 1998 | 43 of 65 studies (66%) | 6 of 14 studies |
| Garg et al., 2005 | All controlled trials to 2004 | 62 of 97 studies (64%) | 7 of 52 trials (13%) |
| Jaspers et al., 2011 | 17 high-quality systematic reviews | 52 of 91 studies (57%) | 25 of 82 studies (30%) |
| Hemens et al., 2011 | Drug prescribing and management | 37 of 59 (64%) | 6 of 29 (21%) |
| Sahota et al., 2011 | Acute care | 22 of 35 (63%) | 3 of 20 (15%) |
| Souza et al., 2011 | Primary preventive care | 25 of 40 (63%) | 4 of 14 (29%) |
| Jia et al., 2016 | Medication safety (20 reviews) | 108 of 143 (75%) | 18 of 90 (20%) |
| Mebrahtu et al., 2021 | Nurses and allied health professionals | 47% of care process measures | 40.7% of patient outcome measures |
Pooled analyses confirm the shape. Across 148 randomised trials, CDSS improved process measures for performing preventive services (odds ratio 1.42, 25 trials), ordering clinical studies (1.72, 20 trials) and prescribing therapies (1.57, 46 trials) (Bright et al., 2012). For EHR-linked CDSS, the 2026 meta-analysis of 47 trials found little to no effect on mortality (risk ratio 0.98, moderate certainty) and a small reduction in morbidity (about 0.92 to 0.93, high certainty) (Biffi et al., 2026). Null results are common in chronic disease: cluster trials in 29 health centres found no clinically significant effect on hypertension or diabetes outcomes (Hetlevik et al., 1999; Hetlevik et al., 2000), and in a review of ten studies (16,312 participants in total), the five that reported blood pressure gave a pooled systolic difference of an insignificant 0.99 mmHg (Anchala et al., 2012).
Medication safety. CDS reliably reduces prescribing errors but less reliably prevents harm. CPOE with CDS reduced prescribing errors without clearly preventing clinical adverse drug events (Ranji et al., 2014); in intensive care, commercial order entry was associated with 85% fewer prescribing errors and 12% lower ICU mortality, but not with shorter stays or lower hospital mortality (Prgomet et al., 2017). In primary and long-term care, 9 of 15 studies with a process primary outcome showed a significant effect, against 1 of 5 with a harm primary outcome (Lampe et al., 2024). In medication review, a hybrid human and machine learning approach detected 94% of severe drug-related problems against 20% for a conventional CDSS (Levivien et al., 2022).
Alerts, overrides and alert fatigue. Only 1.4% of non-interruptive interaction alerts were accepted in one study (Seidling et al., 2011). Overrides are not always errors: of 157,483 alerts, 52.6% were overridden and 53% of overrides were appropriate, from 12% for renal alerts to 92% for allergy alerts (Nanji et al., 2014); a later study found about 60% appropriate overall but only 2.2% for renal alerts (Nanji et al., 2018). Reminder acceptance fell 30% for each additional reminder per encounter (Ancker et al., 2017). Five of 8 published hospital alert governance processes reported lower alert rates (Van Dort et al., 2021).
Implementation, barriers and facilitators. In 44 hospital publications the most commonly reported influences on implementation were workflow fit, usefulness of the output, technical dependencies and design, trust in input data and evidence, and contextual fit (Abell et al., 2023). Increased workload was the greatest barrier in primary care (Meunier et al., 2023), and lack of usefulness and poor ease of use led for medication CDSS (Westerbeek et al., 2021). Effective interventions for older inpatients more often began with an a priori problem analysis (69% versus 0%) (Damoiseaux-Volman et al., 2021). CDSS can be experienced as a threat or as empowerment, depending on status and expertise (Ackerhans et al., 2024).
Usability, acceptance and trust. Near-live simulation revealed workflow barriers that think-aloud testing missed (Richardson et al., 2017). User satisfaction remains understudied (Hardenbol et al., 2020; Knols et al., 2020).
AI, machine learning and large language models. Of 68 explainable AI CDSS studies, 25.0% reported external validation, 92.6% were research prototypes and 2.9% reached real-world deployment (Zandkarimi & Ghorbanzadeh, 2027). When ML diagnostic systems aided clinicians, 50% of results improved, 4% worsened and 46% did not change, with no association in representative clinical settings (Vasey et al., 2021). Five randomised trials showed a small gain in diagnostic accuracy (standardised mean difference 0.182, moderate certainty) (Jeong & Kim, 2026), while in teleconsultation an LLM gave no significant benefit (Srada et al., 2026). Across 12 human-in-the-loop studies none reported oversight during use (Bakker et al., 2026).
Smaller strands. Diagnostic aids have been the weak point: 1 of 5 improved performance by 1998 (Hunt et al., 1998) and 4 of 10 by 2004 (Garg et al., 2005). Nurse-targeted CDS lags medical CDS in volume and level of evidence (Lopez et al., 2017), and gains in nursing compliance and decision time were not always sustained (Akbar et al., 2021).
CDSS in Türkiye
Ten included records have at least one Turkish-affiliated author. Only two describe a CDSS used in a Turkish setting; the rest are reviews, methods papers or international projects.
- A national platform. The Ministry of Health’s Disease Management Platform has offered CDS services in family medicine since January 2020. By September 2023 it had been used by 25,568 professionals in 73,715,269 encounters covering 16,058,904 citizens, and the authors report 3,545,573 obesity, 534,423 high cardiovascular risk, 490,346 diabetes and 144,768 hypertension cases diagnosed through it. Named challenges were interoperability, workflow integration, transitions of care and scalability; enablers included HL7 FHIR conformance and seamless EHR integration (Ulgu et al., 2024).
- Standards-based guideline translation. Within the international CAREPATH project, a team including Turkish-affiliated authors turned 25 guidelines into 65 CDS services, 296 formally defined rules and 346 CDS cards for multimorbidity care plans, using CDS Hooks and HL7 FHIR; this is not a Turkish national deployment (Gencturk et al., 2024).
- Nursing. A CDSS developed for oncology nurses in a gynaecological oncology clinic of a Turkish university hospital was used by 14 nurses, who reported no problems and said it eased needs assessment and individual care planning (Yilmaz & Ozdemir, 2017). A Turkish-authored meta-analysis of five randomised trials (1,880 participants; trial settings not stated in the abstract) found that decision support systems reduced pain severity in patients with cancer (Hedges’ g 0.22) (Sezgin & Bektas, 2022).
- Methods and AI. Other records reviewed usability methods (Cubukcu & Canbaz, 2025), tested five LLM-based systems and found substantial variability in safety, including some potentially harmful advice (Karatas & Öner, 2026), reviewed Alzheimer’s disease decision support, where external validation was lacking (Günaydin & Varli, 2025), and described rare disease CDSS paradigms (Özçetin et al., 2026). Two are multinational studies with Turkish co-authors (Barwise et al., 2016; Ploegmakers et al., 2022).
What is missing. No study in the corpus evaluates the effect of a Turkish CDSS, national or local, on clinicians’ behaviour, patient outcomes or costs; the national platform is described by reach and diagnosed cases, not controlled outcomes. No Turkish alert override data, economic evaluation or randomised trial was found. The search had no language limit and covered all Web of Science editions, but Turkish journals not indexed there (for example in TR Dizin) were not searched and may hold further work. The gap fits a wider pattern: only 7 of 60 machine learning CDSS in infectious diseases used data from low- and middle-income countries (Peiffer-Smadja et al., 2020), and only one of 28 antimicrobial CDSS was developed in one (Bienvenu et al., 2025).
Debates and contradictions in the literature
The table places opposing positions side by side on six axes.
| Axis | Position A | Position B |
|---|---|---|
| Do CDSS improve patient outcomes? | Yes: 61% of studies reported positive patient outcomes and none negative (Kruse & Ehrbar, 2020); a mixed-design meta-analysis linked AKI decision support to lower mortality (odds ratio 0.86) (Zhao et al., 2021). | Rarely: EHR-linked CDSS have little to no effect on mortality (Biffi et al., 2026); a meta-analysis restricted to randomised trials found no mortality benefit for AKI decision support (risk ratio 1.00) (Altobaishat et al., 2024); higher-quality controlled studies report fewer positive effects (O’Neill et al., 2025). |
| Should support be pushed or pulled? | Push: automatically prompting systems succeeded in 73% of trials against 47% for user-activated systems (Garg et al., 2005), and automatic support improves adherence more than on-demand support (Van de Velde et al., 2018). | Pull or choice: in antibiotic stewardship, passive provider-initiated CDSS showed more significant outcomes (Rittmann & Stevens, 2019); a cluster crossover trial found no difference in 30-day mortality between voluntary and compulsory CDSS (hazard ratio 0.87) (Heng et al., 2020). |
| What drives alert fatigue, and must alerts stay for legal safety? | Excessive warnings cause users to ignore vital alerts, and vendors limit alert changes for fear of liability (Kesselheim et al., 2011). | Evidence points to cognitive overload from complexity and repeated alerts rather than desensitisation (Ancker et al., 2017); legal analysis finds that more parsimonious warnings would not carry high litigation risk (Kesselheim et al., 2011). |
| Fewer errors or new errors? | CPOE with CDS reduced paediatric dose errors in 8 studies, and no study reported an increase (Ruutiainen et al., 2024). | Order entry with CDS introduces new error types (Vélez-Díaz-Pallarés et al., 2018), and AI-CDSS bring new risks such as algorithmic bias and reduced vigilance (Alruwaili et al., 2026). |
| Does evidence travel? | Success rates were 74% when authors had developed the system and 28% when they had not (Garg et al., 2005); results should not be generalised across settings lightly (Berlin et al., 2006). | Both commercial and locally developed systems improved process measures, extending benefits beyond experienced academic centres (Bright et al., 2012). |
| Is accuracy, or explanation, the answer for AI? | Explainable AI may increase trust and prevent under- or over-reliance (Antoniadi et al., 2021; Kim et al., 2024). | Accuracy is no longer the main bottleneck, and post-hoc explanations may create an illusion of clarity (Pranata et al., 2026); clinicians find SHAP plots hard to interpret and prefer concise, high-level explanations (Van Dort et al., 2026). |
Many contradictions shrink once design, setting and outcome are explicit. For AKI, the review that pooled observational studies with trials found a mortality benefit that the trial-only review did not (Altobaishat et al., 2024; Zhao et al., 2021), and newer inpatient systems outperformed older ones (risk difference 0.07 for 2016 to 2021 against minus 0.01 for 2010 to 2015) (Ronan et al., 2022). Even a disregarded AI prediction may add value by prompting clinicians to reassess their judgement (Parsons et al., 2025).
Measurement problems
Many disagreements are measurement problems in disguise.
- Unvalidated measures. Of 391 CDSS evaluation studies, 72% showed no evidence of attention to measurement methodology, 8% gave validity evidence and 12% reliability evidence; ignoring measurement methodology can make effect sizes misleading (Scott et al., 2019).
- The override rate trap. A consensus of 24 experts concluded that override rates may not be a good measure of interaction alert effectiveness (Payne et al., 2015). Across 22 systematic reviews, 1 to 11 alert metrics were reported, the most common being alert quantity, override rate and acceptance rate, and only one review defined alert fatigue operationally (Ray et al., 2026).
- Missing exposure and outcome data. Uptake was reported in only 12.4% of eligible studies (Kouri et al., 2022). In medication safety, no study measured process, harm and cost outcomes together (Lampe et al., 2024); in preventive care trials, costs were reported in 15% and adverse events in 5% (Souza et al., 2011); and only 6% of surgical CDS systems reported equity analyses (Ingraham et al., 2023).
- Co-interventions and design. In adult sepsis, 54.8% of CDS implementations came with other interventions (Ackermann et al., 2022), and when CDSS arrive together with new protocols their own success factors cannot be identified (Eslami et al., 2009).
- Reporting and AI metrics. Among 32 randomised trials of clinical decision support, 34% lacked a sample size calculation and 62% did not report adverse events (Augestad et al., 2012), and all 23 reviews in a recent overview had at least two critical weaknesses on AMSTAR 2 (Janssen et al., 2026). In point-of-care imaging AI no study measured patient outcomes (Wadie et al., 2026), and for medication review CDSS the positive predictive value for actual events ranged from 5% to 80% (Damoiseaux-Volman et al., 2022).
Research gaps and agenda
Each question below comes from a gap stated in the corpus.
- Which CDSS features change patient outcomes, not only processes, in pragmatic multi-site trials? Gap: patient outcomes have been understudied since 1998 (Hunt et al., 1998; Ji et al., 2021).
- How can alert fatigue be defined and measured validly, so that alert redesign can be compared across hospitals? Gap: the concept is poorly defined and governance evaluations are rarely published (Ancker et al., 2017; Van Dort et al., 2021).
- What does a CDSS cost to build, run and maintain, and when is it cost-effective? Gap: cost-effectiveness studies are remarkably scarce and standard cost metrics are missing (Fillmore et al., 2013; Jacob et al., 2017).
- How do CDSS for nurses, pharmacists and allied professionals affect their work and their patients? Gap: better quality evaluative research remains pressing after more than 13 years of synthesis, and little is known about implementation in community pharmacy (Curtain & Peterson, 2014; Mebrahtu et al., 2021).
- How should clinicians oversee AI-CDSS during routine use, and how does reliance change over time? Gap: human factors evaluation is needed before deployment, and oversight during use is unreported (Bakker et al., 2026; Vasey et al., 2021).
- Do CDSS designs and effects transfer to health systems outside the high-income countries where most studies were done, including Türkiye, and do they reduce or widen inequities? Gap: evidence from less digitally developed systems is limited, implementation studies come from high-income countries, and equity is seldom evaluated (Bonakdeh et al., 2025; Giordano et al., 2026; Ingraham et al., 2023).
- What keeps a CDSS effective after go-live? Gap: no COPD CDS study reported maintenance strategies, and none of eight longitudinal CDS used living guidelines (Bamgboje-Ayodele et al., 2023; Loftus et al., 2024).
- Do theory-informed implementation strategies produce better adoption than ad hoc ones? Gap: implementation theories, models and frameworks are rarely combined across the full hospital implementation cycle (Fernando et al., 2023).
Implications for practice today
A roadmap for managers:
- Start with the problem. Define the clinical decision to improve and measure the baseline; effective interventions far more often began with an a priori problem analysis (Damoiseaux-Volman et al., 2021).
- Set up governance. Create a multidisciplinary committee that uses clinician feedback, alert data, literature and a visual dashboard (Van Dort et al., 2021).
- Choose and maintain the content. State the evidence behind each rule, which is often left unstated (Newroz et al., 2026), and plan updates; guideline maintenance and the validity of recommendations are frequent barriers (Hendriks et al., 2024).
- Design for the workflow and test with users. Deliver advice automatically at the time and place of decision (Kawamoto et al., 2005) and test it in near-live conditions (Richardson et al., 2017).
- Budget the alerts. Review override appropriateness by alert type, not only override rates, and retire low-value alerts (Nanji et al., 2014; Payne et al., 2015).
- Support the people. Provide training and follow-up, clinical champions, allocated personnel and technical support (Chen et al., 2022).
- Evaluate more than use. Track uptake, processes, harms, costs and equity together (Ingraham et al., 2023; Kouri et al., 2022; Lampe et al., 2024).
- Govern AI separately. Require external validation, drift monitoring and a defined human role (Bakker et al., 2026; Saleem et al., 2026).
Indicators worth tracking:
| Area | Indicator | Why it matters |
|---|---|---|
| Use | Share of eligible encounters in which the CDSS was used or its advice viewed | Uptake averages about one third and is rarely reported (Kouri et al., 2022) |
| Alert burden | Alerts per 100 orders; repeated alerts per encounter | Each additional reminder per encounter lowers acceptance (Ancker et al., 2017) |
| Alert quality | Override rate with appropriateness of overrides by alert type; positive predictive value | Appropriateness varies from 12% to 92% by alert type (Nanji et al., 2014) |
| Process | Adherence to the targeted recommendation | Processes are where CDSS effects are most consistent (Bright et al., 2012) |
| Safety | Adverse drug events; new error types; malfunctions detected | Process gains do not guarantee less harm (Lampe et al., 2024) |
| Cost | Implementation and maintenance cost, including staff time | Labour was the largest implementation cost (Donovan et al., 2023) |
| Equity | Process and outcome indicators by patient subgroup | CDS may widen disparities for underrepresented populations (Ingraham et al., 2023) |
| AI-CDSS | External validation status; performance drift; clinician agreement and override of AI outputs | Reliance on AI outputs has not been reported in primary care studies (Naye et al., 2026) |
Summary
- A CDSS applies knowledge or a model to a specific patient’s data and advises the clinician at the point of decision; definitions differ on role, channel, unit and level.
- Systems are classified by knowledge source, delivery mode, intervention type, autonomy and architecture; knowledge-based systems still dominate.
- CDSS improve care processes in roughly half to three quarters of studies but patient outcomes in far fewer; EHR-linked systems show little to no effect on mortality.
- High override rates, many of them appropriate, show that alert design and governance matter as much as alert content.
- Workflow fit, usefulness, trust, workload and autonomy decide use; average uptake is about one third.
- AI-based CDSS are growing fast, but very few have reached real-world deployment, external validation or patient outcome evaluation.
- Türkiye has a national CDS platform, but no evaluation of its effects on outcomes was found in the corpus.
Discussion questions
- Why do CDSS change clinicians’ actions more often than they change patients’ outcomes? Name at least two explanations from this guide.
- Is a paper sepsis screening score a CDSS? Is a machine learning model that predicts sepsis but is not connected to the EHR? Justify your answers with the common core of the definitions.
- Applied: your hospital’s drug interaction alert is overridden in most cases. Using the evidence on appropriate overrides and alert metrics, what would you measure before deciding to switch it off?
- Applied: a family health centre in Türkiye wants to evaluate the CDS services of the national Disease Management Platform. Draft a study design, choosing outcomes, comparison and data sources.
- When is a passive, on-demand system preferable to an automatic, interruptive one? Use the push versus pull debate.
- Which responsibilities should remain with the clinician when an AI-CDSS gives advice, and how should oversight be documented?
Further reading
- Berner and La Lande (2016): a concise textbook overview of CDSS and their role in patient safety.
- Garg et al. (2005): the classic review that established the gap between practitioner performance and patient outcomes.
- Kawamoto et al. (2005): the review of 70 trials that identified four features independently linked to improved clinical practice.
- Wright and Sittig (2008): a short history of CDS architectures and their limitations.
- Biffi et al. (2026): the most recent meta-analysis of randomised trials of EHR-linked CDSS, with certainty ratings for mortality and morbidity.
- Abell et al. (2023): a clear synthesis of hospital barriers and facilitators mapped to the NASSS framework.
- Ancker et al. (2017): an empirical test of what alert fatigue actually is, with data on repeated alerts and reminders.
- Vasey et al. (2021): a sober review of machine learning diagnostic CDSS used alongside clinicians, showing why accuracy is not enough.
Glossary
| Term | Turkish | Short definition |
|---|---|---|
| Clinical decision support system (CDSS) | Klinik karar destek sistemi (KKDS) | Software that gives clinicians patient-specific advice by applying knowledge or a model to patient data |
| Knowledge base | Bilgi tabanı | The stored rules, guidelines or facts that a knowledge-based CDSS applies |
| Computerised provider order entry (CPOE) | Bilgisayarlı hekim istem girişi | Electronic entry of orders by clinicians; the usual host of medication CDS |
| Interruptive alert | Kesintiye uğratan (araya giren) uyarı | An alert that stops the user’s workflow until it is acknowledged |
| Override | Uyarıyı geçersiz kılma | The decision to continue without following an alert |
| Alert fatigue | Uyarı yorgunluğu | Declining response to alerts because they are too many, repeated or irrelevant |
| Positive predictive value (PPV) | Pozitif kestirim değeri | The share of alerts or flags that correspond to a real problem |
| Interoperability | Birlikte çalışabilirlik | The ability of systems to exchange data and use it with shared meaning |
| Explainable AI (XAI) | Açıklanabilir yapay zekâ | Methods that show users why an AI model produced a given output |
| Human-in-the-loop | Döngüde insan | Keeping human judgement and oversight within the design and use of AI systems |
Frequently asked questions
What is a clinical decision support system? A computer system that uses data about a specific patient and a clinical knowledge base or model to give clinicians an assessment or recommendation when they make a decision.
Is a CDSS the same as an EHR? No. The EHR stores the record; a CDSS reasons over the data and gives advice, usually from inside the EHR.
Do CDSS improve patient outcomes? Sometimes. They improve processes such as prescribing fairly consistently, but trial effects on mortality are small or absent, and on morbidity small.
Why do clinicians override so many alerts? Many alerts are repeated, low in severity or irrelevant to the patient, and many overrides are clinically appropriate.
Is an AI model a CDSS? Only when it is embedded in care and used by clinicians for decisions; most AI models in the literature are still undeployed prototypes.
Related on this site: Electronic health records: an introduction (101) · Clinical decision support system (glossary) · Medication reconciliation: an introduction (101) · Antimicrobial stewardship in hospitals: an introduction (101)
References
- Abell, B., Naicker, S., Rodwell, D., Donovan, T., Tariq, A., Baysari, M., Blythe, R., Parsons, R., & McPhail, S. M. (2023). Identifying barriers and facilitators to successful implementation of computerized clinical decision support systems in hospitals: a NASSS framework-informed scoping review. Implementation Science, 18(1), 32. https://doi.org/10.1186/s13012-023-01287-y
- Ackerhans, S., Huynh, T., Kaiser, C., & Schultz, C. (2024). Exploring the role of professional identity in the implementation of clinical decision support systems: A narrative review. Implementation Science, 19(1), 11. https://doi.org/10.1186/s13012-024-01339-x
- Ackermann, K., Baker, J., Green, M., Fullick, M., Varinli, H., Westbrook, J., & Li, L. (2022). Computerized Clinical Decision Support Systems for the Early Detection of Sepsis Among Adult Inpatients: Scoping Review. Journal of Medical Internet Research, 24(2), e31083. https://doi.org/10.2196/31083
- Akbar, S., Lyell, D., & Magrabi, F. (2021). Automation in nursing decision support systems: A systematic review of effects on decision making, care delivery, and patient outcomes. Journal of the American Medical Informatics Association, 28(11), 2502-2513. https://doi.org/10.1093/jamia/ocab123
- Alruwaili, M. F., Paul-Chima, U. O., & Nneoma, U. C. (2026). Integrating clinical decision support systems, nursing vigilance, and physician prescribing patterns to reduce preventable adverse drug events: a structured evidence-based narrative review on human-AI interface in medication safety. Frontiers in Digital Health, 8, 1831150. https://doi.org/10.3389/fdgth.2026.1831150
- Altobaishat, O., Abouzid, M., Amin, A. M., Bani-Salameh, A., Tanashat, M., Bataineh, O. A., Turkmani, M., Abuelazm, M., & Mohamed, M. M. B. (2024). The effect of clinical decision support systems on clinical outcomes in acute kidney injury: a systematic review and meta-analysis of randomized controlled trials. Renal Failure, 46(2), 2400552. https://doi.org/10.1080/0886022X.2024.2400552
- Anchala, R., Pinto, M. P., Shroufi, A., Chowdhury, R., Sanderson, J., Johnson, L., Blanco, P., Prabhakaran, D., & Franco, O. H. (2012). The Role of Decision Support System (DSS) in Prevention of Cardiovascular Disease: A Systematic Review and Meta-Analysis. PLOS ONE, 7(10), e47064. https://doi.org/10.1371/journal.pone.0047064
- Ancker, J. S., Edwards, A., Nosal, S., Hauser, D., Mauer, E., & Kaushal, R. (2017). Effects of workload, work complexity, and repeated alerts on alert fatigue in a clinical decision support system. BMC Medical Informatics and Decision Making, 17, 36. https://doi.org/10.1186/s12911-017-0430-8
- Antoniadi, A. M., Du, Y. H., Guendouz, Y., Wei, L., Mazo, C., Becker, B. A., & Mooney, C. (2021). Current Challenges and Future Opportunities for XAI in Machine Learning-Based Clinical Decision Support Systems: A Systematic Review. Applied Sciences, 11(11), 5088. https://doi.org/10.3390/app11115088
- Augestad, K. M., Berntsen, G., Lassen, K., Bellika, J. G., Wootton, R., & Lindsetmo, R. O. (2012). Standards for reporting randomized controlled trials in medical informatics: a systematic review of CONSORT adherence in RCTs on clinical decision support. Journal of the American Medical Informatics Association, 19(1), 13-21. https://doi.org/10.1136/amiajnl-2011-000411
- Bakker, M., Van Garderen, A., Paget, T., Zhao, L. J., Naicker, L., Radhakrishnan, A., & Bidargarddi, N. (2026). Human in the loop in AI-enabled clinical decision support: a systematic scoping review and reporting checklist for lifecycle governance. International Journal of Medical Informatics, 222, 106701. https://doi.org/10.1016/j.ijmedinf.2026.106701
- Bamgboje-Ayodele, A., Borg, D. N., McPhail, S. M., & Baysari, M. T. (2023). Clinical decision support systems for chronic obstructive pulmonary disease (COPD) in hospitals: A systematic review. Digital Health, 9, 20552076231219107. https://doi.org/10.1177/20552076231219107
- Barwise, A., Garcia-Arguello, L., Dong, Y., Hulyalkar, M., Vukoja, M., Schultz, M. J., Adhikari, N. K. J., Bonneton, B., Kilickaya, O., Kashyap, R., Gajic, O., & Schmickl, C. N. (2016). Checklist for Early Recognition and Treatment of Acute Illness (CERTAIN): evolution of a content management system for point-of-care clinical decision support. BMC Medical Informatics and Decision Making, 16, 127. https://doi.org/10.1186/s12911-016-0367-3
- Bello, J., Adigun, A. A., Ozoh, P., Abolarinwa, M. O., & Adigun, I. O. (2026). Drug decision support systems: A review of challenges, advances, and emerging trends. Romanian Journal of Information Technology and Automatic Control-Revista Romana de Informatica Si Automatica, 36(2), 63-72. https://doi.org/10.33436/v36i2y202605
- Berlin, A., Sorani, M., & Sim, I. (2006). A taxonomic description of computer-based clinical decision support systems. Journal of Biomedical Informatics, 39(6), 656-667. https://doi.org/10.1016/j.jbi.2005.12.003
- Berner, E. S., & La Lande, T. J. (2016). Overview of Clinical Decision Support Systems. In E. S. Berner (Ed.), Clinical decision support systems: Theory and practice (3rd ed., pp. 1-17). Springer International Publishing. https://doi.org/10.1007/978-3-319-31913-1_1
- Bienvenu, A. L., Ducrocq, J. M., Augé-Caumon, M. J., & Baseilhac, E. (2025). Clinical decision support system to guide antimicrobial selection: a narrative review from 2019 to 2023. Journal of Hospital Infection, 162, 140-152. https://doi.org/10.1016/j.jhin.2025.05.001
- Biffi, A., Castellini, G., Del Castillo, G., De Nard, F., Vismara, C., Cabitza, F., Corrao, G., & Gianola, S. (2026). Effectiveness of computerized decision support systems linked to electronic health records: An updated systematic review with meta-analysis. International Journal of Medical Informatics, 207, 106220. https://doi.org/10.1016/j.ijmedinf.2025.106220
- Bogner, E., Thomas, A., Bajgain, B., van Rassel, C., Sauro, K., & Lee, J. (2026). Real-World Barriers to and Facilitators of Implementing AI-Based Clinical Decision Support Systems: Scoping Review. JMIR Medical Informatics, 14, e89834. https://doi.org/10.2196/89834
- Bonakdeh, E. S., Sohal, A., Moghadam, V. K., Rajabkhah, K., Prajogo, D., Melder, A., Nguyen, Q., Bingham, G., & Tong, E. R. C. (2025). The facilitating and hindering factors of pre-implementation phase in establishment of clinical decision support systems: A systematic review and meta synthesis. Health Policy and Technology, 14(3), 101014. https://doi.org/10.1016/j.hlpt.2025.101014
- Boxwala, A. A., Rocha, B. H., Maviglia, S., Kashyap, V., Meltzer, S., Kim, J., Tsurikova, R., Wright, A., Paterno, M. D., Fairbanks, A., & Middleton, B. (2011). A multi-layered framework for disseminating knowledge for computer-based decision support. Journal of the American Medical Informatics Association, 18, I132-I139. https://doi.org/10.1136/amiajnl-2011-000334
- Bright, T. J., Wong, A., Dhurjati, R., Bristow, E., Bastian, L., Coeytaux, R. R., Samsa, G., Hasselblad, V., Williams, J. W., Musty, M. D., Wing, L., Kendrick, A. S., Sanders, G. D., & Lobach, D. (2012). Effect of Clinical Decision-Support Systems: A Systematic Review. Annals of Internal Medicine, 157(1), 29. https://doi.org/10.7326/0003-4819-157-1-201207030-00450
- Camacho, J., Zanoletti-Mannello, M., Landis-Lewis, Z., Kane-Gill, S. L., & Boyce, R. D. (2020). A Conceptual Framework to Study the Implementation of Clinical Decision Support Systems (BEAR): Literature Review and Concept Mapping. Journal of Medical Internet Research, 22(8), e18388. https://doi.org/10.2196/18388
- Castellano, J., Caporlingua, M., & Ciurleo, R. (2026). Clinical decision support systems for polypharmacy optimization in older patients: a narrative review. European Journal of Clinical Pharmacology, 82(8), 211. https://doi.org/10.1007/s00228-026-04144-1
- Chang, I. C., Hwang, H. G., Hung, W. F., & Li, Y. C. (2007). Physicians’ acceptance of pharmacokinetics-based clinical decision support systems. Expert Systems with Applications, 33(2), 296-303. https://doi.org/10.1016/j.eswa.2006.05.001
- Chen, W., O’Bryan, C. M., Gorham, G., Howard, K., Balasubramanya, B., Coffey, P., Abeyaratne, A., & Cass, A. (2022). Barriers and enablers to implementing and using clinical decision support systems for chronic diseases: a qualitative systematic review and meta-aggregation. Implementation Science Communications, 3(1), 81. https://doi.org/10.1186/s43058-022-00326-x
- Chi, J., Zhong, C. H., Tang, J. Y., Guo, B. Q., Zhang, Y. J., Deng, S. S., Guo, Z. H., & Wu, Y. N. (2026). Clinical Decision Support Systems for cancer symptom management: A scoping review. International Journal of Nursing Studies, 175, 105317. https://doi.org/10.1016/j.ijnurstu.2025.105317
- Chien, S. C., Chen, Y. L., Chien, C. H., Chin, Y. P., Yoon, C. H., Chen, C. Y., Yang, H. C., & Li, Y. C. (2022). Alerts in Clinical Decision Support Systems (CDSS): A Bibliometric Review and Content Analysis. Healthcare, 10(4), 601. https://doi.org/10.3390/healthcare10040601
- Cochrane, J. A., Roberts, O., Ribbons, K., Clark, R., Pua, Y. H., Tan, T. L., Thwin, L., Leung, Y. Y., Liow, M. H. L., Tan, B. Y., & Nilsson, M. (2026). Implementation of clinical decision support tools for treatment selection in knee osteoarthritis: a scoping review. Therapeutic Advances in Musculoskeletal Disease, 18, 1759720X251407070. https://doi.org/10.1177/1759720X251407070
- Cooper, J. G., West, R. M., Clamp, S. E., & Hassan, T. B. (2011). Does computer-aided clinical decision support improve the management of acute abdominal pain? A systematic review. Emergency Medicine Journal, 28(7), 553-557. https://doi.org/10.1136/emj.2009.086801
- Cubukcu, H. C., & Canbaz, H. (2025). Usability assessments in clinical decision support systems. Northern Clinics of Istanbul, 12(3). https://doi.org/10.14744/nci.2024.22316
- Curtain, C., & Peterson, G. M. (2014). Review of computerized clinical decision support in community pharmacy. Journal of Clinical Pharmacy and Therapeutics, 39(4), 343-348. https://doi.org/10.1111/jcpt.12168
- Curtis, C. E., Al Bahar, F., & Marriott, J. F. (2017). The effectiveness of computerised decision support on antibiotic use in hospitals: A systematic review. PLOS ONE, 12(8), e0183062. https://doi.org/10.1371/journal.pone.0183062
- Damoiseaux-Volman, B. A., Medlock, S., van der Meulen, D. M., de Boer, J., Romijn, J. A., van der Velde, N., & Abu-Hanna, A. (2022). Clinical validation of clinical decision support systems for medication review: A scoping review. British Journal of Clinical Pharmacology, 88(5), 2035-2051. https://doi.org/10.1111/bcp.15160
- Damoiseaux-Volman, B. A., van der Velde, N., Ruige, S. G., Romijn, J. A., Abu-Hanna, A., & Medlock, S. (2021). Effect of Interventions With a Clinical Decision Support System for Hospitalized Older Patients: Systematic Review Mapping Implementation and Design Factors. JMIR Medical Informatics, 9(7), e28023. https://doi.org/10.2196/28023
- Delvaux, N., Van Thienen, K., Heselmans, A., Van de Velde, S., Ramaekers, D., & Aertgeerts, B. (2017). The Effects of Computerized Clinical Decision Support Systems on Laboratory Test Ordering: Systematic Review. Archives of Pathology & Laboratory Medicine, 141(4), 585-595. https://doi.org/10.5858/arpa.2016-0115-RA
- Dingel, J., Kleine, A. K., Cecil, J., Sig, A. L., Lermer, E., & Gaube, S. (2024). Predictors of Health Care Practitioners’ Intention to Use AI-Enabled Clinical Decision Support Systems: Meta-Analysis Based on the Unified Theory of Acceptance and Use of Technology. Journal of Medical Internet Research, 26, e57224. https://doi.org/10.2196/57224
- Donovan, T., Abell, B., Fernando, M., McPhail, S. M., & Carter, H. E. (2023). Implementation costs of hospital-based computerised decision support systems: a systematic review. Implementation Science, 18(1), 7. https://doi.org/10.1186/s13012-023-01261-8
- Eslami, S., Abu-Hanna, A., de Jonge, E., & de Keizer, N. F. (2009). Tight glycemic control and computerized decision-support systems: a systematic review. Intensive Care Medicine, 35(9), 1505-1517. https://doi.org/10.1007/s00134-009-1542-0
- Esmaeilzadeh, P., Sambasivan, M., Kumar, N., & Nezakati, H. (2015). Adoption of clinical decision support systems in a developing country: Antecedents and outcomes of physician’s threat to perceived professional autonomy. International Journal of Medical Informatics, 84(8), 548-560. https://doi.org/10.1016/j.ijmedinf.2015.03.007
- Fernando, M., Abell, B., Tyack, Z., Donovan, T., McPhail, S. M., & Naicker, S. (2023). Using Theories, Models, and Frameworks to Inform Implementation Cycles of Computerized Clinical Decision Support Systems in Tertiary Health Care Settings: Scoping Review. Journal of Medical Internet Research, 25, e45163. https://doi.org/10.2196/45163
- Fillmore, C. L., Bray, B. E., & Kawamoto, K. (2013). Systematic review of clinical decision support interventions with potential for inpatient cost reduction. BMC Medical Informatics and Decision Making, 13, 135. https://doi.org/10.1186/1472-6947-13-135
- Garg, A. X., Adhikari, N. K. J., McDonald, H., Rosas-Arellano, M. P., Devereaux, P. J., Beyene, J., Sam, J., & Haynes, R. B. (2005). Effects of computerized clinical decision support systems on practitioner performance and patient outcomes: A systematic review. JAMA, 293(10), 1223-1238. https://doi.org/10.1001/jama.293.10.1223
- Gencturk, M., Erturkmen, G. B. L., Akpinar, A. E., Pournik, O., Ahmad, B., Arvanitis, T. N., Schmidt-Barzynski, W., Robbins, T., Corcoles, R. A., & Abizanda, P. (2024). Transforming evidence-based clinical guidelines into implementable clinical decision support services: the CAREPATH study for multimorbidity management. Frontiers in Medicine, 11, 1386689. https://doi.org/10.3389/fmed.2024.1386689
- Giordano, L., Durand, C., Ahmad, R., Collias, L., Thy, M., Kherabi, Y., Lescure, F. X., Hamard, M., Birgand, G., & Peiffer-Smadja, N. (2026). Strategies and outcomes of CDSS implementation for antimicrobial stewardship in hospital settings: a systematic review. Antimicrobial Resistance and Infection Control, 15(1), 79. https://doi.org/10.1186/s13756-026-01731-w
- Günaydin, T., & Varli, S. (2025). Computer-Aided Decision Support Systems of Alzheimer’s Disease Diagnosis: A Systematic Review. Current Medical Imaging, 21, E15734056359358. https://doi.org/10.2174/0115734056359358250516101749
- Hardenbol, A. X., Knols, B., Louws, M., Meulendijk, M., & Askari, M. (2020). Usability aspects of medication-related decision support systems in the outpatient setting: A systematic literature review. Health Informatics Journal, 26(1), 72-87. https://doi.org/10.1177/1460458218813732
- Haynes, R. B., & Wilczynski, N. L. (2010). Effects of computerized clinical decision support systems on practitioner performance and patient outcomes: Methods of a decision-maker-researcher partnership systematic review. Implementation Science, 5, 12. https://doi.org/10.1186/1748-5908-5-12
- He, W., Chima, S., Emery, J., Manski-Nankervis, J. A., Williams, I., Hunter, B., Nelson, C., & Martinez-Gutierrez, J. (2024). Perceptions of primary care patients on the use of electronic clinical decision support tools to facilitate health care: A systematic review. Patient Education and Counseling, 125, 108290. https://doi.org/10.1016/j.pec.2024.108290
- Hemens, B. J., Holbrook, A., Tonkin, M., Mackay, J. A., Weise-Kelly, L., Navarro, T., Wilczynski, N. L., & Haynes, R. B. (2011). Computerized clinical decision support systems for drug prescribing and management: A decision-maker-researcher partnership systematic review. Implementation Science, 6, 89. https://doi.org/10.1186/1748-5908-6-89
- Hendriks, M. P., Jager, A., Ebben, K. C. W. J., Til, J. A. V., & Siesling, S. (2024). Clinical decision support systems for multidisciplinary team decision-making in patients with solid cancer: Composition of an implementation model based on a scoping review. Critical Reviews in Oncology Hematology, 195, 104267. https://doi.org/10.1016/j.critrevonc.2024.104267
- Heng, S. T., Wong, J., Young, B., Tay, H. L., Tan, S. H., Yap, M. Y., Teng, C. B., Ang, B., Lee, T. H., Tan, H. L., Lew, T. W., Lye, D. C., & Ng, T. M. (2020). Effective Antimicrobial StewaRdship StrategIES (ARIES): Cluster Randomized Trial of Computerized Decision Support System and Prospective Review and Feedback. Open Forum Infectious Diseases, 7(7), ofaa254. https://doi.org/10.1093/ofid/ofaa254
- Hetlevik, I., Holmen, J., & Krüger, O. (1999). Implementing clinical guidelines in the treatment of hypertension in general practice: Evaluation of patient outcome related to implementation of a computer-based clinical decision support system. Scandinavian Journal of Primary Health Care, 17(1), 35-40.
- Hetlevik, I., Holmen, J., Krüger, O., Kristensen, P., Iversen, H., & Furuseth, K. (2000). Implementing clinical guidelines in the treatment of diabetes mellitus in general practice: Evaluation of effort, process, and patient outcome related to implementation of a computer-based decision support system. International Journal of Technology Assessment in Health Care, 16(1), 210-227. https://doi.org/10.1017/S0266462300161185
- Huang, S., Liang, Y. Z., Li, J. R., & Li, X. J. (2023). Applications of Clinical Decision Support Systems in Diabetes Care: Scoping Review. Journal of Medical Internet Research, 25, e51024. https://doi.org/10.2196/51024
- Hunt, D. L., Haynes, R. B., Hanna, S. E., & Smith, K. (1998). Effects of computer-based clinical decision support systems on physician performance and patient outcomes: A systematic review. JAMA, 280(15), 1339-1346. https://doi.org/10.1001/jama.280.15.1339
- Ingraham, N. E., Jones, E. K., King, S., Dries, J., Phillips, M., Loftus, T., Evans, H. L., Melton, G. B., & Tignanelli, C. J. (2023). Re-Aiming Equity Evaluation in Clinical Decision Support: A Scoping Review of Equity Assessments in Surgical Decision Support Systems. Annals of Surgery, 277(3), 359-364. https://doi.org/10.1097/SLA.0000000000005661
- Ip, I. K., Schneider, L. I., Hanson, R., Marchello, D., Hultman, P., Viera, M., Chiang, B., Andriole, K. P., Menard, A., Schade, S., Seltzer, S. E., & Khorasani, R. (2012). Adoption and Meaningful Use of Computerized Physician Order Entry With an Integrated Clinical Decision Support System for Radiology: Ten-Year Analysis in an Urban Teaching Hospital. Journal of the American College of Radiology, 9(2), 129-136. https://doi.org/10.1016/j.jacr.2011.10.010
- Jacob, V., Thota, A. B., Chattopadhyay, S. K., Njie, G. J., Proia, K. K., Hopkins, D. P., Ross, M. N., Pronk, N. P., & Clymer, J. M. (2017). Cost and economic benefit of clinical decision support systems for cardiovascular disease prevention: a community guide systematic review. Journal of the American Medical Informatics Association, 24(3), 669-676. https://doi.org/10.1093/jamia/ocw160
- Janssen, E. R. C., Knoop, J., Farabolini, G., Baldini, N., Hoogeboom, T., Ceravolo, M. G., Negrini, S., & Kiekens, C. (2026). The GUIDE-CDSS framework: a comprehensive framework to GUIDE and evaluate the implementation of Clinical Decision Support Systems in healthcare, based on an overview of reviews. Journal of the American Medical Informatics Association, 33(9), 1811-1821. https://doi.org/10.1093/jamia/ocag080
- Jaspers, M. W. M., Smeulers, M., Vermeulen, H., & Peute, L. W. (2011). Effects of clinical decision-support systems on practitioner performance and patient outcomes: a synthesis of high-quality systematic review findings. Journal of the American Medical Informatics Association, 18(3), 327-334. https://doi.org/10.1136/amiajnl-2011-000094
- Jeng, D. J. F., & Tzeng, G. H. (2012). Social influence on the use of Clinical Decision Support Systems: Revisiting the Unified Theory of Acceptance and Use of Technology by the fuzzy DEMATEL technique. Computers & Industrial Engineering, 62(3), 819-828. https://doi.org/10.1016/j.cie.2011.12.016
- Jeong, M. A., & Kim, S. D. (2026). Impact of AI-Based Clinical Decision Support Systems on Diagnostic Accuracy Among Healthcare Professionals: A Systematic Review and Meta-Analysis of Randomized Controlled Trials. Applied Sciences, 16(10), 5146. https://doi.org/10.3390/app16105146
- Ji, M. T., Yu, G. J., Xi, H. Q., Xu, T., & Qin, Y. W. (2021). Measures of success of computerized clinical decision support systems: An overview of systematic reviews. Health Policy and Technology, 10(1). https://doi.org/10.1016/j.hlpt.2020.11.001
- Jia, P. L., Zhang, L. H., Chen, J. J., Zhao, P. J., & Zhang, M. M. (2016). The Effects of Clinical Decision Support Systems on Medication Safety: An Overview. PLOS ONE, 11(12), 0167683. https://doi.org/10.1371/journal.pone.0167683
- Jing, X., Min, H., Gong, Y., Biondich, P., Robinson, D., Law, T., Nohr, C., Faxvaag, A., Rennert, L., Hubig, N., & Gimbel, R. (2023). Ontologies Applied in Clinical Decision Support System Rules: Systematic Review. JMIR Medical Informatics, 11. https://doi.org/10.2196/43053
- Kaplan, B. (2001). Evaluating informatics applications: Clinical decision support systems literature review. International Journal of Medical Informatics, 64(1), 15-37. https://doi.org/10.1016/S1386-5056(01)00183-6
- Karatas, S. S., & Öner, S. F. (2026). Pre-deployment safety and governance assessment of LLM-based clinical decision support systems: A health technology assessment-oriented evaluation framework. Health Policy and Technology, 15(9), 101281. https://doi.org/10.1016/j.hlpt.2026.101281
- Kaushal, R., Shojania, K. G., & Bates, D. W. (2003). Effects of computerized physician order entry and clinical decision support systems on medication safety: A systematic review. Archives of Internal Medicine, 163(12), 1409-1416. https://doi.org/10.1001/archinte.163.12.1409
- Kawamoto, K., Houlihan, C. A., Balas, E. A., & Lobach, D. F. (2005). Improving clinical practice using clinical decision support systems: a systematic review of trials to identify features critical to success. BMJ, 330(7494), 765-768. https://doi.org/10.1136/bmj.38398.500764.8F
- Kesselheim, A. S., Cresswell, K., Phansalkar, S., Bates, D. W., & Sheikh, A. (2011). Clinical Decision Support Systems Could Be Modified To Reduce ‘Alert Fatigue’ While Still Minimizing The Risk Of Litigation. Health Affairs, 30(12), 2310-2317. https://doi.org/10.1377/hlthaff.2010.1111
- Khan, N., Okoli, C. N., Ekpin, V., Attai, K., Chukwudi, N., Sabi, H., Akwaowo, C., Osuji, J., Benavente, L., & Uzoka, F. M. (2023). Adoption and utilization of medical decision support systems in the diagnosis of febrile Diseases: A systematic literature review. Expert Systems with Applications, 220, 119638. https://doi.org/10.1016/j.eswa.2023.119638
- Khong, P. C. B., Holroyd, E., & Wang, W. R. (2015). A Critical Review of the Theoretical Frameworks and the Conceptual Factors in the Adoption of Clinical Decision Support Systems. CIN: Computers, Informatics, Nursing, 33(12), 555-570. https://doi.org/10.1097/CIN.0000000000000196
- Kilsdonk, E., Peute, L. W., & Jaspers, M. W. M. (2017). Factors influencing implementation success of guideline-based clinical decision support systems: A systematic review and gaps analysis. International Journal of Medical Informatics, 98, 56-64. https://doi.org/10.1016/j.ijmedinf.2016.12.001
- Kim, S. Y., Kim, D. H., Kim, M. J., Ko, H. J., & Jeong, O. R. (2024). XAI-Based Clinical Decision Support Systems: A Systematic Review. Applied Sciences, 14(15), 6638. https://doi.org/10.3390/app14156638
- Knols, B., Louws, M., Hardenbol, A., Dehmeshki, J., & Askari, M. (2020). The usability aspects of medication-related decision support systems in the inpatient setting: A systematic review. Health Informatics Journal, 26(1), 613-627. https://doi.org/10.1177/1460458219841167
- Kouri, A., Yamada, J., Cheung, J. L. S., Van de Velde, S., & Gupta, S. (2022). Do providers use computerized clinical decision support systems? A systematic review and meta-regression of clinical decision support uptake. Implementation Science, 17(1), 21. https://doi.org/10.1186/s13012-022-01199-3
- Kruse, C. S., & Ehrbar, N. (2020). Effects of Computerized Decision Support Systems on Practitioner Performance and Patient Outcomes: Systematic Review. JMIR Medical Informatics, 8(8), e17283. https://doi.org/10.2196/17283
- Kuperman, G. J., Bobb, A., Payne, T. H., Avery, A. J., Gandhi, T. K., Burns, G., Classen, D. C., & Bates, D. W. (2007). Medication-related clinical decision support in computerized provider order entry systems: A review. Journal of the American Medical Informatics Association, 14(1), 29-40. https://doi.org/10.1197/jamia.M2170
- Lampe, D., Grosser, J., Grothe, D., Aufenberg, B., Gensorowsky, D., Witte, J., & Greiner, W. (2024). How intervention studies measure the effectiveness of medication safety-related clinical decision support systems in primary and long-term care: a systematic review. BMC Medical Informatics and Decision Making, 24(1), 188. https://doi.org/10.1186/s12911-024-02596-y
- Levivien, C., Cavagna, P., Grah, A., Buronfosse, A., Courseau, R., Bézie, Y., & Corny, J. (2022). Assessment of a hybrid decision support system using machine learning with artificial intelligence to safely rule out prescriptions from medication review in daily practice. International Journal of Clinical Pharmacy, 44(2), 459-465. https://doi.org/10.1007/s11096-021-01366-4
- Loftus, T. J., Balch, J. A., Marquard, J. L., Ray, J. M., Alper, B. S., Ojha, N., Bihorac, A., Melton-Meaux, G., Khanna, G., & Tignanelli, C. J. (2024). Longitudinal clinical decision support for assessing decisions over time: State-of-the-art and future directions. Digital Health, 10, 20552076241249925. https://doi.org/10.1177/20552076241249925
- Lopez, K. D., Gephart, S. M., Raszewski, R., Sousa, V., Shehorn, L. E., & Abraham, J. (2017). Integrative review of clinical decision support for registered nurses in acute care settings. Journal of the American Medical Informatics Association, 24(2), 441-450. https://doi.org/10.1093/jamia/ocw084
- Mahadevaiah, G., Prasad, R. V., Bermejo, I., Jaffray, D., Dekker, A., & Wee, L. (2020). Artificial intelligence-based clinical decision support in modern medical physics: Selection, acceptance, commissioning, and quality assurance. Medical Physics, 47(5), E228-E235. https://doi.org/10.1002/mp.13562
- Main, C., Moxham, T., Wyatt, J. C., Kay, J., Anderson, R., & Stein, K. (2010). Computerised decision support systems in order communication for diagnostic, screening or monitoring test ordering: systematic reviews of the effects and cost-effectiveness of systems. Health Technology Assessment, 14(48), 1. https://doi.org/10.3310/hta14480
- Mebrahtu, T. F., Skyrme, S., Randell, R., Keenan, A. M., Bloor, K., Yang, H. Q., Andre, D., Ledward, A., King, H., & Thompson, C. (2021). Effects of computerised clinical decision support systems (CDSS) on nursing and allied health professional performance and patient outcomes: a systematic review of experimental and observational studies. BMJ Open, 11(12), e053886. https://doi.org/10.1136/bmjopen-2021-053886
- Meunier, P. Y., Raynaud, C., Guimaraes, E., Gueyffier, F., & Letrilliart, L. (2023). Barriers and Facilitators to the Use of Clinical Decision Support Systems in Primary Care: A Mixed-Methods Systematic Review. Annals of Family Medicine, 21(1), 57-69. https://doi.org/10.1370/afm.2908
- Moon, J., Chladek, J. S., Wilson, P., & Chui, M. A. (2024). Clinical decision support systems in community pharmacies: a scoping review. Journal of the American Medical Informatics Association, 31(1), 231-239. https://doi.org/10.1093/jamia/ocad208
- Moosa, A. S., Seng, J. J. B., & Ng, C. J. (2025). Clinical Decision Support Systems Using Home Blood Pressure Readings to Manage Patients With Hypertension: Scoping Review. Journal of Medical Internet Research, 27, e75551. https://doi.org/10.2196/75551
- Nanji, K. C., Seger, D. L., Slight, S. P., Amato, M. G., Beeler, P. E., Her, Q. L., Dalleur, O., Eguale, T., Wong, A., Silvers, E. R., Swerdloff, M., Hussain, S. T., Maniam, N., Fiskio, J. M., Dykes, P. C., & WBates, D. (2018). Medication-related clinical decision support alert overrides in inpatients. Journal of the American Medical Informatics Association, 25(5), 476-481. https://doi.org/10.1093/jamia/ocx115
- Nanji, K. C., Slight, S. P., Seger, D. L., Cho, I., Fiskio, J. M., Redden, L. M., Volk, L. A., & Bates, D. W. (2014). Overrides of medication-related clinical decision support alerts in outpatients. Journal of the American Medical Informatics Association, 21(3), 487-491. https://doi.org/10.1136/amiajnl-2013-001813
- Naye, F., Ouellet, S., Yousefi, F., Cachinho, C., Bergeron, F., Bhattacharyya, O., Stamenova, V., & Sasseville, M. (2026). AI-Based Clinical Decision Support Systems in Primary Care: Systematic Review of Clinical Implementation. Journal of Medical Internet Research, 28, e96882. https://doi.org/10.2196/96882
- Newroz, B., Gashi, B., Schiefenhövel, F., & Boeker, M. (2026). Effectiveness of Guideline-Based Clinical Decision Support Systems: Protocol for a Systematic Review. JMIR Research Protocols, 15, e87006. https://doi.org/10.2196/87006
- Nielsen, K. M., Packull-McCormick, S. R., & Grant, L. E. (2026). Strategies to support implementation of infectious disease decision support systems: a scoping review. BMC Medical Informatics and Decision Making, 26(1), 238. https://doi.org/10.1186/s12911-026-03515-z
- O’Neill, K., Parrott, H., Neely, C., McLeese, R., Fleming, G., Scott, M., & Bradley, J. M. (2025). Clinical Decision Support Systems in Adults with Chronic Respiratory Disease: A Systematic Review. Current Respiratory Medicine Reviews, 21(2), 125-151. https://doi.org/10.2174/011573398X281958240531065955
- Özçetin, E., Bas, S. E., & Özpay, F. (2026). Architectural and translational perspectives on clinical decision support systems for rare disease diagnosis: a scoping review. International Journal of Medical Informatics, 215, 106442. https://doi.org/10.1016/j.ijmedinf.2026.106442
- Papadopoulos, P., Soflano, M., Chaudy, Y., Adejo, W., & Connolly, T. M. (2022). A systematic review of technologies and standards used in the development of rule-based clinical decision support systems. Health and Technology, 12(4), 713-727. https://doi.org/10.1007/s12553-022-00672-9
- Parsons, C. S., Zuiderwijk, A., Orchard, N. A., Oosterhoff, J. H. F., & de Reuver, M. (2025). Task-Technology Fit of Artificial Intelligence-based clinical decision support systems: a review of qualitative studies. BMC Medical Informatics and Decision Making, 25(1), 397. https://doi.org/10.1186/s12911-025-03237-8
- Payne, T. H., Hines, L. E., Chan, R. C., Hartman, S., Kapusnik-Uner, J., Russ, A. L., Chaffee, B. W., Hartman, C., Tamis, V., Galbreth, B., Glassman, P. A., Phansalkar, S., van der Sijs, H., Gephart, S. M., Mann, G., Strasberg, H. R., Grizzle, A. J., Brown, M., Kuperman, G. J., . . . Malone, D. C. (2015). Recommendations to improve the usability of drug-drug interaction clinical decision support alerts. Journal of the American Medical Informatics Association, 22(6), 1243-1250. https://doi.org/10.1093/jamia/ocv011
- Peiffer-Smadja, N., Rawson, T. M., Ahmad, R., Buchard, A., Pantelis, G., Lescure, F. X., Birgand, G., & Holmes, A. H. (2020). Machine learning for clinical decision support in infectious diseases: a narrative review of current applications. Clinical Microbiology and Infection, 26(5), 584-595. https://doi.org/10.1016/j.cmi.2019.09.009
- Ploegmakers, K. J., Medlock, S., Linn, A. J., Lin, Y. M., Seppälä, L. J., Petrovic, M., Topinkova, E., Ryg, J., Mora, M. A. C., Landi, F., Thaler, H., Szczerbinska, K., Hartikainen, S., Bahat, G., Ilhan, B., Morrissey, Y., Masud, T., van der Velde, N., & van Weert, J. C. M. (2022). Barriers and facilitators in using a Clinical Decision Support System for fall risk management for older people: a European survey. European Geriatric Medicine, 13(2), 395-405. https://doi.org/10.1007/s41999-021-00599-w
- Pranata, Y., Mirwanti, R., Bahtiar, Y. A., & Purwanti, H. (2026). Translational Potential and Explainability of Artificial Intelligence-Based Clinical Decision Support for Adults in Intensive Care: A Scoping Review. Journal of Multidisciplinary Healthcare, 19, S621469. https://doi.org/10.2147/JMDH.S621469
- Prgomet, M., Li, L., Niazkhani, Z., Georgiou, A., & Westbrook, J. I. (2017). Impact of commercial computerized provider order entry (CPOE) and clinical decision support systems (CDSSs) on medication errors, length of stay, and mortality in intensive care units: a systematic review and meta-analysis. Journal of the American Medical Informatics Association, 24(2), 413-422. https://doi.org/10.1093/jamia/ocw145
- Ranji, S. R., Rennke, S., & Wachter, R. M. (2014). Computerised provider order entry combined with clinical decision support systems to improve medication safety: a narrative review. BMJ Quality & Safety, 23(9), 773-780. https://doi.org/10.1136/bmjqs-2013-002165
- Ray, C. E., Wilson, G. M., Hughes, A. M., Goedken, C. C., Liu, E. P. F., Fitzpatrick, M. A., Suda, K. J., Kota, S. M., Nwankpa, C., & Evans, C. T. (2026). Alert fatigue measurement in clinical decision support: a systematic review. Journal of the American Medical Informatics Association, 33(8), 1523-1531. https://doi.org/10.1093/jamia/ocag064
- Raynaud, C., Letrilliart, L., & Meunier, P. Y. (2023). Identification of clinical decision support systems evaluated in primary care. A systematic review of the literature. Exercer: La Revue Francophone de Médecine Générale, (189), 28-35.
- Reese, T. J., Liu, S. R., Steitz, B., McCoy, A., Russo, E., Koh, B., Ancker, J., & Wright, A. (2022). Conceptualizing clinical decision support as complex interventions: a meta-analysis of comparative effectiveness trials. Journal of the American Medical Informatics Association, 29(10), 1744-1756. https://doi.org/10.1093/jamia/ocac089
- Richardson, S., Mishuris, R., O’Connell, A., Feldstein, D., Hess, R., Smith, P., McCullagh, L., McGinn, T., & Mann, D. (2017). “Think aloud” and “Near live” usability testing of two complex clinical decision support tools. International Journal of Medical Informatics, 106, 1-8. https://doi.org/10.1016/j.ijmedinf.2017.06.003
- Rittmann, B., & Stevens, M. P. (2019). Clinical Decision Support Systems and Their Role in Antibiotic Stewardship: a Systematic Review. Current Infectious Disease Reports, 21(8), 29. https://doi.org/10.1007/s11908-019-0683-8
- Ronan, C. E., Crable, E. L., Drainoni, M. L., & Walkey, A. J. (2022). The impact of clinical decision support systems on provider behavior in the inpatient setting: A systematic review and meta-analysis. Journal of Hospital Medicine, 17(5), 368-383. https://doi.org/10.1002/jhm.12825
- Rosati, A., Criscione, M., Lilli, L., Petrillo, M., Capobianco, G., Patarnello, S., & Fagotti, A. (2026). Natural language processing as consultation service platform or clinical decision support system in gynecologic oncology: a systematic review. International Journal of Gynecological Cancer, 36(4), 104558. https://doi.org/10.1016/j.ijgc.2026.104558
- Ruutiainen, H., Holmström, A. R., Kunnola, E., & Kuitunen, S. (2024). Use of Computerized Physician Order Entry with Clinical Decision Support to Prevent Dose Errors in Pediatric Medication Orders: A Systematic Review. Pediatric Drugs, 26(2), 127-143. https://doi.org/10.1007/s40272-023-00614-6
- Sahota, N., Lloyd, R., Ramakrishna, A., Mackay, J. A., Prorok, J. C., Weise-Kelly, L., Navarro, T., Wilczynski, N. L., & Haynes, R. B. (2011). Computerized clinical decision support systems for acute care management: A decision-maker-researcher partnership systematic review of effects on process of care and patient outcomes. Implementation Science, 6, 91. https://doi.org/10.1186/1748-5908-6-91
- Saleem, M., Bidoki, M. Z., Alsuraihi, W., Al-Garadi, M. A., & Ahmed, A. (2026). Real-World Implementation and Evaluation of AI-Driven Clinical Decision Support in Emergency Medicine: A Systematic Review. Healthcare, 14(18), 2922. https://doi.org/10.3390/healthcare14182922
- Scott, P. J., Brown, A. W., Adedeji, T., Wyatt, J. C., Georgiou, A., Eisenstein, E. L., & Friedman, C. P. (2019). A review of measurement practice in studies of clinical decision support systems 1998-2017. Journal of the American Medical Informatics Association, 26(10), 1120-1128. https://doi.org/10.1093/jamia/ocz035
- Seidling, H. M., Phansalkar, S., Seger, D. L., Paterno, M. D., Shaykevich, S., Haefeli, W. E., & Bates, D. W. (2011). Factors influencing alert acceptance: a novel approach for predicting the success of clinical decision support. Journal of the American Medical Informatics Association, 18(4), 479-484. https://doi.org/10.1136/amiajnl-2010-000039
- Sezgin, M. G., & Bektas, H. (2022). The effect of decision support systems on pain in patients with cancer: A systematic review and meta-analysis of randomized controlled trials. Journal of Nursing Scholarship, 54(5), 578-588. https://doi.org/10.1111/jnu.12769
- Shibl, R., Lawley, M., & Debuse, J. (2013). Factors influencing decision support system acceptance. Decision Support Systems, 54(2), 953-961. https://doi.org/10.1016/j.dss.2012.09.018
- Sintchenko, V., Magrabi, F., & Tipper, S. (2007). Are we measuring the right end-points? Variables that affect the impact of computerised decision support on patient outcomes: A systematic review. Medical Informatics and the Internet in Medicine, 32(3), 225-240. https://doi.org/10.1080/14639230701447701
- Souza, N. M., Sebaldt, R. J., Mackay, J. A., Prorok, J. C., Weise-Kelly, L., Navarro, T., Wilczynski, N. L., & Haynes, R. B. (2011). Computerized clinical decision support systems for primary preventive care: A decision-maker-researcher partnership systematic review of effects on process of care and patient outcomes. Implementation Science, 6, 87. https://doi.org/10.1186/1748-5908-6-87
- Srada, Y. B., Bawazir, B., Aghi, S. M., Elsayed, M., Yousif, H., Ibrahim, M., Eltohamy, K. A., & Sim, M. (2026). AI-Assisted Clinical Decision Support Versus Standard Teleconsultation in Adult Medicine: A Systematic Review of Diagnostic Accuracy, Referral and Testing Decisions, and Clinician Confidence. Clinics and Practice, 16(10), 181. https://doi.org/10.3390/clinpract16100181
- Standiford, T. C., Farlow, J. L., Brenner, M. J., Conte, M. L., & Terrell, J. E. (2022). Clinical Decision Support Systems in Otolaryngology-Head and Neck Surgery: A State of the Art Review. Otolaryngology: Head and Neck Surgery, 166(1), 35-47. https://doi.org/10.1177/01945998211004529
- Susanto, A. P., Lyell, D., Widyantoro, B., Berkovsky, S., & Magrabi, F. (2023). Effects of machine learning-based clinical decision support systems on decision-making, care delivery, and patient outcomes: a scoping review. Journal of the American Medical Informatics Association, 30(12), 2050-2063. https://doi.org/10.1093/jamia/ocad180
- Sutton, R. T., Pincock, D., Baumgart, D. C., Sadowski, D. C., Fedorak, R. N., & Kroeker, K. I. (2020). An overview of clinical decision support systems: benefits, risks, and strategies for success. npj Digital Medicine, 3(1), 17. https://doi.org/10.1038/s41746-020-0221-y
- Tai, A. M. Y., Kim, J. J., Schmeckenbecher, J., Kitchin, V., Wang, J., Kazemi, A., Masoudi, R., Fadakar, H., Iorfino, F., & Krausz, R. M. (2024). Clinical decision support systems in addiction and concurrent disorders: A systematic review and meta-analysis. Journal of Evaluation in Clinical Practice, 30(8), 1664-1683. https://doi.org/10.1111/jep.14069
- Thayer, J. G., Franklin, A., Miller, J. M., Grundmeier, R. W., Rogith, D., & Wright, A. (2024). A scoping review of rule-based clinical decision support malfunctions. Journal of the American Medical Informatics Association, 31(10), 2405-2413. https://doi.org/10.1093/jamia/ocae187
- Ulgu, M. M., Erturkmen, G. B. L., Yuksel, M., Namli, T., Postaci, S., Gencturk, M., Kabak, Y., Sinaci, A. A., Gonul, S., Dogac, A., Altunay, Z. Ö., Ekinci, B., Aydin, S., & Birinci, S. (2024). A Nationwide Chronic Disease Management Solution via Clinical Decision Support Services: Software Development and Real-Life Implementation Report. JMIR Medical Informatics, 12, e49986. https://doi.org/10.2196/49986
- Van de Velde, S., Heselmans, A., Delvaux, N., Brandt, L., Marco-Ruiz, L., Spitaels, D., Cloetens, H., Kortteisto, T., Roshanov, P., Kunnamo, I., Aertgeerts, B., Vandvik, P. O., & Flottorp, S. (2018). A systematic review of trials evaluating success factors of interventions with computerised clinical decision support. Implementation Science, 13, 114. https://doi.org/10.1186/s13012-018-0790-1
- Van Dort, B. A., Engelsma, T., Sneekes, P., Peute, L., & Medlock, S. (2026). Explainable AI in hospital clinical decision support systems: A scoping review of healthcare professionals’ perspectives. PLOS Digital Health, 5(5), e0001417. https://doi.org/10.1371/journal.pdig.0001417
- Van Dort, B. A., Zheng, W. Y., Sundar, V., & Baysari, M. T. (2021). Optimizing clinical decision support alerts in electronic medical records: a systematic review of reported strategies adopted by hospitals. Journal of the American Medical Informatics Association, 28(1), 177-183. https://doi.org/10.1093/jamia/ocaa279
- Varghese, J., Kleine, M., Gessner, S. I., Sandmann, S., & Dugas, M. (2018). Effects of computerized decision support system implementations on patient outcomes in inpatient care: a systematic review. Journal of the American Medical Informatics Association, 25(5), 593-602. https://doi.org/10.1093/jamia/ocx100
- Vasey, B., Ursprung, S., Beddoe, B., Taylor, E. H., Marlow, N., Bilbro, N., Watkinson, P., & McCulloch, P. (2021). Association of Clinician Diagnostic Performance With Machine Learning-Based Decision Support Systems: A Systematic Review. JAMA Network Open, 4(3), e211276. https://doi.org/10.1001/jamanetworkopen.2021.1276
- Vélez-Díaz-Pallarés, M., Pérez-Menéndez-Conde, C., & Bermejo-Vicedo, T. (2018). Systematic review of computerized prescriber order entry and clinical decision support. American Journal of Health-System Pharmacy, 75(23), 1909-1921. https://doi.org/10.2146/ajhp170870
- Wadie, P., Zakher, B., Elgazzar, K., Alsbakhi, A., & Alhejaily, A. M. G. (2026). AI in Point-of-Care Imaging for Clinical Decision Support: Systematic Review of Diagnostic Accuracy, Task-Shifting, and Explainability. JMIR AI, 5, E80928. https://doi.org/10.2196/80928
- Wake, D. T., Smith, D. M., Kazi, S., & Dunnenberger, H. M. (2022). Pharmacogenomic Clinical Decision Support: A Review, How-to Guide, and Future Vision. Clinical Pharmacology & Therapeutics, 112(1), 44-57. https://doi.org/10.1002/cpt.2387
- Wang, E., Brenn, B. R., & Matava, C. T. (2020). State of the art in clinical decision support applications in pediatric perioperative medicine. Current Opinion in Anesthesiology, 33(3), 388-394. https://doi.org/10.1097/ACO.0000000000000850
- Watson, H. A., Tribe, R. M., & Shennan, A. H. (2019). The role of medical smartphone apps in clinical decision-support: A literature review. Artificial Intelligence in Medicine, 100, 101707. https://doi.org/10.1016/j.artmed.2019.101707
- Westerbeek, L., Ploegmakers, K. J., De Bruijn, G. J., Linn, A. J., van Weert, J. C. M., Daams, J. G., van der Velde, N., van Weert, H. C., Abu-Hanna, A., & Medlock, S. (2021). Barriers and facilitators influencing medication-related CDSS acceptance according to clinicians: A systematic review. International Journal of Medical Informatics, 152, 104506. https://doi.org/10.1016/j.ijmedinf.2021.104506
- Wingfield, L. R., Salaun, A., Khan, A., Webb, H., Zhu, T. T., & Knight, S. (2024). Clinical Decision Support Systems Used in Transplantation: Are They Tools for Success or an Unnecessary Gadget? A Systematic Review. Transplantation, 108(1), 72-99. https://doi.org/10.1097/TP.0000000000004627
- Wright, A., & Sittig, D. F. (2008). A four-phase model of the evolution of clinical decision support architectures. International Journal of Medical Informatics, 77(10), 641-649. https://doi.org/10.1016/j.ijmedinf.2008.01.004
- Wright, A., Sittig, D. F., Ash, J. S., Feblowitz, J., Meltzer, S., McMullen, C., Guappone, K., Carpenter, J., Richardson, J., Simonaitis, L., Evans, R. S., Nichol, W. P., & Middleton, B. (2011). Development and evaluation of a comprehensive clinical decision support taxonomy: comparison of front-end tools in commercial and internally developed electronic health record systems. Journal of the American Medical Informatics Association, 18(3), 232-242. https://doi.org/10.1136/amiajnl-2011-000113
- Wulff, A., Montag, S., Marschollek, M., & Jack, T. (2019). Clinical Decision-Support Systems for Detection of Systemic Inflammatory Response Syndrome, Sepsis, and Septic Shock in Critically Ill Patients: A Systematic Review. Methods of Information in Medicine, 58, e43-e57. https://doi.org/10.1055/s-0039-1695717
- Yilmaz, A. A., & Ozdemir, L. (2017). Development and Implementation of the Clinical Decision Support System for Patients With Cancer and Nurses’ Experiences Regarding the System. International Journal of Nursing Knowledge, 28(1), 4-12. https://doi.org/10.1111/2047-3095.12099
- Zandkarimi, E., & Ghorbanzadeh, K. (2027). Explainable artificial intelligence in clinical decision support systems: a systematic review of techniques, clinical applications, evaluation, and future directions. International Journal of Medical Informatics, 223, 106785. https://doi.org/10.1016/j.ijmedinf.2026.106785
- Zhao, Y. L., Zheng, X. Z., Wang, J. W., Xu, D. M., Li, S. L., Lv, J. C., & Yang, L. (2021). Effect of clinical decision support systems on clinical outcome for acute kidney injury: a systematic review and meta-analysis. BMC Nephrology, 22(1), 271. https://doi.org/10.1186/s12882-021-02459-y
- Zolhavarieh, S., Parry, D., & Bai, Q. (2017). Issues Associated With the Use of Semantic Web Technology in Knowledge Acquisition for Clinical Decision Support Systems: Systematic Review of the Literature. JMIR Medical Informatics, 5(3), 2-12. https://doi.org/10.2196/medinform.6169
Source verification and use of AI. Author names, publication years and DOIs in the reference list were checked against the Web of Science records of the included studies, and titles, journals, volumes and pages were taken from the same records. Every claim attributed to a source was checked against that source’s title and abstract; full texts were not reviewed, so numbers are reported as the abstracts state them. AI tools were used to support title and abstract screening, to extract evidence from abstracts into a structured template, to draft the text and to generate the figures. Responsibility for the content rests with the author, Prof. Dr. Mehmet Nurullah Kurutkan.
Data and supplementary material. The full list of the 1,067 included records, the screening log with exclusion reasons and the source verification report are provided in the supplementary file “CDSS_101_supplementary.xlsx”, available from the author on request.
Cite this page (APA 7)
Kurutkan, M. N. (2026, November 17). Clinical Decision Support Systems (CDSS): An Introduction (101). The Health Topics. https://healthtopic.org/topics/clinical-decision-support-systems-an-introduction-101/
