Antimicrobial Resistance (AMR) has been recognized as a global public health emergency, with projections indicating it could cause 10 million deaths annually by 2050 if effective interventions are not made. The irrational and unnecessary usage of antibiotics contributes to the emergence of multidrug-resistant (MDR) bacterial pathogens, leading to higher mortality, longer hospital stays, and increased healthcare costs. In response to this pressing challenge, artificial intelligence (AI) technology has emerged as a critical tool in combating AMR.
This comprehensive study, conducted by Zhongli Wang, Gaopei Zhu, and Shixue Li, systematically maps the knowledge landscape and development trends of AI applications in AMR research.
Methodology The researchers performed a comprehensive bibliometric analysis using the Web of Science Core Collection database, covering publications from 2014 to 2024. They integrated multiple bibliometric approaches, including:
- VOSviewer for visualizing collaboration networks and research clusters.
- CiteSpace for temporal evolution analysis.
- Quantitative analysis of publication metrics, co-authorship patterns, keyword co-occurrence, and citation impact.
Key Findings The analysis of 2,408 publications revealed several significant trends and contributions:
- Publication Growth: There has been a remarkable annual growth in publications, increasing from 4 in 2014 to 549 in 2023 (22.7% of total output), demonstrating a sharp acceleration, especially post-2020. This surge correlates with significant advances in AI applications for antimicrobial research and increased funding.
- Leading Contributors:
- Countries: The United States (707 publications), China (581), and India (233) are the leading contributors, with strong international collaborations, particularly between the U.S. and China. The U.S. leads due to its strong research infrastructure, while China leverages extensive medical data and rapid AI innovation, and India benefits from its IT sector and cost-effective drug development.
- Institutions: The Chinese Academy of Sciences (53), Harvard Medical School (43), and University of California San Diego (37) are identified as top contributing institutions. MIT, though ranking fourth, has the highest total link strength (TLS), indicating extensive and highly interconnected research.
- Authors: Sean Ekins (18 publications), Chia-Ru Chung (15), and Mahmoud Huleihel (14) are among the most prolific authors in this field.
- Major Breakthroughs and Co-cited References:
- AlphaFold: “Highly accurate protein structure prediction with AlphaFold” (2021) by Jumper et al. is the most frequently co-cited reference (6,811 citations). This work significantly enhances antimicrobial drug design by providing detailed structural predictions of pathogenic proteins and insights into AMR mechanisms.
- Deep Learning for Antibiotic Discovery: “A deep learning approach to antibiotic discovery” (2020) by Stokes et al. is the second most co-cited reference (4,784 citations). This innovative study used a deep learning model to screen millions of compounds, leading to the discovery of Halicin, a novel antibiotic effective against a broad spectrum of resistant pathogens, including Mycobacterium tuberculosis.
- Comprehensive Antibiotic Resistance Database (CARD): The CARD 2020 by Alcock et al. (2020) highlights the essential role of informatics in combating AMR, offering a curated collection of DNA/protein sequences and tools to understand the molecular basis of bacterial AMR.
- Enduring Research Clusters and Emerging Trends:
- Enduring Clusters (2014-2024): Sepsis, artificial neural networks, antimicrobial resistance, antimicrobial peptides (ABPs), drug repurposing, and molecular docking.
- Recent Trends: Increasing application of AI technologies in traditional approaches, particularly in MALDI-TOF MS for pathogen identification and graph neural networks for large-scale molecular screening. There is also growing attention to “tetracycline,” “big data,” and strategies for addressing drug resistance and Mycobacterium tuberculosis. The integration of artificial neural networks (ANNs) with drug repurposing also shows promise for urgent clinical needs.
Conclusion This bibliometric analysis underscores the critical role of artificial intelligence in enhancing progress in the discovery of antimicrobial drugs, particularly in the fight against AMR. AI capabilities demonstrate observable potential to be proactive in combating the growing global challenge of AMR by enhancing the fast, efficient, and predictive performance of drug discovery methods. The study not only identifies current trends but also offers a strategic approach for future investigations.
Reference for the source article:
Wang, Z., Zhu, G., & Li, S. (2025). Mapping knowledge landscapes and emerging trends in artificial intelligence for antimicrobial resistance: bibliometric and visualization analysis. Frontiers in Medicine, 12, 1492709. https://doi.org/10.3389/fmed.2025.1492709