MACHINE LEARNING-BASED PREDICTION OF ANTIBIOTIC RESISTANCE USING MICROBIAL AND GENOMIC DATA
Abstract
Antimicrobial resistance (AMR) is becoming a growing global health threat, affecting treatment outcomes, lives and placing a significant burden on healthcare systems. This study aimed to describe temporal, socioeconomic and pathogen-specific trends in antibiotic resistance, and to use machine-learning techniques to forecast multidrug resistance (MDR) based on microbial, epidemiological, clinical and health-system characteristics. Trends in resistance, MDR and extensively drug-resistant infection were evaluated by descriptive analysis over years, national income groups, World Health Organization (WHO) pathogen-priority categories and by the major pathogens. The models, including Logistic Regression, Random Forest and Extra Trees, were developed and assessed by accuracy, precision, sensitivity, specificity, F1-score, balanced accuracy and receiver operating characteristic area under the curve. The results revealed a continuous rise in resistance, MDR and Extensively Drug-Resistant (XDR) from 2010 to 2025. Low-income countries had the most resistance burden, and WHO critical priority and Gram-negative pathogens had the highest resistance rates. Logistic Regression had the highest accuracy (80.05%) and ROC-AUC (0.861) followed by Random Forest and Extra Trees. AMR-attributable mortality, income group, WHO priority status, Gram classification, and pathogen type were important predictors. Overall, the results provide evidence that interpretable machine-learning models have the potential to assist AMR surveillance and early risk identification of MDR. But predictive systems should be used in addition to laboratory susceptibility testing, antimicrobial stewardship, clinical judgement and One Health surveillance. Expansion of genomic features, external validation and locally representative data should be included in future research to enhance clinical generalisability.
Downloads
References
2.Aronin, S. I., Dunne, M. W., Kalvin, C. Y., Watts, J. A., & Gupta, V. (2022). Increased rates of extended-spectrum beta-lactamase isolates in patients hospitalized with culture-positive urinary Enterobacterales in the United States: 2011–2020. Diagnostic Microbiology and Infectious Disease, 103(4), 115717.
3.Aruhomukama, D. (2025). Applying genomic AI to combat antibiotic resistance in low-income countries. Nature Machine Intelligence, 7(9), 1369-1370.
4.Bhatt, G., Goel, S., Grover, S., Kaur, N., & Singh, S. (2021). A cross sectional study to assess tobacco use and its correlates among patients attending non-communicable disease clinics of a Northern Jurisdiction in India. Journal of family medicine and primary care, 10(8), 2915-2922.
5.Bilal, H., Khan, M. N., Khan, S., Shafiq, M., Fang, W., Khan, R. U., ... & Xu, B. (2025). The role of artificial intelligence and machine learning in predicting and combating antimicrobial resistance. Computational and structural biotechnology journal, 27, 423-439.
6.Cars, O., Chandy, S. J., Mpundu, M., Peralta, A. Q., Zorzet, A., & So, A. D. (2021). Resetting the agenda for antibiotic resistance through a health systems perspective. The Lancet Global Health, 9(7), e1022–e1027. doi:10.1016/S2214-109X(21)00163-7
7.Christaki, E., Marcou, M., & Tofarides, A. (2020). Antimicrobial resistance in bacteria: mechanisms, evolution, and persistence. Journal of molecular evolution, 88(1), 26-40.
8.Djordjevic, S. P., Jarocki, V. M., Seemann, T., Cummins, M. L., Watt, A. E., Drigo, B., ... & Howden, B. P. (2024). Genomic surveillance for antimicrobial resistance—a One Health perspective. Nature Reviews Genetics, 25(2), 142-157.
9.Farhat, F., Athar, M. T., Ahmad, S., Madsen, D. Ø., & Sohail, S. S. (2023). Antimicrobial resistance and machine learning: past, present, and future. Frontiers in Microbiology, 14, 1179312.
10.Fernandez, G. (2022). Turning the juggernaut. Lancet Planetary Health, 6(2), E75-E75.
11.Ikhimiukor, O. O., Odih, E. E., Donado-Godoy, P., & Okeke, I. N. (2022). A bottom-up view of antimicrobial resistance transmission in developing countries. Nature Microbiology, 7(6), 757-765.
12.Kim, J. I., Maguire, F., Tsang, K. K., Gouliouris, T., Peacock, S. J., McAllister, T. A., ... & Beiko, R. G. (2022). Machine learning for antimicrobial resistance prediction: current practice, limitations, and clinical perspective. Clinical microbiology reviews, 35(3), e00179-21.
13.Laxminarayan, R., Frost, I., Van Boeckel, T., Kariuki, S., Khan, E. A., Limmathurotsakul, D., ... & Zhu, Y. G. (2020). Correction to Lancet Infect Dis 2020; published online Feb 11. https://doi. org/10.1016/S1473-3099 (20) 30003-7 (The Lancet Infectious Diseases (2020) 20 (4)(e51–e60),(S1473309920300037),(10.1016/S1473-3099 (20) 30003-7)). The Lancet Infectious Diseases, 20(4), e50-e50.
14.Lewnard, J. A., Charani, E., Gleason, A., Hsu, L. Y., Khan, W. A., Karkey, A., ... & Laxminarayan, R. (2024). Burden of bacterial antimicrobial resistance in low-income and middle-income countries avertible by existing interventions: an evidence review and modelling analysis. The Lancet, 403(10442), 2439-2454.
15.Majumder, M. A. A., Rahman, S., Cohall, D., Bharatha, A., Singh, K., Haque, M., & Gittens-St Hilaire, M. (2020). Antimicrobial stewardship: fighting antimicrobial resistance and protecting global public health. Infection and drug resistance, 4713-4738.
16.Martin-Blondel, G., Marcelin, A. G., Soulié, C., Kaisaridi, S., Lusivika-Nzinga, C., Zafilaza, K., ... & Yordanov, Y. (2023). Time to negative PCR conversion amongst high-risk patients with mild-to-moderate Omicron BA. 1 and BA. 2 COVID-19 treated with sotrovimab or nirmatrelvir. Clinical Microbiology and Infection, 29(4), 543-e5.
17.Mathew, P., Chandy, S. J., & Ranjalkar, J. (2024). Community engagement to mitigate antimicrobial resistance in low-and middle-income countries–an essential strategy for implementation of national action plans on AMR. The Lancet Regional Health-Southeast Asia, 24.
18.Naghavi, M., Vollset, S. E., Ikuta, K. S., Swetschinski, L. R., Gray, A. P., Wool, E. E., ... & Dekker, D. M. (2024). Global burden of bacterial antimicrobial resistance 1990–2021: a systematic analysis with forecasts to 2050. The Lancet, 404(10459), 1199-1226.
19.Nsubuga, M., Galiwango, R., Jjingo, D., & Mboowa, G. (2024). Generalizability of machine learning in predicting antimicrobial resistance in E. coli: a multi-country case study in Africa. BMC genomics, 25(1), 287.
20.Pokharel, S., Raut, S., & Adhikari, B. (2019). Tackling antimicrobial resistance in low-income and middle-income countries. BMJ global health, 4(6).
21.Robins-Browne, R. M., Holt, K. E., Ingle, D. J., Hocking, D. M., Yang, J., & Tauschek, M. (2016). Are Escherichia coli pathotypes still relevant in the era of whole-genome sequencing?. Frontiers in cellular and infection microbiology, 6, 141.
22.Rogers Van Katwyk, S., Hoffman, S. J., Mendelson, M., Taljaard, M., & Grimshaw, J. M. (2020). Strengthening the science of addressing antimicrobial resistance: a framework for planning, conducting and disseminating antimicrobial resistance intervention research. Health Research Policy and Systems, 18(1), 60.
23.Singh, R., Lin, Y. W., Zhao, J., & Li, J. (2026). Artificial Intelligence and Machine Learning in Antimicrobial Discovery, Resistance Prediction, and Precision Therapy. International Journal of Antimicrobial Agents, 107715.
24.Suraj, M. K. (2025). Global Antibiotic Resistance Intelligence 2010–25: 50 countries × 25 pathogens × 16 years—Resistance rates & mortality [Data set]. Kaggle. https://www.kaggle.com/datasets/meruvakodandasuraj/global-antibiotic-resistance-intelligence-201025
25.Valavarasu, S., Sangu, Y., & Mahapatra, T. (2025). Prediction of antibiotic resistance from antibiotic susceptibility testing results from surveillance data using machine learning. Scientific Reports, 15(1), 30509.
26.van Belkum, A., Burnham, C. A. D., Rossen, J. W., Mallard, F., Rochas, O., & Dunne Jr, W. M. (2020). Innovative and rapid antimicrobial susceptibility testing systems. Nature Reviews Microbiology, 18(5), 299-311.
Copyright (c) 2026 IJRDO - JOURNAL OF BIOLOGICAL SCIENCE
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Author(s) and co-author(s) jointly and severally represent and warrant that the Article is original with the author(s) and does not infringe any copyright or violate any other right of any third parties, and that the Article has not been published elsewhere. Author(s) agree to the terms that the IJRDO Journal will have the full right to remove the published article on any misconduct found in the published article.
