Prediction of antibiotic resistance from antibiotic susceptibility testing results from surveillance data using machine learning
Abstract Antimicrobial resistance is a growing global health threat, and artificial intelligence offers a promising avenue for developing advanced tools to address this challenge. In this study, we applied various machine learning techniques to predict bacterial antibiotic resistance using the Pfize...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-08-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-14078-w |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849226339694936064 |
|---|---|
| author | Swetha Valavarasu Yasaswini Sangu Tanmaya Mahapatra |
| author_facet | Swetha Valavarasu Yasaswini Sangu Tanmaya Mahapatra |
| author_sort | Swetha Valavarasu |
| collection | DOAJ |
| description | Abstract Antimicrobial resistance is a growing global health threat, and artificial intelligence offers a promising avenue for developing advanced tools to address this challenge. In this study, we applied various machine learning techniques to predict bacterial antibiotic resistance using the Pfizer ATLAS Antibiotics dataset. This comprehensive dataset includes patient demographic data, sample collection details, antibiotic susceptibility test results, and resistance phenotypes for 917,049 bacterial isolates. The dataset was divided into two subsets: Phenotype-Only and Phenotype + Genotype, excluding and including 589,998 isolates with genotype data, respectively. Both subsets underwent exploratory data analysis, preprocessing, machine learning model training, validation, and optimization. XGBoost consistently outperformed other models, achieving AUC values of 0.96 and 0.95 for the Phenotype-Only and Phenotype + Genotype sets, respectively. Hyperparameter tuning yielded slight accuracy improvements, while data balancing techniques notably increased recall. Across all models, the antibiotic used emerged as the most influential feature in predicting resistance outcomes. The SHAP summary plots generated provide insights into model interpretability. Our findings provide valuable insights into global AMR patterns and demonstrate the potential of AI-driven approaches for resistance prediction to help inform clinical decision-making and support the formulation of effective AMR mitigation policies, subject to the availability of highly granular datasets. |
| format | Article |
| id | doaj-art-349100a1103d4666a5ec3db7f3ef7d0f |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-349100a1103d4666a5ec3db7f3ef7d0f2025-08-24T11:23:01ZengNature PortfolioScientific Reports2045-23222025-08-0115111210.1038/s41598-025-14078-wPrediction of antibiotic resistance from antibiotic susceptibility testing results from surveillance data using machine learningSwetha Valavarasu0Yasaswini Sangu1Tanmaya Mahapatra2Department of Computer Science and Information Systems, Birla Institute of Technology and ScienceDepartment of Computer Science and Information Systems, Birla Institute of Technology and ScienceDepartment of Computer Science and Information Systems, Birla Institute of Technology and ScienceAbstract Antimicrobial resistance is a growing global health threat, and artificial intelligence offers a promising avenue for developing advanced tools to address this challenge. In this study, we applied various machine learning techniques to predict bacterial antibiotic resistance using the Pfizer ATLAS Antibiotics dataset. This comprehensive dataset includes patient demographic data, sample collection details, antibiotic susceptibility test results, and resistance phenotypes for 917,049 bacterial isolates. The dataset was divided into two subsets: Phenotype-Only and Phenotype + Genotype, excluding and including 589,998 isolates with genotype data, respectively. Both subsets underwent exploratory data analysis, preprocessing, machine learning model training, validation, and optimization. XGBoost consistently outperformed other models, achieving AUC values of 0.96 and 0.95 for the Phenotype-Only and Phenotype + Genotype sets, respectively. Hyperparameter tuning yielded slight accuracy improvements, while data balancing techniques notably increased recall. Across all models, the antibiotic used emerged as the most influential feature in predicting resistance outcomes. The SHAP summary plots generated provide insights into model interpretability. Our findings provide valuable insights into global AMR patterns and demonstrate the potential of AI-driven approaches for resistance prediction to help inform clinical decision-making and support the formulation of effective AMR mitigation policies, subject to the availability of highly granular datasets.https://doi.org/10.1038/s41598-025-14078-wAntibiotic resistanceAntibiotic susceptibility testingMachine learningAMR prediction |
| spellingShingle | Swetha Valavarasu Yasaswini Sangu Tanmaya Mahapatra Prediction of antibiotic resistance from antibiotic susceptibility testing results from surveillance data using machine learning Scientific Reports Antibiotic resistance Antibiotic susceptibility testing Machine learning AMR prediction |
| title | Prediction of antibiotic resistance from antibiotic susceptibility testing results from surveillance data using machine learning |
| title_full | Prediction of antibiotic resistance from antibiotic susceptibility testing results from surveillance data using machine learning |
| title_fullStr | Prediction of antibiotic resistance from antibiotic susceptibility testing results from surveillance data using machine learning |
| title_full_unstemmed | Prediction of antibiotic resistance from antibiotic susceptibility testing results from surveillance data using machine learning |
| title_short | Prediction of antibiotic resistance from antibiotic susceptibility testing results from surveillance data using machine learning |
| title_sort | prediction of antibiotic resistance from antibiotic susceptibility testing results from surveillance data using machine learning |
| topic | Antibiotic resistance Antibiotic susceptibility testing Machine learning AMR prediction |
| url | https://doi.org/10.1038/s41598-025-14078-w |
| work_keys_str_mv | AT swethavalavarasu predictionofantibioticresistancefromantibioticsusceptibilitytestingresultsfromsurveillancedatausingmachinelearning AT yasaswinisangu predictionofantibioticresistancefromantibioticsusceptibilitytestingresultsfromsurveillancedatausingmachinelearning AT tanmayamahapatra predictionofantibioticresistancefromantibioticsusceptibilitytestingresultsfromsurveillancedatausingmachinelearning |