Predicting over-the-counter antibiotic use in rural Pune, India, using machine learning methods
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
OBJECTIVES: Over-the-counter (OTC) antibiotic use can cause antibiotic resistance, threatening global public health gains. To counter OTC use, this study used machine learning (ML) methods to identify predictors of OTC antibiotic use in rural Pune, India.METHODS: The features of OTC antibiotic use were selected using stepwise logistic, lasso, random forest, XGBoost, and Boruta algorithms. Regression and tree-based models with all confirmed and tentatively important features were built to predict the use of OTC antibiotics. Five-fold cross-validation was used to tune the models’ hyperparameters. The final model was selected based on the highest area under the curve (AUROC) with a 95% confidence interval (CI) and the lowest log-loss.RESULTS: In rural Pune, the prevalence of OTC antibiotic use was 35.9% (95% CI, 31.6 to 40.5). The perception that buying medicines directly from a medicine shop/pharmacy is useful, using antibiotics for eye-related complaints, more household members consuming antibiotics, and longer duration and higher doses of antibiotic consumption in rural blocks and other social groups were confirmed as important features by the Boruta algorithm. The final model was the XGBoost+Boruta model with 7 predictors (AUROC, 0.934; 95% CI, 0.891 to 0.978; log-loss, 0.279) log-loss.CONCLUSIONS: XGBoost+Boruta, with 7 predictors, was the most accurate model for predicting OTC antibiotic use in rural Pune. Using OTC antibiotics for eye-related complaints, higher consumption of antibiotics and the perception that buying antibiotics directly from a medicine shop/pharmacy is useful were identified as key factors for planning interventions to improve awareness about proper antibiotic use.
Abstract
OBJECTIVES: Over-the-counter (OTC) antibiotic use can cause antibiotic resistance, threatening global public health gains. To counter OTC use, this study used machine learning (ML) methods to identify predictors of OTC antibiotic use in rural Pune, India.METHODS: The features of OTC antibiotic use were selected using stepwise logistic, lasso, random forest, XGBoost, and Boruta algorithms. Regression and tree-based models with all confirmed and tentatively important features were built to predict the use of OTC antibiotics. Five-fold cross-validation was used to tune the models’ hyperparameters. The final model was selected based on the highest area under the curve (AUROC) with a 95% confidence interval (CI) and the lowest log-loss.RESULTS: In rural Pune, the prevalence of OTC antibiotic use was 35.9% (95% CI, 31.6 to 40.5). The perception that buying medicines directly from a medicine shop/pharmacy is useful, using antibiotics for eye-related complaints, more household members consuming antibiotics, and longer duration and higher doses of antibiotic consumption in rural blocks and other social groups were confirmed as important features by the Boruta algorithm. The final model was the XGBoost+Boruta model with 7 predictors (AUROC, 0.934; 95% CI, 0.891 to 0.978; log-loss, 0.279) log-loss.CONCLUSIONS: XGBoost+Boruta, with 7 predictors, was the most accurate model for predicting OTC antibiotic use in rural Pune. Using OTC antibiotics for eye-related complaints, higher consumption of antibiotics and the perception that buying antibiotics directly from a medicine shop/pharmacy is useful were identified as key factors for planning interventions to improve awareness about proper antibiotic use.
참고문헌 (45)
- Nafade V, "Over-the-counter antibiotic dispensing by pharmacies : a standardised patient study in Udupi district, India", BMJ Glob Health, 4, pp.e001869~ (2019)[DOI]
- Adhikari B, "Why do people purchase antibiotics over-the-counter? A qualitative study with patients, clinicians and dispensers in central, eastern and western Nepal", BMJ Glob Health, 6, pp.e005829~ (2021)[DOI]
- Jacobs TG, "Assessing the impact of law enforcement to reduce over-the-counter(OTC)sales of antibiotics in low-and middle-income countries; a systematic literature review", BMC Health Serv Res, 19, pp.536~ (2019)[DOI]
- Porter G, "Over-the-counter sales of antibiotics for human use in India : the challenges and opportunities for regulation", Med Law Int, 21, pp.147~173 (2021)[DOI]
- Kotwani A, "Knowledge and behavior of consumers towards the non-prescription purchase of antibiotics : an insight from a qualitative study from New Delhi, India", Pharm Pract(Granada), 19, pp.2206~ (2021)[DOI]
- Blondeau LD, "Diagnostics and therapy in veterinary dermatology", pp.163~174 (2021), John Wiley & Sons, Inc
- Franco BE, "The determinants of the antibiotic resistance process", Infect Drug Resist, 2, pp.1~11 (2009)[DOI]
- Nayiga S, "Use of antibiotics to treat humans and animals in Uganda: a cross-sectional survey of households and farmers in rural, urban and peri-urban settings", JAC Antimicrob Resist, 2, pp.dlaa082~ (2020)[DOI]
- Kotwani A, "Over-the-counter sale of antibiotics in India : a qualitative study of providers’ perspectives across two states", Antibiotics(Basel), 10, pp.1123~ (2021)[DOI]
- "Kerala comes up with operation AMRITH to tackle AMR" (2024)[URL]
- Rabaan AA, "Application of artificial intelligence in combating high antimicrobial resistance rates", Antibiotics(Basel), 11, pp.784~ (2022)[DOI]
- Liu Z, "Evaluation of machine learning models for predicting antimicrobial resistance of Actinobacillus pleuropneumoniae from whole genome sequences", Front Microbiol, 11, pp.48~ (2020)[DOI]
- Yang Y, "Machine learning for classifying tuberculosis drug-resistance from DNA sequencing data", Bioinformatics, 34, pp.1666~1671 (2018)[DOI]
- Arango-Argoty G, "DeepARG : a deep learning approach for predicting antibiotic resistance genes from metagenomic data", Microbiome, 6, pp.23~ (2018)[DOI]
- Stokes JM, "A deep learning approach to antibiotic discovery", Cell, 180, pp.688~702 (2020)[DOI]
- Oonsivilai M, "Using machine learning to guide targeted and locally-tailored empiric antibiotic prescribing in a children’s hospital in Cambodia", Wellcome Open Res, 3, pp.131~ (2018)[DOI]
- Martínez-Agüero S, "Machine learning techniques to identify antimicrobial resistance in the intensive care unit", Entropy(Basel), 21, pp.603~ (2019)[DOI]
- Feretzakis G, "Using machine learning techniques to aid empirical antibiotic therapy decisions in the intensive care unit of a general hospital in Greece", Antibiotics(Basel), 9, pp.50~ (2020)[DOI]
- Brown LD, "Interval estimation for a binomial proportion", Stat Sci, 16, pp.101~133 (2001)[DOI]
- Tibshirani R, "Regression shrinkage and selection via the lasso", J R Stat Soc Ser B Stat Methodol, 58, pp.267~288 (1996)[DOI]
- Kursa MB, "Feature selection with the boruta package", J Stat Softw, 36, pp.1~13 (2010)[DOI]
- Breiman L, "Random forests", Mach Learn, 45, pp.5~32 (2001)[DOI]
- Friedman JH, "Greedy function approximation : a gradient boosting machine", Ann Stat, 29, pp.1189~1232 (2001)[DOI]
- Viljanen M, "A machine learning approach to small area estimation : predicting the health, housing and well-being of the population of Netherlands", Int J Health Geogr, 21, pp.4~ (2022)[DOI]
- Mahajan U, "Advances in signal and data processing. Lecture notes in electrical engineering, vol 703", pp.561~573 (2021), Springer
- Fernández-Delgado M, "Do we need hundreds of classifiers to solve real world classification problems?", J Mach Learn Res, 15, pp.3133~3181 (2014)
- Harrison CJ, "Machine learning in medicine : a practical introduction to natural language processing", BMC Med Res Methodol, 21, pp.158~ (2021)[DOI]
- Wiemken TL, "Machine learning in epidemiology and health outcomes research", Annu Rev Public Health, 41, pp.21~36 (2020)[DOI]
- Toubiana L, "Some innovative approaches for public health and epidemiology informatics", Yearb Med Inform, 25, pp.247~250 (2016)[DOI]
- Diallo G, "Novelty in public health and epidemiology informatics", Yearb Med Inform, 31, pp.273~275 (2022)[DOI]
- Poudel GR, "Machine learning for prediction of cognitive health in adults using sociodemographic, neighbourhood environmental, and lifestyle factors", Int J Environ Res Public Health, 19, pp.10977~ (2022)[DOI]
- Peng Z, "Whole-genome sequencing and gene sharing network analysis powered by machine learning identifies antibiotic resistance sharing between animals, humans and environment in livestock farming", PLoS Comput Biol, 18, pp.e1010018~ (2022)[DOI]
- Ren Y, "Prediction of antimicrobial resistance based on whole-genome sequencing and machine learning", Bioinformatics, 38, pp.325~334 (2022)[DOI]
- Imchen M, "Current trends in experimental and computational approaches to combat antimicrobial resistance", Front Genet, 11, pp.563975~ (2020)[DOI]
- Corbin CK, "Personalized antibiograms for machine learning driven antibiotic selection", Commun Med(Lond), 2, pp.38~ (2022)[DOI]
- Kouchaki S, "Application of machine learning techniques to tuberculosis drug resistance analysis", Bioinformatics, 35, pp.2276~2282 (2019)[DOI]
- Sharma A, "Tuberculosis drug resistance profiling based on machine learning : a literature review", Braz J Infect Dis, 26, pp.102332~ (2022)[DOI]
- Wilkins JJ, "Pharmacometrics in tuberculosis : progress and opportunities", Int J Antimicrob Agents, 60, pp.106620~ (2022)[DOI]
- David L, "Artificial intelligence and antibiotic discovery", Antibiotics(Basel), 10, pp.1376~ (2021)[DOI]
- Sakagianni A, "Using machine learning to predict antimicrobial resistance-a literature review", Antibiotics(Basel), 12, pp.452~ (2023)[DOI]
- Yasir M, "Application of decision-tree-based machine learning algorithms for prediction of antimicrobial resistance", Antibiotics(Basel), 11, pp.1593~ (2022)[DOI]
- Maviglia R, "Machine learning and antibiotic management", Antibiotics(Basel), 11, pp.304~ (2022)[DOI]
- Anahtar MN, "Applications of machine learning to the problem of antimicrobial resistance : an emerging model for translational research", J Clin Microbiol, 59, pp.e0126020~ (2021)[DOI]
- Wong JG, "Risk prediction models to guide antibiotic prescribing : a study on adult patients with uncomplicated upper respiratory tract infections in an emergency department", Antimicrob Resist Infect Control, 9, pp.171~ (2020)[DOI]