Predicting over-the-counter antibiotic use in rural Pune, India, using machine learning methods
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 we...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Korean Society of Epidemiology
2024-04-01
|
| Series: | Epidemiology and Health |
| Subjects: | |
| Online Access: | http://www.e-epih.org/upload/pdf/epih-46-e2024044.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850196568996577280 |
|---|---|
| author | Pravin Arun Sawant Sakshi Shantanu Hiralkar Yogita Purushottam Hulsurkar Mugdha Sharad Phutane Uma Satish Mahajan Abhay Machindra Kudale |
| author_facet | Pravin Arun Sawant Sakshi Shantanu Hiralkar Yogita Purushottam Hulsurkar Mugdha Sharad Phutane Uma Satish Mahajan Abhay Machindra Kudale |
| author_sort | Pravin Arun Sawant |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-f65de940f8da4fae97ec7e64b211f2e2 |
| institution | OA Journals |
| issn | 2092-7193 |
| language | English |
| publishDate | 2024-04-01 |
| publisher | Korean Society of Epidemiology |
| record_format | Article |
| series | Epidemiology and Health |
| spelling | doaj-art-f65de940f8da4fae97ec7e64b211f2e22025-08-20T02:13:26ZengKorean Society of EpidemiologyEpidemiology and Health2092-71932024-04-014610.4178/epih.e20240441510Predicting over-the-counter antibiotic use in rural Pune, India, using machine learning methodsPravin Arun Sawant0Sakshi Shantanu Hiralkar1Yogita Purushottam Hulsurkar2Mugdha Sharad Phutane3Uma Satish Mahajan4Abhay Machindra Kudale5 Department of Health Sciences, School of Health Sciences, Savitribai Phule Pune University, Pune, India Department of Health Sciences, School of Health Sciences, Savitribai Phule Pune University, Pune, India Department of Health Sciences, School of Health Sciences, Savitribai Phule Pune University, Pune, India Department of Health Sciences, School of Health Sciences, Savitribai Phule Pune University, Pune, India Department of Health Sciences, School of Health Sciences, Savitribai Phule Pune University, Pune, India Department of Health Sciences, School of Health Sciences, Savitribai Phule Pune University, Pune, IndiaOBJECTIVES 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.http://www.e-epih.org/upload/pdf/epih-46-e2024044.pdfantibiotic resistanceantibioticpharmacymachine learningalgorithmindia |
| spellingShingle | Pravin Arun Sawant Sakshi Shantanu Hiralkar Yogita Purushottam Hulsurkar Mugdha Sharad Phutane Uma Satish Mahajan Abhay Machindra Kudale Predicting over-the-counter antibiotic use in rural Pune, India, using machine learning methods Epidemiology and Health antibiotic resistance antibiotic pharmacy machine learning algorithm india |
| title | Predicting over-the-counter antibiotic use in rural Pune, India, using machine learning methods |
| title_full | Predicting over-the-counter antibiotic use in rural Pune, India, using machine learning methods |
| title_fullStr | Predicting over-the-counter antibiotic use in rural Pune, India, using machine learning methods |
| title_full_unstemmed | Predicting over-the-counter antibiotic use in rural Pune, India, using machine learning methods |
| title_short | Predicting over-the-counter antibiotic use in rural Pune, India, using machine learning methods |
| title_sort | predicting over the counter antibiotic use in rural pune india using machine learning methods |
| topic | antibiotic resistance antibiotic pharmacy machine learning algorithm india |
| url | http://www.e-epih.org/upload/pdf/epih-46-e2024044.pdf |
| work_keys_str_mv | AT pravinarunsawant predictingoverthecounterantibioticuseinruralpuneindiausingmachinelearningmethods AT sakshishantanuhiralkar predictingoverthecounterantibioticuseinruralpuneindiausingmachinelearningmethods AT yogitapurushottamhulsurkar predictingoverthecounterantibioticuseinruralpuneindiausingmachinelearningmethods AT mugdhasharadphutane predictingoverthecounterantibioticuseinruralpuneindiausingmachinelearningmethods AT umasatishmahajan predictingoverthecounterantibioticuseinruralpuneindiausingmachinelearningmethods AT abhaymachindrakudale predictingoverthecounterantibioticuseinruralpuneindiausingmachinelearningmethods |