Skip Navigation
Skip to contents

Epidemiol Health : Epidemiology and Health

OPEN ACCESS
SEARCH
Search

Search

Page Path
HOME > Search
2 "Antibiotic resistance"
Filter
Filter
Article category
Keywords
Publication year
Authors
Original Articles
Predicting over-the-counter antibiotic use in rural Pune, India, using machine learning methods
Pravin Arun Sawant, Sakshi Shantanu Hiralkar, Yogita Purushottam Hulsurkar, Mugdha Sharad Phutane, Uma Satish Mahajan, Abhay Machindra Kudale
Epidemiol Health. 2024;46:e2024044.   Published online April 13, 2024
DOI: https://doi.org/10.4178/epih.e2024044
  • 2,500 View
  • 84 Download
AbstractAbstract PDFSupplementary Material
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.
Summary
Characteristics of Shigella sonnei Isolated in Kyungsangbuk-do in 1998: Biochemical Characteristics, Biotyping, Antibiotic Resistance Pattern, and Plasmid Profile.
Chang Kyu Sohn, Wan Huh, Doo Young Lee, Si Kyu Lim, Je Wook Lee, Byung Chun Kim, Wan Park
Korean J Epidemiol. 1999;21(2):227-233.
  • 5,694 View
  • 8 Download
AbstractAbstract PDF
Abstract
Thirty nine strains and 109 strains of Shigella sonnei were isolated from the outbreaks of Youngchun and Kyungju, respectively, while 15 strains were isolated from sporadic cases of eight regions in Kyungbuk province from September to November in 1998. We investigated the relationship among the S. sonnei strains by using biochemical characteristics, biotyping, antibiotic resistance pattern, and plasmid profile. Among the isolates, seven strains of S. sonnei isolated in Youngchun showed gelatin hydrolyase positive but the others showed gelatin hydrolyase negative. One hundred and fifty two strains were a type, while eleven among thirty nine strains isolated in Youngchun were g type. Antibiotics resistance patterns of S. sonnei strains isolated in Youngchun and Kyungju were significantly different. Thirty nine strains of S. sonnei isolated in Youngchun were resistant to SM, TE, and TMP/SMX, while eighty six of S. sonnei among one hundred and nine strains isolated in Kyungju were resistant to AM, CB, K, SM, TE, and TMP/SMX. Antibiotics resistance patterns of residual twenty three isolates were similar to those of eighty six strains. The Plasmid profiles of strains of S. sonnei isolated from the Kyungju were different from those of S. sonnei strains isolated in Youngchun. The Plasmid profiles of S. sonnei strains isolated from Youngchun were identical to those of a S. sonnei strains randomly selected from the outbreak in Daegu in 1998. The Plasmid profiles of S. sonnei strains isolated from Kyungju were identical to those of two strains of S. sonnei randomly selected from the outbreaks of Kanglung and Wonju in 1998. From the above results, it is considered that the strains of S. sonnei isolated from Kyungju and Youngchun region are not identical clone.
Summary

Epidemiol Health : Epidemiology and Health
TOP