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.
OBJECTIVES Antibiotic exposure in children is a possible contributor to the increasing asthma prevalence in several countries. The present study aimed to investigate the association between antibiotic exposure and the risk of developing childhood asthma at 2-8 years of age.
METHODS
A case-control study was undertaken among children aged 2-8 years old between March and September 2010 in the Urmia district in the northwest of Iran. The cases were doctor-diagnosed asthmatic children based on Global Initiative for Asthma criteria (n=207), and the controls were children without respiratory symptoms (n=400) selected by frequency matching by age and gender. Clinical data including antibiotic exposure was collected by a validated and reliable questionnaire, which was completed by interviewing parents/guardians.
RESULTS
Antibiotic consumption during the first year of life increased the odds ratio [OR] of asthma symptoms at 2-8 years of age (crude OR, 2.26; 95% confidence interval [CI], 1.53-3.35; p<0.01), and the strength of association was similar after adjusting for a family history of asthma or atopic disorder, preterm delivery, birth order, and delivery method (adjusted OR, 1.91; 95% CI, 1.27-2.88; p=0.03).
CONCLUSIONS
Our study suggests that antibiotic consumption in children was associated with an increased risk of childhood asthma, and an additional confirmative study is needed.
Summary
Citations
Citations to this article as recorded by
Innovative Therapeutic Strategies for Asthma: The Role of Gut Microbiome in Airway Immunity Yaqin Liu, Junjie Dai, Guibao Zhou, Rongchang Chen, Chengwen Bai, Fei Shi Journal of Asthma and Allergy.2025; Volume 18: 257. CrossRef
Progress in Etiology of Persistent Wheezing in Infants 睿 彭 Advances in Clinical Medicine.2024; 14(04): 909. CrossRef
Antibiotic exposure and adverse long-term health outcomes in children: A systematic review and meta-analysis Quynh A Duong, Laure F Pittet, Nigel Curtis, Petra Zimmermann Journal of Infection.2022; 85(3): 213. CrossRef
Analysis of medication patterns for pediatric asthma patients in emergency department: Does the sequence placement of glucocorticoids administration matter? Hoon Jang, Mustafa Ozkaynak, Claudia R. Amura, Turgay Ayer, Marion R. Sills Journal of Asthma.2021; 58(2): 180. CrossRef
Factors Associated With First Medication Time for Children Treated in the Emergency Department for Asthma Hoon Jang, Mustafa Ozkaynak, Turgay Ayer, Marion R. Sills Pediatric Emergency Care.2021; 37(1): e42. CrossRef
Predicting hospitalization of pediatric asthma patients in emergency departments using machine learning Marion R. Sills, Mustafa Ozkaynak, Hoon Jang International Journal of Medical Informatics.2021; 151: 104468. CrossRef
Risk factors of asthma in the Asian population: a systematic review and meta-analysis Yang Yie Sio, Fook Tim Chew Journal of Physiological Anthropology.2021;[Epub] CrossRef
Association of infant antibiotic exposure and risk of childhood asthma: A meta-analysis Zeyi Zhang, Jingjing Wang, Haixia Wang, Yizhang Li, Yuanmin Jia, Mo Yi, Ou Chen World Allergy Organization Journal.2021; 14(11): 100607. CrossRef
Early-Life Exposure to Oral Antibiotics and Lung Function Into Early Adulthood Karoliny dos Santos, Caroline J. Lodge, Michael J. Abramson, Bircan Erbas, Catherine M. Bennett, Jennie Hui, Shyamali C. Dharmage, Adrian J. Lowe Chest.2020; 157(2): 334. CrossRef
The relationship of prenatal antibiotic exposure and infant antibiotic administration with childhood allergies: a systematic review Ruth Baron, Meron Taye, Isolde Besseling-van der Vaart, Joanne Ujčič-Voortman, Hania Szajewska, Jacob C. Seidell, Arnoud Verhoeff BMC Pediatrics.2020;[Epub] CrossRef
Respiratory morbidity, atopy and asthma at school age in preterm infants aged 32–35 weeks Júlia Morata-Alba, Maria Teresa Romero-Rubio, Silvia Castillo-Corullón, Amparo Escribano-Montaner European Journal of Pediatrics.2019; 178(7): 973. CrossRef
Evaluation of Allergic Symptoms Prevalence and Its Relationship with Acetaminophen/Antibiotic Use and Hospitalization Among School-Aged Children in Tehran, Iran Mohammad Reza Fazlollahi, Javid Morad Abbasi, Vahid Ghobadi Dana, Alireza Yousefzade, Nastaran Sabetkish, Shahpar Haghighat Iranian Red Crescent Medical Journal.2017;[Epub] CrossRef
Airway Microbiota and the Implications of Dysbiosis in Asthma Juliana Durack, Homer A. Boushey, Susan V. Lynch Current Allergy and Asthma Reports.2016;[Epub] CrossRef
Early-life antibiotic use is associated with wheezing among children with high atopic risk: a prospective European study Wenjie Sun, Erik R. Svendsen, Wilfried J. J. Karmaus, Joachim Kuehr, Johannes Forster Journal of Asthma.2015; 52(7): 647. CrossRef
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.