Integrating AI-Driven Triage into Digital Pharmacy Systems for Rational Antibiotic Use in Low-Resource Settings

Emon Ghosh, Md. Jobayer Rahman, Shamim Ahamed, Marium Salwa, Tahmina Foyez, Khondaker A. Mamun
Proceedings of The Second AAAI Bridge Program on AI for Medicine and Healthcare, PMLR 317:102-109, 2026.

Abstract

Antimicrobial resistance (AMR) is becoming a bigger threat to global health, especially in low- and middle-income countries (LMICs), where antibiotics are often given out without a prescription. This study presents a hybrid Artificial Intelligence (AI) framework to improve rational antibiotic utilization by integrating pharmacies, telemedicine practitioners, and policymakers through an integrated digital infrastructure. The digital intervention system was implemented in 28 community pharmacies and showed significant improvements in how people used antibiotics. Specifically, the percentage of people who self-medicated with antibiotics dropped from 4.05% to 0.86%, and the percentage of people who bought antibiotics with a prescription jumped from 27.6% to 43.5%. We propose an AI framework that combines a machine learning (ML)-based and a large language model (LLM)-based symptom checker for intelligent triage and clinical decision support. These models will enable efficient analysis of both structured and narrative symptom data, which will help pharmacists provide advice and doctors refer patients right away. The suggested model demonstrates a scalable, data-driven, and human-in-the-loop approach to antibiotic stewardship, with the potential to support future AMR mitigation and healthcare accessibility in LMICs settings.

Cite this Paper

BibTeX
@InProceedings{pmlr-v317-ghosh26a, title = {Integrating AI-Driven Triage into Digital Pharmacy Systems for Rational Antibiotic Use in Low-Resource Settings}, author = {Ghosh, Emon and Rahman, Md. Jobayer and Ahamed, Shamim and Salwa, Marium and Foyez, Tahmina and Mamun, Khondaker A.}, booktitle = {Proceedings of The Second AAAI Bridge Program on AI for Medicine and Healthcare}, pages = {102--109}, year = {2026}, editor = {Wu, Junde and Pan, Jiazhen and Zhu, Jiayuan and Luo, Luyang and Li, Yitong and Xu, Min and Jin, Yueming and Rueckert, Daniel}, volume = {317}, series = {Proceedings of Machine Learning Research}, month = {20--21 Jan}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v317/main/assets/ghosh26a/ghosh26a.pdf}, url = {https://proceedings.mlr.press/v317/ghosh26a.html}, abstract = {Antimicrobial resistance (AMR) is becoming a bigger threat to global health, especially in low- and middle-income countries (LMICs), where antibiotics are often given out without a prescription. This study presents a hybrid Artificial Intelligence (AI) framework to improve rational antibiotic utilization by integrating pharmacies, telemedicine practitioners, and policymakers through an integrated digital infrastructure. The digital intervention system was implemented in 28 community pharmacies and showed significant improvements in how people used antibiotics. Specifically, the percentage of people who self-medicated with antibiotics dropped from 4.05% to 0.86%, and the percentage of people who bought antibiotics with a prescription jumped from 27.6% to 43.5%. We propose an AI framework that combines a machine learning (ML)-based and a large language model (LLM)-based symptom checker for intelligent triage and clinical decision support. These models will enable efficient analysis of both structured and narrative symptom data, which will help pharmacists provide advice and doctors refer patients right away. The suggested model demonstrates a scalable, data-driven, and human-in-the-loop approach to antibiotic stewardship, with the potential to support future AMR mitigation and healthcare accessibility in LMICs settings.} }
Endnote
%0 Conference Paper %T Integrating AI-Driven Triage into Digital Pharmacy Systems for Rational Antibiotic Use in Low-Resource Settings %A Emon Ghosh %A Md. Jobayer Rahman %A Shamim Ahamed %A Marium Salwa %A Tahmina Foyez %A Khondaker A. Mamun %B Proceedings of The Second AAAI Bridge Program on AI for Medicine and Healthcare %C Proceedings of Machine Learning Research %D 2026 %E Junde Wu %E Jiazhen Pan %E Jiayuan Zhu %E Luyang Luo %E Yitong Li %E Min Xu %E Yueming Jin %E Daniel Rueckert %F pmlr-v317-ghosh26a %I PMLR %P 102--109 %U https://proceedings.mlr.press/v317/ghosh26a.html %V 317 %X Antimicrobial resistance (AMR) is becoming a bigger threat to global health, especially in low- and middle-income countries (LMICs), where antibiotics are often given out without a prescription. This study presents a hybrid Artificial Intelligence (AI) framework to improve rational antibiotic utilization by integrating pharmacies, telemedicine practitioners, and policymakers through an integrated digital infrastructure. The digital intervention system was implemented in 28 community pharmacies and showed significant improvements in how people used antibiotics. Specifically, the percentage of people who self-medicated with antibiotics dropped from 4.05% to 0.86%, and the percentage of people who bought antibiotics with a prescription jumped from 27.6% to 43.5%. We propose an AI framework that combines a machine learning (ML)-based and a large language model (LLM)-based symptom checker for intelligent triage and clinical decision support. These models will enable efficient analysis of both structured and narrative symptom data, which will help pharmacists provide advice and doctors refer patients right away. The suggested model demonstrates a scalable, data-driven, and human-in-the-loop approach to antibiotic stewardship, with the potential to support future AMR mitigation and healthcare accessibility in LMICs settings.
APA
Ghosh, E., Rahman, M.J., Ahamed, S., Salwa, M., Foyez, T. & Mamun, K.A.. (2026). Integrating AI-Driven Triage into Digital Pharmacy Systems for Rational Antibiotic Use in Low-Resource Settings. Proceedings of The Second AAAI Bridge Program on AI for Medicine and Healthcare, in Proceedings of Machine Learning Research 317:102-109 Available from https://proceedings.mlr.press/v317/ghosh26a.html.

Related Material