Disc Diffusion Reader: an AI-powered potential solution to combat antibiotic resistance in developing countries

Introduction: Antimicrobial resistance (AMR) is a global health challenge, and antimicrobial susceptibility testing (AST) is vital for guiding treatment. Although widely used, the Kirby-Bauer method depends on skilled interpretation, which can be time-intensive and error-prone. This study explored...

Full description

Saved in:
Bibliographic Details
Main Authors: Hoang B Nguyen, Thanh L Phan, Thi T Ung, Thi KL Nguyen
Format: Article
Language:English
Published: The Journal of Infection in Developing Countries 2025-05-01
Series:Journal of Infection in Developing Countries
Subjects:
Online Access:https://jidc.org/index.php/journal/article/view/21108
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850210071002218496
author Hoang B Nguyen
Thanh L Phan
Thi T Ung
Thi KL Nguyen
author_facet Hoang B Nguyen
Thanh L Phan
Thi T Ung
Thi KL Nguyen
author_sort Hoang B Nguyen
collection DOAJ
description Introduction: Antimicrobial resistance (AMR) is a global health challenge, and antimicrobial susceptibility testing (AST) is vital for guiding treatment. Although widely used, the Kirby-Bauer method depends on skilled interpretation, which can be time-intensive and error-prone. This study explored the potential of an artificial intelligence (AI)-driven progressive web app (PWA) to automate the analysis of Kirby-Bauer test images, thereby enhancing accuracy and efficiency. Methodology: Images of Kirby-Bauer test results were annotated to train the Faster R-CNN ResNet-50 to detect agar plates, inhibition zones, and antibiotic discs. MobileNetv2 was used for antibiotic disc classification. A Human-in-the-Loop (HITL) approach enabled technicians to correct errors and improve model performance through retraining. The PWA, built with VueJS and Python-PHP, provided real-time analysis aligned with the Clinical and Laboratory Standards Institute (CLSI) and the European Committee on Antimicrobial Susceptibility Testing (EUCAST) standards. Results: The application achieved 92.95% accuracy for inhibition zone detection and 96.92% accuracy for antibiotic disc identification, with a performance improvement of 99.28% following HITL corrections. The measurements closely aligned with those of the technicians in 89.54% of the cases. The system processed up to 50 images per hour, supporting reliable and rapid AST workflow. Conclusions: The AI-powered “Disc Diffusion Reader” demonstrated high accuracy and efficiency, by reducing interpretation variability in the AST workflows. Its scalability and adaptability, particularly in low-resource settings, make it a valuable tool for combating AMR. Continuous retraining and validation will ensure sustained reliability, and highlight the potential of AI-driven solutions in modern microbiology.
format Article
id doaj-art-d30b367462184d7a9dfaa1724ba2f89f
institution OA Journals
issn 1972-2680
language English
publishDate 2025-05-01
publisher The Journal of Infection in Developing Countries
record_format Article
series Journal of Infection in Developing Countries
spelling doaj-art-d30b367462184d7a9dfaa1724ba2f89f2025-08-20T02:09:51ZengThe Journal of Infection in Developing CountriesJournal of Infection in Developing Countries1972-26802025-05-01190510.3855/jidc.21108Disc Diffusion Reader: an AI-powered potential solution to combat antibiotic resistance in developing countriesHoang B Nguyen0Thanh L Phan1Thi T Ung2Thi KL Nguyen3Department of Microbiology, Hue University of Medicine and Pharmacy, Hue University, Hue City, VietnamCenter for Information Technology, Hue University of Medicine and Pharmacy, Hue University, Hue City, VietnamDepartment of Microbiology, Hue University of Medicine and Pharmacy, Hue University, Hue City, VietnamDepartment of Microbiology, Hue University of Medicine and Pharmacy, Hue University, Hue City, Vietnam Introduction: Antimicrobial resistance (AMR) is a global health challenge, and antimicrobial susceptibility testing (AST) is vital for guiding treatment. Although widely used, the Kirby-Bauer method depends on skilled interpretation, which can be time-intensive and error-prone. This study explored the potential of an artificial intelligence (AI)-driven progressive web app (PWA) to automate the analysis of Kirby-Bauer test images, thereby enhancing accuracy and efficiency. Methodology: Images of Kirby-Bauer test results were annotated to train the Faster R-CNN ResNet-50 to detect agar plates, inhibition zones, and antibiotic discs. MobileNetv2 was used for antibiotic disc classification. A Human-in-the-Loop (HITL) approach enabled technicians to correct errors and improve model performance through retraining. The PWA, built with VueJS and Python-PHP, provided real-time analysis aligned with the Clinical and Laboratory Standards Institute (CLSI) and the European Committee on Antimicrobial Susceptibility Testing (EUCAST) standards. Results: The application achieved 92.95% accuracy for inhibition zone detection and 96.92% accuracy for antibiotic disc identification, with a performance improvement of 99.28% following HITL corrections. The measurements closely aligned with those of the technicians in 89.54% of the cases. The system processed up to 50 images per hour, supporting reliable and rapid AST workflow. Conclusions: The AI-powered “Disc Diffusion Reader” demonstrated high accuracy and efficiency, by reducing interpretation variability in the AST workflows. Its scalability and adaptability, particularly in low-resource settings, make it a valuable tool for combating AMR. Continuous retraining and validation will ensure sustained reliability, and highlight the potential of AI-driven solutions in modern microbiology. https://jidc.org/index.php/journal/article/view/21108drug resistanceartificial intelligencedeveloping countriesdisc diffusion methodneural networks
spellingShingle Hoang B Nguyen
Thanh L Phan
Thi T Ung
Thi KL Nguyen
Disc Diffusion Reader: an AI-powered potential solution to combat antibiotic resistance in developing countries
Journal of Infection in Developing Countries
drug resistance
artificial intelligence
developing countries
disc diffusion method
neural networks
title Disc Diffusion Reader: an AI-powered potential solution to combat antibiotic resistance in developing countries
title_full Disc Diffusion Reader: an AI-powered potential solution to combat antibiotic resistance in developing countries
title_fullStr Disc Diffusion Reader: an AI-powered potential solution to combat antibiotic resistance in developing countries
title_full_unstemmed Disc Diffusion Reader: an AI-powered potential solution to combat antibiotic resistance in developing countries
title_short Disc Diffusion Reader: an AI-powered potential solution to combat antibiotic resistance in developing countries
title_sort disc diffusion reader an ai powered potential solution to combat antibiotic resistance in developing countries
topic drug resistance
artificial intelligence
developing countries
disc diffusion method
neural networks
url https://jidc.org/index.php/journal/article/view/21108
work_keys_str_mv AT hoangbnguyen discdiffusionreaderanaipoweredpotentialsolutiontocombatantibioticresistanceindevelopingcountries
AT thanhlphan discdiffusionreaderanaipoweredpotentialsolutiontocombatantibioticresistanceindevelopingcountries
AT thitung discdiffusionreaderanaipoweredpotentialsolutiontocombatantibioticresistanceindevelopingcountries
AT thiklnguyen discdiffusionreaderanaipoweredpotentialsolutiontocombatantibioticresistanceindevelopingcountries