Towards AI-Based Strep Throat Detection and Interpretation for Remote Australian Indigenous Communities
Sensors · 10.09.2025 · 25 (18) · 5636
DOI: 10.3390/s25185636 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 10.09.2025. Verfasst von Prasanna Asokan und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Electrical Engineering, Computing and Mathematics Sciences, Curtin University, Perth, WA 6102, Australia. Hauptthemen laut MEDLINE: Pharyngitis, Streptococcal Infections, Artificial Intelligence. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the support from Department of Health WA and Curtin University as part of The Challenge 2024, Department of Health WA and Curtin University.
Abstract (Originalsprache)
Streptococcus pharyngitis (strep throat) poses a significant health challenge in rural and remote Indigenous communities in Australia, where access to medical resources is limited. Delays in diagnosis and treatment increase the risk of serious complications, including acute rheumatic fever and rheumatic heart disease. This paper presents a proof-of-concept AI-based diagnostic model designed to support clinicians in underserved communities. The model combines a lightweight Swin Transformer–based image classifier with a BLIP-2-based explainable image annotation system. The classifier predicts strep throat from throat images, while the explainable model enhances transparency by identifying key clinical features such as tonsillar swelling, erythema, and exudate, with synthetic labels generated using GPT-4o-mini. The classifier achieves 97.1% accuracy and an ROC-AUC of 0.993, with an inference time of 13.8 ms and a model size of 28 million parameters; these results demonstrate suitability for deployment in resource-constrained settings. As a proof-of-concept, this work illustrates the potential of AI-assisted diagnostics to improve healthcare access and could benefit similar research efforts that support clinical decision-making in remote and underserved regions.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Electrical Engineering, Computing and Mathematics Sciences, Curtin University, Perth, WA 6102, Australia.
- Curtin School of Allied Health, Curtin University, Perth, WA 6102, Australia.
- Exercise Physiology Department, Fiona Stanley Hospital, Perth, WA 6102, Australia.
- School of Molecular and Life Sciences, Curtin University, Perth, WA 6102, Australia.
ORCID-Profile: Duc Son Pham, Kit Yan Chan, Susannah Soon, Andrew Maiorana
Förderung
- the support from Department of Health WA and Curtin University as part of The Challenge 2024
- Department of Health WA and Curtin University
Zitieren
APA
Asokan, P., Truong, T. T., Pham, D. S., Chan, K. Y., Soon, S., Maiorana, A., & Hollingsworth, C. (2025). Towards AI-Based Strep Throat Detection and Interpretation for Remote Australian Indigenous Communities. Sensors, 25(18), 5636. https://doi.org/10.3390/s25185636
Vancouver
Asokan P, Truong TT, Pham DS, Chan KY, Soon S, Maiorana A, et al. Towards AI-Based Strep Throat Detection and Interpretation for Remote Australian Indigenous Communities. Sensors. 2025;25(18):5636. doi:10.3390/s25185636
BibTeX
@article{Asokan2025,
author = {Asokan, Prasanna and Truong, Thanh Thu and Pham, Duc Son and Chan, Kit Yan and Soon, Susannah and Maiorana, Andrew and Hollingsworth, Cate},
title = {Towards AI-Based Strep Throat Detection and Interpretation for Remote Australian Indigenous Communities},
journal = {Sensors},
year = {2025},
volume = {25},
number = {18},
pages = {5636},
doi = {10.3390/s25185636}
}
EUVIMED