Towards AI-Based Strep Throat Detection and Interpretation for Remote Australian Indigenous Communities
Open Access
Abstract
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.Keywords
Funding Information
- Department of Health WA and Curtin University (DoH202310626/7)
This publication has 30 references indexed in Scilit:
- An analytic research and review of the literature on practice of artificial intelligence in healthcareEuropean Journal of Medical Research, 2025
- Assessing GPT-4 multimodal performance in radiological image analysisEuropean Radiology, 2024
- Measuring the Impact of AI in the Diagnosis of Hospitalized PatientsJAMA, 2023
- The epidemiology of superficial Streptococcal A (impetigo and pharyngitis) infections in Australia: A systematic reviewPLOS ONE, 2023
- Treatment of recurrent acute tonsillitis—a systematic review and clinical practice recommendationsFrontiers in Surgery, 2023
- Rethinking and Improving Relative Position Encoding for Vision Transformer2021
- Enablers and Barriers to Accessing Healthcare Services for Aboriginal People in New South Wales, AustraliaInternational Journal of Environmental Research and Public Health, 2021
- Toward automated severe pharyngitis detection with smartphone camera using deep learning networksComputers in Biology and Medicine, 2020
- Throat Detection and Health Classification Using Neural Network2019
- Are scabies and impetigo “normalised”? A cross-sectional comparative study of hospitalised children in northern Australia assessing clinical recognition and treatment of skin infectionsPLOS Neglected Tropical Diseases, 2017