DiaBreath: A Low-Cost, Non-Invasive Diabetes Monitor via Breath

Diabetes mellitus is a chronic metabolic disorder that necessitates frequent blood glucose monitoring, usually through painful and inconvenient methods. Volatile organic compounds (VOCs) in breath have been used as biomarkers for diabetes detection in non-invasive, Internet of Things (IoT)-based devices. Nevertheless, the cost, compactness, and mobility challenges of existing devices limit their general adoption. We present DiaBreath, a novel, affordable, non-invasive multi-sensor device for the early prediction of diabetes, solving these challenges. DiaBreath consists of a) a dataset of 552 patient breath samples, b) a stable machine-learning pipeline to predict diabetes based on feature engineering, c) a simple interface to generate pre-diagnostic reports, and d) an optimal six-VOC sensor combination that is chosen with an ablation study. DiaBreath exhibits superior predictive power, with an accuracy of 97.6%, to enable efficient and scalable early diagnosis in public health centers, especially in resource-constrained settings. DiaBreath’s low cost and compact size make it highly adaptable for implementation in rural and underserved regions, where access to timely diabetes screening is limited. This technology improves non-invasive diabetes monitoring, making early diagnosis more cost-effective and accessible globally.