AI-Powered Thermography for Diabetic Foot Risk Stratification: A Multi-Center Screening Study (Preprint)

BACKGROUND Diabetic foot complications are among the most severe and costly outcomes associated with diabetes, with high prevalence particularly in the Middle East and North Africa (MENA) region. Current screening tools are often limited by subjectivity, invasiveness, or scalability challenges, underscoring the need for innovative approaches. OBJECTIVE This multi-center study aimed to evaluate the performance of an AI-powered thermographic system—Thermal Foot Scan (TFScan)—in identifying patients at elevated risk of diabetic foot complications through non-invasive temperature profiling. METHODS A descriptive cross-sectional study was conducted across four regions in Saudi Arabia, enrolling 1,120 individuals with diabetes. Participants underwent thermal imaging using a smartphone-compatible infrared camera, with AI algorithms analyzing angiosomal temperature patterns and asymmetries. Risk was stratified into four categories (very low, low, moderate, high). Associations between TFScan classifications and clinical risk factors, symptoms of neuropathy, and thermal abnormalities were assessed. RESULTS While 90.7% of participants were classified as very low or low risk, 9.3% were identified as moderate or high risk. This higher-risk group exhibited significantly greater prevalence of key diabetic complications. Peripheral artery disease (PAD) was present in 20.2% of moderate/high-risk participants compared to just 0.8% in lower-risk individuals (p < 0.05). Cardiovascular disease (57.7% vs. 30.8%), neuropathy (11.5% vs. 3.6%), foot deformities (14.7% vs. 0.6%), and symptoms of Loss of Protective Sensation (LOPS, 51.0% vs. 34.8%) were all significantly more frequent in the high-risk subgroup. Thermal imaging further revealed pronounced abnormalities: temperature asymmetries >2.2°C were observed in 7.1% overall, with the highest asymmetry and Thermal Change Index (TCI) scores concentrated in moderate and high-risk groups. These individuals also exhibited greater deviations in angiosomal temperature deltas—exceeding 2°C in key vascular territories such as the medial plantar and lateral plantar arteries—suggesting both early inflammatory states and critical perfusion deficits. CONCLUSIONS The TFScan system effectively stratified diabetic patients into clinically meaningful risk categories, with moderate and high-risk groups exhibiting a significantly higher burden of vascular, neuropathic, and thermal abnormalities. These findings highlight the potential of AI-enhanced thermography to serve as a scalable, objective screening tool for proactive diabetic foot management. Further longitudinal studies are warranted to validate its predictive power and support widespread clinical adoption.