Building an Artificial Intelligence-Driven Early Warning System and Home Management Protocol for a Diabetic Foot Ulcer Recurrence Cohort

Diabetes is one of the major chronic diseases, and diabetic foot ulcer (DFU) is a significant adverse prognosis of diabetes. The recurrence of DFU after healing involves multiple risk factors, such as changes in foot loading patterns, patient compliance, family care capacity, blood glucose monitoring, the degree of ischemia, and control of systemic diseases. Early identification of signs of DFU recurrence and timely follow-up interventions are crucial for improving prognosis, reducing disability rates, and lowering healthcare costs. However, traditional follow-up systems lack individualized strategies (e.g., insufficient risk stratification, rigid follow-up intervals, inadequate compliance management), often resulting in low follow-up efficacy. High-risk patients prone to recurrence may not receive frequent enough follow-ups for early detection, while low-risk patients unlikely to recur may undergo multiple unnecessary visits, increasing the burden on both patients and healthcare providers. This inefficiency is a key reason for the persistently high rates of disability and mortality among patients with recurrent DFU. Establishing individualized follow-up strategies for DFU, leveraging advanced technologies to address core bottlenecks such as delayed recurrence warnings and insufficient home management, represents an effective technical approach to solving these problems.

Our center aims to establish and refine a specialized cohort for active DFU follow-up, along with a multimodal database with comprehensive indicators. We plan to explore a high-risk foot grading system for preventing DFU recurrence and develop targeted follow-up protocols. Using AI technology, we will create a wound alert system capable of identifying DFU recurrence and explore a remote healthcare and AI-assisted prevention and control system for DFU recurrence, centered on patient self-management at home.