Advanced computational approaches for detecting subclinical diabetic peripheral neuropathy: Current prospects and future directions

Abstract

Diabetic peripheral neuropathy (DPN) is one of the most common and debilitating complications of diabetes mellitus. Early, subclinical stages of DPN are often asymptomatic and remain undetected until significant nerve damage occurs, limiting treatment options. Artificial intelligence (AI) has emerged as a promising tool to enhance early detection by identifying subtle patterns in electrophysiological, imaging, or sensor-based data that may not be recognized by conventional diagnostic methods. However, the current landscape of AI applications in subclinical DPN remains unclear. The aim of this study was to map and synthesize the existing literature on the use of AI-based methods for the early detection of subclinical DPN. A comprehensive search of PubMed, Scopus, Web of Science, and Google Scholar was conducted up to August 25, 2025. Eligible studies included those applying AI or machine learning techniques to identify or predict subclinical DPN in patients with type 1 or type 2 diabetes. Non-English articles, studies without AI implementation, and reviews were excluded. Data were charted on study characteristics, AI methodology, dataset type, and reported outcomes. Preliminary evidence suggests that AI has been applied across multiple modalities, including nerve conduction studies, corneal confocal microscopy, wearable sensor data, and electrophysiological signals. Techniques ranged from traditional machine learning models such as support vector machines and random forests to deep learning architectures including convolutional neural networks. While several studies reported high sensitivity and accuracy for early detection, most were limited by small sample sizes, lack of external validation, and heterogeneous definitions of “subclinical” DPN. In conclusion, AI-based approaches demonstrate substantial potential for the early identification of subclinical DPN, which could enable earlier interventions and improve patient outcomes. Nonetheless, the field is still in its early stages, and robust multicenter datasets, standardized definitions, and explainable AI models are required to facilitate clinical adoption. Future research should focus on validation in diverse populations and integration into routine diabetic care pathways.