Development and Multicenter External Validation of a Real-Time Artificial Intelligence Diagnostic System for…

AI / informaticsGerontology· Apr 2026

Development and Multicenter External Validation of a Real-Time Artificial Intelligence Diagnostic System for Diabetic Peripheral Neuropathy Based on Wearable Devices.

Junlin Ran, Pengcheng Huang, Min He … Chenzhen Du

Assistive Technology & WearablesAI / informaticsDiagnosisQ2IF 3.1

Wearable-sensor AI model distinguishes diabetic peripheral neuropathy with AUROC 0.80

Development and Multicenter External Validation of a Real-Time Artificial Intelligence Diagnostic System for Diabetic Peripheral Neuropathy Based on Wearable Devices.

Junlin Ran … Chenzhen Du

Gerontology · Apr 2026

Background

Diabetic peripheral neuropathy (diabetic peripheral neuropathy) is a frequent diabetes complication, affecting over half of patients and causing pain, falls, ulcers, and amputations if undetected.

Purpose

This study developed and validated STRIDE, a machine learning model using wearable gait and balance data for real-time diabetic peripheral neuropathy classification.

Methods

In this study conducted across multiple centers, 206 participants from Chongqing hospitals were categorized as follows: healthy controls (n = 32), diabetics without diabetic peripheral neuropathy (n = 47), asymptomatic diabetic peripheral neuropathy (n = 48), and symptomatic diabetic peripheral neuropathy (n = 79).

n = 206 participants

Results

the model correctly separated neuropathy from non-neuropathy cases most of the time (1.0 is perfect)

AUROC 0.80 (95% CI 0.64 to 0.92)

null 0

0.64

0.92

CI excludes the null - significant

More results

Key SHAP features: stride length variability (weight = 0.61) and double-support time.

External validation: initial accuracy 78.6%, recall 86.5%, precision 88.9%; three of four false positives developed diabetic peripheral neuropathy within 1 year, yielding 89.3% adjusted concordance.

More results

STRIDE outperformed other parameters in mid-term prediction, unaffected by anemia for up to 4 years.

“

Conclusion

STRIDE provides a scalable, interpretable tool for diabetic peripheral neuropathy classification, supporting early intervention and improved outcomes. Larger longitudinal studies are needed for clinical integration.

Development and Multicenter External Validation of a Real-Time Artificial Intelligence Diagnostic System for Diabetic Peripheral Neuropathy Based on Wearable Devices.

Development and Multicenter External Validation of a Real-Time Artificial Intelligence Diagnostic System for Diabetic Peripheral Neuropathy Based on Wearable Devices.

Related papers