EUVIMEDEUVIMED entdecken
Multizentrische StudieValidierungsstudie

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, Liling Deng, Qingqing Chen, Yiwen Qin, David G Armstrong, Bijan Najafi, Edward Jude, Yanzhong Wang, Wuquan Deng, Chenzhen Du

Gerontology · 08.04.2026 · 1-17

DOI: 10.1159/000551704 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift Gerontology, online erschienen am 08.04.2026. Verfasst von Junlin Ran und 11 weiteren Autor:innen. Beteiligte Einrichtung: Diabetic Foot Medical Research Center, Department of Endocrinology, Chongqing University Central Hospital, School of Medicine, Chongqing University, …. Hauptthemen laut MEDLINE: Diabetic Neuropathies, Wearable Electronic Devices, Artificial Intelligence. Die Arbeit nennt 39 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Diabetic peripheral neuropathy (DPN) is a frequent diabetes complication, affecting over half of patients and causing pain, falls, ulcers, and amputations if undetected. Traditional methods like electromyography are resource-intensive and inaccessible. This study developed and validated STRIDE, a machine learning model using wearable gait and balance data for real-time DPN classification.

Methods

In this study conducted across multiple centers, 206 participants from Chongqing hospitals were categorized as follows: healthy controls (n = 32), diabetics without DPN (n = 47), asymptomatic DPN (n = 48), and symptomatic DPN (n = 79). A separate group of 42 was used for validation. During a one-minute walk and modified balance test, LEG-Sys/BalanSens sensors produced 68 features. STRIDE used random forest and logistic regression with cross-validation. The metrics used were area under the receiver operating characteristic curve (AUROC), accuracy, sensitivity, specificity, F1-score, and SHAP for interpretability, with a scoring system allowing for real-time evaluation.

Results

Random forest achieved AUROC 0.80 (95% CI: 0.64–0.92); logistic regression 0.79 (95% CI: 0.62–0.95). 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 DPN within 1 year, yielding 89.3% adjusted concordance. STRIDE outperformed other parameters in mid-term prediction, unaffected by anemia for up to 4 years.

Conclusion

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

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Diabetic NeuropathiesWearable Electronic DevicesArtificial IntelligenceHumansFemaleMaleMachine LearningAgedMiddle AgedGaitRandom ForestPostural BalanceROC CurveSensitivity and Specificity

Stichwörter der Autor:innen

Biomechanical parametersDiabetic peripheral neuropathyMachine learningPrediction model

Autor:innen und Institutionen

  • Diabetic Foot Medical Research Center, Department of Endocrinology, Chongqing University Central Hospital, School of Medicine, Chongqing University, Chongqing, China.
  • General Practice Department, Chongqing Southwest Hospital, Chongqing, China.
  • Department of Surgery, Keck School of Medicine of University of Southern California, Los Angeles, California, USA.
  • Center for Advanced Surgical and Interventional Technology (CASIT), Department of Surgery, Geffen College of Medicine, UCLA, Los Angeles, California, USA.
  • Department of Diabetes and Endocrinology, Tameside and Glossop Integrated Care NHS Foundation Trust and University of Manchester, Ashton under Lyne, UK.
  • School of Life Course and Population Health Sciences, King's College London, London, UK.

Zitieren

APA

Ran, J., Huang, P., He, M., Deng, L., Chen, Q., Qin, Y., Armstrong, D. G., Najafi, B., Jude, E., Wang, Y., Deng, W., & Du, C. (2026). Development and Multicenter External Validation of a Real-Time Artificial Intelligence Diagnostic System for Diabetic Peripheral Neuropathy Based on Wearable Devices. Gerontology, 1-17. https://doi.org/10.1159/000551704

Vancouver

Ran J, Huang P, He M, Deng L, Chen Q, Qin Y, et al. Development and Multicenter External Validation of a Real-Time Artificial Intelligence Diagnostic System for Diabetic Peripheral Neuropathy Based on Wearable Devices. Gerontology. 2026:1-17. doi:10.1159/000551704

BibTeX
@article{Ran2026,
  author = {Ran, Junlin and Huang, Pengcheng and He, Min and Deng, Liling and Chen, Qingqing and Qin, Yiwen and Armstrong, David G and Najafi, Bijan and Jude, Edward and Wang, Yanzhong and Deng, Wuquan and Du, Chenzhen},
  title = {Development and Multicenter External Validation of a Real-Time Artificial Intelligence Diagnostic System for Diabetic Peripheral Neuropathy Based on Wearable Devices},
  journal = {Gerontology},
  year = {2026},
  pages = {1--17},
  doi = {10.1159/000551704}
}
Kostenlos starten →