Artificial Intelligence Analysis of Standard 12‐Lead Electrocardiograms for Screening of Symptomatic Diabetic Peripheral Neuropathy
Authors' conclusion
AI analysis of the standard ECG demonstrated a strong association with the presence of symptom-defined peripheral neuropathy but lacked sensitivity for milder presentation.
Study context
- Population
- People with diabetes enrolled in the Silesia-Diabetes Heart Project; mean age 54 ± 17; 52% female
- Participants
- 640 people
- Comparison
- Artificial intelligence (AI) models trained on standard 12-lead electrocardiograms (ECG) vs Michigan Neuropathy Screening Instrument Questionnaire (MNSI-Q)-defined diabetic peripheral neuropathy (DPN)
- Outcome
- Identification of highly symptomatic DPN (MNSI-Q ≥ 7)
Methodological detailsobservational
- Observational
Performance
As reported in the abstract
Highly symptomatic DPN (MNSI-Q ≥ 7)
| Test or model | AUC | Accuracy | Sensitivity |
|---|---|---|---|
| XGBoost | 0.89 (95% CI 0.88-0.91) | 88.5% | 93.4% |
XGBoost
AUC0.89 (95% CI 0.88-0.91)
Accuracy88.5%
Sensitivity93.4%
Further findings
Model performance at broader screening threshold (MNSI ≥ 4, moderately symptomatic DPN)
- The model showed substantially lower predictive capability when tested against the broader screening threshold of MNSI ≥ 4: AUC
- 0.64
Original publication
Artificial Intelligence Analysis of Standard 12‐Lead Electrocardiograms for Screening of Symptomatic Diabetic Peripheral Neuropathy. Diabetes Obes Metab. Published 19 August 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →