Artificial intelligence‐enhanced electrocardiogram analysis for identifying cardiac autonomic neuropathy in patients with diabetes
Authors' conclusion
Our study highlights the potential of using ML techniques, particularly motifs and discords, to effectively detect dsCAN in patients with diabetes. This approach could be applied in large-scale screening of CAN, particularly to identify definite/severe CAN where cardiovascular risk factor modification may be initiated.
Study context
- Population
- Patients with diabetes; mean age 54 ± 17 years, 54% female; 100 diagnosed with cardiac autonomic neuropathy (CAN) (38 dsCAN, 62 early CAN (eCAN))
- Participants
- 205 patients
- Comparison
- Machine learning (ML) analysis of 12-lead, 10-s ECG for detecting CAN
- Outcome
- Classification of definite or severe CAN (dsCAN): accuracy, precision, recall, F1 score, AUC
Methodological detailsmachine learning, 10-fold cross validation, support vector machine classification
- Machine learning
- 10-fold cross validation
- Support vector machine classification
Performance
As reported in the abstract
dsCAN classification
| Test or model | Accuracy | F1 score | Recall | Precision | AUC |
|---|---|---|---|---|---|
| Motifs and discords | 0.92 | 0.92 | 0.94 | 0.91 | 0.93 (95% CI 0.91-0.94) |
Motifs and discords
Accuracy0.92
F1 score0.92
Recall0.94
Precision0.91
AUC0.93 (95% CI 0.91-0.94)
Further findings
| Outcome | Values |
|---|---|
| Detection of any stage of CANBest results | Motifs and discords accuracy 0.65 · F1 score 0.68 · recall 0.75 · precision 0.68 · AUC 0.68 (95% CI 0.54-0.81) |
Original publication
Artificial intelligence‐enhanced electrocardiogram analysis for identifying cardiac autonomic neuropathy in patients with diabetes. Diabetes Obes Metab. Published 11 April 2024. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →