Copyright: ©Author(s) 2026.
World J Cardiol. Mar 26, 2026; 18(3): 116217
Published online Mar 26, 2026. doi: 10.4330/wjc.v18.i3.116217
Published online Mar 26, 2026. doi: 10.4330/wjc.v18.i3.116217
Table 4 The models performance metrics
| Validation cluster | Area under the receiver operating characteristic curve | Sensitivity | Specificity | Positive predictive value | Negative predictive value | Threshold |
| Cluster 1 | 0.947 | 0.969 | 0.781 | 0.948 | 0.862 | 0.350 |
| Cluster 2 | 0.835 | 0.816 | 0.725 | 0.875 | 0.625 | 0.221 |
| Cluster 3 | 0.589 | 0.398 | 0.941 | 0.956 | 0.330 | 0.131 |
| Cluster 4 | 0.880 | 0.750 | 0.833 | 0.875 | 0.682 | 0.164 |
- Citation: Karbovskaya AD, Marzoog BA, Stroeva A, Suvorov A, Chomakhidze P, Gognieva D, Kuznetsova N, Syrkin A, Fadeev VV, Ismailova SM, Poluboyarinova IV, Kopylov P. Machine learning-based detection of diabetes mellitus from single-lead electrocardiography: A phenotype-stratified approach. World J Cardiol 2026; 18(3): 116217
- URL: https://www.wjgnet.com/1949-8462/full/v18/i3/116217.htm
- DOI: https://dx.doi.org/10.4330/wjc.v18.i3.116217