BPG is committed to discovery and dissemination of knowledge
Systematic Reviews
Copyright: ©Author(s) 2026.
World J Cardiol. Jun 26, 2026; 18(6): 120747
Published online Jun 26, 2026. doi: 10.4330/wjc.120747
Table 4 Risk-of-bias assessment using QUADAS-2 domains
Ref.
Patient selection (risk of bias/applicability)
Index test (including feature selection and overfitting risk)
Reference standard
Flow and timing (including external validation)
Overall ML-specific concerns
Kayvanpour et al[8], 2021Low/LowLow (10-fold CV was reported, but feature-selection timing was not fully clear)Low (diagnosis strictly adjudicated by a board of 3 expert cardiologists using ESC guidelines)Low (internal CV only; no external)Moderate overfitting risk due to no external validation
Ren et al[13], 2024Unclear/LowLow (LASSO/SCAD used for selection; validation on matched sample)UnclearHigh (no formal validation split reported)Limited validation; ML mainly for feature identification
Samadishadlou et al[14], 2023Low/LowLow (7:3 split and 10-fold CV)UnclearLow (internal only)Small test set; class imbalance addressed using sample weighting
Samadishadlou et al[15], 2024Low/LowLow (LASSO and 5/10-fold CV)UnclearLow (internal and independent test set)Improved validation compared to prior work
Reel et al[16], 2025Low/LowLow (8:2 split and balanced accuracy metric)UnclearLow (internal only)Use of balanced accuracy helps with potential imbalance
Sajid et al[17], 2024Low/LowLow (8:2 and 10-fold CV and hold-out)UnclearLow (internal only)Ensemble methods; good internal practices
Yerukala Sathipati et al[18], 2025Unclear/Low (small n = 15)Low (8:2 split)UnclearLow (external validation performed via independent GEO dataset)Very small sample; high risk of overfitting
Jusic et al[19], 2023Low/LowLow (8:2 and 10-fold CV)UnclearLow (internal only)Small cohort
Errington et al[20], 2021Low/LowLow (10-fold CV and external datasets)UnclearLow (external validation performed)Strongest validation approach among included studies


Write to the Help Desk