Interpretable detection of left ventricular hypertrophy using commercial ECG features and machine learning: a study based on the PTB-XL+ dataset - Summary - MDSpire

Interpretable detection of left ventricular hypertrophy using commercial ECG features and machine learning: a study based on the PTB-XL+ dataset

  • By

  • Qibao Zhou

  • Xiao Luo

  • Kaihui Du

  • June 4, 2026

  • 0 min

Share

Objective:

To evaluate the utility of PTB-XL+ pre-extracted commercial ECG features for interpretable LVH detection.

Key Findings:
  • XGBoost achieved the highest performance with AUC values of 0.9859 for GE 12SL, 0.9853 for UNIG, and 0.9828 for ECGDeli.
  • Commercial features were found to perform similarly to open-source ECGDeli.
  • Key features identified included V5–V6 T-wave changes, precordial R-wave amplitude, V1 QRS area, and age as a non-ECG predictor.
Interpretation:

Limitations:
  • The study is retrospective and relies on a single dataset, which may limit the generalizability of the findings.
  • Performance may vary with different populations or ECG devices.
Conclusion:

The study demonstrates that interpretable ML models can achieve high performance in LVH detection.

Original Source(s)

Interpretable detection of left ventricular hypertrophy using commercial ECG features and machine learning: a study based on the PTB-XL+ dataset

  • by Qibao Zhou, Xiao Luo, Kaihui Du

  • June 4, 2026

Related Content

Case Report: Adult-onset Still’s disease presenting with massive hemorrhagic pericardial effusion without the characteristic rash

Development and validation of a predictive model for postoperative delirium in patients undergoing cardiac surgery

Development and validation of a clinical prediction model for postoperative atrial fibrillation after lung cancer surgery: a machine-learning–based study