The prompt diagnosis of Left Ventricular Hypertrophy (LVH), Myocardial Ischemia, and Left Anterior Fascicular Block (LAFB) through comprehensive heart monitoring will enhance medical management of congenital heart diseases. The diagnostic tool electrocardiography records heart electrical activity to identify these conditions while being extensively used for diagnosis. The visual interpretation of ECG by clinicians through traditional methods creates imprecise diagnostic results that increases clinical workload and assessment variability. This research assesses the performance of machine learning (ML) and deep learning (DL) models which include Random Forest and Gradient Boosting alongside Artificial Neural Networks (ANNs) and Long Short-Term Memory (LSTM) for automated ECG signal classification into Normal, LVH, Myocardial Ischemia, and LAFB categories. Analysis using ANN achieved the most accurate classification with results showing 83.52% accuracy while generating an AUC-ROC score of 95.94%. Random Forest closely trailed with 83.03% accuracy alongside an AUC-ROC value of 95.58%. The model performances of Gradient Boosting and LSTM achieved accuracy rates of 82.47% and 82.40%, respectively. Automated ECG interpretation provides enhanced diagnostic precision together with earlier disease recognition and eliminates human interpretation mistakes which results in transformative patient healthcare effects and diagnostic assessment progress.