Related Experiment Video
Updated: Aug 12, 2026
Analyzing Long-Term Electrocardiography Recordings to Detect Arrhythmias in Mice
Published on: May 23, 2021
Electrocardiogram Abnormality Classification From Summary Statistics With Patient-Level Validation and
Sungjoon Hong1, Christina Hartnett2, Michael Ruane2
1Department of Osteopathic Manipulative Medicine, College of Osteopathic Medicine, New York Institute of Technology, Old Westbury, New York, USA.
Background:
Machine learning (ML) applications in clinical medicine are vulnerable to data leakage, particularly temporal leakage from post-diagnostic features and patient-level leakage from improper partitioning, compromising electrocardiogram (ECG) abnormality detection systems. This study addresses these vulnerabilities through patient-level data splitting and systematic evaluation across multiple classification scenarios.
Methods:
ECG data from 4419 observations representing 2180 unique patients were analyzed using Random Under-Sampling Boosting (RUSBoost). Three binary classification scenarios were defined: Scenario 1 (Abnormal vs. Normal, excluding borderline), Scenario 2 (Abnormal + Borderline vs. Normal), and Scenario 3 (Abnormal vs. Normal + Borderline). Patient-level stratified partitioning (60:20:20) prevented information leakage. Models were evaluated using accuracy, sensitivity, specificity, F1-score, learning curves, and precision-recall curves across all partitions.
Results:
Scenario 1 demonstrated optimal generalization with test accuracy of 70.79%, sensitivity of 60.30%, specificity of 86.50%, and F1-score of 0.712, exhibiting monotonic decline across partitions (73.98%→71.50%→70.79%). Scenario 2 achieved 65.26% test accuracy with greater degradation (6.17 percentage points), reflecting increased difficulty when borderline cases were grouped with abnormal findings. Scenario 3 exhibited problematic non-monotonic patterns (71.84%→67.71%→69.36%) with premature convergence, indicating fundamental generalization challenges despite near-balanced classes (1.07:1 ratio).
Conclusions:
Aggregate metrics alone inadequately support clinical deployment decisions. Medical AI evaluation must examine learning dynamics, generalization stability, and precision-recall calibration across partitions. Process-focused standards assessing monotonic decline, convergence characteristics, and calibration stability are essential for reliable ECG abnormality detection deployment.
Related Concept Videos
01:29Electrocardiogram
Three major waveforms are present in a typical ECG recording: the P wave, the QRS complex, and the T...
01:30Dysrhythmias V: Evaluating Dysrhythmias
01:28Electrocardiogram Fundamentals
An electrocardiogram (ECG) is a diagnostic tool for identifying cardiac conditions such as arrhythmias, conduction abnormalities, and myocardial ischemia.
Definition
An electrocardiogram (ECG) visualizes the heart's electrical activity by tracing the electrical movement associated with each heartbeat on a graph or monitor. As the heart beats, an electrical wave passes through it, correlating with the cardiac cycle events.
Parts of an ECG
An ECG utilizes electrodes on the skin to...
01:25ECG Interpretation of Arrhythmias II: Atrial, Junctional and Ventricular Arrhythmias
01:24ECG Interpretation of Rhythms
Components of the Electrocardiogram
The primary components of a normal ECG waveform in Normal sinus rhythm(NSR) include the P wave, PR interval, QRS complex, ST segment, T wave, and occasionally a U wave.
ECG waveforms are divided by vertical and horizontal lines at standard intervals.
The horizontal axis measures time and rate, and the vertical axis measures amplitude or voltage. When...
01:30Pulse rhythm
Conversely, an irregular pulse pattern is termed dysrhythmia, stemming from disruptions in cardiac muscle...