A C5.0 white-box machine learning algorithm achieved a balanced accuracy of 95.35% in classifying four cardiac rhythm classes using five interpretable ECG features.
Does a white-box machine learning approach (C5.0) accurately classify cardiac arrhythmias from ECG data while providing interpretable decision rules?
A white-box machine learning algorithm (C5.0) can accurately classify cardiac arrhythmias from ECG data with 95.35% balanced accuracy while providing transparent, clinically interpretable decision rules based on just 5 features.
We present the results from a white-box machine learning approach to detect cardiac arrhythmias using electrocardiographic data. A C5.0 is trained to recognize four classes using common features. The four classes are (i) atrial fibrillation and atrial flutter, (ii) tachycardias (iii), sinus bradycardia and (iv) sinus rhythm. Data from 10,646 subjects, 83% of whom have at least one arrhythmia and 17% of whom exhibit a normal sinus rhythm, are used. The C5.0 is trained using 10-fold cross-validation and is able to achieve a balanced accuracy of 95.35%. By using the white-box machine learning approach, a clear and comprehensible tree structure can be revealed, which has selected the 5 most important features from a total of 24 features. These 5 features are ventricular rate, RR-Interval variation, atrial rate, age and difference between longest and shortest RR-Interval. The combination of ventricular rate, RR-Interval variation and atrial rate is especially relevant to achieve classification accuracy, which can be disclosed through the tree. The tree assigns unique values to distinguish the classes. These findings could be applied in medicine in the future. It can be shown that a white-box machine learning approach can reveal granular structures, thus confirming known linear relationships and also revealing nonlinear relationships. To highlight the strength of the C5.0 with respect to this structural revelation, the results of further white-box machine learning and black-box machine learning algorithms are presented.
Rieg et al. (Thu,) conducted a other in Cardiac arrhythmias (n=10,646). White-box machine learning (C5.0 algorithm) vs. Other machine learning algorithms (GLM, Logit, k-NN, Naive Bayes, Random Forest, XGBoost) was evaluated on Balanced accuracy for 4-class arrhythmia detection. A C5.0 white-box machine learning algorithm achieved a balanced accuracy of 95.35% in classifying four cardiac rhythm classes using five interpretable ECG features.