Obstructive Lung Disease Classification from Electrocardiograms Using Machine Learning

Pulmonary diseases, such as chronic obstructive pulmonary disease (COPD) and asthma, are among the leading causes of death in the US. These lung diseases often are diagnosed by pulmonologists using physical exam (e.g., lung auscultation) and objective measurement of lung function with pulmonary function testing (PFT). These extensive tests, however, can be inaccessible to many patients due to limited resources and availability. Nowadays hand-held medical devices (e.g., electrocardiogram (ECG) monitors) are already available to such patients and can yield ECG data that potentially could be used for diagnosis. In this paper, we explore the use of easily accessible ECGs to train machine learning models to classify obstructive lung disease (OLD). Not only do we utilize the time-series raw ECG directly, we also define and employ eleven features derived from the PQRST sequences of the ECGs. To this end, we develop and experiment with two approaches: deep neural network models (e.g., Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs)) trained using the ECG signals directly, and non-neural models (e.g., support vector machines (SVMs) and logistic regression) trained using the derived features from ECGs. In the task of classifying whether a patient has OLD or not, our results show that deep neural network models outperformed the non-neural models, though the difference is within 3% on accuracy and F1-score metrics.