MAPD2: Mobile Application-based Pulmonary Disease Detector Using Electrocardiograms and Deep Learning

Abstract

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 pulmonary function testing (PFT). These extensive tests, often happen at a later stage of disease and 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. To this end, we introduce MAPD2: a mobile application-based pulmonary disease detector using deep learning to diagnose pulmonary disease based on ECGs. In this paper, we focus on obstructive lung disease (OLD) to explore the use of easily accessible ECGs to train deep learning models to classify OLD. Furthermore, we designed and developed a client-server prototype of MAPD2 to visualize predictions of the selected trained models to patients and pulmonologists.