Digitizing paper based ECG files to foster deep learning based analysis of existing clinical datasets: An exploratory analysis

Recently, we developed and validated a deep learning model for detecting left ventricular dysfunction based on a standard 12-lead ECG. However, this model largely depends on the availability of digital ECG data: 10s for all 12 leads sampled at 500 Hz stored as a numeric array. This limits the ability to validate or scale this technology to institutions that store ECGs as PDF or image files (“paper” ECGs). Methods do exist to create digital signals from the archived paper copies of the ECGs. The primary objective of this study was to evaluate how well the AI-ECG model output obtained using digitized paper ECGs agreed with the predictions from the native digital ECGs for the detection of low ejection fraction. Our study demonstrates an agreement between deep learning model predictions obtained from digitized paper-based ECGs and native digital ECGs and provides some insight into potential expandability of ECG-based deep learning models including the importance of captured duration (10-s vs. 2-5-s recordings) and ECG vectors (precordial leads vs. limb leads).