Researchers at Mount Sinai Hospital and the Mount Sinai School of Medicine have found that AI-powered analysis of electrocardiograms (ECG) offers a promising path for the early detection of COPD.
Their study results, “Automated Diagnosis of Chronic Obstructive Pulmonary Disease Using Deep Learning Applied to Electrocardiograms,” were published in eBioMedicine, part of The Lancet Discovery Science.
According to a news release, the researchers used a Convolutional Neural Network model to analyze more than 208,000 ECGs from more than 18,000 COPD cases. The primary outcome for the study was the accuracy of a new clinical COPD diagnosis, as determined by the International Classification of Disease codes.
The team found that AI-powered ECG analysis could allow for earlier diagnosis of COPD, allowing for quicker treatment and more effective management. The authors wrote, “The model exhibited robust performance across diverse populations.”
Co-author Monica Kraft, MD, health system chair of the department of medicine at Mount Sinai, said the study was the first to demonstrate that deep learning models can accurately detect COPD across large, real-world patient cohorts. She said the study also focuses on elements that previous studies have not.
“Unlike previous exploratory work, our analysis includes external validation across distinct cohorts over various times and locations, as well as analysis in the subgroup categories of irregular heartbeat and smoking exposure,” she said.
Co-author Girish Nadkarni, MD, MPH, CPH, chief AI officer and chair of the department of artificial intelligence and human health at Mount Sinai, said the tool could have potential implications for areas that might otherwise not have access to diagnostic tools.
“The use of such AI-enhanced diagnostic tools can be expanded to remote or under-resourced areas where access to specialized diagnostic facilities might be limited,” she said.
