An artificial intelligence algorithm was able to determine a patient's sex and an estimated age from electrocardiogram data, and thus could potentially be used to measure overall health, a new study suggests.
The study was led by researchers from Rochester, Minn.-based Mayo Clinic and published Aug. 27 in the American Heart Association's journal Circulation: Arrhythmia and Electrophysiology. In it, researchers trained a convolutional neural network to use deep learning to read ECG data to determine a patient's age and sex.
When applied to patient data, the AI determined sex with 90 percent accuracy, but often offered an age that was off by an average of seven years. By studying other health factors of patients with the biggest age discrepancies, the researchers hypothesized that the AI-predicted age may in fact represent more of a "physiological age," and thus a measure of overall health.
For example, many of the patients for whom the AI predicted an age at least seven years above their chronological age had heart conditions such as low ejection fraction, hypertension and coronary disease. Conversely, the age estimations were lower than the chronological age of patients who had experienced few or no adverse health events.
"Being able to more accurately assess overall health status may help doctors determine which patients they should examine further to determine if there are asymptomatic or currently silent diseases that could benefit from early diagnosis and intervention," said study author Suraj Kapa, MD, an assistant professor of medicine and director of augmented and virtual reality innovation at Mayo Clinic.
More articles on AI:
Physician viewpoint: AI needs a 'Turing test' to determine medical feasibility
AdventHealth launches largest AI-enabled Mission Control command center in US
Google DeepMind co-founder placed on leave for alleged controversial projects