Science Desk · NIH · NHLBI

ECGs recorded during sleep studies predicted 10-year cardiac risk in NIH-supported study

A deep learning model paired overnight ECGs with sleep-stage data; findings were published in the journal Sleep.

Agency release dated 2026-10-09

What the record says

• NIH says ECGs recorded during polysomnography, paired with sleep-stage information, were used to assess risk of future adverse cardiac events.
• The team examined 10-year risk of outcomes including atrial fibrillation, stroke, myocardial infarction and heart failure.
• NHLBI’s acting director said evaluating whether this improves traditional risk prediction is an important next step.

Source: NIH — Deep learning model using ECGs during sleep studies can predict cardiovascular outcomes. Notice Nearby summarized this release; it adds no claims beyond the agency record.