Our smartwatch could detect hypertension and sleep apnea, a new study reveals

Adjust Comment Print

A new study showed that Cardiogram's deep neural network technology, called DeepHeart, can detect hypertension and sleep apnea.

Earlier this year, another study conducted by UCSF and Cardiogram successfully detected abnormal heart rhythm (arrhythmia) in Apple Watch wearers.

Last May, Cardiogram and UCSF demonstrated the ability of Apple Watch to detect irregularities in rhythmic function of the heart with an impressive 97 percent accuracy. On this, the algorithm returned its 90 percent sleep apnea and 82 percent hypertension accuracy - a performance described by authors of the study as "surprisingly good".

Sleep apnea affects an estimated 22 million adults in the USA, with another 80 percent of cases of moderate and severe obstructive sleep apnea undiagnosed, according to the American Sleep Apnea Association. In addition, 80 percent of cases of moderate and severe obstructive sleep apnea remain undiagnosed.

"What if we could transform wearables people already own - Apple Watches, Android Wears, Garmins, and Fitbits - into affordable, everyday screening tools using artificial intelligence?" wrote Cardiogram co-founder Brandon Ballinger in a Medium post.

Sleep apnea is a potentially serious sleep disorder largely associated with heavy snoring in which breathing repeatedly stops. This new study will have a big impact in medicine by somehow eliminating all the need of physical check-up for the diagnosis of hypertension and sleep apnea [which are both common but serious medical conditions by the way] using a simple device.

Another 75 million American adults have high blood pressure or hypertension, putting them at high risk for heart disease and stroke which are the top causes of death in the US. DeepHeart was trained on data from 70 percent of participants and tested on the 30 percent of participants that weren't the same participants used to collect the data.

Hsieh believes this study shows promise for other wearable technology to incorporate a heart-rate sensors including FitBits.

The study is promising as a way to diagnose health problems in people who may not they have it.

He adds: 'Then you'd guide them through the appropriate final diagnosis, which would be through a blood pressure cuff and then treatment'.