The Apple Watch could be used to see a heart condition that induces over 100,000 strokes every year, according to a new survey.
Heart health app Cardiogram and researchers from the University of California, San Francisco( UCSF) Cardiology Health eHeart project teamed up to take a closer look at just how effective the Watch can be at tracking the most clinically common heart abnormality, atrial fibrillation( AF ).
The irregularity, which is treatable but tough to diagnose employing current medical standard practices, is the leading cause of heart failure.
The mRhythm project that give rise to the pairing looked at the Apple Watch-sourced heart rate reads from 6,158 Cardiogram users. The data was then used to build an algorithm to see the distinct heart rate variability pattern caused by AF.
The team used an AI technique called semi-supervised deep learning to qualify a neural network to sift through the data to identify the heart rate irregularities. The method is similar to the recent work on Stanford that used an AI neural network to identify skin cancer, although that survey depended on one of Google’s image recognition algorithms , not an entirely new one.
After being taught, the research team’s algorithm “ve managed to” see atrial fibrillation accurately 97 percent of the cases, which Cardiogram software engineer Avesh Singh claims thump existing methods of diagnosis in a blog post.
The study’s makes were presented for the first time at the 2017 Heart Rhythmconference.
“The most promising finding of our study is proof that consumer-grade wearables can be used to detect cancer, ” Singh wrote. “The future is bright here, and there are a few research directions that are particularly interesting to us.”
We know the Apple Watch is an increasingly health and fitness focused device thanks to Tim Cook, but this is a whole new degree of tracking prowess. While the Watch’s sensors provide the means to collect the data, it’s important to note it can only do so much. The real story is the algorithm and how it might potentially be used by medical professionals going forward.
Dr. Gregory M. Marcus, one of the study’s result researchers and administrator of clinical research for the Division of Cardiology at UCSF, constructed that abundantly clear in an emailed statement to Mashable .
“A lot of device companies market their sensors or trackers as means to enhance health, ” he wrote. “However, its important to emphasize that rigorous analyses, involving major investments from those companies and meaningful involvement of clinicians and clinical researchers, is needed to obtain the kind of real ‘outcomes data’ that they are able convincingly demonstrate impacts on health.”
So what’s next? Singh supposes a new frontier in associated drug, where the algorithm can be put to work to help Cardiogram detect AF in its users and then follow through in the care, too, guiding them through the process with smart notifications and continuous targeted monitoring.
“Using wearables, we can not only detect cancer early, but can also guidebook patients down the road to recovery, ” he wrote.
Maybe smartwatches aren’t so useless after all.
Read more here: http :// mashable.com /