While developers push forward with new health tech, other research teams on the hunt for solutions for specific medical conditions or health problems sometimes find new uses for existing technology. That’s what happened at MyoKardia, a South San Francisco-based clinical-stage biopharmaceutical company. MyoKardia discovered an important new use for optical biosensors similar to the sensors used in fitness trackers.
Scientists at MyoKardia studied the effectiveness of wrist-worn photoplethysmography (PPG) optical sensors in detecting obstructive hypertrophic cardiomyopathy (oHMC). According to the research team, approximately 630,000 people in the U.S. have HMC, but only about 15% are diagnosed. HCM is a genetic disorder that causes the left ventricle of the heart to thicken, reducing its pumping capacity. In their study, MyoKardia scientists employed artificial intelligence machine learning algorithms to detect obstructed blood flow by analyzing data from a wristband PPG sensor. In their presentation at the American Heart Association (AHA) Scientific Sessions in November 2017, MyoKardia researchers reported that its proprietary algorithm identified individuals with oHCM with 95% accuracy.
Further work with PPG devices and oHCM involves additional testing, potentially expanding to other wearable platforms, screening for other forms of cardiomyopathy, and monitoring oHCM patient treatment effects. This is just one more example of how personally-generated data sets can be mined to find correlations that can lead to the early detection and treatment of disease.