Press & Media

physIQ touts VA study showing AI predicting hospitalizations

Written by physIQ | February 25, 2020

Originally published in Mass Device

physIQ today is touting results from a study testing the ability to detect heart failure exacerbation using wearable sensors and personalized analytics based on artificial intelligence.

The Link-HF study set out to assess the ability to predict rehospitalization due to heart failure exacerbation using analytics applied to continuous wearable sensor data, according to a news release. The study enrolled 100 people upon discharge from heart failure hospitalization across four U.S. Department of Veteran’s Affairs (VA) hospitals and monitored them for up to 90 days without intervention.

Data revealed a mean detection lead time as high as 10.4 days prior to the hospitalization or emergency room visit, with as high as 88% sensitivity and 86% specificity. According to the release, such a lead time interval should permit intervention aimed at preventing hospitalization.

Chicago-based physIQ, along with the VA, published the results in the American Heart Association’s Circulation – Heart Failure journal.

The study evaluated the company’s PinpointIQ continuous data collection platform designed to have machine learning establish a personalized model of baseline physiological behavior to detect anomalies that may be predictive of hospitalization.

Upon discharge from hospitalization, patients were given four-day adhesive sensor patches for the chest and a smartphone to upload data for the analytics algorithms to detect physiologic changes.

“This study demonstrates that integration of novel non-invasive technology and machine learning analytics provides an accurate prediction of clinical decompensation in heart failure,” said Dr. Josef Stehlik, co-chief of the Salt Lake City Veterans Administration Medical Center’s advanced heart failure program.

“This work has the potential to reduce hospitalization and improve quality of life of patients with heart failure,” Stehlik said in a news release.

physIQ CEO Gary Conkright acknowledged that there is a lot of buzz around digital medicine these days.

“But the reality is that very few companies have been able to demonstrate the clinical rigor required in a healthcare use case. The publication of this study is yet another example of how we at physIQ continue to lead the market in developing FDA-cleared technology and clinical validation,” Conkright said.

Earlier this month, physIQ raised $6 million, adding to the $500,000 investment it received from the Purdue Research Foundation’s Foundry Investment Fund in January.