Highmark Health Reducing Uneccessary Invasive Heart Scans with AI

Highmark Health has a program in place, titled Highmark VITAL, that assists in the making of FDA-approved medical technologies available to patients sooner by helping display the efficacy of these therapies. The Pittsburgh organization is a parent company to Highmark BCBS, encompassing the Pennsylvania, Delaware, West Virginia, and Alleghany Health Network.

Through this program, Highmark Health began working with HeartFlow in 2016. This medtech company focuses on using machine learning to develop a 3D heart model, improving diagnosis and treatment of cardiovascular disease. A model such as the one HeartFlow strives to create would allow physicians to better visualize the way a plaque buildup in the heart affects blood flow, and subsequently how to go about treating the patient.

So far, this AI machine learning analysis has been conducted on approximately 100 patients, with results showing that the system can decrease negative angiograms by over 83%, cutting costs by 45% per patient. These profound results were reported by Highmark Health.

“Recent studies suggest that invasive coronary angiography is associated with higher rates of placement of coronary stents,” said Moneal Shah, lead researcher at the Alleghany Health Network. “The HeartFlow analysis adds a functional assessment of coronary artery function to the anatomical information produced by coronary CT, allowing physicians to diagnose obstructive coronary artery disease with greater certainty through wholly non-invasive techniques and to reduce the number of unnecessary invasive coronary angiography procedures.”

Highmark Health program’s clinical trials on HeartFlow consisted of patients who had previously underwent a cardiac stress test and were under consideration for invasive coronary angiogram. As an alternative, the patients were offered the non-invasive computed tomography angiogram as an alternative. If this computed angiogram portrayed significant coronary artery disease, the researchers then analyzed the images with HeartFlow to detect any significant defects. If lesions were detected, the patients were then advised to opt into invasive angiography. If no lesions were detected, however, patients were not advised to undergo the invasive procedure. Shah claims that this strategy better identifies patients with coronary artery disease that was non-obstructive, or not present at all, and prevented unnecessary invasive procedure.

Shaw also explained the team observed “A reduction in per member/per month costs of approximately 45 percent over the 90-day period following computed tomography angiogram, or invasive coronary angiogram in the control group,” and that the cost reduction was the result of “avoiding invasive angiography procedures in the 83 percent of patients receiving computed tomography angiogram whose results indicated absence of any obstruction of coronary blood flow.”

How Highmark Health uses #DeepLearning, 3D #Tech to cut unnecessary angiograms | #Healthcare IT News #deeplearning #ANN #AI #IA #machinelearning #BigData #DataScience #artificialintelligence #computerintelligence https://t.co/lhDUx6JUh4

— NS.ai (Nils Schaetti) (@nschaetti) August 23, 2018

Source: https: Healthcare IT News