Viz.ai, a disease detection and intelligent care coordination company, said in its announcement Tuesday that with ML scanning images from across a health system, more patients with suspected HCM can be identified and diagnosed earlier.
“Hypertrophic cardiomyopathy is a devastating disease that is often undetected until it is too late,” said Dr. Chris Mansi, CEO and co-founder at Viz.ai, in the statement.
According to the company’s website, one million people in the U.S. have HCM, but only 20% have been diagnosed. While it’s the leading cause of sudden cardiac death in people under age 35, early detection and treatment can result in normal longevity and quality of life.
With the platform detecting non-obstructive and obstructive HCM, providers can get their patients to the right cardiology specialist faster. After it receives the HCM alert, the appropriate care team can review the patient’s ECG, coordinate follow-up with an echocardiogram and access images and reports on the Viz mobile application.
The HCM artificial intelligence is one of twelve FDA-cleared algorithms on the San Francisco-based company’s enterprise-wide AI platform.
Deployment of the algorithm, developed with more than 830,000 ECG exams from 300,000 individuals across multiple global locations, is financially supported by a multi-year agreement with Bristol Myers Squibb, Viz.ai noted.
THE LARGER TREND
Over the past five years, FDA has been evolving its approach to regulating and approving AI-enabled tools – with its De Novo pathway meant to be well-suited for low- to moderate-risk devices to obtain marketing authorization, as then FDA Commissioner Dr. Scott Gottlieb said in 2019. (Just this past month, Gottlieb penned an op-ed explaining how AI “may take on doctors’ roles sooner rather than later.”)
Hypertrophic cardiomyopathy most severely affects younger people that inherit it. Reggie Lewis and other famous young athletes experienced cardiac arrest unexpectedly from undiagnosed HCM.
This past year, Cedars-Sinai also created an AI tool to help identify hypertrophic cardiomyopathy and cardiac amyloidosis.
“Our AI algorithm can pinpoint disease patterns that can’t be seen by the naked eye, and then use these patterns to predict the right diagnosis,” Dr. David Ouyang, cardiologist in the Smidt Heart Institute, said in a statement about his study’s publication in JAMA Cardiology.
At the time, these researchers acknowledged potential bias in the available training images.
“For example, although hereditary cardiac amyloidosis is known to disproportionately affect black individuals in the U.S., they are underrepresented in study cohorts, and care must be taken to extrapolate the performance of deep learning algorithms in populations with different demographic characteristics,” they said.
Still, AI is thought to be a promising modality for improving cardiology care.
The previous year, researchers at the Mayo Clinic looked at how AI could detect heart failure. More specifically, low ejection fraction – the measure of blood the left ventricle pumps out with each contraction – which is a sign of heart failure.
“To put it in absolute terms, for every 1,000 patients screened, the AI screening yielded five new diagnoses of low ejection fraction over usual care,” said Xiaoxi Yao, a health outcomes researcher in cardiovascular diseases at Mayo Clinic, in a statement.
ON THE RECORD
“Given the high prevalence of patients with suspected HCM who remain undiagnosed, flagging and connecting them quickly to the right providers is critical to improve health outcomes,” said Dr. Matthew Martinez, director of sports cardiology and HCM for Atlantic Health System in the Viz.ai announcement. “The role of artificial intelligence in cardiology is growing exponentially and adding the HCM module to Viz.ai will help increase awareness and reach for HCM patients.”
Andrea Fox is senior editor of Healthcare IT News.
Healthcare IT News is a HIMSS Media publication.