Heart disease remains the leading cause of death around the world, but a flood of tech developers are hoping that artificial intelligence software might be the key to reducing that mortality rate.
Latest to join the fray are Novartis and Anumana—a joint venture of the Mayo Clinic and Nference—which have teamed up to develop new AI algorithms. The collaboration is aimed at catching otherwise overlooked cases of life-threatening heart disease as early as possible, even before symptoms arise.
Victor Bulto, president of Novartis’ U.S.-based Innovative Medicines division, explained that the partnership came about as the Big Pharma has realized the need to “look beyond therapeutic innovation and reimagine how we approach cardiovascular care.”
Together, Novartis and the AI developer plan to build algorithms that analyze electrocardiogram readings for signs of cardiovascular disease that would be missed by human physicians. The AI will be trained to look through that ECG data for signs of left ventricular dysfunction or a weak heart pump—both of which are often precursors to heart failure—and atherosclerosis, in which build-ups in the artery walls can lead to heart attack or stroke.
“Many heart diseases develop for years before signs and symptoms appear, but the first event may be life-threatening,” said Paul Friedman, M.D., chair of Anumana’s Mayo Clinic board of advisors. “AI enables us to uncover hidden signals our bodies transmit to detect otherwise occult heart diseases, potentially years before symptoms appear.”
Friedman continued, “This collaboration has the potential to transform the use of a ubiquitous inexpensive test, the ECG, with the aim of democratizing disease detection and helping medical care teams to proactively manage heart disease ahead of time and prevent some clinical events from ever happening.”
Beyond the AI algorithms, Novartis and Anumana are also planning to develop another software solution that will help guide healthcare providers through the creation of treatment plans for patients that could prevent avoidable hospitalizations and reduce the risk of cardiovascular death.
In its new approach to tackling heart disease, Novartis has chosen a knowledgeable partner. An AI algorithm developed by Mayo Clinic researchers and now licensed to Anumana has been proven to help physicians significantly increase the number of cases of low ejection fraction they can catch at its earliest stages.
A study published last year concluded that using AI to analyze routine ECG data resulted in 32% more diagnoses of the heart condition compared to the current standard of care, which traditionally requires time-consuming and expensive cardiac ultrasounds.
Plus, in the year since Anumana launched, it has already embarked on projects to detect signs of pulmonary hypertension in ECG readings—in a partnership with Johnson & Johnson’s Janssen—and help diagnose low ejection fraction using only single-lead ECG readings from the Apple Watch.