- St. Louis Startup Secures $6M to Advance Medical Research
If left untreated, PH can cause premature disability, heart failure, and death. However, patients often experience significant delays of over two years from the onset of symptoms to a diagnosis.
“The major goal of this study is to determine whether an Eko algorithm based on phonocardiography coupled with electrocardiography can identify the presence and severity of pulmonary hypertension when compared to the current gold standard," Gaurav Choudhary, MD, principal study investigator, and director of Cardiovascular Research at the Alpert Medical School of Brown University and Lifespan Cardiovascular Institute. "This machine learning algorithm has the potential to be a low cost, easily implementable, and sustainable medical technology that assists healthcare professionals in identifying more patients with pulmonary hypertension."
As of now, physicians use echocardiography and right heart catheterization to diagnose PH. Even though ECG-based AI models exist and have been clinically proven to improve PH diagnosis, deployment of the models remains challenging.
To address these existing challenges, Eko formed a research partnership with Lifespan Health System's Cardiovascular Institute to collect real-world PCG and ECG data and develop an easy-to-deploy early identification tool.
"This SBIR grant is a testament to our focus on developing pioneering AI for early detection and management of cardiopulmonary diseases," Connor Landgraf, co-founder and CEO of Eko, said. "Early detection and intervention play a critical role in preventing the progression of heart disease. Our focus is to make AI-powered tools cost-effective, easily accessible, and scalable that support clinical decision-making so millions of patients will get information sooner that could extend their lives. This is how we change the standard of cardiac care.”
AI and machine learning also hold promises for cancer care. A recent study shows that machine-learning algorithms can help clinicians detect patients at high risk for colorectal cancer.
“When carefully implemented and supported by healthcare providers, machine learning can be a low-cost, noninvasive supplement to other colorectal cancer screening efforts,” said Keith Boell, DO, co-author of the study and chief quality officer for population initiatives at Geisinger, in the press release. “This technology can act as a safety net, potentially preventing missed or delayed diagnosis among some patients who may already have undiagnosed signs of disease.”