New machine learning algorithm to support clinical decision making in early detection of cardiovascular disease
OAKLAND, California., September 20, 2022 /PRNewswire/ — Eko, a digital health company applying machine learning to fight heart and lung disease, announced today that it has been awarded an $2.7 million Small Business Innovation Research (SBIR) Phase II direct grant from the National Institutes of Health (NIH) Department of Health and Human Services (HHS). The grant will fund the development of a machine learning algorithm that detects and stratifies pulmonary hypertension (PH) using phonocardiogram (PCG) and electrocardiogram (ECG) data provided by Eko’s smart stethoscopes.
Pulmonary hypertension is a serious condition that occurs when the pressure in the vessels that carry blood from the heart to the lungs is higher than normal, putting strain on the heart. PH affects up to 1% of the world’s population and is an indicator of poor health outcomes.¹ PH can lead to premature disability, heart failure and death. Unfortunately, there is often a delay of more than two years between the onset of symptoms and the diagnosis of severe forms of PH.²
The gold standards for diagnosing PH are echocardiography and right heart catheterization, which are costly, invasive, and require a cardiac specialist. ECG-based AI models are clinically proven to improve the diagnosis of PH, but are difficult to deploy.³ To address this challenge, Eko formed a research partnership with Lifespan Health System’s Cardiovascular Institute to compare real-world PCG and ECG data with Eko to collect DUO-ECG + digital stethoscope. This data will help develop an algorithm that can detect PH and stratify its severity. This easy-to-use early detection tool aims to diagnose PH earlier and more accurately, leading to useful interventions that can save patients’ lives.
“The primary objective of this study is to determine whether an Eko algorithm based on phonocardiography coupled with electrocardiography can detect the presence and severity of pulmonary hypertension compared to the current gold standard,” said Dr. Gaurav ChoudharyPrincipal Investigator and Ruth and Paul Levinger Professor of Cardiology and Director of Cardiovascular Research at Alpert Medical School of University of Brown and Lifespan Cardiovascular Institute. “This machine learning algorithm has the potential to be a low-cost, easy-to-implement, and sustainable medical technology that will help healthcare professionals identify more patients with pulmonary hypertension.”
This award marks Eko’s fourth NIH SBIR grant, matching all of the NIH’s previous funding for cardiopulmonary machine learning development 6 million dollars. a previous one $2.7 million Grant, awarded to the company in July 2020, funded a collaboration with Northwestern Medicine Bluhm Cardiovascular Institute to validate algorithms that help healthcare professionals (HCPs) identify pathologic heart murmurs and valvular heart disease (VHD) during routine physician visits. This grant to VHD directly contributed to the FDA clearance and commercialization of Eko Murmur Analysis Software (EMAS) – the first and only machine learning algorithm to help HCPs identify structural heart murmurs using a smart stethoscope.
“This SBIR grant is a testament to our focus on developing breakthrough AI for the early detection and treatment of cardiopulmonary disease,” said Connor Landgrave, co-founder and CEO of Eko. “Early detection and intervention play a critical role in preventing the progression of heart disease. Our focus is to make AI-powered tools that support clinical decision-making cost-effective, easily accessible and scalable, so that millions of patients receive earlier information that could extend their lives. This is how we are changing the standard of heart care.”
Eko, a digital health company, advances heart and lung disease detection and monitoring by healthcare professionals with its innovative suite of digital tools, patient and provider software, and AI-powered analytics. The FDA-cleared platform is used by hundreds of thousands of healthcare professionals worldwide, enabling them to see earlier and with greater accuracy, diagnose with greater confidence, manage treatment effectively, and ultimately provide their patients with the best possible care. Eko is headquartered in Oakland, Californiawith more than $125 million in funding from Highland Capital Partners, Questa Capital, Artis Ventures, DigiTx Partners, NTTVC, Morningside Technology Ventures Limited, Mayo Clinic, Sutter Health and others. Visit www.ekohealth.com for more information.
About the lifespan
Founded in 1994, Lifespan is a not-for-profit healthcare system based in Providence, R.I consisting of three teaching hospitals of the Warren Alpert Medical School of University of Brown: Rhode Island Hospital and its Hasbro Children’s Hospital; The Miriam Hospital; and Bradley Hospital, the nation’s first pediatric psychiatric hospital; Newport Hospital, a community hospital offering a wide range of healthcare services; Gateway Healthcare, the largest provider of behavioral healthcare in the community; Lifespan Physician Group, the largest multidisciplinary practice in Rhode Island; and Coastal Medical, a primary care medical practice. Lifelong teaching hospitals are among the top recipients of National Institutes of Health research grants nationwide. Get the hospitals $121 million in external research funding in fiscal year 2021. All Lifespan-affiliated partners are not-for-profit organizations that rely on community support to deliver programs and services.
- Markus Humbert, et al. 2022 ESC/ERS Guidelines for the Diagnosis and Management of Pulmonary Hypertension: Developed by the Task Force on the Diagnosis and Management of Pulmonary Hypertension of the European Society of Cardiology (ESC) and the European Respiratory Society (ERS). Supported by the International Society for Heart and Lung Transplantation (ISHLT) and the European Reference Network on Rare Respiratory Diseases (ERN-LUNG), European Heart Journal, ehac237, Aug 2022. https://doi.org/10.1093/eurheartj/ehac237
- Markus Humbert, et al. pulmonary arterial hypertension France Findings from a National Registry, American Journal of Respiratory and Critical Care Medicine, Volume 173, Issue 9, February 2006. https://doi.org/10.1164/rccm.200510-1668OC
- Chih Min Liu, MD, et al. An electrocardiogram with artificial intelligence improves the diagnosis and prediction of mortality in patients with pulmonary hypertension, JACC: ASIAVolume 2, Number 3, 2022. https://www.jacc.org/doi/epdf/10.1016/j.jacasi.2022.02.008
Eko media contact
Alexander Romero Wilson
Media contact lifetime