Dascena, Inc., a machine learning diagnostic algorithm company that is targeting early disease intervention to improve patient care outcomes, today announced that a poster highlighting the ability of a Dascena machine learning algorithm to provide earlier identification of acute coronary syndrome (ACS) is being presented during the Heart Failure Society of American (HFSA) Virtual Annual Scientific Meeting 2020. The meeting is taking place virtually from September 30 to October 6, 2020, and all posters are now available online for registered attendees. The poster (#3681) is titled "A machine learning approach to early identification of acute coronary syndrome."
Of more than 8 million emergency department visits for chest pain each year, about 10% of them result in an ACS diagnosis. Today, ACS is diagnosed through an exclusion process using traditional risk stratification systems including TIMI, GRACE and PURSUIT, which demonstrate methodological limitations and poor implementation in clinical settings. Dascena developed a machine learning algorithm to detect ACS that demonstrated an area under the receiver operating curve (AUROC) of 86% for the detection of ACS, compared to 62% by the GRACE system.
"ACS is a severe and common clinical condition with significant associated morbidity and mortality," said Jana Hoffman, Ph.D., vice president of science at Dascena. "Machine learning algorithms may be able to provide earlier detection of ACS in hospitalized patients, and we may be able to accelerate timely treatment and ultimately improve patient outcomes in clinical practice."
Dascena is developing machine learning diagnostic algorithms to enable early disease intervention and improve care outcomes for patients. For more information, visit Dascena.com.
Dan Budwick, 1AB