Project 1 - HEARTSPOT: Evaluating a Machine Learning System to Aid Decision-Making in the Emergency Department for Patients with ADRD

An emergency department clinician treating a patient with acute coronary syndrome (ACS) faces difficult decisions about whether to recommend invasive treatment. If the patient is cognitively impaired, assessing health risks and benefits is even more complex. This project is testing a machine learning tool called HEARTSPOT that helps clinicians make this difficult decision. HEARTSPOT uses an augmented intelligence algorithm that draws from the electronic medical records of a massive database of past patients to detect risk signals for current patients. It examines each patient’s medical history faster and more completely than any human could and presents a summary of its findings to the emergency department clinician in real time. The goal is to give clinicians as much synthesized information on patient risk as possible at the point of deciding on the ACS treatment path. The project may improve ACS decisions for all patients, but particularly for ADRD patients, for whom the algorithm may help fill critical information gaps necessary for clinicians to accurately assess ACS risk.