PO-04-205 A NOVEL ARTIFICIAL INTELLIGENCE ALGORITHM TO IDENTIFY PATIENTS AT RISK OF SUDDEN CARDIAC ARREST

Abstract

Sudden cardiac death (SCD) from cardiac arrest is a major international public health problem accounting for an estimated 15%-20% of all deaths. Implantable cardioverter defibrillators (ICD) have been demonstrated to improve survival in high-risk populations. While 500,000 patients experience SCD annually, there are only 75,000 ICDs implanted annually suggesting a significant treatment gap. To determine if a novel artificial intelligence enabled clinical decision support algorithm can improve identification of patients at risk for sudden cardiac arrest An evidence based algorithm was created to identify patients at risk for sudden cardiac arrest that had not been referred to electrophysiology. This algorithm was embedded in an electronic medical record and used natural language processing to review patient records, including progress notes, diagnostic studies and appointments. The algorithm would prompt clinicians to order additional diagnostic studies or refer patients to electrophysiology for consultation if appropriate. In 6 months of usage, the clinical decision support algorithm screened 27,112 patients, 34,360 echocardiograms and identified 1,112 patients at risk for SCA. Alerts were sent for 208 patients, out of which 88 alerts were acted upon while 120 were pending action. In 55 patients who received a follow up echocardiogram, the EF remained < 35% and 22 of these patients were referred to EP, out of which 4 patients received an ICD. A novel artificial intelligence clinical decision support algorithm is a feasible and effective means of identifying patients at risk of sudden cardiac arrest. Further study is needed to asses the relative impact of this intervention on clinical care.