ARTIFICIAL INTELLIGENCE AS A PREDICTIVE TOOL TO IDENTIFY PATIENTS AT HIGH-RISK FOR NON ST ELEVATION MYOCARDIAL INFARCTION READMISSION: A RETROSPECTIVE STUDY

Abstract

TOPIC: Education, Research, and Quality Improvement TYPE: Original Investigations PURPOSE: Cardiovascular death is the number one cause of death in the US. Over half of these deaths are due to myocardial infarction. While high costs and hospital admissions due to myocardial infarction are common, there is additional stress to the healthcare system with regards to readmission. In an effort to curb the cost of readmission and to improve patient outcomes, the Centers for Medicare and Medicaid Services have used 30-day hospital readmission rates as a metric to evaluate quality of care provided by hospitals across the country and to determine reimbursement. A commercially available AI machine learning tool was deployed through the electronic health record (EHR) at our institution to predict risk of readmission. The aim of our work was to assess the accuracy of an artificial intelligence-based tool in predicting which patients are at high-risk for readmission at 30 days and comparing it with a validated prediction tool, the LACE index for patients admitted with non ST elevation myocardial infarction (NSTEMI). Prospectively identifying patients hospitalized with NSTEMI who are at high risk for readmission could help prevent readmissions. METHODS: Data was collected retrospectively on patients 18 years or older with a primary diagnosis of NSTEMI and discharged from a tertiary care center from 11/26/2018 to 02/01/2020. We evaluated the effectiveness and accuracy of the proprietary AI product to identify patients at high risk for hospital readmission. This was compared with the risk predictions made by the LACE Index. The primary evaluated outcome was all-cause readmissions for HF within 30-days from the index hospitalization. The statistical method for comparison was logistic regression with LACE score as a single predictor. Sensitivities were compared after choosing a threshold that most closely matched the proprietary AI product specificity. RESULTS: A logistic regression with LACE Index score as a single predictor was used. Sensitivities were compared after choosing a threshold which resulted in the specificity most closely matching AI product specificity. After matching for specificity, the proprietary AI product had a greater sensitivity (4.7%) as compared to LACE Index score (2.7%) in detecting all-cause readmissions for NSTEMI. CONCLUSIONS: This study concludes that a proprietary AI product was a more useful predictor of readmission rates for NSTEMI as compared to prior conventional prediction tools, specifically the LACE index score. Models using AI should be implicated in clinical settings to predict readmission rates for all medical conditions to reduce readmission and overall improve patient care. We recommend that future studies should be performed to include AI models in everyday practice. CLINICAL IMPLICATIONS: Artificial intelligence can be an important asset in the future of medicine. It can be used to improve overall patient care and clinical outcomes. DISCLOSURES: No relevant relationships by Asad Cheema, source=Web Response No relevant relationships by radhika deshpande, source=Web Response No relevant relationships by Michael Gleason, source=Web Response No relevant relationships by Daniel Holtz, source=Web Response No relevant relationships by Cameron Koester, source=Web Response No relevant relationships by Abhishek Kalidas Kulkarni, source=Web Response No relevant relationships by Zurain Niaz, source=Web Response No relevant relationships by vivek prakash, source=Web Response No relevant relationships by Prashanth Singanallur, source=Web Response