Evaluation of a Machine Learning-guided Strategy for Elevated Lipoprotein(a) Screening in Health Systems

Abstract

ABSTRACTBackgroundWhile universal screening for Lp(a) is increasingly recommended, fewer than 0.5% of the patients undergo Lp(a) testing. Here, we assessed the feasibility of deploying Algorithmic Risk Inspection for Screening Elevated Lp(a) (ARISE), a validated machine learning tool, to health system EHRs to increase the yield of Lp(a) testing.MethodsWe randomly sampled 100,000 patients from the Yale-New Haven Health System (YNHHS) to evaluate the feasibility of ARISE deployment. We also evaluated Lp(a) tested populations in the YNHHS (N=7,981) and the Vanderbilt University Medical Center (VUMC) (N=10,635) to assess the association of ARISE score with elevated Lp(a). To compare the representativeness of the Lp(a) tested population, we included 456,815 participants from the UK Biobank and 23,280 from three US-based cohorts of ARIC, CARDIA, and MESA.ResultsAmong 100,000 randomly selected YNHHS patients, 413 (0.4%) had undergone Lp(a) measurement. ARISE score could be computed for 31,586 patients based on existing data, identifying 2,376 (7.5%) patients with a high probability of elevated Lp(a). A positive ARISE score was associated with significantly higher odds of elevated Lp(a) in the YNHHS (OR 1.87, 95% CI, 1.65-2.12) and the VUMC (OR 1.41, 95% CI, 1.24-1.60). The Lp(a) tested population significantly differed from other study cohorts in terms of ARISE features.ConclusionsWe demonstrate the feasibility of deployment of ARISE in US health systems to define the risk of elevated Lp(a), enabling a high-yield testing strategy. We also confirm the very low adoption of Lp(a) testing, which is also being restricted to a highly selected population.