Development and Multinational Validation of a Novel Algorithmic Strategy for High Lp(a) Screening

Abstract

Importance: Elevated lipoprotein(a) [Lp(a)] is associated with atherosclerotic cardiovascular disease (ASCVD) and major adverse cardiovascular events (MACE). However, fewer than 0.5% of patients undergo Lp(a) testing, limiting the evaluation and use of novel targeted therapeutics currently under development. Objective: We developed and validated a machine learning model to enable targeted screening for elevated Lp(a). Design: Cross-sectional Setting: 4 multinational population-based cohorts Participants: We included 456,815 participants from the UK Biobank (UKB), the largest cohort with protocolized Lp(a) testing for model development. The model's external validity was assessed in Atherosclerosis Risk in Communities (ARIC) (N=14,484), Coronary Artery Risk Development in Young Adults (CARDIA) (N=4,124), and Multi-Ethnic Study of Atherosclerosis (MESA) (N=4,672) cohorts. Exposures: Demographics, medications, diagnoses, procedures, vitals, and laboratory measurements from UKB and linked electronic health records (EHR) were candidate input features to predict high Lp(a). We used the pooled cohort equations (PCE), an ASCVD risk marker, as a comparator to identify elevated Lp(a). Main Outcomes and Measures: The main outcome was elevated Lp(a) (>=150 nmol/L), and the number-needed-to-test (NNT) to find one case with elevated Lp(a). We explored the association of the model's prediction probabilities with all-cause and cardiovascular mortality, and MACE. Results: The Algorithmic Risk Inspection for Screening Elevated Lp(a) (ARISE) used low-density lipoprotein cholesterol, statin use, triglycerides, high-density lipoprotein cholesterol, history of ASCVD, and anti-hypertensive medication use as input features. ARISE outperformed cardiovascular risk stratification through PCE for predicting elevated Lp(a) with a significantly lower NNT (4.0 versus 8.0 [with or without PCE], P<0.001). ARISE performed comparably across external validation cohorts and subgroups, reducing the NNT by up to 67.3%, depending on the probability threshold. Over a median follow-up of 4.2 years, a high ARISE probability was also associated with a greater hazard of all-cause death and MACE (age/sex-adjusted hazard ratio [aHR], 1.35, and 1.38, respectively, P<0.001), with a greater increase in cardiovascular mortality (aHR, 2.17, P<0.001). Conclusions and Relevance: ARISE optimizes screening for elevated Lp(a) using commonly available clinical features. ARISE can be deployed in EHR and other settings to encourage greater Lp(a) testing and to improve identifying cases eligible for novel targeted therapeutics in trials.

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

“…This study builds upon the current literature by demonstrating the feasibility of deployment of a novel algorithmic strategy in a large and diverse US health system for increasing the yield of Lp(a) testing. 18 Despite the clinical significance of elevated Lp(a) and current guideline recommendations for once-in-a-lifetime universal screening for this condition, only 0.4% have undergone Lp(a) testing which aligns with the reported measures from other health systems and claims databases. [15][16][17] Adherence to guideline recommendations in realworld clinical practice remains a challenge in different domains of medicine and cardiology with implementation science being an active area of interest and research.…”

“…Additionally, we have previously demonstrated that undergoing Lp(a) testing does not affect adverse cardiovascular outcomes for individuals with a negative ARISE score, underscoring that the implementation of ARISE does not lead to worse outcomes in those not advised to undergo testing. 18…”

“…[15][16][17] To address the limited testing of Lp(a) in contemporary practice, we have developed and validated a novel machine learning model to increase the yield of Lp(a) testing using six features, including ASCVD history, use of statins, use of anti-hypertensive medications, serum low-density lipoprotein cholesterol (LDL-C), serum high-density lipoprotein cholesterol (HDL-C), and serum triglycerides. 18 The model, Algorithmic Risk Inspection for Screening Elevated Lp(a) (ARISE), demonstrated a consistent reduction of the number-needed-to-test to find one case with elevated Lp(a) by more than 50% in four multinational cohorts. Given the computability of ARISE's features in electronic health records (EHR), deployment of ARISE in health systems with subsequent testing of screen-positive patients has the potential to identify a large number of patients with elevated Lp(a) at scale.…”

“…Given the computability of ARISE’s features in electronic health records (EHR), deployment of ARISE in health systems with subsequent testing of screen-positive patients has the potential to identify a large number of patients with elevated Lp(a) at scale. 18 However, the feasibility of its deployment in EHR and its implications for Lp(a) screening have not been assessed previously.…”