Machine learning methods for propensity and disease risk score estimation in high-dimensional data: a plasmode simulation and real-world data cohort analysis

Journal article

Introduction: Machine learning (ML) methods are promising and scalable alternatives for propensity score (PS) estimation, but their comparative performance in disease risk score (DRS) estimation remains unexplored. Methods: We used real-world data comparing antihypertensive users to non-users with 69 negative control outcomes, and plasmode simulations to study the performance of ML methods in PS and DRS estimation. We conducted a cohort study using UK primary care records. Further, we conducted a plasmode simulation with synthetic treatment and outcome mimicking empirical data distributions. We compared four PS and DRS estimation methods: 1. Reference: Logistic regression including clinically chosen confounders. 2. Logistic regression with L1 regularisation (LASSO). 3. Multi-layer perceptron (MLP). 4. Extreme Gradient Boosting (XgBoost). Covariate balance, coverage of the null effect of negative control outcomes (real-world data) and bias based on the absolute difference between observed and true effects (for plasmode) were estimated. 632,201 antihypertensive users and nonusers were included. Results: ML methods outperformed the reference method for PS estimation in some scenarios, both in terms of covariate balance and coverage/bias. Specifically, XgBoost achieved the best performance. DRS-based methods performed worse than PS in all tested scenarios. Discussion: We found that ML methods could be reliable alternatives for PS estimation. ML-based DRS methods performed worse than PS ones, likely given the rarity of outcomes.

Authors: Guo, Y; Strauss, VY; Català, M; Jödicke, AM; Khalid, S

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Frontiers Media
• Journal: Frontiers in Pharmacology
• Volume: 15
• Article number: 1395707
• Publication date: 2024-10-28
• Acceptance date: 2024-10-17
• DOI: 10.3389/fphar.2024.1395707
• EISSN: 1663-9812
• ISSN: 1663-9812
• Language: English
• Keywords: machine learning; negative control; observational research; treatment effect; propensity scores; disease risk scores