arXiv subjects

Gabriel Zayas-Caban

Publications and source records attributed to Gabriel Zayas-Caban.

3 recordsLinked to original sources

arXiv2025

Designing a quasi-experiment to study the clinical impact of adaptive risk prediction models

Clinical risk prediction is a valuable tool for guiding healthcare interventions toward those most likely to benefit. Yet, evaluating the pairing of a risk prediction model with an intervention using randomized controlled trials presents substantial challenges, making quasi-experimental designs an attractive alternatives. Existing designs, however, assume that both the model and the decision rules used to trigger interventions (typically a risk threshold) remain fixed. This limits their utility in modern healthcare, where both are routinely updated. We introduce a regression discontinuity framework that accommodates adaptation in both the model and the risk threshold. We precisely characterize the form of interference introduced by these adaptations and exploit this structure to establish conditions for identification and thus design estimation strategies. The key idea is to define counterfactual risks-the scores patients would have received under hypothetical reorderings-thereby restoring local exchangeability and enabling valid estimation of the local average treatment effect. Our estimator leverages the fact that, although counterfactual risk vectors grow with time, they typically lie in a low-dimensional space. In simulations of cardiovascular prevention programs, we show that our method accurately recovers treatment effects even as thresholds adapt to meet operational or clinical targets and models are updated to align predicted and observed outcomes or to exclude demographic predictors such as race.

stat.ME↗

arXiv2023

Unveiling Bias in Sequential Decision Making: A Causal Inference Approach for Stochastic Service Systems

In many stochastic service systems, decision-makers find themselves making a sequence of decisions, with the number of decisions being unpredictable. To enhance these decisions, it is crucial to uncover the causal impact these decisions have through careful analysis of observational data from the system. However, these decisions are not made independently, as they are shaped by previous decisions and outcomes. This phenomenon is called sequential bias and violates a key assumption in causal inference that one person's decision does not interfere with the potential outcomes of another. To address this issue, we establish a connection between sequential bias and the subfield of causal inference known as dynamic treatment regimes. We expand these frameworks to account for the random number of decisions by modeling the decision-making process as a marked point process. Consequently, we can define and identify causal effects to quantify sequential bias. Moreover, we propose estimators and explore their properties, including double robustness and semiparametric efficiency. In a case study of 27,831 encounters with a large academic emergency department, we use our approach to demonstrate that the decision to route a patient to an area for low acuity patients has a significant impact on the care of future patients.

stat.ME↗

arXiv2022

Evaluation of a Split Flow Model for the Emergency Department

Split flow models, in which a physician rather than a nurse performs triage, are increasingly being used in hospital emergency departments (EDs) to improve patient flow. Before deciding whether such interventions should be adopted, it is important to understand how split flows causally impact patient flow and outcomes. We employ causal inference methodology to estimate average causal effects of a split flow model on time to be roomed, time to disposition after being roomed, admission decisions, and ED revisits at a large tertiary teaching hospital that uses a split flow model during certain hours each day. We propose a regression discontinuity (RD) design to identify average causal effects, which we formalize with causal diagrams. Using electronic health records data (n = 21,570), we estimate that split flow increases average time to be roomed by about 4.6 minutes (95% CI: [2.9,6.2] minutes) but decreases average time to disposition by 14.4 minutes (95% CI: [4.1,24.7] minutes), leading to an overall reduction in length of stay. Split flow is also found to decrease admission rates by 5.9% (95% CI: [2.3%, 9.4%]) but not at the expense of a significant change in revisit rates. Lastly, we find that the split flow model is especially effective at reducing length of stay during low congestion levels, which mediation analysis partly attributes to early task initiation by the physician assigned to triage.

stat.AP↗