Unifying Data-Adaptive Longitudinal Treatment-Effect Subgroup Discovery and Pretreatment Membership Prediction
Abstract
Precision medicine seeks to match patients with treatments from which they are most likely to benefit. A key step toward this goal is to learn treatment-effect heterogeneity from longitudinal study data. This requires discovering subgroups with distinct treatment-effect trajectories and predicting subgroup membership for new patients from pretreatment information. Existing methods do not fully unify these tasks. Covariate-informed membership models typically prespecify the subgroup number or covariance structure, whereas data-adaptive discovery methods often require prediction in a separate stage. We propose a data-adaptive semiparametric mixture-of-experts framework that unifies longitudinal treatment-effect subgroup discovery and pretreatment membership prediction. Subgroup-specific varying-coefficient functions characterize treatment-effect trajectories, while flexible covariance functions account for within-subject dependence. A covariate-dependent gating model links membership to pretreatment characteristics. A penalty on global component weights removes redundant subgroups, while separate gating coefficients allow patient-specific membership probabilities among retained subgroups. A blockwise generalized expectation--maximization algorithm estimates all model components under a single penalized observed-data objective. We establish consistent subgroup-number selection, convergence rates for the functional estimators, and asymptotic normality for the finite-dimensional parameters. Simulations show reliable subgroup-number selection and more accurate conditional membership prediction than a two-step procedure. Applications to the SANAD epilepsy study and the COMPETE migraine trial identify distinct temporal treatment-effect patterns.
Related
- Estimating Group Average Treatment Effects in High-Risk Populations with Unobserved Target Membership
- Byzantine-Robust Federated RAG via Aligned Calibration and Fixed-Membership Conformal Prediction
- Causal discovery and inference in COVID-19: A multiscale longitudinal analysis using mixtures of DAGs
- PAR2COX: Survival-Informed Tensor Decomposition for Phenotyping and Risk Prediction from Irregular Longitudinal Data
- Online Individualized Treatment Selection under Partial Feedback: False Discovery Control and Minimax Optimality
BibTeX
@misc{zhang2026unifying,
title = {{Unifying Data-Adaptive Longitudinal Treatment-Effect Subgroup Discovery and Pretreatment Membership Prediction}},
author = {Pu Zhang and Yuheng Li and Jiakun Jiang},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.41886},
eprint = {2610.41886},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.41886},
note = {CC0},
}
RIS
TY - UNPB
TI - Unifying Data-Adaptive Longitudinal Treatment-Effect Subgroup Discovery and Pretreatment Membership Prediction
AU - Pu Zhang
AU - Yuheng Li
AU - Jiakun Jiang
PY - 2026
DA - 2026/10/30
PB - arXiv
DO - 10.48550/arxiv.2610.41886
UR - https://arxiv.org/abs/2610.41886
AB - Precision medicine seeks to match patients with treatments from which they are most likely to benefit. A key step toward this goal is to learn treatment-effect heterogeneity from longitudinal study data. This requires discovering subgroups with distinct treatment-effect trajectories and predicting subgroup membership for new patients from pretreatment information. Existing methods do not fully unify these tasks. Covariate-informed membership models typically prespecify the subgroup number or covariance structure, whereas data-adaptive discovery methods often require prediction in a separate stage. We propose a data-adaptive semiparametric mixture-of-experts framework that unifies longitudinal treatment-effect subgroup discovery and pretreatment membership prediction. Subgroup-specific varying-coefficient functions characterize treatment-effect trajectories, while flexible covariance functions account for within-subject dependence. A covariate-dependent gating model links membership to pretreatment characteristics. A penalty on global component weights removes redundant subgroups, while separate gating coefficients allow patient-specific membership probabilities among retained subgroups. A blockwise generalized expectation--maximization algorithm estimates all model components under a single penalized observed-data objective. We establish consistent subgroup-number selection, convergence rates for the functional estimators, and asymptotic normality for the finite-dimensional parameters. Simulations show reliable subgroup-number selection and more accurate conditional membership prediction than a two-step procedure. Applications to the SANAD epilepsy study and the COMPETE migraine trial identify distinct temporal treatment-effect patterns.
ER -