Estimating Treatment Effects for Depression in Longitudinal Therapy Switching Settings
For clinicians and researchers in depression treatment, this provides a method to estimate treatment effects in realistic switching scenarios, though it is domain-specific and incremental.
The authors tackle the challenge of estimating individualized treatment effects for depression when patients switch medications, using a proprietary clinical trial dataset. They benchmark 8 estimators and find Causal Forest performs best, revealing that symptom benefits vary by switch direction and that confounding-adjusted estimates are modest but actionable.
Depression treatment often requires switching medications due to inadequate response or adverse effects. Estimating individualized treatment effects in this setting is challenging because treatment assignment is confounded by patient characteristics, switching induces time-varying selection, and counterfactual outcomes are not observed in follow-up data. Using a proprietary longitudinal major depressive disorder (MDD) clinical trial dataset, we formulate a next-visit counterfactual prediction task to estimate Hamilton Depression Rating Scale (HAMD-17) total scores under alternative treatments. We benchmark 8 estimators, including meta-learners, residual-based methods, and tree-based approaches. Causal Forest (CF) demonstrates the most favorable and consistent performance across all criteria. Our analysis shows that symptom benefits concentrate in specific switch directions, with dose intensification being generally beneficial. Notably, we identify a counterintuitive exception where a lower-intensity regimen outperforms a higher-intensity alternative for specific patient subsets. While crude observational comparisons substantially overstate gains, confounding-adjusted estimates yield modest, actionable magnitudes. These findings provide prospectively testable candidates for clinical decision support in depression care.