B0855
Title: Individual causal effect estimation accounting for latent disease state in bipolar disorder smartphone studies
Authors: Linda Valeri - Columbia University (United States)
Charlotte Fowler - Columbia University Mailman School of Public Health (United States) [presenting]
Abstract: Individuals with bipolar disorder tend to cycle through disease states such as depression and mania. The heterogeneous nature of disease across states complicates the evaluation of interventions for bipolar disorder patients, as varied interventional success is observed within and across individuals. It is hypothesized that the disease state acts as a confounder and effect modifier for the causal effect of a given intervention on health outcomes. An N-of-1 approach is proposed to address this dilemma using an adapted autoregressive hidden Markov model applied to longitudinal mobile health data collected from individuals with bipolar disorder. This method allows deriving a latent variable from daily survey responses to be treated as a confounder and effect modifier between the exposure and outcome of interest. A counterfactual approach is employed for causal inference and to obtain a g-formula estimator to recover said effect. The performance of the proposed method is compared with naive approaches across different simulation scenarios and in an application to a multi-year smartphone study of bipolar patients.