Uncovering social states in healthy and clinical populations using digital phenotyping and Hidden Markov Models

Background Brain related disorders are characterized by observable behavioral symptoms, for example social withdrawal. Smartphones can passively collect behavioral data reflecting digital activities, such as communication app usage and calls. This data is collected objectively in real time, avoiding recall bias, and may therefore be a useful tool for measuring behaviors related to social functioning. Despite promising clinical utility, analyzing smartphone data is challenging as datasets often include a range of missingness-prone temporal features. Objective Hidden Markov Models (HMMs) provide interpretable, lower-dimensional temporal representations of data, allowing missingness. We aimed to investigate the HMM as a method for modeling smartphone time series data. Methods We applied an HMM to an aggregate dataset of smartphone measures designed to assess phone-related social functioning in healthy controls (HCs), participants with schizophrenia, Alzheimer’s disease (AD) and memory complaints. We trained the HMM on a subset of HCs (n=91) and selected a model with socially “active” and “inactive” states, then generated hidden state sequences per participant and calculated their “total dwell time”, i.e. the percentage of time spent in the socially active state. Linear regression models were used to compare the total dwell time to social and clinical measures in a subset of participants with available measures, and logistic regression was used to compare total dwell times between diagnostic groups and HCs. We primarily report results from a two-state HMM but also verified results in HMMs with more hidden states, and trained on the whole participant dataset. Results We identified lower total dwell times in AD (n=26) versus withheld HCs (n=156) (odds ratio=0.95, FDR corrected P <.001), as well as in participants with memory complaints (n=57) (odds ratio=0.97, FDR corrected P =0.004). The AD result was very robust across HMM variations, whilst the memory complaints result was less robust. We also observed an interaction between AD group and total dwell time when predicting social functioning (FDR corrected P =0.02). No significant relationships regarding total dwell time were identified for participants with schizophrenia (n=18). Conclusions We found the HMM to be a practical, interpretable method for digital phenotyping analysis, providing an objective phenotype that is a possible indicator of social functioning.