Background: Previous human ethology studies have demonstrated that the patient’s and the therapist’s nonverbal behaviors of their interpersonal interactions in therapy have been found to influence a patient’s depression symptomology. Pairing novel statistical techniques such as the hidden Markov model (HMM), interpersonal interaction dynamics can be uncovered by partitioning time into empirically-derived nonverbal communication states. This approach allows for better patient-therapist behavioral dynamics distinctions in predicting depression improvement and, subsequently, for the processes behind depression improvement. Methods: The first part of a therapy sessions was recorded on video to examine the interpersonal interaction behaviors of patients and therapists, in agreement with previous human ethological studies. A Bayesian multivariate multilevel HMM was fitted on the recorded nonverbal behavioral data. Results: It is demonstrated that patients that show improvement in the depression score are characterized by interpersonal interaction dynamics of hyperfocus when listening to their therapist in psychotherapy when compared to non-improving patients. The data supports evidence for the emergence of differences in interpersonal interaction dynamics through changed durations of the patient hyper focused listening states, but not through changed state-switching dynamics over time. Limitations: It should be pointed out is that due to our relatively small sample size that we could not conduct more complex HMM algorithm analyses. Conclusions: We hold that utilizing the HMM will improve human ethological behavior studies in the discover of interpersonal interaction dynamics that occur in therapy and be able to use these dynamics to predict patient depression symptom improvement. This repository contains the accompanying code for the manuscript: "Hidden Markov Model Detection of Interpersonal Interaction dynamics in Predicting Patient Depression Improvement in Psychotherapy: Proof-of-Concept Study". It comprehends R code to: (1) run the multilevel hidden Markov model on the interpersonal interaction behaviors of patients and therapists and (2) post-process the obtained results in (1). Please note that the empirical data used in (1) is not available as part of this repository.

Version 0.2.0 was used for the R package mHMMbayes