Bayesian network analysis of antidepressant treatment trajectories

It is currently difficult to successfully choose the correct type of antidepressant for individual patients. To discover patterns in patient characteristics, treatment choices and outcomes, we performed retrospective Bayesian network analysis combined with natural language processing (NLP). This study was conducted at two mental healthcare facilities in the Netherlands. Adult patients admitted and treated with antidepressants between 2014 and 2020 were included. Outcome measures were antidepressant continuation, prescription duration and four treatment outcome topics: core complaints, social functioning, general well-being and patient experience, extracted through NLP of clinical notes. Combined with patient and treatment characteristics, Bayesian networks were constructed at both facilities and compared. Antidepressant choices were continued in 66% and 89% of antidepressant trajectories. Score-based network analysis revealed 28 dependencies between treatment choices, patient characteristics and outcomes. Treatment outcomes and prescription duration were tightly intertwined and interacted with antipsychotics and benzodiazepine co-medication. Tricyclic antidepressant prescription and depressive disorder were important predictors for antidepressant continuation. We show a feasible way of pattern discovery in psychiatry data, through combining network analysis with NLP. Further research should explore the found patterns in patient characteristics, treatment choices and outcomes prospectively, and the possibility of translating these into a tool for clinical decision support.

Automated summary

Currently, it is challenging to choose the right antidepressant for individual patients. In this study, we used retrospective Bayesian network analysis and natural language processing to identify patterns in patient characteristics, treatment choices, and outcomes. We collected data from adult patients treated with antidepressants at two mental healthcare facilities in the Netherlands between 2014 and 2020. By analyzing clinical notes, we extracted outcome measures such as antidepressant continuation, prescription duration, and treatment outcome topics. Our findings revealed dependencies between treatment choices, patient characteristics, and outcomes. Tightly intertwined with treatment outcomes and prescription duration were the use of antipsychotics and benzodiazepines. Tricyclic antidepressant prescription and depressive disorder were significant predictors for antidepressant continuation. This study offers a feasible approach for pattern discovery in psychiatry data, and further research should explore the potential translation of these patterns into clinical decision support tools.