Department of Economics and Business Economics

A precision medicine approach for psychiatric disease based on repeated symptom scores

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperJournal articleResearchpeer-review



  • Anthony T Fojo, Johns Hopkins University School of Medicine, Department of Medicine, Division of General Internal Medicine, Baltimore, MD, USA. Electronic address:
  • ,
  • Katherine L Musliner
  • Peter P Zandi, Department of Mental Health, Johns Hopkins University Bloomberg School of Public Health, Baltimore, MD, USA.
  • ,
  • Scott L Zeger, Department of Biostatistics, Johns Hopkins Bloomberg School of Public Health, Baltimore, Maryland, USA.

For psychiatric diseases, rich information exists in the serial measurement of mental health symptom scores. We present a precision medicine framework for using the trajectories of multiple symptoms to make personalized predictions about future symptoms and related psychiatric events. Our approach fits a Bayesian hierarchical model that estimates a population-average trajectory for all symptoms and individual deviations from the average trajectory, then fits a second model that uses individual symptom trajectories to estimate the risk of experiencing an event. The fitted models are used to make clinically relevant predictions for new individuals. We demonstrate this approach on data from a study of antipsychotic therapy for schizophrenia, predicting future scores for positive, negative, and general symptoms, and the risk of treatment failure in 522 schizophrenic patients with observations over 8 weeks. While precision medicine has focused largely on genetic and molecular data, the complementary approach we present illustrates that innovative analytic methods for existing data can extend its reach more broadly. The systematic use of repeated measurements of psychiatric symptoms offers the promise of precision medicine in the field of mental health.

Original languageEnglish
JournalJournal of Psychiatric Research
Pages (from-to)147-155
Number of pages9
Publication statusPublished - 2017

    Research areas

  • Journal Article

See relations at Aarhus University Citationformats

Download statistics

No data available

ID: 116768167