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

Anthony Fojo, Katherine L. Musliner, Peter P Zandi, Scott Zeger

Research output: Contribution to journalArticle

Abstract

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 (US)
Pages (from-to)147-155
Number of pages9
JournalJournal of Psychiatric Research
Volume95
DOIs
StatePublished - Dec 1 2017

Fingerprint

Precision Medicine
Psychiatry
Mental Health
Treatment Failure
Antipsychotic Agents
Molecular Biology
Schizophrenia
Population
Medicine
Therapeutics
Trajectory

Keywords

  • Data mining
  • Mental health
  • Patient reported outcome measures
  • Precision medicine
  • Schizophrenia

ASJC Scopus subject areas

  • Arts and Humanities (miscellaneous)
  • Psychiatry and Mental health
  • Biological Psychiatry

Cite this

A precision medicine approach for psychiatric disease based on repeated symptom scores. / Fojo, Anthony; Musliner, Katherine L.; Zandi, Peter P; Zeger, Scott.

In: Journal of Psychiatric Research, Vol. 95, 01.12.2017, p. 147-155.

Research output: Contribution to journalArticle

@article{0361fb19bbe444b5870a5f607406f5ca,
title = "A precision medicine approach for psychiatric disease based on repeated symptom scores",
abstract = "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.",
keywords = "Data mining, Mental health, Patient reported outcome measures, Precision medicine, Schizophrenia",
author = "Anthony Fojo and Musliner, {Katherine L.} and Zandi, {Peter P} and Scott Zeger",
year = "2017",
month = "12",
day = "1",
doi = "10.1016/j.jpsychires.2017.08.008",
language = "English (US)",
volume = "95",
pages = "147--155",
journal = "Journal of Psychiatric Research",
issn = "0022-3956",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - A precision medicine approach for psychiatric disease based on repeated symptom scores

AU - Fojo, Anthony

AU - Musliner, Katherine L.

AU - Zandi, Peter P

AU - Zeger, Scott

PY - 2017/12/1

Y1 - 2017/12/1

N2 - 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.

AB - 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.

KW - Data mining

KW - Mental health

KW - Patient reported outcome measures

KW - Precision medicine

KW - Schizophrenia

UR - http://www.scopus.com/inward/record.url?scp=85028461968&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85028461968&partnerID=8YFLogxK

U2 - 10.1016/j.jpsychires.2017.08.008

DO - 10.1016/j.jpsychires.2017.08.008

M3 - Article

VL - 95

SP - 147

EP - 155

JO - Journal of Psychiatric Research

JF - Journal of Psychiatric Research

SN - 0022-3956

ER -