The Early Psychosis Screener for Internet (EPSI)-SR: Predicting 12 month psychotic conversion using machine learning

B B Brodey; R R Girgis; O V Favorov; C E Bearden; S W Woods; J Addington; D O Perkins; E F Walker; B A Cornblatt; G Brucato; S E Purcell; I S Brodey; K S Cadenhead

doi:10.1016/j.schres.2019.01.015

The Early Psychosis Screener for Internet (EPSI)-SR: Predicting 12 month psychotic conversion using machine learning

Schizophr Res. 2019 Jun;208:390-396. doi: 10.1016/j.schres.2019.01.015. Epub 2019 Feb 15.

Authors

B B Brodey¹, R R Girgis², O V Favorov³, C E Bearden⁴, S W Woods⁵, J Addington⁶, D O Perkins⁷, E F Walker⁸, B A Cornblatt⁹, G Brucato¹⁰, S E Purcell¹¹, I S Brodey¹², K S Cadenhead¹³

Affiliations

¹ TeleSage, Inc., 201 East Rosemary St., Chapel Hill, NC 27514, USA. Electronic address: bb@telesage.com.
² New York State Psychiatric Institute, 1051 Riverside Drive, New York, NY 10032, USA. Electronic address: Ragy.Girgis@nyspi.columbia.edu.
³ Department of Biomedical Engineering, University of North Carolina at Chapel Hill, 152 MacNider Hall, Campus Box 7575, Chapel Hill, NC 27599, USA. Electronic address: favorov@email.unc.edu.
⁴ Departments of Psychiatry and Biobehavioral Sciences and Psychology, University of California Los Angeles, 757 Westwood Plaza, Los Angeles, CA 90095, USA. Electronic address: cbearden@mednet.ucla.edu.
⁵ PRIME Psychosis Prodrome Research Clinic, Connecticut Mental Health Center B-38, 34 Park Street, New Haven, CT 06519, USA. Electronic address: scott.woods@yale.edu.
⁶ Hotchkiss Brain Institute, Department of Psychiatry, University of Calgary, 3280 Hospital Drive NW, Calgary, Alberta T2N 4Z6, Canada. Electronic address: jmadding@ucalgary.ca.
⁷ Department of Psychiatry, School of Medicine, University of North Carolina at Chapel Hill, 101 Manning Dr, Chapel Hill, NC 27514, USA. Electronic address: diana_perkins@med.unc.edu.
⁸ Departments of Psychology and Psychiatry, Emory University, 36 Eagle Row, Atlanta, GA 30322, USA. Electronic address: psyefw@emory.edu.
⁹ Department of Psychiatry Research, The Zucker Hillside Hospital, 75-59 263rd St., Glen Oaks, New York 11004, USA. Electronic address: BCornblatt@northwell.edu.
¹⁰ New York State Psychiatric Institute, 1051 Riverside Drive, New York, NY 10032, USA. Electronic address: Gary.Brucato@nyspi.columbia.edu.
¹¹ TeleSage, Inc., 201 East Rosemary St., Chapel Hill, NC 27514, USA. Electronic address: spurcell@telesage.com.
¹² Department of English and Comparative Literature, University of North Carolina at Chapel Hill, Chapel Hill, NC 27514, USA. Electronic address: brodey@email.unc.edu.
¹³ Department of Psychiatry, University of California, San Diego, 9500 Gilman Drive, La Jolla, California 92093-0810, USA. Electronic address: kcadenhead@ucsd.edu.

PMID: 30777603
DOI: 10.1016/j.schres.2019.01.015

Abstract

Introduction: A faster and more accurate self-report screener for early psychosis is needed to promote early identification and intervention.

Methods: Self-report Likert-scale survey items were administered to individuals being screened with the Structured Interview for Psychosis-risk Syndromes (SIPS) and followed at eight early psychosis clinics. An a priori analytic plan included Spectral Clustering Analysis to reduce the item pool, followed by development of Support Vector Machine (SVM) classifiers.

Results: The cross-validated positive predictive value (PPV) of the EPSI at the default cut-off (76.5%) exceeded that of the clinician-administered SIPS (68.5%) at separating individuals who would not convert to psychosis within 12 months from those who either would convert within 12 months or who had already experienced a first episode psychosis (FEP). When used in tandem with the SIPS on clinical high risk participants, the EPSI increased the combined PPV to 86.6%. The SVM classified as FEP/converters only 1% of individuals in non-clinical and 4% of clinical low risk populations. Sensitivity of the EPSI, however, was 51% at the default cut-off.

Discussion: The EPSI identifies, comparably to the SIPS but in less time and with fewer resources, individuals who are either at very high risk to develop a psychotic disorder within 12 months or who are already psychotic. At its default cut-off, EPSI misses 49% of current or future psychotic cases. The cut-off can, however, be adjusted based on purpose. The EPSI is the first validated assessment to predict 12-month psychotic conversion. An online screening system, www.eps.telesage.org, is under development.

Keywords: Attenuated psychotic syndrome; First episode psychosis; PQ-B; Prodromal psychosis; SIPS; Schizophrenia.

Publication types

Multicenter Study
Research Support, N.I.H., Extramural

MeSH terms

Diagnosis, Computer-Assisted*
Early Diagnosis
Humans
Internet*
Machine Learning*
Predictive Value of Tests
Psychotic Disorders / diagnosis*
Psychotic Disorders / psychology
Risk Assessment
Support Vector Machine