The Early Psychosis Screener (EPS): Quantitative validation against the SIPS using machine learning

SCHIZOPHRENIA RESEARCH

卷:197

Article

Brodey, B. B.¹  Girgis, R. R.²  Favorov, O., V³  Addington, J.⁴  Perkins, D. O.⁵  Bearden, C. E.^6,7  Woods, S. W.⁸  Walker, E. F.^9,10  Cornblatt, B. A.¹¹  Brucato, G.²  Walsh, B.⁸  Elkin, K. A.¹  Brodey, I. S.¹² 

[1] TeleSage Inc, 201 East Rosemary St, Chapel Hill, NC 27514 USA

[2] New York State Psychiat Inst & Hosp, 1051 Riverside Dr,Unit 31, New York, NY 10032 USA

[3] Univ N Carolina, Dept Biomed Engn, 152 MacNider Hall,Campus Box 7575, Chapel Hill, NC 27599 USA

[4] Univ Calgary, Dept Psychiat, Hotchkiss Brain Inst, 3280 Hosp Dr NW, Calgary, AB T2N 4Z6, Canada

[5] Univ N Carolina, Sch Med, Dept Psychiat, 101 Manning Dr, Chapel Hill, NC 27514 USA

[6] Univ Calif Los Angeles, Dept Psychiat & Biobehav Sci, 300 Med Plaza,Rm 2265, Los Angeles, CA 90095 USA

[7] Univ Calif Los Angeles, Dept Psychol, 300 Med Plaza,Rm 2265, Los Angeles, CA 90095 USA

[8] Connecticut Mental Hlth Ctr, PRIME Psychosis Prodrome Res Clin, B-38,34 Pk St, New Haven, CT 06519 USA

[9] Emory Univ, Dept Psychol, 36 Eagle Row, Atlanta, GA 30322 USA

[10] Emory Univ, Dept Psychiat, 36 Eagle Row, Atlanta, GA 30322 USA

[11] Zucker Hillside Hosp, Dept Psychiat Res, 75-59 263rd St, Glen Oaks, NY 11004 USA

[12] Univ N Carolina, 434 Greenlaw,Campus Box 3520, Chapel Hill, NC 27599 USA

关键词: SIPS;    PQ-B;    NAPLS;    Psychosis;    Prodromal;    Schizophrenia;    Screener;    Machine learning;   

DOI  :  10.1016/j.schres.2017.11.030

来源: Elsevier

【 摘 要 】

Machine learning techniques were used to identify highly informative early psychosis self-report items and to validate an early psychosis screener (EPS) against the Structured Interview for Psychosis-risk Syndromes (SIPS). The Prodromal Questionnaire-Brief Version (PQ-B) and 148 additional items were administered to 229 individuals being screened with the SIPS at 7 North American Prodrome Longitudinal Study sites and at Columbia University. Fifty individuals were found to have SIPS scores of 0, 1, or 2, making them clinically low risk (CLR) controls; 144 were classified as clinically high risk (CHR) (SIPS 3-5) and 35 were found to have first episode psychosis (FEP) (SIPS 6). Spectral clustering analysis, performed on 124 of the items, yielded two cohesive item groups, the first mostly related to psychosis and mania, the second mostly related to depression, anxiety, and social and general work/school functioning. Items within each group were sorted according to their usefulness in distinguishing between CLR and CHR individuals using the Minimum Redundancy Maximum Relevance procedure. A receiver operating characteristic area under the curve (AUC) analysis indicated that maximal differentiation of CLR and CHR participants was achieved with a 26-item solution (AUC = 0.899 +/- 0.001). The EPS-26 outperformed the PQ-B (AUC = 0.834 +/- 0.001). For screening purposes, the self-report EPS-26 appeared to differentiate individuals who are either CLR or CHR approximately as well as the clinician-administered SIPS. The EPS-26 may prove useful as a self-report screener and may lead to a decrease in the duration of untreated psychosis. A validation of the EPS-26 against actual conversion is underway. (C) 2017 Elsevier B.V. All rights reserved.

【 授权许可】

Free