King's College London

Research portal

Individualized Diagnostic and Prognostic Models for Patients With Psychosis Risk Syndromes: A Meta-analytic View on the State of the Art

Research output: Contribution to journalArticle

Standard

Individualized Diagnostic and Prognostic Models for Patients With Psychosis Risk Syndromes : A Meta-analytic View on the State of the Art. / Sanfelici, Rachele; Dwyer, Dominic B; Antonucci, Linda A; Koutsouleris, Nikolaos.

In: Biological psychiatry, Vol. 88, No. 4, 15.08.2020, p. 349-360.

Research output: Contribution to journalArticle

Harvard

Sanfelici, R, Dwyer, DB, Antonucci, LA & Koutsouleris, N 2020, 'Individualized Diagnostic and Prognostic Models for Patients With Psychosis Risk Syndromes: A Meta-analytic View on the State of the Art', Biological psychiatry, vol. 88, no. 4, pp. 349-360. https://doi.org/10.1016/j.biopsych.2020.02.009

APA

Sanfelici, R., Dwyer, D. B., Antonucci, L. A., & Koutsouleris, N. (2020). Individualized Diagnostic and Prognostic Models for Patients With Psychosis Risk Syndromes: A Meta-analytic View on the State of the Art. Biological psychiatry, 88(4), 349-360. https://doi.org/10.1016/j.biopsych.2020.02.009

Vancouver

Sanfelici R, Dwyer DB, Antonucci LA, Koutsouleris N. Individualized Diagnostic and Prognostic Models for Patients With Psychosis Risk Syndromes: A Meta-analytic View on the State of the Art. Biological psychiatry. 2020 Aug 15;88(4):349-360. https://doi.org/10.1016/j.biopsych.2020.02.009

Author

Sanfelici, Rachele ; Dwyer, Dominic B ; Antonucci, Linda A ; Koutsouleris, Nikolaos. / Individualized Diagnostic and Prognostic Models for Patients With Psychosis Risk Syndromes : A Meta-analytic View on the State of the Art. In: Biological psychiatry. 2020 ; Vol. 88, No. 4. pp. 349-360.

Bibtex Download

@article{cbf2855e2497436ea483bda8e8e72119,
title = "Individualized Diagnostic and Prognostic Models for Patients With Psychosis Risk Syndromes: A Meta-analytic View on the State of the Art",
abstract = "BACKGROUND: The clinical high risk (CHR) paradigm has facilitated research into the underpinnings of help-seeking individuals at risk for developing psychosis, aiming at predicting and possibly preventing transition to the overt disorder. Statistical methods such as machine learning and Cox regression have provided the methodological basis for this research by enabling the construction of diagnostic models (i.e., distinguishing CHR individuals from healthy individuals) and prognostic models (i.e., predicting a future outcome) based on different data modalities, including clinical, neurocognitive, and neurobiological data. However, their translation to clinical practice is still hindered by the high heterogeneity of both CHR populations and methodologies applied.METHODS: We systematically reviewed the literature on diagnostic and prognostic models built on Cox regression and machine learning. Furthermore, we conducted a meta-analysis on prediction performances investigating heterogeneity of methodological approaches and data modality.RESULTS: A total of 44 articles were included, covering 3707 individuals for prognostic studies and 1052 individuals for diagnostic studies (572 CHR patients and 480 healthy control subjects). CHR patients could be classified against healthy control subjects with 78% sensitivity and 77% specificity. Across prognostic models, sensitivity reached 67% and specificity reached 78%. Machine learning models outperformed those applying Cox regression by 10% sensitivity. There was a publication bias for prognostic studies yet no other moderator effects.CONCLUSIONS: Our results may be driven by substantial clinical and methodological heterogeneity currently affecting several aspects of the CHR field and limiting the clinical implementability of the proposed models. We discuss conceptual and methodological harmonization strategies to facilitate more reliable and generalizable models for future clinical practice.",
author = "Rachele Sanfelici and Dwyer, {Dominic B} and Antonucci, {Linda A} and Nikolaos Koutsouleris",
note = "Copyright {\textcopyright} 2020 Society of Biological Psychiatry. Published by Elsevier Inc. All rights reserved.",
year = "2020",
month = aug,
day = "15",
doi = "10.1016/j.biopsych.2020.02.009",
language = "English",
volume = "88",
pages = "349--360",
journal = "Biological psychiatry",
issn = "0006-3223",
publisher = "Elsevier",
number = "4",

}

RIS (suitable for import to EndNote) Download

TY - JOUR

T1 - Individualized Diagnostic and Prognostic Models for Patients With Psychosis Risk Syndromes

T2 - A Meta-analytic View on the State of the Art

AU - Sanfelici, Rachele

AU - Dwyer, Dominic B

AU - Antonucci, Linda A

AU - Koutsouleris, Nikolaos

N1 - Copyright © 2020 Society of Biological Psychiatry. Published by Elsevier Inc. All rights reserved.

PY - 2020/8/15

Y1 - 2020/8/15

N2 - BACKGROUND: The clinical high risk (CHR) paradigm has facilitated research into the underpinnings of help-seeking individuals at risk for developing psychosis, aiming at predicting and possibly preventing transition to the overt disorder. Statistical methods such as machine learning and Cox regression have provided the methodological basis for this research by enabling the construction of diagnostic models (i.e., distinguishing CHR individuals from healthy individuals) and prognostic models (i.e., predicting a future outcome) based on different data modalities, including clinical, neurocognitive, and neurobiological data. However, their translation to clinical practice is still hindered by the high heterogeneity of both CHR populations and methodologies applied.METHODS: We systematically reviewed the literature on diagnostic and prognostic models built on Cox regression and machine learning. Furthermore, we conducted a meta-analysis on prediction performances investigating heterogeneity of methodological approaches and data modality.RESULTS: A total of 44 articles were included, covering 3707 individuals for prognostic studies and 1052 individuals for diagnostic studies (572 CHR patients and 480 healthy control subjects). CHR patients could be classified against healthy control subjects with 78% sensitivity and 77% specificity. Across prognostic models, sensitivity reached 67% and specificity reached 78%. Machine learning models outperformed those applying Cox regression by 10% sensitivity. There was a publication bias for prognostic studies yet no other moderator effects.CONCLUSIONS: Our results may be driven by substantial clinical and methodological heterogeneity currently affecting several aspects of the CHR field and limiting the clinical implementability of the proposed models. We discuss conceptual and methodological harmonization strategies to facilitate more reliable and generalizable models for future clinical practice.

AB - BACKGROUND: The clinical high risk (CHR) paradigm has facilitated research into the underpinnings of help-seeking individuals at risk for developing psychosis, aiming at predicting and possibly preventing transition to the overt disorder. Statistical methods such as machine learning and Cox regression have provided the methodological basis for this research by enabling the construction of diagnostic models (i.e., distinguishing CHR individuals from healthy individuals) and prognostic models (i.e., predicting a future outcome) based on different data modalities, including clinical, neurocognitive, and neurobiological data. However, their translation to clinical practice is still hindered by the high heterogeneity of both CHR populations and methodologies applied.METHODS: We systematically reviewed the literature on diagnostic and prognostic models built on Cox regression and machine learning. Furthermore, we conducted a meta-analysis on prediction performances investigating heterogeneity of methodological approaches and data modality.RESULTS: A total of 44 articles were included, covering 3707 individuals for prognostic studies and 1052 individuals for diagnostic studies (572 CHR patients and 480 healthy control subjects). CHR patients could be classified against healthy control subjects with 78% sensitivity and 77% specificity. Across prognostic models, sensitivity reached 67% and specificity reached 78%. Machine learning models outperformed those applying Cox regression by 10% sensitivity. There was a publication bias for prognostic studies yet no other moderator effects.CONCLUSIONS: Our results may be driven by substantial clinical and methodological heterogeneity currently affecting several aspects of the CHR field and limiting the clinical implementability of the proposed models. We discuss conceptual and methodological harmonization strategies to facilitate more reliable and generalizable models for future clinical practice.

U2 - 10.1016/j.biopsych.2020.02.009

DO - 10.1016/j.biopsych.2020.02.009

M3 - Article

C2 - 32305218

VL - 88

SP - 349

EP - 360

JO - Biological psychiatry

JF - Biological psychiatry

SN - 0006-3223

IS - 4

ER -

View graph of relations

© 2020 King's College London | Strand | London WC2R 2LS | England | United Kingdom | Tel +44 (0)20 7836 5454