Rachele Sanfelici1, Dominic B Dwyer2, Linda A Antonucci3, Nikolaos Koutsouleris4. 1. Department of Psychiatry and Psychotherapy, Ludwig-Maximilian-University Munich, Germany; Max Planck School of Cognition, Leipzig, Germany. 2. Department of Psychiatry and Psychotherapy, Ludwig-Maximilian-University Munich, Germany. 3. Department of Psychiatry and Psychotherapy, Ludwig-Maximilian-University Munich, Germany; Department of Education, Psychology, and Communication, University of Bari "Aldo Moro," Bari, Italy. 4. Department of Psychiatry and Psychotherapy, Ludwig-Maximilian-University Munich, Germany; Max Planck Institute of Psychiatry Munich, Munich, Germany. Electronic address: nikolaos.koutsouleris@med.uni-muenchen.de.
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.
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 CHRpatients and 480 healthy control subjects). CHRpatients 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.
Authors: Nikolaos Koutsouleris; Michelle Worthington; Dominic B Dwyer; Lana Kambeitz-Ilankovic; Rachele Sanfelici; Paolo Fusar-Poli; Marlene Rosen; Stephan Ruhrmann; Alan Anticevic; Jean Addington; Diana O Perkins; Carrie E Bearden; Barbara A Cornblatt; Kristin S Cadenhead; Daniel H Mathalon; Thomas McGlashan; Larry Seidman; Ming Tsuang; Elaine F Walker; Scott W Woods; Peter Falkai; Rebekka Lencer; Alessandro Bertolino; Joseph Kambeitz; Frauke Schultze-Lutter; Eva Meisenzahl; Raimo K R Salokangas; Jarmo Hietala; Paolo Brambilla; Rachel Upthegrove; Stefan Borgwardt; Stephen Wood; Raquel E Gur; Philip McGuire; Tyrone D Cannon Journal: Biol Psychiatry Date: 2021-07-06 Impact factor: 13.382
Authors: Rosanne J Turner; Femke Coenen; Femke Roelofs; Karin Hagoort; Aki Härmä; Peter D Grünwald; Fleur P Velders; Floortje E Scheepers Journal: BMC Psychiatry Date: 2022-06-17 Impact factor: 4.144
Authors: Ganesh B Chand; Pankhuri Singhal; Dominic B Dwyer; Junhao Wen; Guray Erus; Jimit Doshi; Dhivya Srinivasan; Elizabeth Mamourian; Erdem Varol; Aristeidis Sotiras; Gyujoon Hwang; Paola Dazzan; Rene S Kahn; Hugo G Schnack; Marcus V Zanetti; Eva Meisenzahl; Geraldo F Busatto; Benedicto Crespo-Facorro; Christos Pantelis; Stephen J Wood; Chuanjun Zhuo; Russell T Shinohara; Haochang Shou; Yong Fan; Nikolaos Koutsouleris; Antonia N Kaczkurkin; Tyler M Moore; Anurag Verma; Monica E Calkins; Raquel E Gur; Ruben C Gur; Marylyn D Ritchie; Theodore D Satterthwaite; Daniel H Wolf; Christos Davatzikos Journal: Am J Psychiatry Date: 2022-04-12 Impact factor: 19.242
Authors: Carl B Roth; Andreas Papassotiropoulos; Annette B Brühl; Undine E Lang; Christian G Huber Journal: Int J Environ Res Public Health Date: 2021-08-05 Impact factor: 3.390
Authors: Paolo Fusar-Poli; Christoph U Correll; Celso Arango; Michael Berk; Vikram Patel; John P A Ioannidis Journal: World Psychiatry Date: 2021-06 Impact factor: 79.683
Authors: Tyler M Moore; Monica E Calkins; Adon F G Rosen; Ellyn R Butler; Kosha Ruparel; Paolo Fusar-Poli; Nikolaos Koutsouleris; Philip McGuire; Tyrone D Cannon; Ruben C Gur; Raquel E Gur Journal: Psychol Med Date: 2021-01-12 Impact factor: 10.592
Authors: Linda A Antonucci; Alessandra Raio; Giulio Pergola; Barbara Gelao; Marco Papalino; Antonio Rampino; Ileana Andriola; Giuseppe Blasi; Alessandro Bertolino Journal: BMC Psychol Date: 2021-03-23