Prediction of Early Symptom Remission in Two Independent Samples of First-Episode Psychosis Patients Using Machine Learning

Research output: Contribution to journal › Journal article › Research › peer-review

Standard

Prediction of Early Symptom Remission in Two Independent Samples of First-Episode Psychosis Patients Using Machine Learning. / Soldatos, Rigas F.; Cearns, Micah; Nielsen, Mette Ø.; Kollias, Costas; Xenaki, Lida Alkisti; Stefanatou, Pentagiotissa; Ralli, Irene; Dimitrakopoulos, Stefanos; Hatzimanolis, Alex; Kosteletos, Ioannis; Vlachos, Ilias I.; Selakovic, Mirjana; Foteli, Stefania; Nianiakas, Nikolaos; Mantonakis, Leonidas; Triantafyllou, Theoni F.; Ntigridaki, Aggeliki; Ermiliou, Vanessa; Voulgaraki, Marina; Psarra, Evaggelia; Sørensen, Mikkel E.; Bojesen, Kirsten B.; Tangmose, Karen; Sigvard, Anne M.; Ambrosen, Karen S.; Meritt, Toni; Syeda, Warda; Glenthøj, Birte Y.; Koutsouleris, Nikolaos; Pantelis, Christos; Ebdrup, Bjørn H.; Stefanis, Nikos.

In: Schizophrenia Bulletin, Vol. 48, No. 1, 2022, p. 122-133.

Research output: Contribution to journal › Journal article › Research › peer-review

Harvard

Soldatos, RF, Cearns, M, Nielsen, MØ, Kollias, C, Xenaki, LA, Stefanatou, P, Ralli, I, Dimitrakopoulos, S, Hatzimanolis, A, Kosteletos, I, Vlachos, II, Selakovic, M, Foteli, S, Nianiakas, N, Mantonakis, L, Triantafyllou, TF, Ntigridaki, A, Ermiliou, V, Voulgaraki, M, Psarra, E, Sørensen, ME, Bojesen, KB, Tangmose, K, Sigvard, AM, Ambrosen, KS, Meritt, T, Syeda, W, Glenthøj, BY, Koutsouleris, N, Pantelis, C, Ebdrup, BH & Stefanis, N 2022, 'Prediction of Early Symptom Remission in Two Independent Samples of First-Episode Psychosis Patients Using Machine Learning', Schizophrenia Bulletin, vol. 48, no. 1, pp. 122-133. https://doi.org/10.1093/schbul/sbab107

APA

Soldatos, R. F., Cearns, M., Nielsen, M. Ø., Kollias, C., Xenaki, L. A., Stefanatou, P., Ralli, I., Dimitrakopoulos, S., Hatzimanolis, A., Kosteletos, I., Vlachos, I. I., Selakovic, M., Foteli, S., Nianiakas, N., Mantonakis, L., Triantafyllou, T. F., Ntigridaki, A., Ermiliou, V., Voulgaraki, M., ... Stefanis, N. (2022). Prediction of Early Symptom Remission in Two Independent Samples of First-Episode Psychosis Patients Using Machine Learning. Schizophrenia Bulletin, 48(1), 122-133. https://doi.org/10.1093/schbul/sbab107

Vancouver

Soldatos RF, Cearns M, Nielsen MØ, Kollias C, Xenaki LA, Stefanatou P et al. Prediction of Early Symptom Remission in Two Independent Samples of First-Episode Psychosis Patients Using Machine Learning. Schizophrenia Bulletin. 2022;48(1):122-133. https://doi.org/10.1093/schbul/sbab107

Author

Soldatos, Rigas F. ; Cearns, Micah ; Nielsen, Mette Ø. ; Kollias, Costas ; Xenaki, Lida Alkisti ; Stefanatou, Pentagiotissa ; Ralli, Irene ; Dimitrakopoulos, Stefanos ; Hatzimanolis, Alex ; Kosteletos, Ioannis ; Vlachos, Ilias I. ; Selakovic, Mirjana ; Foteli, Stefania ; Nianiakas, Nikolaos ; Mantonakis, Leonidas ; Triantafyllou, Theoni F. ; Ntigridaki, Aggeliki ; Ermiliou, Vanessa ; Voulgaraki, Marina ; Psarra, Evaggelia ; Sørensen, Mikkel E. ; Bojesen, Kirsten B. ; Tangmose, Karen ; Sigvard, Anne M. ; Ambrosen, Karen S. ; Meritt, Toni ; Syeda, Warda ; Glenthøj, Birte Y. ; Koutsouleris, Nikolaos ; Pantelis, Christos ; Ebdrup, Bjørn H. ; Stefanis, Nikos. / Prediction of Early Symptom Remission in Two Independent Samples of First-Episode Psychosis Patients Using Machine Learning. In: Schizophrenia Bulletin. 2022 ; Vol. 48, No. 1. pp. 122-133.

Bibtex

@article{46915c49f5b64733a3b573778e621b3e,

title = "Prediction of Early Symptom Remission in Two Independent Samples of First-Episode Psychosis Patients Using Machine Learning",

abstract = "BACKGROUND: Validated clinical prediction models of short-term remission in psychosis are lacking. Our aim was to develop a clinical prediction model aimed at predicting 4-6-week remission following a first episode of psychosis. METHOD: Baseline clinical data from the Athens First Episode Research Study was used to develop a Support Vector Machine prediction model of 4-week symptom remission in first-episode psychosis patients using repeated nested cross-validation. This model was further tested to predict 6-week remission in a sample of two independent, consecutive Danish first-episode cohorts. RESULTS: Of the 179 participants in Athens, 120 were male with an average age of 25.8 years and average duration of untreated psychosis of 32.8 weeks. 62.9% were antipsychotic-na{\"i}ve. Fifty-seven percent attained remission after 4 weeks. In the Danish cohort, 31% attained remission. Eleven clinical scale items were selected in the Athens 4-week remission cohort. These included the Duration of Untreated Psychosis, Personal and Social Performance Scale, Global Assessment of Functioning and eight items from the Positive and Negative Syndrome Scale. This model significantly predicted 4-week remission status (area under the receiver operator characteristic curve (ROC-AUC) = 71.45, P < .0001). It also predicted 6-week remission status in the Danish cohort (ROC-AUC = 67.74, P < .0001), demonstrating reliability. CONCLUSIONS: Using items from common and validated clinical scales, our model significantly predicted early remission in patients with first-episode psychosis. Although replicated in an independent cohort, forward testing between machine learning models and clinicians' assessment should be undertaken to evaluate the possible utility as a routine clinical tool.",

keywords = "first-episode/psychosis, machine learning, prediction, psychopathology, psychosis, remission, schizophrenia",

author = "Soldatos, {Rigas F.} and Micah Cearns and Nielsen, {Mette {\O}.} and Costas Kollias and Xenaki, {Lida Alkisti} and Pentagiotissa Stefanatou and Irene Ralli and Stefanos Dimitrakopoulos and Alex Hatzimanolis and Ioannis Kosteletos and Vlachos, {Ilias I.} and Mirjana Selakovic and Stefania Foteli and Nikolaos Nianiakas and Leonidas Mantonakis and Triantafyllou, {Theoni F.} and Aggeliki Ntigridaki and Vanessa Ermiliou and Marina Voulgaraki and Evaggelia Psarra and S{\o}rensen, {Mikkel E.} and Bojesen, {Kirsten B.} and Karen Tangmose and Sigvard, {Anne M.} and Ambrosen, {Karen S.} and Toni Meritt and Warda Syeda and Glenth{\o}j, {Birte Y.} and Nikolaos Koutsouleris and Christos Pantelis and Ebdrup, {Bj{\o}rn H.} and Nikos Stefanis",

note = "Publisher Copyright: {\textcopyright} The Author(s) 2021. Published by Oxford University Press on behalf of the Maryland Psychiatric Research Center.All rights reserved. For permissions, please email: journals.permissions@oup.com.",

year = "2022",

doi = "10.1093/schbul/sbab107",

language = "English",

volume = "48",

pages = "122--133",

journal = "Schizophrenia Bulletin",

issn = "0586-7614",

publisher = "Oxford University Press",

number = "1",

}

RIS

TY - JOUR

T1 - Prediction of Early Symptom Remission in Two Independent Samples of First-Episode Psychosis Patients Using Machine Learning

AU - Soldatos, Rigas F.

AU - Cearns, Micah

AU - Nielsen, Mette Ø.

AU - Kollias, Costas

AU - Xenaki, Lida Alkisti

AU - Stefanatou, Pentagiotissa

AU - Ralli, Irene

AU - Dimitrakopoulos, Stefanos

AU - Hatzimanolis, Alex

AU - Kosteletos, Ioannis

AU - Vlachos, Ilias I.

AU - Selakovic, Mirjana

AU - Foteli, Stefania

AU - Nianiakas, Nikolaos

AU - Mantonakis, Leonidas

AU - Triantafyllou, Theoni F.

AU - Ntigridaki, Aggeliki

AU - Ermiliou, Vanessa

AU - Voulgaraki, Marina

AU - Psarra, Evaggelia

AU - Sørensen, Mikkel E.

AU - Bojesen, Kirsten B.

AU - Tangmose, Karen

AU - Sigvard, Anne M.

AU - Ambrosen, Karen S.

AU - Meritt, Toni

AU - Syeda, Warda

AU - Glenthøj, Birte Y.

AU - Koutsouleris, Nikolaos

AU - Pantelis, Christos

AU - Ebdrup, Bjørn H.

AU - Stefanis, Nikos

N1 - Publisher Copyright: © The Author(s) 2021. Published by Oxford University Press on behalf of the Maryland Psychiatric Research Center.All rights reserved. For permissions, please email: journals.permissions@oup.com.

PY - 2022

Y1 - 2022

N2 - BACKGROUND: Validated clinical prediction models of short-term remission in psychosis are lacking. Our aim was to develop a clinical prediction model aimed at predicting 4-6-week remission following a first episode of psychosis. METHOD: Baseline clinical data from the Athens First Episode Research Study was used to develop a Support Vector Machine prediction model of 4-week symptom remission in first-episode psychosis patients using repeated nested cross-validation. This model was further tested to predict 6-week remission in a sample of two independent, consecutive Danish first-episode cohorts. RESULTS: Of the 179 participants in Athens, 120 were male with an average age of 25.8 years and average duration of untreated psychosis of 32.8 weeks. 62.9% were antipsychotic-naïve. Fifty-seven percent attained remission after 4 weeks. In the Danish cohort, 31% attained remission. Eleven clinical scale items were selected in the Athens 4-week remission cohort. These included the Duration of Untreated Psychosis, Personal and Social Performance Scale, Global Assessment of Functioning and eight items from the Positive and Negative Syndrome Scale. This model significantly predicted 4-week remission status (area under the receiver operator characteristic curve (ROC-AUC) = 71.45, P < .0001). It also predicted 6-week remission status in the Danish cohort (ROC-AUC = 67.74, P < .0001), demonstrating reliability. CONCLUSIONS: Using items from common and validated clinical scales, our model significantly predicted early remission in patients with first-episode psychosis. Although replicated in an independent cohort, forward testing between machine learning models and clinicians' assessment should be undertaken to evaluate the possible utility as a routine clinical tool.

AB - BACKGROUND: Validated clinical prediction models of short-term remission in psychosis are lacking. Our aim was to develop a clinical prediction model aimed at predicting 4-6-week remission following a first episode of psychosis. METHOD: Baseline clinical data from the Athens First Episode Research Study was used to develop a Support Vector Machine prediction model of 4-week symptom remission in first-episode psychosis patients using repeated nested cross-validation. This model was further tested to predict 6-week remission in a sample of two independent, consecutive Danish first-episode cohorts. RESULTS: Of the 179 participants in Athens, 120 were male with an average age of 25.8 years and average duration of untreated psychosis of 32.8 weeks. 62.9% were antipsychotic-naïve. Fifty-seven percent attained remission after 4 weeks. In the Danish cohort, 31% attained remission. Eleven clinical scale items were selected in the Athens 4-week remission cohort. These included the Duration of Untreated Psychosis, Personal and Social Performance Scale, Global Assessment of Functioning and eight items from the Positive and Negative Syndrome Scale. This model significantly predicted 4-week remission status (area under the receiver operator characteristic curve (ROC-AUC) = 71.45, P < .0001). It also predicted 6-week remission status in the Danish cohort (ROC-AUC = 67.74, P < .0001), demonstrating reliability. CONCLUSIONS: Using items from common and validated clinical scales, our model significantly predicted early remission in patients with first-episode psychosis. Although replicated in an independent cohort, forward testing between machine learning models and clinicians' assessment should be undertaken to evaluate the possible utility as a routine clinical tool.

KW - first-episode/psychosis

KW - machine learning

KW - prediction

KW - psychopathology

KW - psychosis

KW - remission

KW - schizophrenia

U2 - 10.1093/schbul/sbab107

DO - 10.1093/schbul/sbab107

M3 - Journal article

C2 - 34535800

AN - SCOPUS:85120073214

VL - 48

SP - 122

EP - 133

JO - Schizophrenia Bulletin

JF - Schizophrenia Bulletin

SN - 0586-7614

IS - 1

ER -

ID: 313653694