A multivariate cognitive approach to predict social functioning in recent onset psychosis in response to computerized cognitive training

Nina Walter; Julian Wenzel; Shalaila S. Haas; Letizia Squarcina; Carolina Bonivento; Anne Ruef; Dominic Dwyer; Theresa Lichtenstein; Öznur Bastrük; Alexandra Stainton; Linda A. Antonucci; Paolo Brambilla; Stephen J. Wood; Rachel Upthegrove; Stefan Borgwardt; Rebekka Lencer; Eva Meisenzahl; Raimo K.R. Salokangas; Christos Pantelis; Alessandro Bertolino; Nikolaos Koutsouleris; Joseph Kambeitz; Lana Kambeitz-Ilankovic

doi:10.1016/j.pnpbp.2023.110864

A multivariate cognitive approach to predict social functioning in recent onset psychosis in response to computerized cognitive training

Nina Walter, Julian Wenzel, Shalaila S. Haas, Letizia Squarcina, Carolina Bonivento, Anne Ruef, Dominic Dwyer, Theresa Lichtenstein, Öznur Bastrük, Alexandra Stainton, Linda A. Antonucci, Paolo Brambilla, Stephen J. Wood, Rachel Upthegrove, Stefan Borgwardt, Rebekka Lencer, Eva Meisenzahl, Raimo K.R. Salokangas, Christos Pantelis, Alessandro BertolinoNikolaos Koutsouleris, Joseph Kambeitz, Lana Kambeitz-Ilankovic

Psychosis Studies

Research output: Contribution to journal › Article › peer-review

2 Citations (Scopus)

Abstract

Clinical and neuroimaging data has been increasingly used in recent years to disentangle heterogeneity of treatment response to cognitive training (CT) and predict which individuals may achieve the highest benefits. CT has small to medium effects on improving cognitive and social functioning in recent onset psychosis (ROP) patients, who show the most profound cognitive and social functioning deficits among psychiatric patients. We employed multivariate pattern analysis (MVPA) to investigate the potential of cognitive data to predict social functioning improvement in response to 10 h of CT in patients with ROP. A support vector machine (SVM) classifier was trained on the naturalistic data of the Personalized Prognostic Tools for Early Psychosis Management (PRONIA) study sample to predict functioning in an independent sample of 70 ROP patients using baseline cognitive data. PRONIA is a part of a FP7 EU grant program that involved 7 sites across 5 European countries, designed and conducted with the main aim of identifying (bio)markers associated with an enhanced risk of developing psychosis in order to improve early detection and prognosis. Social functioning was predicted with a balanced accuracy (BAC) of 66.4% (Sensitivity 78.8%; Specificity 54.1%; PPV 60.5%; NPV 74.1%; AUC 0.64; P = 0.01). The most frequently selected cognitive features (mean feature weights > ± 0.2) included the (1) correct number of symbol matchings within the Digit Symbol Substitution Test, (2) the number of distracting stimuli leading to an error within 300 and 200 trials in the Continuous Performance Test and (3) the dynamics of verbal fluency between 15 and 30 s within the Verbal Fluency Test, phonetic part. Next, the SVM classifier generated on the PRONIA sample was applied to the intervention sample, that obtained 54 ROP patients who were randomly assigned to a social cognitive training (SCT) or treatment as usual (TAU) group and dichotomized into good (GF-S ≥ 7) and poor (GF-S

Original language	English
Article number	110864
Journal	Progress in Neuro-Psychopharmacology and Biological Psychiatry
Volume	128
Early online date	23 Sept 2023
DOIs	https://doi.org/10.1016/j.pnpbp.2023.110864
Publication status	Published - 10 Jan 2024

Keywords

Social functioning
Recent onset psychosis
Social cognitive training
Machine learning
Treatment response

Access to Document

10.1016/j.pnpbp.2023.110864

https://www.sciencedirect.com/science/article/pii/S0278584623001501

Cite this

Walter, N., Wenzel, J., Haas, S. S., Squarcina, L., Bonivento, C., Ruef, A., Dwyer, D., Lichtenstein, T., Bastrük, Ö., Stainton, A., Antonucci, L. A., Brambilla, P., Wood, S. J., Upthegrove, R., Borgwardt, S., Lencer, R., Meisenzahl, E., Salokangas, R. K. R., Pantelis, C., ... Kambeitz-Ilankovic, L. (2024). A multivariate cognitive approach to predict social functioning in recent onset psychosis in response to computerized cognitive training. Progress in Neuro-Psychopharmacology and Biological Psychiatry, 128, Article 110864. https://doi.org/10.1016/j.pnpbp.2023.110864

@article{7cdc22736cb64cd28d22ca1d51dbe66c,

title = "A multivariate cognitive approach to predict social functioning in recent onset psychosis in response to computerized cognitive training",

abstract = "Clinical and neuroimaging data has been increasingly used in recent years to disentangle heterogeneity of treatment response to cognitive training (CT) and predict which individuals may achieve the highest benefits. CT has small to medium effects on improving cognitive and social functioning in recent onset psychosis (ROP) patients, who show the most profound cognitive and social functioning deficits among psychiatric patients. We employed multivariate pattern analysis (MVPA) to investigate the potential of cognitive data to predict social functioning improvement in response to 10 h of CT in patients with ROP. A support vector machine (SVM) classifier was trained on the naturalistic data of the Personalized Prognostic Tools for Early Psychosis Management (PRONIA) study sample to predict functioning in an independent sample of 70 ROP patients using baseline cognitive data. PRONIA is a part of a FP7 EU grant program that involved 7 sites across 5 European countries, designed and conducted with the main aim of identifying (bio)markers associated with an enhanced risk of developing psychosis in order to improve early detection and prognosis. Social functioning was predicted with a balanced accuracy (BAC) of 66.4% (Sensitivity 78.8%; Specificity 54.1%; PPV 60.5%; NPV 74.1%; AUC 0.64; P = 0.01). The most frequently selected cognitive features (mean feature weights > ± 0.2) included the (1) correct number of symbol matchings within the Digit Symbol Substitution Test, (2) the number of distracting stimuli leading to an error within 300 and 200 trials in the Continuous Performance Test and (3) the dynamics of verbal fluency between 15 and 30 s within the Verbal Fluency Test, phonetic part. Next, the SVM classifier generated on the PRONIA sample was applied to the intervention sample, that obtained 54 ROP patients who were randomly assigned to a social cognitive training (SCT) or treatment as usual (TAU) group and dichotomized into good (GF-S ≥ 7) and poor (GF-S ",

keywords = "Social functioning, Recent onset psychosis, Social cognitive training, Machine learning, Treatment response",

author = "Nina Walter and Julian Wenzel and Haas, {Shalaila S.} and Letizia Squarcina and Carolina Bonivento and Anne Ruef and Dominic Dwyer and Theresa Lichtenstein and {\"O}znur Bastr{\"u}k and Alexandra Stainton and Antonucci, {Linda A.} and Paolo Brambilla and Wood, {Stephen J.} and Rachel Upthegrove and Stefan Borgwardt and Rebekka Lencer and Eva Meisenzahl and Salokangas, {Raimo K.R.} and Christos Pantelis and Alessandro Bertolino and Nikolaos Koutsouleris and Joseph Kambeitz and Lana Kambeitz-Ilankovic",

note = "Funding Information: This study was supported by EU-FP7 project PRONIA (Personalized Prognostic Tools for Early Psychosis Management) under the Grant Agreement No° 602152 (PI: NK), NARSAD Young Investigator Award of the Brain & Behavior Research Foundation No° 28474 (PI: LK-I) and LMU excellent (LKI). NK, JK and RKRA are currently honorary speakers for Otsuka/Lundbeck. RU received grants from Medical Research Council, grants from the National Institute for Health Research, and personal fees from Sunovion. C Pantelis was supported by a National Health and Medical Research Council (NHMRC) Senior Principal Research Fellowship (1105825), an aNHMRC L3 Investigator Grant (1196508), and NHMRC-EU grant (1075379). SSH is supported by NIH National Institute of Mental Health, grant T32MH122394. The remaining authors including members of the PRONIA consortium have nothing to disclose. Publisher Copyright: {\textcopyright} 2023 Elsevier Inc.",

year = "2024",

month = jan,

day = "10",

doi = "10.1016/j.pnpbp.2023.110864",

language = "English",

volume = "128",

journal = "Progress in Neuro-Psychopharmacology and Biological Psychiatry",

issn = "0278-5846",

publisher = "Elsevier Inc.",

}

Walter, N, Wenzel, J, Haas, SS, Squarcina, L, Bonivento, C, Ruef, A, Dwyer, D, Lichtenstein, T, Bastrük, Ö, Stainton, A, Antonucci, LA, Brambilla, P, Wood, SJ, Upthegrove, R, Borgwardt, S, Lencer, R, Meisenzahl, E, Salokangas, RKR, Pantelis, C, Bertolino, A, Koutsouleris, N, Kambeitz, J & Kambeitz-Ilankovic, L 2024, 'A multivariate cognitive approach to predict social functioning in recent onset psychosis in response to computerized cognitive training', Progress in Neuro-Psychopharmacology and Biological Psychiatry, vol. 128, 110864. https://doi.org/10.1016/j.pnpbp.2023.110864

TY - JOUR

T1 - A multivariate cognitive approach to predict social functioning in recent onset psychosis in response to computerized cognitive training

AU - Walter, Nina

AU - Wenzel, Julian

AU - Haas, Shalaila S.

AU - Squarcina, Letizia

AU - Bonivento, Carolina

AU - Ruef, Anne

AU - Dwyer, Dominic

AU - Lichtenstein, Theresa

AU - Bastrük, Öznur

AU - Stainton, Alexandra

AU - Antonucci, Linda A.

AU - Brambilla, Paolo

AU - Wood, Stephen J.

AU - Upthegrove, Rachel

AU - Borgwardt, Stefan

AU - Lencer, Rebekka

AU - Meisenzahl, Eva

AU - Salokangas, Raimo K.R.

AU - Pantelis, Christos

AU - Bertolino, Alessandro

AU - Koutsouleris, Nikolaos

AU - Kambeitz, Joseph

AU - Kambeitz-Ilankovic, Lana

N1 - Funding Information: This study was supported by EU-FP7 project PRONIA (Personalized Prognostic Tools for Early Psychosis Management) under the Grant Agreement No° 602152 (PI: NK), NARSAD Young Investigator Award of the Brain & Behavior Research Foundation No° 28474 (PI: LK-I) and LMU excellent (LKI). NK, JK and RKRA are currently honorary speakers for Otsuka/Lundbeck. RU received grants from Medical Research Council, grants from the National Institute for Health Research, and personal fees from Sunovion. C Pantelis was supported by a National Health and Medical Research Council (NHMRC) Senior Principal Research Fellowship (1105825), an aNHMRC L3 Investigator Grant (1196508), and NHMRC-EU grant (1075379). SSH is supported by NIH National Institute of Mental Health, grant T32MH122394. The remaining authors including members of the PRONIA consortium have nothing to disclose. Publisher Copyright: © 2023 Elsevier Inc.

PY - 2024/1/10

Y1 - 2024/1/10

N2 - Clinical and neuroimaging data has been increasingly used in recent years to disentangle heterogeneity of treatment response to cognitive training (CT) and predict which individuals may achieve the highest benefits. CT has small to medium effects on improving cognitive and social functioning in recent onset psychosis (ROP) patients, who show the most profound cognitive and social functioning deficits among psychiatric patients. We employed multivariate pattern analysis (MVPA) to investigate the potential of cognitive data to predict social functioning improvement in response to 10 h of CT in patients with ROP. A support vector machine (SVM) classifier was trained on the naturalistic data of the Personalized Prognostic Tools for Early Psychosis Management (PRONIA) study sample to predict functioning in an independent sample of 70 ROP patients using baseline cognitive data. PRONIA is a part of a FP7 EU grant program that involved 7 sites across 5 European countries, designed and conducted with the main aim of identifying (bio)markers associated with an enhanced risk of developing psychosis in order to improve early detection and prognosis. Social functioning was predicted with a balanced accuracy (BAC) of 66.4% (Sensitivity 78.8%; Specificity 54.1%; PPV 60.5%; NPV 74.1%; AUC 0.64; P = 0.01). The most frequently selected cognitive features (mean feature weights > ± 0.2) included the (1) correct number of symbol matchings within the Digit Symbol Substitution Test, (2) the number of distracting stimuli leading to an error within 300 and 200 trials in the Continuous Performance Test and (3) the dynamics of verbal fluency between 15 and 30 s within the Verbal Fluency Test, phonetic part. Next, the SVM classifier generated on the PRONIA sample was applied to the intervention sample, that obtained 54 ROP patients who were randomly assigned to a social cognitive training (SCT) or treatment as usual (TAU) group and dichotomized into good (GF-S ≥ 7) and poor (GF-S

AB - Clinical and neuroimaging data has been increasingly used in recent years to disentangle heterogeneity of treatment response to cognitive training (CT) and predict which individuals may achieve the highest benefits. CT has small to medium effects on improving cognitive and social functioning in recent onset psychosis (ROP) patients, who show the most profound cognitive and social functioning deficits among psychiatric patients. We employed multivariate pattern analysis (MVPA) to investigate the potential of cognitive data to predict social functioning improvement in response to 10 h of CT in patients with ROP. A support vector machine (SVM) classifier was trained on the naturalistic data of the Personalized Prognostic Tools for Early Psychosis Management (PRONIA) study sample to predict functioning in an independent sample of 70 ROP patients using baseline cognitive data. PRONIA is a part of a FP7 EU grant program that involved 7 sites across 5 European countries, designed and conducted with the main aim of identifying (bio)markers associated with an enhanced risk of developing psychosis in order to improve early detection and prognosis. Social functioning was predicted with a balanced accuracy (BAC) of 66.4% (Sensitivity 78.8%; Specificity 54.1%; PPV 60.5%; NPV 74.1%; AUC 0.64; P = 0.01). The most frequently selected cognitive features (mean feature weights > ± 0.2) included the (1) correct number of symbol matchings within the Digit Symbol Substitution Test, (2) the number of distracting stimuli leading to an error within 300 and 200 trials in the Continuous Performance Test and (3) the dynamics of verbal fluency between 15 and 30 s within the Verbal Fluency Test, phonetic part. Next, the SVM classifier generated on the PRONIA sample was applied to the intervention sample, that obtained 54 ROP patients who were randomly assigned to a social cognitive training (SCT) or treatment as usual (TAU) group and dichotomized into good (GF-S ≥ 7) and poor (GF-S

KW - Social functioning

KW - Recent onset psychosis

KW - Social cognitive training

KW - Machine learning

KW - Treatment response

UR - http://www.scopus.com/inward/record.url?scp=85172888327&partnerID=8YFLogxK

U2 - 10.1016/j.pnpbp.2023.110864

DO - 10.1016/j.pnpbp.2023.110864

M3 - Article

SN - 0278-5846

VL - 128

JO - Progress in Neuro-Psychopharmacology and Biological Psychiatry

JF - Progress in Neuro-Psychopharmacology and Biological Psychiatry

M1 - 110864

ER -

A multivariate cognitive approach to predict social functioning in recent onset psychosis in response to computerized cognitive training

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this