TY - JOUR

T1 - Using brain structural neuroimaging measures to predict psychosis onset for individuals at clinical high-risk

AU - Zhu, Yinghan

AU - Maikusa, Norihide

AU - Radua, Joaquim

AU - Sämann, Philipp G

AU - Fusar-Poli, Paolo

AU - Agartz, Ingrid

AU - Andreassen, Ole A

AU - Bachman, Peter

AU - Baeza, Inmaculada

AU - Chen, Xiaogang

AU - Choi, Sunah

AU - Corcoran, Cheryl M

AU - Ebdrup, Bjørn H

AU - Fortea, Adriana

AU - Garani, Ranjini Rg

AU - Glenthøj, Birte Yding

AU - Glenthøj, Louise Birkedal

AU - Haas, Shalaila S

AU - Hamilton, Holly K

AU - Hayes, Rebecca A

AU - He, Ying

AU - Heekeren, Karsten

AU - Kasai, Kiyoto

AU - Katagiri, Naoyuki

AU - Kim, Minah

AU - Kristensen, Tina D

AU - Kwon, Jun Soo

AU - Lawrie, Stephen M

AU - Lebedeva, Irina

AU - Lee, Jimmy

AU - Loewy, Rachel L

AU - Mathalon, Daniel H

AU - McGuire, Philip

AU - Mizrahi, Romina

AU - Mizuno, Masafumi

AU - Møller, Paul

AU - Nemoto, Takahiro

AU - Nordholm, Dorte

AU - Omelchenko, Maria A

AU - Raghava, Jayachandra M

AU - Røssberg, Jan I

AU - Rössler, Wulf

AU - Salisbury, Dean F

AU - Sasabayashi, Daiki

AU - Smigielski, Lukasz

AU - Sugranyes, Gisela

AU - Takahashi, Tsutomu

AU - Tamnes, Christian K

AU - Tang, Jinsong

AU - Theodoridou, Anastasia

AU - ENIGMA Clinical High Risk for Psychosis Working Group

N1 - © 2024. The Author(s).

PY - 2024

Y1 - 2024

N2 - Machine learning approaches using structural magnetic resonance imaging (sMRI) can be informative for disease classification, although their ability to predict psychosis is largely unknown. We created a model with individuals at CHR who developed psychosis later (CHR-PS+) from healthy controls (HCs) that can differentiate each other. We also evaluated whether we could distinguish CHR-PS+ individuals from those who did not develop psychosis later (CHR-PS-) and those with uncertain follow-up status (CHR-UNK). T1-weighted structural brain MRI scans from 1165 individuals at CHR (CHR-PS+, n = 144; CHR-PS-, n = 793; and CHR-UNK, n = 228), and 1029 HCs, were obtained from 21 sites. We used ComBat to harmonize measures of subcortical volume, cortical thickness and surface area data and corrected for non-linear effects of age and sex using a general additive model. CHR-PS+ (n = 120) and HC (n = 799) data from 20 sites served as a training dataset, which we used to build a classifier. The remaining samples were used external validation datasets to evaluate classifier performance (test, independent confirmatory, and independent group [CHR-PS- and CHR-UNK] datasets). The accuracy of the classifier on the training and independent confirmatory datasets was 85% and 73% respectively. Regional cortical surface area measures-including those from the right superior frontal, right superior temporal, and bilateral insular cortices strongly contributed to classifying CHR-PS+ from HC. CHR-PS- and CHR-UNK individuals were more likely to be classified as HC compared to CHR-PS+ (classification rate to HC: CHR-PS+, 30%; CHR-PS-, 73%; CHR-UNK, 80%). We used multisite sMRI to train a classifier to predict psychosis onset in CHR individuals, and it showed promise predicting CHR-PS+ in an independent sample. The results suggest that when considering adolescent brain development, baseline MRI scans for CHR individuals may be helpful to identify their prognosis. Future prospective studies are required about whether the classifier could be actually helpful in the clinical settings.

AB - Machine learning approaches using structural magnetic resonance imaging (sMRI) can be informative for disease classification, although their ability to predict psychosis is largely unknown. We created a model with individuals at CHR who developed psychosis later (CHR-PS+) from healthy controls (HCs) that can differentiate each other. We also evaluated whether we could distinguish CHR-PS+ individuals from those who did not develop psychosis later (CHR-PS-) and those with uncertain follow-up status (CHR-UNK). T1-weighted structural brain MRI scans from 1165 individuals at CHR (CHR-PS+, n = 144; CHR-PS-, n = 793; and CHR-UNK, n = 228), and 1029 HCs, were obtained from 21 sites. We used ComBat to harmonize measures of subcortical volume, cortical thickness and surface area data and corrected for non-linear effects of age and sex using a general additive model. CHR-PS+ (n = 120) and HC (n = 799) data from 20 sites served as a training dataset, which we used to build a classifier. The remaining samples were used external validation datasets to evaluate classifier performance (test, independent confirmatory, and independent group [CHR-PS- and CHR-UNK] datasets). The accuracy of the classifier on the training and independent confirmatory datasets was 85% and 73% respectively. Regional cortical surface area measures-including those from the right superior frontal, right superior temporal, and bilateral insular cortices strongly contributed to classifying CHR-PS+ from HC. CHR-PS- and CHR-UNK individuals were more likely to be classified as HC compared to CHR-PS+ (classification rate to HC: CHR-PS+, 30%; CHR-PS-, 73%; CHR-UNK, 80%). We used multisite sMRI to train a classifier to predict psychosis onset in CHR individuals, and it showed promise predicting CHR-PS+ in an independent sample. The results suggest that when considering adolescent brain development, baseline MRI scans for CHR individuals may be helpful to identify their prognosis. Future prospective studies are required about whether the classifier could be actually helpful in the clinical settings.

U2 - 10.1038/s41380-024-02426-7

DO - 10.1038/s41380-024-02426-7

M3 - Journal article

C2 - 38332374

JO - Molecular Psychiatry

JF - Molecular Psychiatry

SN - 1359-4184

ER -