A Pattern of Cognitive Deficits Stratified for Genetic and Environmental Risk Reliably Classifies Patients With Schizophrenia From Healthy Control Subjects

TY - JOUR

T1 - A Pattern of Cognitive Deficits Stratified for Genetic and Environmental Risk Reliably Classifies Patients With Schizophrenia From Healthy Control Subjects

AU - Antonucci, Linda A.

AU - Pergola, Giulio

AU - Pigoni, Alessandro

AU - Dwyer, Dominic

AU - Kambeitz-Ilankovic, Lana

AU - Penzel, Nora

AU - Romano, Raffaella

AU - Gelao, Barbara

AU - Torretta, Silvia

AU - Rampino, Antonio

AU - Trojano, Maria

AU - Caforio, Grazia

AU - Falkai, Peter

AU - Blasi, Giuseppe

AU - Koutsouleris, Nikolaos

AU - Bertolino, Alessandro

PY - 2020/4/15

Y1 - 2020/4/15

N2 - Background: Schizophrenia risk is associated with both genetic and environmental risk factors. Furthermore, cognitive abnormalities are established core characteristics of schizophrenia. We aim to assess whether a classification approach encompassing risk factors, cognition, and their associations can discriminate patients with schizophrenia (SCZs) from healthy control subjects (HCs). We hypothesized that cognition would demonstrate greater HC-SCZ classification accuracy and that combined gene–environment stratification would improve the discrimination performance of cognition. Methods: Genome-wide association study–based genetic, environmental, and neurocognitive classifiers were trained to separate 337 HCs from 103 SCZs using support vector classification and repeated nested cross-validation. We validated classifiers on independent datasets using within-diagnostic (SCZ) and cross-diagnostic (clinically isolated syndrome for multiple sclerosis, another condition with cognitive abnormalities) approaches. Then, we tested whether gene–environment multivariate stratification modulated the discrimination performance of the cognitive classifier in iterative subsamples. Results: The cognitive classifier discriminated SCZs from HCs with a balanced accuracy (BAC) of 88.7%, followed by environmental (BAC = 65.1%) and genetic (BAC = 55.5%) classifiers. Similar classification performance was measured in the within-diagnosis validation sample (HC-SCZ BACs, cognition = 70.5%; environment = 65.8%; genetics = 49.9%). The cognitive classifier was relatively specific to schizophrenia (HC–clinically isolated syndrome for multiple sclerosis BAC = 56.7%). Combined gene–environment stratification allowed cognitive features to classify HCs from SCZs with 89.4% BAC. Conclusions: Consistent with cognitive deficits being core features of the phenotype of SCZs, our results suggest that cognitive features alone bear the greatest amount of information for classification of SCZs. Consistent with genes and environment being risk factors, gene–environment stratification modulates HC-SCZ classification performance of cognition, perhaps providing another target for refining early identification and intervention strategies.

AB - Background: Schizophrenia risk is associated with both genetic and environmental risk factors. Furthermore, cognitive abnormalities are established core characteristics of schizophrenia. We aim to assess whether a classification approach encompassing risk factors, cognition, and their associations can discriminate patients with schizophrenia (SCZs) from healthy control subjects (HCs). We hypothesized that cognition would demonstrate greater HC-SCZ classification accuracy and that combined gene–environment stratification would improve the discrimination performance of cognition. Methods: Genome-wide association study–based genetic, environmental, and neurocognitive classifiers were trained to separate 337 HCs from 103 SCZs using support vector classification and repeated nested cross-validation. We validated classifiers on independent datasets using within-diagnostic (SCZ) and cross-diagnostic (clinically isolated syndrome for multiple sclerosis, another condition with cognitive abnormalities) approaches. Then, we tested whether gene–environment multivariate stratification modulated the discrimination performance of the cognitive classifier in iterative subsamples. Results: The cognitive classifier discriminated SCZs from HCs with a balanced accuracy (BAC) of 88.7%, followed by environmental (BAC = 65.1%) and genetic (BAC = 55.5%) classifiers. Similar classification performance was measured in the within-diagnosis validation sample (HC-SCZ BACs, cognition = 70.5%; environment = 65.8%; genetics = 49.9%). The cognitive classifier was relatively specific to schizophrenia (HC–clinically isolated syndrome for multiple sclerosis BAC = 56.7%). Combined gene–environment stratification allowed cognitive features to classify HCs from SCZs with 89.4% BAC. Conclusions: Consistent with cognitive deficits being core features of the phenotype of SCZs, our results suggest that cognitive features alone bear the greatest amount of information for classification of SCZs. Consistent with genes and environment being risk factors, gene–environment stratification modulates HC-SCZ classification performance of cognition, perhaps providing another target for refining early identification and intervention strategies.

KW - Cognition

KW - Disease markers

KW - Gene–environment

KW - Machine learning

KW - Predictive psychiatry

KW - Schizophrenia

UR - http://www.scopus.com/inward/record.url?scp=85077732387&partnerID=8YFLogxK

U2 - 10.1016/j.biopsych.2019.11.007

DO - 10.1016/j.biopsych.2019.11.007

M3 - Article

SN - 0006-3223

VL - 87

SP - 697

EP - 707

JO - Biological psychiatry

JF - Biological psychiatry

IS - 8

ER -