Estimating Exposome Score for Schizophrenia Using Predictive Modeling Approach in Two Independent Samples: The Results From the EUGEI Study

Lotta-Katrin Pries, Agustin Lage-Castellanos, Philippe Delespaul, Gunter Kenis, Jurjen J. Luykx, Bochao D. Lin, Alexander L. Richards, Berna Akdede, Tolga Binbay, Vesile Altinyazar, Berna Yalincetin, Guvem Gumus-Akay, Burcin Cihan, Haldun Soygur, Halis Ulas, Eylem Sahin Cankurtaran, Semra Ulusoy Kaymak, Marina M. Mihaljevic, Sanja Andric Petrovic, Tijana MirjanicMiguel Bernardo, Bibiana Cabrera, Julio Bobes, Pilar A. Saiz, Maria Paz Garcia-Portilla, Julio Sanjuan, Eduardo J. Aguilar, Jose Luis Santos, Estela Jimenez-Lopez, Manuel Arrojo, Angel Carracedo, Gonzalo Lopez, Javier Gonzalez-Penas, Mara Parellada, Nadja P. Maric, Cem Atbasoglu, Alp Ucok, Koksal Alptekin, Meram Can Saka, Celso Arango, Michael O'Donovan, Bart P. F. Rutten, Jim van Os, Sinan Guloksuz*, Genetic Risk and Outcome of Psychosis (GROUP) Investigators

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review


Exposures constitute a dense network of the environment: exposome. Here, we argue for embracing the exposome paradigm to investigate the sum of nongenetic “risk” and show how predictive modeling approaches can be used to construct an exposome score (ES; an aggregated score of exposures) for schizophrenia. The training dataset consisted of patients with schizophrenia and controls, whereas the independent validation dataset consisted of patients, their unaffected siblings, and controls. Binary exposures were cannabis use, hearing impairment, winter birth, bullying, and emotional, physical, and sexual abuse along with physical and emotional neglect. We applied logistic regression (LR), Gaussian Naive Bayes (GNB), the least absolute shrinkage and selection operator (LASSO), and Ridge penalized classification models to the training dataset. ESs, the sum of weighted exposures based on coefficients from each model, were calculated in the validation dataset. In addition, we estimated ES based on meta-analyses and a simple sum score of exposures. Accuracy, sensitivity, specificity, area under the receiver operating characteristic, and Nagelkerke’s R2 were compared. The ESMeta-analyses performed the worst, whereas the sum score and the ESGNB were worse than the ESLR that performed similar to the ESLASSO and ESRIDGE. The ESLR distinguished patients from controls (odds ratio [OR] = 1.94, P < .001), patients from siblings (OR = 1.58, P < .001), and siblings from controls (OR = 1.21, P = .001). An increase in ESLR was associated with a gradient increase of schizophrenia risk. In reference to the remaining fractions, the ESLR at top 30%, 20%, and 10% of the control distribution yielded ORs of 3.72, 3.74, and 4.77, respectively. Our findings demonstrate that predictive modeling approaches can be harnessed to evaluate the exposome.
Original languageEnglish
Pages (from-to)960-965
Number of pages6
JournalSchizophrenia Bulletin
Issue number5
Publication statusPublished - Sept 2019


  • schizophrenia
  • psychosis
  • predictive modeling
  • machine learning
  • risk score
  • environment
  • childhood trauma
  • cannabis
  • winter birth
  • hearing impairment

Cite this