Combined pattern of childhood psycho-behavioral characteristics in patients with schizophrenia: a retrospective study in Japan

Abstract Background Although epidemiological and genetic studies have provided scientific evidence that places schizophrenia into the framework of early neurodevelopmental disorders, the psycho-behavioral characteristics of children that later go on to develop schizophrenia have not been sufficiently clarified. This study aimed to retrospectively identify characteristics specific to patients with schizophrenia during childhood via their guardians’ reporting of these characteristics. Methods Participants included 54 outpatients with schizophrenia in their twenties who fulfilled DSM-IV-TR criteria. Additionally, 192 normal healthy subjects participated as sex- and age-matched controls. The guardians of all participants were recruited to rate participants’ childhood characteristics from 6 to 8 years of age on a modified version of the Child Behavior Checklist (CBCL), which was used as a retrospective assessment questionnaire. Using t-tests, logistic regression, and Receiver Operating Characteristic (ROC) curve analysis, we estimated the psycho-behavioral characteristics specific to schizophrenia during childhood. Using the obtained logistic regression model, we prototyped a risk-predicting algorithm based on the CBCL scores. Results Among the eight CBCL subscale t-scores, “withdrawn” (p = 0.002), “thought problems” (p = 0.001), and “lack of aggressive behavior” (p = 0.002) were each significantly associated with the later diagnosis of schizophrenia, although none of these mean scores were in the clinical range at the time of childhood. The algorithm of the logistic regression model, based on eight CBCL subscales, had an area under the ROC curve of 82.8% (95% CI: 76–89%), which indicated that this algorithm’s prediction of late development of schizophrenia has moderate accuracy. Conclusions The results suggest that according to guardian reports, participants showed psycho-behavioral characteristics during childhood, different to those of healthy controls, which could be predictive of the later development of schizophrenia. Our newly developed algorithm is available to use in future studies to further test its validity.