Cortical thickness distinguishes between major depression and schizophrenia in adolescents

BMC Psychiatry

Yixiao Fu¹  Yadong Peng²  Jinxiang Tang³  Kangcheng Wang⁴  Zheyi Zhou⁵  Dongtao Wei⁵  Li Song⁵  Jiang Qiu⁶ 

[1] Department of Psychiatry, The First Affiliated Hospital of Chongqing Medical University, No.1, Yixueyuan Road, Yuzhong District, 400016, Chongqing, China;Department of Psychiatry, The First Affiliated Hospital of Chongqing Medical University, No.1, Yixueyuan Road, Yuzhong District, 400016, Chongqing, China;Department of Psychology, Chongqing Health Center for Women and Children, 401147, Chongqing, China;Department of Psychiatry, The First Affiliated Hospital of Chongqing Medical University, No.1, Yixueyuan Road, Yuzhong District, 400016, Chongqing, China;Sleep and Psychology Center, The Bishan Hospital of Chongqing, 402760, Chongqing, China;Faculty of Psychology, Shandong Normal University, 250014, Jinan, Shandong, China;Key Laboratory of Cognition and Personality (SWU), Ministry of Education, 400715, Chongqing, China;Faculty of Psychology, Southwest University, No.2 Tiansheng Road, Beibei District, 400715, Chongqing, China;Key Laboratory of Cognition and Personality (SWU), Ministry of Education, 400715, Chongqing, China;Faculty of Psychology, Southwest University, No.2 Tiansheng Road, Beibei District, 400715, Chongqing, China;Collaborative Innovation Center of Assessment Toward Basic Education Quality, Southwest University Branch, Beijing Normal University, 100875, Beijing, China;

关键词: Depression;    Schizophrenia;    Adolescence;    Cortical thickness;    Machine learning;   

DOI  :  10.1186/s12888-021-03373-1

来源: Springer

【 摘 要 】

BackgroundEarly diagnosis of adolescent psychiatric disorder is crucial for early intervention. However, there is extensive comorbidity between affective and psychotic disorders, which increases the difficulty of precise diagnoses among adolescents.MethodsWe obtained structural magnetic resonance imaging scans from 150 adolescents, including 67 and 47 patients with major depressive disorder (MDD) and schizophrenia (SCZ), as well as 34 healthy controls (HC) to explore whether psychiatric disorders could be identified using a machine learning technique. Specifically, we used the support vector machine and the leave-one-out cross-validation method to distinguish among adolescents with MDD and SCZ and healthy controls.ResultsWe found that cortical thickness was a classification feature of a) MDD and HC with 79.21% accuracy where the temporal pole had the highest weight; b) SCZ and HC with 69.88% accuracy where the left superior temporal sulcus had the highest weight. Notably, adolescents with MDD and SCZ could be classified with 62.93% accuracy where the right pars triangularis had the highest weight.ConclusionsOur findings suggest that cortical thickness may be a critical biological feature in the diagnosis of adolescent psychiatric disorders. These findings might be helpful to establish an early prediction model for adolescents to better diagnose psychiatric disorders.

【 授权许可】

CC BY