Detection of Schizophrenia Cases From Healthy Controls With Combination of Neurocognitive and Electrophysiological Features

Frontiers in Psychiatry

Chuan-Yue Wang¹  Ji-Cong Zhang²  Yu Fan³  Fang Dong³  Qi-Jing Bo³  Fu-Chun Zhou³  Qing Tian³  Ning-Bo Yang⁴  Liang Li⁵  Ming Fan⁶  Guang-Zhong Yin⁸ 

[1] Advanced Innovation Center for Human Brain Protection, Capital Medical University, Beijing, China;Beijing Advanced Innovation Centre for Biomedical Engineering, Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, The School of Biological Science and Medical Engineering, Beihang University, Beijing, China;Beijing Key Laboratory of Mental Disorders, The National Clinical Research Center for Mental Disorders, Beijing Anding Hospital, Beijing Institute for Brain Disorders Center of Schizophrenia, Capital Medical University, Beijing, China;Department of Psychiatry, First Affiliated Hospital of Henan University of Science and Technology, Luoyang, China;Department of Psychology, Peking University, Beijing, China;Institute of Military Cognition and Brain Sciences, Academy of Military Medical Sciences, Beijing, China;Laboratory of Brain Disorders, Collaborative Innovation Center for Brain Disorders, Beijing Institute of Brain Disorders, Capital Medical University, Ministry of Science and Technology, Beijing, China;Suzhou Guangji Hospital, The Affiliated Guangji Hospital of Soochow University, The Institute of Mental Health, Suzhou, China;

关键词: schizophrenia;    neurocognition;    electrophysiology;    electroencephalography;    prepulse inhibition (PPI);    biomarker;   

DOI  :  10.3389/fpsyt.2022.810362

来源: DOAJ

【 摘 要 】

BackgroundThe search for a method that utilizes biomarkers to identify patients with schizophrenia from healthy individuals has occupied researchers for decades. However, no single indicator can be employed to achieve the good in clinical practice. We aim to develop a comprehensive machine learning pipeline based on neurocognitive and electrophysiological combined features for distinguishing schizophrenia patients from healthy people.MethodsIn the present study, 69 patients with schizophrenia and 50 healthy controls participated. Neurocognitive (contains seven specific domains of cognition) and electrophysiological [prepulse inhibition, electroencephalography (EEG) power spectrum, detrended fluctuation analysis, and fractal dimension (FD)] features were collected, all these features were taken together to generate the identification models of schizophrenia by applying logistics, random forest, and extreme gradient boosting algorithm. The classification capabilities of these models were also evaluated.ResultsBoth the neurocognitive and electrophysiological feature sets showed a good classification effect with the highest accuracy greater than 85% and AUC greater than 90%. Specifically, the performances of the combined neurocognitive and electrophysiological feature sets achieved the highest accuracy of 93.28% and AUC of 97.91%. The extreme gradient boosting algorithm as a whole presented more stably and precisely in classification efficiency.ConclusionThe highest classification accuracy of 93.28% by combination of neurocognitive and electrophysiological features shows that both measurements are appropriate indicators to be used in discriminating schizophrenia patients and healthy individuals. Also, among three algorithms, extreme gradient boosting had better classified performances than logistics and random forest algorithms.

【 授权许可】

Unknown