Deng Yi, Hung Karen S Y, Lui Simon S Y, Chui William W H, Lee Joe C W, Wang Yi, Li Zhi, Mak Henry K F, Sham Pak C, Chan Raymond C K, Cheung Eric F C
Castle Peak Hospital, Hong Kong, China; Neuropsychology and Applied Cognitive Neuroscience Laboratory, CAS Key Laboratory of Mental Health, Institute of Psychology, Chinese Academy of Sciences, Beijing, China; Cognitive Analysis & Brain Imaging Laboratory, MIND Institute, University of California, Davis, CA, United States.
Castle Peak Hospital, Hong Kong, China.
Prog Neuropsychopharmacol Biol Psychiatry. 2019 Jan 10;88:66-73. doi: 10.1016/j.pnpbp.2018.06.010. Epub 2018 Jun 20.
Schizophrenia has been characterized as a neurodevelopmental disorder of brain disconnectivity. However, whether disrupted integrity of white matter tracts in schizophrenia can potentially serve as individual discriminative biomarkers remains unclear.
A random forest algorithm was applied to tractography-based diffusion properties obtained from a cohort of 65 patients with first-episode schizophrenia (FES) and 60 healthy individuals to investigate the machine-learning discriminative power of white matter disconnectivity. Recursive feature elimination was used to select the ultimate white matter features in the classification. Relationships between algorithm-predicted probabilities and clinical characteristics were also examined in the FES group.
The classifier was trained by 80% of the sample. Patients were distinguished from healthy individuals with an overall accuracy of 71.0% (95% confident interval: 61.1%, 79.6%), a sensitivity of 67.3%, a specificity of 75.0%, and the area under receiver operating characteristic curve (AUC) was 79.3% (χ2 p < 0.001). In validation using the held-up 20% of the sample, patients were distinguished from healthy individuals with an overall accuracy of 76.0% (95% confident interval: 54.9%, 90.6%), a sensitivity of 76.9%, a specificity of 75.0%, and an AUC of 73.1% (χ2 p = 0.012). Diffusion properties of inter-hemispheric fibres, the cerebello-thalamo-cortical circuits and the long association fibres were identified to be the most discriminative in the classification. Higher predicted probability scores were found in younger patients.
Our findings suggest that the widespread connectivity disruption observed in FES patients, especially in younger patients, might be considered potential individual discriminating biomarkers.
精神分裂症被认为是一种大脑连接性中断的神经发育障碍。然而，精神分裂症患者白质束完整性的破坏是否有可能作为个体鉴别生物标志物仍不清楚。
应用随机森林算法对65例首发精神分裂症（FES）患者和60名健康个体的基于纤维束成像的扩散特性进行分析，以研究白质连接中断的机器学习鉴别能力。采用递归特征消除法在分类中选择最终的白质特征。还在FES组中检查了算法预测概率与临床特征之间的关系。
分类器由80%的样本进行训练。患者与健康个体的区分总体准确率为71.0%（95%置信区间：61.1%，79.6%），敏感性为67.3%，特异性为75.0%，受试者操作特征曲线下面积（AUC）为79.3%（χ2 p < 0.001）。在使用预留的20%样本进行验证时，患者与健康个体的区分总体准确率为76.0%（95%置信区间：54.9%，90.6%），敏感性为76.9%，特异性为75.0%，AUC为73.1%（χ2 p = 0.012）。半球间纤维、小脑-丘脑-皮质回路和长联合纤维的扩散特性被确定为分类中最具鉴别力的特征。在年轻患者中发现了更高的预测概率得分。
我们的研究结果表明，在FES患者中观察到的广泛连接中断，尤其是在年轻患者中，可能被视为潜在的个体鉴别生物标志物。
