Department of Psychiatry and Psychotherapy, Otto von Guericke University, Leipziger Str. 44, 39120, Magdeburg, Germany.
3rd Faculty of Medicine, Charles University, Ruska 87, 100 00, Prague, Czech Republic.
BMC Psychiatry. 2018 Apr 10;18(1):97. doi: 10.1186/s12888-018-1678-y.
Early diagnosis of schizophrenia could improve the outcome of the illness. Unlike classical between-group comparisons, machine learning can identify subtle disease patterns on a single subject level, which could help realize the potential of MRI in establishing a psychiatric diagnosis. Machine learning has previously been predominantly tested on gray-matter structural or functional MRI data. In this paper we used a machine learning classifier to differentiate patients with a first episode of schizophrenia-spectrum disorder (FES) from healthy controls using diffusion tensor imaging.
We applied linear support-vector machine (SVM) and traditional tract based spatial statistics between group analyses to brain fractional anisotropy (FA) data from 77 FES and 77 age and sex matched healthy controls. We also evaluated the effects of medication and symptoms on the SVM classification.
The SVM distinguished between patients and controls with significant accuracy of 62.34% (p = 0.005). Participants with FES showed widespread FA reductions relative to controls in a large cluster (N = 56,647 voxels, corrected p = 0.002). The white matter regions, which contributed to the correct identification of participants with FES, overlapped with the regions, which showed lower FA in patients relative to controls. There was no association between the classification performance and medication or symptoms.
Our results provide a proof of concept that SVM might help differentiate FES patients early in the course of illness from healthy controls using white-matter fractional anisotropy. As there was no effect of medications or symptoms, the SVM classification seemed to be based on trait rather than state markers and appeared to capture the lower FA in FES participants relative to controls.
早期诊断精神分裂症可以改善疾病的预后。与传统的组间比较不同，机器学习可以在单个受试者水平上识别微妙的疾病模式，这有助于发挥 MRI 在建立精神科诊断方面的潜力。机器学习之前主要在灰质结构或功能 MRI 数据上进行测试。在本文中，我们使用机器学习分类器，通过弥散张量成像（DTI），将首次发作的精神分裂症谱系障碍（FES）患者与健康对照者区分开来。
我们应用线性支持向量机（SVM）和传统的基于束的空间统计学方法对 77 名 FES 患者和 77 名年龄和性别匹配的健康对照者的脑分数各向异性（FA）数据进行分析。我们还评估了药物和症状对 SVM 分类的影响。
SVM 区分了患者和对照组，准确率为 62.34%（p=0.005）。与对照组相比，FES 患者在一个大的簇中表现出广泛的 FA 降低（N=56647 个体素，校正后 p=0.002）。有助于正确识别 FES 患者的白质区域与患者相对于对照组 FA 较低的区域重叠。分类性能与药物或症状之间没有相关性。
我们的结果提供了一个概念验证，即 SVM 可能有助于在疾病早期将 FES 患者与健康对照者区分开来，使用的是白质分数各向异性。由于药物或症状没有影响，SVM 分类似乎基于特征而不是状态标志物，并且似乎捕捉到了 FES 参与者相对于对照组的 FA 较低。
