Evaluation of machine learning algorithms and structural features for optimal MRI-based diagnostic prediction in psychosis.
Evaluation of machine learning algorithms and structural features for optimal MRI-based diagnostic prediction in psychosis.
复制标题
DOI：
10.1371/journal.pone.0175683
复制
发表时间：
2017
期刊：
影响因子：
3.7
通讯作者：
Pomarol-Clotet E
中科院分区：
文献类型：
--
作者：
Salvador R;Radua J;Canales-Rodríguez EJ;Solanes A;Sarró S;Goikolea JM;Valiente A;Monté GC;Natividad MDC;Guerrero-Pedraza A;Moro N;Fernández-Corcuera P;Amann BL;Maristany T;Vieta E;McKenna PJ;Pomarol-Clotet E
相对大量的研究已经调查了结构磁共振成像（sMRI）数据区分精神分裂症患者和健康对照的能力。然而，他们中很少有人也包括双相情感障碍患者，允许临床相关的歧视两种精神病诊断。为了评估sMRI数据对精神病诊断预测的有效性，我们客观地评估了各种常用机器学习算法的区分能力。（脊、套索、弹性网和L0范数正则化逻辑回归、支持向量分类器、正则化判别分析、随机森林和高斯过程分类器）对主要sMRI特征的分析，包括基于灰色和白色物质体素的形态测量（VBM），基于顶点的皮质厚度和体积、感兴趣区域体积测量和基于小波的形态测量（WBM）图。在健康对照组（N = 127）、精神分裂症患者（N = 128）和双相情感障碍患者（N = 128）的匹配样本的成对分类中，考虑了算法和数据特征的所有可能组合。结果表明，特征类型的选择很重要，灰质VBM（无数据简化）提供最佳诊断预测率（分类器平均值：精神分裂症与健康75%，双相情感障碍与健康63%，精神分裂症与双相情感障碍62%），而算法通常产生非常相似的结果。事实上，这些灰质VBM准确率甚至没有通过将所有特征类型组合在单个预测模型中来提高。同时考虑三个组的进一步多类分类明显缺乏双相组的预测能力，可能是由于其中间解剖特征，位于健康对照组和精神分裂症患者中观察到的特征之间。最后，我们提供了MRIPredict（https：//www.nitrc.org/projects/mripredt/），一个SPM，FSL和R的免费工具，可以轻松地基于VBM图像进行体素预测。
A relatively large number of studies have investigated the power of structural magnetic resonance imaging (sMRI) data to discriminate patients with schizophrenia from healthy controls. However, very few of them have also included patients with bipolar disorder, allowing the clinically relevant discrimination between both psychotic diagnostics. To assess the efficacy of sMRI data for diagnostic prediction in psychosis we objectively evaluated the discriminative power of a wide range of commonly used machine learning algorithms (ridge, lasso, elastic net and L0 norm regularized logistic regressions, a support vector classifier, regularized discriminant analysis, random forests and a Gaussian process classifier) on main sMRI features including grey and white matter voxel-based morphometry (VBM), vertex-based cortical thickness and volume, region of interest volumetric measures and wavelet-based morphometry (WBM) maps. All possible combinations of algorithms and data features were considered in pairwise classifications of matched samples of healthy controls (N = 127), patients with schizophrenia (N = 128) and patients with bipolar disorder (N = 128). Results show that the selection of feature type is important, with grey matter VBM (without data reduction) delivering the best diagnostic prediction rates (averaging over classifiers: schizophrenia vs. healthy 75%, bipolar disorder vs. healthy 63% and schizophrenia vs. bipolar disorder 62%) whereas algorithms usually yielded very similar results. Indeed, those grey matter VBM accuracy rates were not even improved by combining all feature types in a single prediction model. Further multi-class classifications considering the three groups simultaneously made evident a lack of predictive power for the bipolar group, probably due to its intermediate anatomical features, located between those observed in healthy controls and those found in patients with schizophrenia. Finally, we provide MRIPredict (https://www.nitrc.org/projects/mripredict/), a free tool for SPM, FSL and R, to easily carry out voxelwise predictions based on VBM images.