Department of Radiology, Nanjing Medical University Affiliated Nanjing Brain Hospital, Nanjing, China.
Institute of Brain Functional Imaging, Nanjing Medical University, Nanjing, China.
Brain Behav. 2021 May;11(5):e02103. doi: 10.1002/brb3.2103. Epub 2021 Mar 10.
The current diagnosis of Parkinson's disease (PD) comorbidity with depression (DPD) largely depends on clinical evaluation. However, the modality may tend to lack precision in detecting PD with depression. A radiomic approach that combines functional connectivity and activity with clinical scores has the potential to achieve accurate and differential diagnosis between PD and DPD.
In this study, we aimed to employ the radiomic approach to extract large-scale features of functional connectivity and activity for differentiating among DPD, PD with no depression (NDPD), and healthy controls (HC). We extracted 6,557 features of five types from all subjects including clinical characteristics, resting-state functional connectivity (RSFC), amplitude of low-frequency fluctuation (ALFF), regional homogeneity (ReHo), and voxel-mirrored homotopic connectivity (VMHC). Lasso, random forest, and support vector machine (SVM) were implemented for feature selection and dimension reduction based on the training sets, and the prediction performance for different methods in the testing sets was compared.
The results showed that nineteen features were selected for the group of DPD versus HC, 34 features were selected for the group of NDPD versus HC, and 17 features were retained for the group of DPD versus NDPD. In the testing sets, Lasso prediction achieved the accuracies of 0.95, 0.96, and 0.85 for distinguishing between DPD and HC, NDPD and HC, and DPD and NDPD, respectively. Random forest achieved the accuracies of 0.90, 0.82, and 0.90 for distinguishing between DPD and HC, NDPD and HC, and DPD and NDPD, respectively, while SVM yielded the accuracies of 1, 0.86 and 0.65 for distinguishing between DPD and HC, NDPD and HC, and DPD and NDPD, respectively.
By identifying aberrant functional connectivity and activity as potential biomarkers, the radiomic approach facilitates a deeper understanding and provides new insights into the pathophysiology of DPD to support the clinical diagnosis with high prediction accuracy.
目前帕金森病（PD）合并抑郁（DPD）的诊断在很大程度上依赖于临床评估。然而，这种方法可能在检测 PD 伴抑郁时缺乏准确性。一种结合功能连接和活动与临床评分的放射组学方法有可能实现 PD 与 DPD 之间的准确和鉴别诊断。
在这项研究中，我们旨在采用放射组学方法提取功能连接和活动的大规模特征，以区分 DPD、无抑郁的 PD（NDPD）和健康对照（HC）。我们从所有受试者中提取了包括临床特征、静息态功能连接（RSFC）、低频振幅（ALFF）、区域同质性（ReHo）和镜像同伦连接（VMHC）在内的五种类型的 6557 个特征。基于训练集，采用 Lasso、随机森林和支持向量机（SVM）进行特征选择和降维，比较不同方法在测试集中的预测性能。
结果显示，DPD 与 HC 组有 19 个特征被选中，NDPD 与 HC 组有 34 个特征被选中，DPD 与 NDPD 组有 17 个特征被保留。在测试集中，Lasso 预测对 DPD 与 HC、NDPD 与 HC 以及 DPD 与 NDPD 的区分准确率分别为 0.95、0.96 和 0.85。随机森林对 DPD 与 HC、NDPD 与 HC 以及 DPD 与 NDPD 的区分准确率分别为 0.90、0.82 和 0.90，而 SVM 对 DPD 与 HC、NDPD 与 HC 以及 DPD 与 NDPD 的区分准确率分别为 1、0.86 和 0.65。
通过识别功能连接和活动的异常作为潜在的生物标志物，放射组学方法有助于深入了解和提供 DPD 的病理生理学新见解，以支持具有高预测准确性的临床诊断。
