Department of Radiology, The First Hospital of China Medical University, No. 155 Nanjing North Street, Shenyang, 110001, Liaoning, China.
Shenyang University of Technology, No.111, Shenliao West Road, Shenyang, 110870, Liaoning, China.
J Transl Med. 2023 May 8;21(1):310. doi: 10.1186/s12967-023-04158-8.
Cognitive dysfunction is the most common non-motor symptom in Parkinson's disease (PD), and timely detection of a slight cognitive decline is crucial for early treatment and prevention of dementia. This study aimed to build a machine learning model based on intra- and/or intervoxel metrics extracted from diffusion tensor imaging (DTI) to automatically classify PD patients without dementia into mild cognitive impairment (PD-MCI) and normal cognition (PD-NC) groups.
We enrolled PD patients without dementia (52 PD-NC and 68 PD-MCI subtypes) who were assigned to the training and test datasets in an 8:2 ratio. Four intravoxel metrics, including fractional anisotropy (FA), mean diffusivity (MD), axial diffusivity (AD), and radial diffusivity (RD), and two novel intervoxel metrics, local diffusion homogeneity (LDH) using Spearman's rank correlation coefficient (LDHs) and Kendall's coefficient concordance (LDHk), were extracted from the DTI data. Decision tree, random forest, and eXtreme gradient boosting (XGBoost) models based on individual and combined indices were built for classification, and model performance was assessed and compared via the area under the receiver operating characteristic curve (AUC). Finally, feature importance was evaluated using SHapley Additive exPlanation (SHAP) values.
The XGBoost model based on a combination of the intra- and intervoxel indices achieved the best classification performance, with an accuracy of 91.67%, sensitivity of 92.86%, and AUC of 0.94 in the test dataset. SHAP analysis showed that the LDH of the brainstem and MD of the right cingulum (hippocampus) were important features.
More comprehensive information on white matter changes can be obtained by combining intra- and intervoxel DTI indices, improving classification accuracy. Furthermore, machine learning methods based on DTI indices can be used as alternatives for the automatic identification of PD-MCI at the individual level.
认知功能障碍是帕金森病（PD）最常见的非运动症状，及时发现轻度认知衰退对于早期治疗和预防痴呆症至关重要。本研究旨在构建一种基于扩散张量成像（DTI）提取的体素内和/或体素间指标的机器学习模型，以自动将无痴呆的 PD 患者分为轻度认知障碍（PD-MCI）和正常认知（PD-NC）组。
我们纳入了无痴呆的 PD 患者（52 名 PD-NC 和 68 名 PD-MCI 亚型），并将其按照 8:2 的比例分配到训练和测试数据集。从 DTI 数据中提取了 4 个体素内指标，包括各向异性分数（FA）、平均扩散系数（MD）、轴向扩散系数（AD）和径向扩散系数（RD），以及 2 种新的体素间指标，即基于 Spearman 秩相关系数的局部扩散均匀度（LDH）和 Kendall 系数一致性（LDHk）。基于个体和联合指标构建了决策树、随机森林和极端梯度提升（XGBoost）模型进行分类，并通过接收者操作特征曲线下的面积（AUC）评估和比较模型性能。最后，使用 Shapley 加性解释（SHAP）值评估特征重要性。
基于体素内和体素间指标组合的 XGBoost 模型在测试数据集上的分类性能最佳，准确率为 91.67%，灵敏度为 92.86%，AUC 为 0.94。SHAP 分析表明，脑干的 LDH 和右侧扣带（海马）的 MD 是重要特征。
通过结合体素内和体素间 DTI 指标，可以获得更全面的白质变化信息，从而提高分类准确性。此外，基于 DTI 指标的机器学习方法可以作为个体水平 PD-MCI 自动识别的替代方法。
