Li Wenjia, Rao Quanrui, Dong Shuying, Zhu Mengyuan, Yang Zhen, Huang Xianggeng, Liu Guangchen
School of Mathematics and Statistics, Ludong University, Yantai 264025, China.
School of Information and Electrical Engineering, Ludong University, Yantai 264025, China.
J Neurosci Methods. 2025 Mar;415:110363. doi: 10.1016/j.jneumeth.2025.110363. Epub 2025 Jan 18.
Parkinson's disease (PD), the second most common neurodegenerative disease in the world, is usually not diagnosed until the later stages of the disease, when patients might have already missed the best treatment period. Therefore, more effective prediction methods based on artificial intelligence (AI) are needed to assist physicians in timely diagnosis.
An explainable deep learning-based early Parkinson's disease diagnostic model, Parkinson's Integrative Diagnostic Gated Network (PIDGN), was designed by fusing Single Nucleotide Polymorphism (SNP) and brain sMRI data. Firstly, unimodal internal information was extracted using EmsembleTree dimensionality reduction method, Transformer encoder and 3D ResNet. Secondly, gated attention fusion technique was utilized to explore the inter-modal interactions. Finally, the classification results were output through the fully connected layer. SHapley additive interpretation (SHAP) values and Gradient-weighted Class Activation Mapping (Grad-CAM) techniques were used to help explain the importance of SNPs and brain regions for PD.
The results showed that the PIDGN model achieved the best results with the accuracy of 0.858 and AUROC of 0.897. Top 20 SNPs and the brain regions near the midbrain potentially related to PD were identified using two explainable techniques via SHAP values and Grad-CAM respectively.
The PIDGN model trained by fusing genetic and imaging data outperforms 13 other commonly used unimodal or bimodal models. Explainable PIDGN model helps deepen understanding of several SNPs and sMRI key factors that may affect PD. This study provides a potentially effective solution for automated early diagnosis of PD using AI.
帕金森病（PD）是世界上第二常见的神经退行性疾病，通常在疾病后期才被诊断出来，此时患者可能已经错过了最佳治疗期。因此，需要更有效的基于人工智能（AI）的预测方法来协助医生进行及时诊断。
通过融合单核苷酸多态性（SNP）和脑结构磁共振成像（sMRI）数据，设计了一种基于可解释深度学习的早期帕金森病诊断模型——帕金森综合诊断门控网络（PIDGN）。首先，使用集成树降维方法、Transformer编码器和3D残差网络（3D ResNet）提取单峰内部信息。其次，利用门控注意力融合技术探索多模态交互。最后，通过全连接层输出分类结果。使用夏普利值（SHapley additive interpretation，SHAP）和梯度加权类激活映射（Gradient-weighted Class Activation Mapping，Grad-CAM）技术来帮助解释SNP和脑区对帕金森病的重要性。
结果表明，PIDGN模型取得了最佳结果，准确率为0.858，曲线下面积（AUROC）为0.897。分别通过SHAP值和Grad-CAM这两种可解释技术，确定了与帕金森病潜在相关的前20个SNP以及中脑附近的脑区。
融合遗传和影像数据训练的PIDGN模型优于其他13种常用的单峰或双峰模型。可解释的PIDGN模型有助于加深对可能影响帕金森病的几个SNP和sMRI关键因素的理解。本研究为利用人工智能实现帕金森病的自动化早期诊断提供了一种潜在有效的解决方案。
