ABSTRACT
Objective@#To construct symptom-formula-herb heterogeneous graphs structured Treatise on Febrile Diseases (Shang Han Lun,《伤寒论》) dataset and explore an optimal learning method represented with node attributes based on graph convolutional network (GCN).@*Methods@#Clauses that contain symptoms, formulas, and herbs were abstracted from Treatise on Febrile Diseases to construct symptom-formula-herb heterogeneous graphs, which were used to propose a node representation learning method based on GCN − the Traditional Chinese Medicine Graph Convolution Network (TCM-GCN). The symptom-formula, symptom-herb, and formula-herb heterogeneous graphs were processed with the TCM-GCN to realize high-order propagating message passing and neighbor aggregation to obtain new node representation attributes, and thus acquiring the nodes’ sum-aggregations of symptoms, formulas, and herbs to lay a foundation for the downstream tasks of the prediction models.@*Results@#Comparisons among the node representations with multi-hot encoding, non-fusion encoding, and fusion encoding showed that the Precision@10, Recall@10, and F1-score@10 of the fusion encoding were 9.77%, 6.65%, and 8.30%, respectively, higher than those of the non-fusion encoding in the prediction studies of the model.@*Conclusion@#Node representations by fusion encoding achieved comparatively ideal results, indicating the TCM-GCN is effective in realizing node-level representations of heterogeneous graph structured Treatise on Febrile Diseases dataset and is able to elevate the performance of the downstream tasks of the diagnosis model.
ABSTRACT
OBJECTIVE@#To propose a coupled convolutional and graph convolutional network (CCGCN) model for diagnosis of Alzheimer's disease (AD) and its prodromal stage.@*METHODS@#The disease-related brain regions generated by group-wise comparison were used as the input. The convolutional neural networks (CNNs) were used to extract disease-related features from different locations on brain magnetic resonance (MR) images. The generated features via the graph convolutional network (GCN) were processed, and graph pooling was performed to analyze the inherent relationship between the brain topology and the diagnosis task adaptively. Through ADNI dataset, we acquired the accuracy, sensitivity and specificity of the diagnosis tasks for AD and its prodromal stages, followed by an ablation study on the model structure.@*RESULTS@#The CCGCN model outperformed the current state-of-the-art methods and showed a classification accuracy of 92.5% for AD with a sensitivity of 88.1% and a specificity of 96.0%.@*CONCLUSIONS@#Based on the structural and topological features of the brain MR images, the proposed CCGCN model shows excellent performance in AD diagnosis and is expected to provide important assistance to physicians in disease diagnosis.