In TCM (Traditional Chinese Medicine) facial diagnosis, facial morphology features are essential for symptom differentiation and treatment selection. Face shape, as one of the facial morphology features, can help TCM physicians understand the patient’s condition by observing the patient's overall appearance. Existing face shape classification methods do not use the face shape dataset based on the TCM theory and do not consider the symmetry of the face shape, which leads to the poor generalization performance of the model. This paper establishes a new TCM-based face shape dataset annotated by several TCM physicians and proposes a new mechanism RSM (Region Symmetry Mask) for face shape classification. The key points of the face are detected by face detection technology, which is then processed to get the region symmetry mask map of the cheeks. The region symmetry mask map can guide the model to extract strongly correlated features. Finally, the classifier is used to output the categories of the face shape. The experimental results on the new TCM-based face shape dataset show that the accuracy of the method with RSM is increased by 3%-5% compared with other methods, indicating that the RSM mechanism is effective for face shape classification.

Adverse drug-drug interaction (ADDI) is a significant life-threatening issue for public health. The current methods for ADDI prediction usually work in a "nondiscriminatory" manner by treating each feature without discrimination and equally employing all features into ADDI modeling. Driven by this issue, we propose a Dependence Guided Discriminative Feature Selection (DGDFS) model for ADDI prediction, in which molecular structure and side effect are adopted with the incorporation of l2,0-norm equality constraints to select discriminative molecular substructures and side effects and three dependence based terms among molecular structure, side effect, and ADDIs to guide feature selection. Extensive experiments demonstrate the superior performance of DGDFS compared with fourteen state-of-the-art ADDI prediction and feature selection models.

Adverse drug-drug interaction (ADDI) is referred to as a situation where the unpleasant or adverse effects caused by the co-administration of two drugs, which becomes a significant problem for public health. With the increasing availability of healthcare data, many methods are proposed for ADDI prediction. However, these methods usually work in a “nondiscriminatory” manner, i.e., they treat each feature without discrimination and equally incorporate all features into the predictive models. In practice, only a few features are essentially discriminative and relevant to ADDIs. In this paper, we propose a Dependence Guided Discriminative Feature Selection (DGDFS) model for ADDI prediction. In DGDFS, two drug attributes, molecular structure and side effect are adopted to model the adverse interaction among drugs and$l_{2,0}$-norm equality constraints are introduced to select discriminative molecular substructures and side effects for ADDI prediction. Besides, three dependence guided terms, i.e., the dependence between molecular structure and ADDI, the dependence between side effect and ADDI, and the dependence between molecular structure and side effect, are designed to guide feature selection. An iterative algorithm based on the alternating direction method of multipliers is developed for optimization. Experimental results indicate the effectiveness of DGDFS compared with fourteen baselines and its three variants.

Resembling the role of disease diagnosis in Western medicine, pathogenesis (also called Bing Ji) diagnosis is one of the utmost important tasks in traditional Chinese medicine (TCM). In TCM theory, pathogenesis is a complex system composed of a group of interrelated factors, which is highly consistent with the character of systems science (SS). In this paper, we introduce a heuristic definition called pathogenesis network (PN) to represent pathogenesis in the form of the directed graph. Accordingly, a computational method of pathogenesis diagnosis, called network differentiation (ND), is proposed by integrating the holism principle in SS. ND consists of three stages. The first stage is to generate all possible diagnoses by Cartesian Product operated on specified prior knowledge corresponding to the input symptoms. The second stage is to screen the validated diagnoses by holism principle. The third stage is to pick out the clinical diagnosis by physician-computer interaction. Some theorems are stated and proved for the further optimization of ND in this paper. We conducted simulation experiments on 100 clinical cases. The experimental results show that our proposed method has an excellent capability to fit the holistic thinking in the process of physician inference.

Adverse drug-drug interaction has been a critical issue for the development of drugs. In Traditional Chinese Medicine, adverse herb-herb interaction is a negative reaction in patients after the absorption of decoction of Incompatible Herb Pair (IHP). Recently, many methods have been proposed for IHP research, but most of them focused on revealing and analyzing the adverse reaction of some known IHPs, despite that a number of new IHPs have been discovered by accidents. Up to now, IHPs have been a serious threat to public health in the TCM medication. In this paper, we propose a novel supervised learning framework for potential IHP prediction. In this framework, we model the prediction task as a non-negative matrix tri-factorization problem, in which two important herb attributes (efficacy and flavor) and their correlation are incorporated to characterize the incompatible relationship among herbs. A hypothetical test method is adopted to evaluate the statistical significance of dissimilar characteristics of two attributes and the results are used as a regularization term to improve the accuracy of IHP prediction. Experiments on the real-world IHP dataset demonstrate that the proposed framework is very effective for prediction of potential IHPs.