| Summary: | This article is oriented to the research of the vehicle-mounted intelligent traditional Chinese medicine (TCM) syndrome differentiation system to provide a quick and accurate diagnosis suggestion for smart and mobile medical vehicles. Nowadays, TCM modernization has attached more and more attention due to its remarkable clinical effect. The typical TCM diagnosis process is to induces the syndrome types of a patient from the four-diagnosis symptoms based on syndrome differentiation theory, that is, given a set of symptoms to treat, an overall syndrome representation is learned by fusing all the symptoms effectively to mimic how a doctor induce the syndromes. Therefore, we believe that an overall description of symptoms of a patient is very important for the follow-up treatment and should be handled carefully and properly. However, due to the complexity and diversity of syndromes, most recommended prescription of a patient lacks the explicit ground-truth of syndrome. Therefore, in this article, a new TCM syndrome differentiation method based on multi-label classification method and deep learning method was proposed to learn the implicit symptoms induction process in the real diagnosis. A Deep Belief Network (DBN) was used to reconstruct the TCM diagnosis model based on the Rrestricted Boltzman Machine (RBM) mechanism. Towards symptoms-syndrome groups learning, a symptom vector representing the symptom collection of a patient is constructed as the input of DBN, which was used to train the symptom data and labeled samples to build an unsupervised model at first. And then the parameters of DBN was adjusted gradually based on back propagation method. Secondly, binary classification algorithm was used to convert the multi-label classification problem into several corresponding labels. Each binary classifier model corresponds to a binary classifier to complete the classification from symptoms to corresponding syndrome types. Finally, Experiments were conducted on a self-built TCM clinical records database, demonstrating obvious improvements on the classification accuracy and convergence rate. Further studies should focus on the promotion of effectiveness of the proposed model to be more in line with the actual needs of onboard medical diagnosis and treatment.
|
|---|
