A Traditional Chinese Medicine Syndrome Classification Model Based on Cross-Feature Generation by Convolution Neural Network: Model Development and Validation

Abstract

Background: Nowadays, intelligent medicine is gaining widespread attention, and great progress has been made in Western medicine with the help of artificial intelligence to assist in decision making. Compared with Western medicine, traditional Chinese medicine (TCM) involves selecting the specific treatment method, prescription, and medication based on the dialectical results of each patient's symptoms. For this reason, the development of a TCM-assisted decision-making system has lagged. Treatment based on syndrome differentiation is the core of TCM treatment; TCM doctors can dialectically classify diseases according to patients' symptoms and optimize treatment in time. Therefore, the essence of a TCM-assisted decision-making system is a TCM intelligent, dialectical algorithm. Symptoms stored in electronic medical records are mostly associated with patients' diseases; however, symptoms of TCM are mostly subjectively identified. In general electronic medical records, there are many missing values. TCM medical records, in which symptoms tend to cause high-dimensional sparse data, reduce algorithm accuracy.

Objective: This study aims to construct an algorithm model compatible for the multidimensional, highly sparse, and multiclassification task of TCM syndrome differentiation, so that it can be effectively applied to the intelligent dialectic of different diseases.

Methods: The relevant terms in electronic medical records were standardized with respect to symptoms and evidence-based criteria of TCM. We structuralized case data based on the classification of different symptoms and physical signs according to the 4 diagnostic examinations in TCM diagnosis. A novel cross-feature generation by convolution neural network model performed evidence-based recommendations based on the input embedded, structured medical record data.

Results: The data set included 5273 real dysmenorrhea cases from the Sichuan TCM big data management platform and the Chinese literature database, which were embedded into 60 fields after being structured and standardized. The training set and test set were randomly constructed in a ratio of 3:1. For the classification of different syndrome types, compared with 6 traditional, intelligent dialectical models and 3 click-through-rate models, the new model showed a good generalization ability and good classification effect. The comprehensive accuracy rate reached 96.21%.

Conclusions: The main contribution of this study is the construction of a new intelligent dialectical model combining the characteristics of TCM by treating intelligent dialectics as a high-dimensional sparse vector classification task. Owing to the standardization of the input symptoms, all the common symptoms of TCM are covered, and the model can differentiate the symptoms with a variety of missing values. Therefore, with the continuous improvement of disease data sets, this model has the potential to be applied to the dialectical classification of different diseases in TCM.

Keywords: TCM; cross-FGCNN; intelligent syndrome differentiation.

Figure 1

Intelligent syndrome differentiation block diagram. TCM: traditional Chinese medicine.

Figure 2

An example of electronic medical record preprocessing. EMR: electronic medical record.

Figure 3

Model structure. DNN: deep neural network; FGCNN: feature generation by convolution neural network.

Figure 4

Coating color field of data embedding module.

Figure 5

Cross network.

Figure 6

Improved feature generation by convolution neural network.

Figure 7

Cross-FGCNN accuracy-iteration times scatter diagram. FGCNN: feature generation by convolution neural network.

Figure 8

Cross-FGCNN confusion matrix. FGCNN: feature generation by convolution neural network; LKD: liver-kidney depletion; PCCBS: pattern of congealing cold with stasis; CDS: cold and dampness stagnation; LCD: liver constraint and dampness-heat; DQB: deficiency qi and blood; QBS: qi stagnation and blood stasis; KDBS: kidney deficiency and blood stasis; SDH: stagnation dampness-heat; YDIC: yang deficiency and internal cold.

Figure 9

ROC Curves of CTR models. ROC: receiver operating characteristic; CTR: click-through-rate; FGCNN: feature generation by convolution neural network; deep neural network; LKD: liver-kidney depletion; PCCBS: pattern of congealing cold with stasis; CDS: cold and dampness stagnation; LCD: liver constraint and dampness-heat; DQB: deficiency qi and blood; QBS: qi stagnation and blood stasis; KDBS: kidney deficiency and blood stasis; SDH: stagnation dampness-heat; YDIC: yang deficiency and internal cold.

Figure 10

ROC curves of traditional intelligence dialectical models. ROC: receiver operating characteristic; ANN: artificial neural network; SVM: support vector machine; LKD: liver-kidney depletion; PCCBS: pattern of congealing cold with stasis; CDS: cold and dampness stagnation; LCD: liver constraint and dampness-heat; DQB: deficiency qi and blood; QBS: qi stagnation and blood stasis; KDBS: kidney deficiency and blood stasis; SDH: stagnation dampness-heat; YDIC: yang deficiency and internal cold; ML-KNN: multilabel K nearest neighbor.