A Recommendation Model for Medical Data Visualization Based on Information Entropy and Decision Tree Optimized by Two Correlation Coefficients

Medical practitioners usually have difficulties in obtaining information effectively from massive data due to limited time and energy. This paper proposes a novel recommendation model for medical data visualization based on decision tree and information entropy optimized by two correlation coefficients, that is, Pearson's correlation coefficient and Kendall's correlation coefficient(P&K.CC). After investigating visualization techniques under different medical scenarios, we construct a medical domain knowledge-based decision tree which employs two correlation coefficients as new measures of feature quality to confirm the optimal splitting attributes and points in its growth, as well as prioritize the medical datasets based on improved information entropy. Finally, in contrast to several traditional decision tree classifiers, the results indicated that the proposed method achieves a better accuracy of the scenario classification of medical data. At the same time, the method can find the datasets that perform better in knowledge presentation and visualization.