Classification Models for Medical Data with Interpretative Rules

ABSTRACT

The raging of COVID-19 has been going on for a long time. Thus, it is essential to find a more accurate classification model for recognizing positive cases. In this paper, we use a variety of classification models to recognize the positive cases of SARS. We conduct evaluation with two types of SARS datasets, numerical and categorical types. For the sake of more clear interpretability, we also generate explanatory rules for the models. Our prediction models and rule generation models both get effective results on these two kinds of datasets. All explanatory rules achieve an accuracy of more than 70%, which indicates that the classification model can have strong inherent explanatory ability. We also make a brief analysis of the characteristics of different rule generation models. We hope to provide new possibilities for the interpretability of the classification models. © 2021, Springer Nature Switzerland AG.