Feature selection method and device based on clinical data

The invention discloses a feature selection method and device based on clinical data, and belongs to the technical field of digital medical treatment. According to the invention, the fitness function of the genetic algorithm is improved by using a filtering method and an mRMR factor, and a clinical data feature selection method based on an mRMR-GA algorithm is provided. Meanwhile, in order to ensure more effective calculation of mRMR factors and calculation of mutual information by using density function estimation, kernel density function estimation has the advantage of a probability density function smoother than density histogram estimation, and finally, feature selection processing by using a genetic algorithm is a mode of searching a feature space set based on a feature relationship, and a better feature set selection result can be obtained. In a prediction model used for a specified prediction task, the optimal feature subset of the prediction target is determined based on the method, then the predictio