MULTI-LABEL LEARNING-BASED POST-PHYSICAL EXAMINATION CHRONIC DISEASE PROGNOSIS SYSTEM

摘要

Provided is a multi-label learning-based post-physical examination chronic disease prognosis system, comprising a data acquisition module, a data pre-processing module, a basic prediction-model building module, and a local prediction module; the data acquisition module is used for acquiring physical examination data of a physical examination user; the basic prediction-model building module is used for building a multi-label learning model for physical examination scenarios; the local prediction module comprises a local model training unit and a prediction unit; the local model training unit solidifies the trained local prediction model into the local prediction module; the prediction unit outputs a prediction prognosis index for the occurrence of a plurality of chronic diseases; finally, the expected times of occurrence of the chronic diseases in the future are obtained. The system uses a multi-label learning method, and extracts the internal relationships in the case of concurrent chronic diseases, which is in line with the features of high concurrency of chronic diseases, and can better perform accurate prediction of the future occurrence of chronic diseases.