Chronic heart failure prediction model construction method and device, equipment and storage medium

Abstract

The invention provides a chronic heart failure prediction model construction method and device, equipment and a storage medium, and the method comprises the steps: obtaining biomedical literature sample data, multi-disease clinical sample data and target disease clinical sample data; according to the biomedical literature sample data, training the general big language model to generate a biomedical big language model; according to the clinical sample data of multiple diseases, instruction fine tuning training is carried out on the biomedicine large language model, and a clinical biomedicine large language model is generated; and according to the clinical sample data of the target disease, performing low-rank adaptation fine tuning training on the clinical biomedicine large language model, and taking the clinical biomedicine large language model after the training is finished as a chronic heart failure prediction model. According to the method, under the condition of limited real clinical data samples, the model prediction accuracy is higher, the stability is higher, and the robustness is higher.

Images