Sepsis prognosis prediction method based on ensemble learning algorithm

The invention belongs to the technical field of data mining, and particularly relates to a sepsis prognosis prediction method based on an ensemble learning algorithm. The method comprises the following steps: S1, data acquisition: acquiring electronic data information of a patient, and extracting effective characteristic variables; S2, data preprocessing: carrying out data discretization and a z-score standardization method by adopting quartile division; S3, feature selection: performing feature selection by adopting a Spearman correlation coefficient, and calculating a correlation coefficient of each feature to the target research object; S4, prediction model training: inputting data into the constructed prediction model, and continuously adjusting parameters according to a training result to enable the model to achieve optimal performance; and S5, model evaluation: testing and evaluating the trained model by using the test set. The method has the advantages of being scientific, reliable, high in accuracy, g