Method and device for processing mortality prediction

Abstract

Embodiments of the invention provide a method and device for processing mortality prediction. The method includes the steps: obtaining the age and detection index parameters of a patient to be predicted, wherein the detection index parameters comprises alkaline phosphatase, glutamyl transpeptidase, and hepatitis B E antigen, whether hepatic encephalopathy occurs, serum sodium, blood coagulation, zymogen activity and the total bilirubin; and inputting the age and the detection index parameter to a preset model; inputting the age and the detection index parameters to a preset model, and taking the output result of the preset model as the mortality prediction result of the patient to be predicted within a preset number of days, wherein the preset model is built based on ANN. The device executes the above method. The method and device for processing mortality prediction can improve the prediction accuracy for mortality, caused by acute-on-chronic liver failure related to viral hepatitis B,of a patient within the preset number of days by taking the output result of the preset model constructed based on ANN as the prediction result of the mortality of the patient to be predicted withinthe preset number of days.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of medical prediction, and in particular to a processing method and device for predicting mortality. Background technique [0002] With the increasing incidence of hepatitis B virus (HBV)-associated acute-on-chronic liver failure (ACLF), it is particularly important to predict the mortality of patients caused by HBV-associated acute-on-chronic liver failure. [0003] Existing techniques use the advanced liver disease model MELD and / or modified MELD to predict the mortality of ACLF patients, however, the prediction accuracy is not satisfactory. There is no effective method in the prior art to predict the mortality of patients with hepatitis B-associated acute-on-chronic liver failure within a preset number of days. [0004] Therefore, how to avoid the above-mentioned defects and how to improve the prediction accuracy of the mortality of patients with hepatitis B-related acute-on-chronic...

AI Technical Summary

Problems solved by technology

[0003] Existing techniques use the advanced liver disease model MELD and / or modified MELD to predict the mortality of ACLF patients, however, the prediction accuracy is not satisfactory

There is no effective method in the existing technology to predict the mortality of patients with hepatitis B-associated acute-on-chronic liver failure within a preset number of days

Images