Severe pancreatitis prediction model construction method based on machine learning method

Abstract

The invention discloses a severe pancreatitis prediction model construction method based on a machine learning method, and the method comprises the following steps: obtaining clinical and laboratory index related data of a prediction object, and carrying out the preprocessing of the obtained data; removing missing or slightly-changed indexes; carrying out data binning; screening a severe pancreatitis data prediction model; pre-training the selected model; screening and determining characteristic indexes associated with 10 severe pancreatitis according to a pre-training result, and training again; according to the working characteristic curve of the subject, a threshold value suitable for a prediction algorithm is determined, and then a final severe pancreatitis data prediction model is obtained. The non-invasive severe pancreatitis diagnosis model based on multiple clinical indexes solves the problem of diagnosis lag, is high in prediction speed and high in accuracy, and can provide reference for clinical diagnosis of severe pancreatitis.

Description

technical field [0001] The invention relates to the field of disease diagnosis, in particular to a method for constructing a prediction model of severe pancreatitis based on a machine learning method. Background technique [0002] Existing scoring systems for severe pancreatitis include acute physiology and chronic health assessment, or predict the severity of acute pancreatitis (AP) based on a single or a small number of laboratory indicators. Existing laboratory technology scoring systems such as acute physiology and chronic health assessment Evaluation indicators such as Acute Physiology and Chronic Health Evaluation (APACHE II) and Bedside Index for Severity in Acute Pancreatitis (BISAP) are cumbersome, and physicians have a lot of work pressure and subjective evaluation. In addition, it takes >48h or even 72h after the onset to further determine the severity of AP, which leads to a serious delay in the treatment and diagnosis of the disease and affects the best time ...

AI Technical Summary

Problems solved by technology

[0002] Existing scoring systems for severe pancreatitis include acute physiology and chronic health assessment, or predict the severity of acute pancreatitis (AP) based on a single or a small number of laboratory indicators. Existing laboratory technology scoring systems such as acute physiology and chronic health assessment Acute Physiology and Chronic Health Evaluation (APACHE II), Bedside Index for Severity in Acute Pancreatitis (BISAP) and other evaluation indicators are cumbersome, and physicians have high work pressure and subjective evaluation

In addition, it takes >48h or even 72h after the onset to further determine the severity of AP, which leads to a serious delay in the treatment and diagnosis of the disease and affects the best time for treatment; moreover, the data of multiple laboratory diagnostic techniques obtained by different medical centers and laboratories need to rely on clinical Physician's interpretation has the defects of general repeatability and subjective bias

Images