Prediction model for pulmonary infection after cardiac surgery and construction method thereof

Abstract

The invention discloses a prediction model for pulmonary infection after cardiac surgery and a construction method thereof. The method comprises the following steps: screening out evaluation indexes related to pulmonary infection after cardiac surgery from various clinical data of a cardiac surgery patient in a perioperative period; bringing the evaluation indexes into a Logistic regression modelto analyze, calculate and determine regression coefficients of risk factors of pulmonary infection after cardiac surgery; obtaining a risk score through the regression coefficient of each risk factor;and finally, combining the risk score with a pulmonary infection risk prediction function to calculate a pulmonary infection probability value, so that a risk prediction model based on a scoring system can be established. The prediction model disclosed by the invention is good in fitting, shows better risk prediction capability compared with the existing foreign model, can achieve the purpose ofearly screening postoperative pulmonary infection high-risk patients, and plays a role in early prevention, early discovery and early treatment, thereby reducing the incidence rate of postoperative pulmonary infection of the heart.

Description

technical field [0001] The invention relates to the field of biotechnology, in particular to a prediction model of pulmonary infection after cardiac surgery and a construction method thereof. Background technique [0002] Pulmonary infection is the most common complication after cardiac surgery, and is closely related to increased postoperative mortality, prolonged stay in the intensive care unit, and prolonged postoperative hospital stay. Therefore, the associated medical expenses and resource consumption are also greatly increased. According to reports at home and abroad, the rate of pulmonary infection after cardiac surgery is between 2.1% and 21.6%, which varies greatly between different countries and regions and different medical institutions. [0003] In recent years, the state of the art in cardiac surgery and anesthesia has advanced dramatically, as has the demographics of patients undergoing cardiac surgery. The proportion of elderly patients undergoing surgery ha...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to provide a prediction model of pulmonary infection after cardiac surgery and its construction method to solve the problem that the existing lung disease prediction model is too mechanical to calculate and predict through simple functions, and lacks further screening and deep mining of pathogenic factor data Waiting for treatment, the problem of poor risk prediction ability

[0008] In order to realize the prediction model and construction method of the above-mentioned pulmonary infection after cardiac surgery, the existing lung disease prediction model is too mechanical to calculate and predict through simple functions, lacks further screening and deep mining of pathogenic factor data, and the risk prediction ability is not enough. For the best problem, the present invention provides the following technical solutions:

Images