Convenient layered senile MODS early death risk assessment model and device and establishment method

Abstract

The invention discloses a convenient layered old-age MODS early-stage death risk assessment model and device and an establishment method thereof. The assessment module is based on an XGBoost model fused with an SHAP method, and the assessment module comprises four sub-modules, and the four sub-modules are used for performing death risk assessment and providing risk factor contribution degree analysis based on 13 or 14 input characteristics for the elderly patients or the young elderly patients respectively. According to the convenient layered old-age MODS early-stage death risk assessment model and device, a doctor can conveniently and accurately assess the disease emergency and danger degree of a patient.

Description

technical field [0001] The present invention relates to machine learning, in particular to an early death risk assessment model for multiple organ failure in the elderly based on an interpretable machine learning model, a device, and a method for establishing the same for two types of elderly groups. Background technique [0002] Multiple organ failure (MODS) is a hot spot in the research of modern critical care medicine. It mostly occurs in the clinical syndrome of two or more systems or organ dysfunctions that occur successively after the body suffers acute injuries such as severe trauma, shock, infection, and major surgery. . It is a leading cause of morbidity and mortality in intensive care unit (ICU) patients. With the aging of the ICU population, the elderly have aging organs, low function, and multiple chronic diseases. The existing clinical scoring system cannot be well applied to the evaluation of elderly patients. Moreover, there are great differences between you...

AI Technical Summary

Problems solved by technology

Recently, more and more literatures have shown that clinical scoring systems such as the Sequential Organ Failure Assessment (SOFA) score and the Acute Physiology and Chronic Health Evaluation-II (APACHE-II) score cannot accurately assess and predict the risk of death in patients, and the reasons can be summarized is: the weights of the included prognostic factors are assigned by experts, but this does not reflect the characteristics of a larger population; the degree of failure of each organ system is added linearly but this does not reflect the complexity and intrinsic between real organ systems relevance; and the performance of these systems has not been adequately validated with multicenter, large cohort data

Images