Early death risk assessment model establishing method and device based on ensemble learning

Abstract

The invention provides an early death risk assessment model establishing method and device based on ensemble learning. The method and device are used for assessing the death risk of an old multi-organfailure patient during hospitalization based on diagnosis and treatment data of the first day when the old multi-organ failure patient enters an intensive care unit. The method comprises the steps ofdata set construction, data processing and model construction and evaluation. The method comprises the following steps: acquiring three pieces of demographic information, five pieces of vital sign information, five laboratory examination indexes and two clinical indexes of a patient on the first day during living in an intensive care unit; inputting the data into a risk assessment device, and carrying out internal data preprocessing, feature calculation and model operation. Finally, the risk of adverse outcomes in the hospital of the patient can be predicted early, and doctors are helped to treat the patient as soon as possible.

Description

technical field [0001] The present invention relates to a death risk assessment method and device, in particular to a method and device for establishing an early death risk assessment model for multiple organ failure in the elderly based on integrated learning. Background technique [0002] Multiple organ failure syndrome (MODS) is characterized by the progressive physiological dysfunction of two or more organs (organ systems) stimulated by certain triggers. Multiple organ failure in the elderly (MODSE) is a clinical syndrome with insidious onset, multiple etiologies, complex pathogenesis, and easy to be ignored by clinicians. It is an important cause of death in elderly critically ill patients. According to relevant literature reports, if three or more organ failures occur, the mortality rate is 50% to 100%. At the same time, its treatment and nursing costs are very huge. According to statistics, the average medical cost per patient is about 22,000 US dollars, and the tota...

AI Technical Summary

Problems solved by technology

However, the above scoring features are usually modeled using logistic regression, which does not take into account the correlation between organ functions

It is also assumed that there is a linear superposition relationship between predictor variables and outcomes, and the complexity of real disease progression and evolution is far from being expressed and quantified by a simple linear model; the weights / coefficients assigned to each sub-score are subject to greater subjectivity, namely Select and assign weights to the corresponding variables based on the cognition of the mortality prediction correlation of the expert group, which has not been verified by a large number of experimental data; the elderly have many basic diseases, many complications, organ aging and functional decline, etc. , adult assessment criteria do not apply to older adults

However, these scores rarely provide a more detailed evaluation plan for elderly patients

Images