Method and system of detecting artifacts in ICU patient records based on multivariate logistic regression

Abstract

The invention discloses a method of detecting artifacts in ICU patient records based on multivariate logistic regression. The method includes: calculating ICU probability of a patient by a multivariate logistic regression expression, and comparing the probability to a set threshold to establishing a binary classifier used to judge whether the ICU patient is going to die or not. The method has the advantages that presetting preconditions having predictive variables obeying normal distribution is not required; the predictive variables can be continuous or disperse; the number of predictive variables in a model is reduced as far as possible, and complexity of the model is reduced while prediction accuracy is guaranteed. The invention further discloses a system to implement the method. The system has the advantages that the problem of non-specificity in existing risk prediction models can be solved effectively; compared to existing models, the model allows prediction to be more accurate and specific.

Description

technical field [0001] The invention belongs to the technical field of medical detection, and in particular relates to a method and system for detecting artifacts in ICU patient records based on multiple logistic regression. Background technique [0002] Healthcare technologies such as biomedical sensors, monitoring systems, and medical devices are rapidly advancing in performance and ubiquity (many devices) in what is now the Intensive Care Unit (ICU). The creation of additional data streams is imposing significant "information overload" challenges on healthcare workers, and limited medical resources and high costs in the ICU mean that not all patients receive specialized care. Accurate evaluation of the patient's condition and reliable risk prediction are important basis for deciding whether the patient needs intensive care and controlling the quality of care. In some extreme cases, where intensive care is doomed, doctors need to make a decision to stop using the device t...

AI Technical Summary

Problems solved by technology

[0005] Aiming at the above-mentioned technical problems existing in the prior art, the present invention provides a method and system for detecting artifacts in ICU patient records based on multiple logistic regression, which realizes the severe analysis of specific individual patients and solves the non-specificity of traditional methods question

Images