Emergency patient early death rate prediction method and system based on integrated model

Abstract

The invention relates to the field of medical data mining, in particular to an emergency patient early death rate prediction method and system based on an integrated model. The system includes portable health monitoring equipment, a medical equipment terminal, a patient monitoring management system, an electronic health record, a central business server, a central storage server, a data loading module, a data preprocessing module, a feature construction and selection module, a model construction and updating module, a patient prediction module, a patient sorting module and a patient early warning module. The method the following steps: step 1, collecting measured values of various physiological indexes of an emergency patient during a check-in period, preprocessing the obtained original data, and extracting a prediction index; 2, mining and constructing effective data features, and deleting redundant features; 3, processing a data category imbalance problem; 4, constructing an integrated model, and predicting the early death rate of the emergency patients by using the integrated model; and 5, counting a prediction result; The problem that an existing system is low in prediction precision is solved.

Description

technical field [0001] The invention relates to the field of medical data mining, in particular to a method and system for predicting early mortality of emergency patients based on an integrated model. Background technique [0002] The emergency department is the department with the most intensively ill patients and the most types of diseases in the hospital. It aims to provide professional care for critical patients and continuously monitor various vital indicators. Effective resource management and staffing are often constrained in the early stages of healthcare, which have been shown to positively correlate with patient outcomes. Timely and accurate assessment of the degree of patient crisis through a large amount of clinical data can assist doctors to make timely treatment measures and potentially reduce patient mortality. Therefore, early mortality prediction of emergency patients is one of the important subjects of clinical research. [0003] The traditional methods ...

AI Technical Summary

Problems solved by technology

[0005] Based on the above problems, the present invention provides an integrated model-based early mortality prediction method and system for emergency patients, which solves the problem of low prediction accuracy in existing systems

Images