Sepsis data processing system

Abstract

The invention discloses a sepsis data processing system which comprises a model training unit and a prediction unit. The model training unit is trained according to patient data provided by an intensive care medicine database to obtain an identification model, the identification model is stored in a storage unit, the prediction unit identifies output representation identification results by the identification model, the model training unit comprises a data preprocessing module, a data separation module, a training data integration module and a model training module, the data preprocessing module preprocesses the patient data from the intensive care medicine database to obtain the preprocessing patient data, the data separation module divides the preprocessing patient data into a finally diagnosed sepsis forward training data and finally diagnosed non-sepsis reversal training data, the training data integration module integrates training data into a training data set, and the model training module is trained according to the training data set to obtain the identification model. The system has the advantages that influence of man-made decision factors is relieved, potential characteristics of data are more easily excavated, and sepsis prediction accuracy is effectively improved.

Description

technical field [0001] The invention relates to the technical field of patient data processing, in particular to a sepsis data processing system. Background technique [0002] In modern society, a large amount of medical data has been preserved in recent years. However, due to the sensitivity, specificity, coexistence of structured data and unstructured data of medical data, most of the medical data cannot be directly Allowed for data analysis. These various problems have led to the importance of data preprocessing based on disease diagnosis. The present invention is based on the research of the MIMICIII database, and has certain versatility of the ICU medical database. [0003] Sepsis (Sepsis) is a common systemic multi-system infection reaction, which often leads to life-threatening as a complication when patients are hospitalized. Among them, in the ICU intensive care unit ward, sepsis is one of the main causes of death of patients. Moreover, as time goes by, the dete...

AI Technical Summary

Problems solved by technology

Most of the existing prediction methods are based on statistics. Although the interpretability is good, the prediction effect is often poor.

Images