Health risk key event detection method and system based on time window cutting

Abstract

The invention discloses a method and system for detecting key health risk events based on time window cutting. The method includes: S100. Input the patient's electronic medical record into the trained deep learning model, and obtain the important index and Mortality risk index; S200. Divide the detection target of the key event of the patient's health risk into four types according to the time window, and detect the four types respectively based on the obtained important index of each physiological index and the death risk index, and screen out It is necessary to propose physiological indicators of key health risk events; S300, based on a visual interface, display the detection process and detection results of key health risk events of patients. The invention can excavate more valuable and reference information from the patient's electronic medical record data in the hospital to help doctors diagnose.

Description

Technical field [0001] The present invention relates to the field of health risk detection, and in particular to a key event detection method and system based on time window cutting. Background technique [0002] For patients with chronic diseases, patients with critically ill patients, assessing their death risks, helping medical staff adopt sexual treatment measures as soon as possible and improving patient survival probability. However, the risk assessment of death is very complicated. It is necessary to comprehensively analyze multiple physiological indicators of patients. Consider static information such as patient age, gender, past history history, and combine a large number of medical knowledge, only medical knowledge, and clinical experience. The doctor can make more accurate assessment results under the premise of investing a lot of time and energy. In the clinical practice, medical institutions tend to lead to poor assessments due to lack of adequate expert resources. O...

AI Technical Summary

Problems solved by technology

However, the assessment of mortality risk is very complicated. It needs to comprehensively analyze multiple physiological indicators of the patient, consider static information such as the patient's age, gender, and past medical history, and combine a large amount of medical knowledge to make the final judgment. Only those with rich medical knowledge and clinical experience Doctors can get more accurate assessment results only after investing a lot of time and energy

However, in clinical practice, medical institutions often have poor evaluation results due to the lack of sufficient expert resources

Images