System for predicting risk of death of patient

A patient-risk technology, applied in the system field of predicting patient death risk, can solve problems such as high adjusted hazard ratio of in-hospital mortality, reduced predictive value, and changes in physiological parameters

Active Publication Date: 2020-09-04
PEKING UNIV THIRD HOSPITAL
View PDF3 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, unlike ICU inpatients, emergency patients can undergo drastic changes in physiological parameters within the first few hours of resuscitation and intensive care, and the predictive value of SAPS 3 applied to such patients will be greatly reduced
In addition, EDICU patients had higher adjusted hazard ratios for in-hospital mortality compared with patients in general and cardiovascular ICUs
Therefore, the scoring system based on ICU is not suitable for EDICU patients

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • System for predicting risk of death of patient
  • System for predicting risk of death of patient
  • System for predicting risk of death of patient

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0130] Embodiment 1 screening patients and collecting experimental data

[0131] From March 2016 to October 2016, patients who visited the emergency department of Beijing Third Hospital and needed treatment in the emergency care unit system (emergency rescue room and emergency care unit) due to their illness. The disease classification of the patients included in the study was grade 1 (endangered patients) or grade 2 (critically ill patients).

[0132] Inclusion criteria:

[0133] 1. Patients who have been treated in the emergency room or emergency care unit;

[0134] 2. Age ≥ 16 years old;

[0135] Exclusion criteria:

[0136] 1. Patients who have no spontaneous breathing or heartbeat when they come to the hospital, and are declared clinically dead;

[0137] 2. Pregnant patients;

[0138] 3. Patients with serious missing data;

[0139] After repeated discussions, the research team specified the data collection plan, made a unified case report form, discussed and unified...

Embodiment 2

[0151] Example 2 Screening the prediction parameters included in the prediction system from the collected patient data

[0152] The new model stage of the prediction system of this application is derived, and logistic regression is used to analyze the association between each variable and the mortality rate. Only variables that were significantly associated with mortality (ie, P<0.1) were used to derive risk-adjusted scores.

[0153] At the initial stage of model establishment, the relationship between each univariate and death was preliminarily studied. Except for age, which has a linear relationship with mortality, other variables have a more complex relationship with death. We therefore adjusted these variables as categorical variables. Different variables were grouped according to their relationship with mortality, and if the variables had standard normal ranges clinically, they were grouped according to their standard ranges.

[0154] The medical history data of the pa...

Embodiment 3

[0159] Example 3 Determination of the 7-day mortality prediction system model for critically ill patients in the emergency department

[0160] A total of 1624 cases were included in the study, with an average age of 64.7±18.1 years, and 969 cases (60%) were male. The basic information of the patients is shown in Table 1.

[0161] Table 1 includes the basic information of the patients

[0162]

[0163] Note: The measurement data of normal distribution is represented by mean ± standard deviation; the measurement data of non-normal distribution is represented by M(P25, P75); *P<0.05, **P<0.01.

[0164] From the considered continuous variables, we classified the variables on the basis of the standard ranges of each variable, combined with clinical experience, expert opinion, the physiological characteristics of patients in my country, and the severity of the disease, and determined the cut-off values ​​for their classification (see Table 2). Based on group discussions and reco...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to a system for predicting the risk of death of a patient. The system for predicting the risk of death of a patient comprises: a data acquisition module used for obtaining the medical history of a patient, physiological parameters of the patient and laboratory parameters of the patient, wherein the physiological parameters comprise the Glasgow Coma Scale of the patient, the heart rate of the patient, the systolic pressure of the patient and the oxygen saturation of the patient, and the laboratory parameters comprise the hemoglobin level, the leukocyte count, the creatinine concentration, the blood potassium concentration, the blood sodium concentration, the urea content, the platelet count, the total bilirubin concentration, the D-dimer level and the fibrinogen content of the patient; and a module for calculating the death risk of the patient used for calculating the information acquired in the data acquisition module so as to calculate the 7-day death rate (p) ofthe patient.

Description

technical field [0001] This application relates to a system for predicting the risk of death of patients. The system can be used to assess the risk of death of critically ill patients in the emergency department, so as to assess the severity and poor prognosis of the disease, and then guide the treatment process for critically ill patients in the emergency department. Background technique [0002] With the increasing level of population aging and the rising prevalence of chronic diseases, there are more and more critically ill patients. ICU is usually the place where critically ill patients finally receive treatment, but the treatment of critically ill patients is very expensive and resources are limited. Critically ill patients often stay in the emergency department because they cannot be admitted to the ICU for treatment in time. The number of patients requiring intensive care treatment in the emergency department has increased by 75%. Not only is the number of people incr...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G16H50/30A61B5/00
CPCG16H50/30A61B5/7275Y02A90/10
Inventor 马青变葛洪霞梁杨李楠翟樯榕
Owner PEKING UNIV THIRD HOSPITAL
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap