Prediction system for sepsis in intensive care unit, storage medium and equipment
An intensive care unit and prediction system technology, applied in the field of medical data mining, can solve problems such as the uncertainty of scoring standards, and achieve the effect of fast prediction speed and high prediction accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0034] Such as figure 1 As shown, the present embodiment provides a sepsis prediction system in an intensive care unit, which specifically includes the following modules:
[0035] (1) A data preprocessing module, which is used to obtain the medical monitoring data of the person to be monitored in the intensive care unit and perform preprocessing on it.
[0036] For example, the medical monitoring data in the intensive care unit includes 40 characteristic indicators such as 8 vital signs indicators, 26 laboratory indicators and 6 demographic indicators, and the time stamp of the data indicators is recorded every hour. Figure 4 A table of characteristics of sepsis care in the intensive care unit is given, which records medical monitoring data in the intensive care unit.
[0037] Wherein, the preprocessing includes normalizing the obtained medical monitoring data of the person to be monitored in the intensive care unit, filling missing values, and screening and replacing abnorm...
Embodiment 2
[0074] This embodiment provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the following steps are implemented:
[0075] Obtain and preprocess the medical monitoring data of the person to be monitored in the intensive care unit;
[0076] Receive preprocessed medical monitoring data in chronological order and perform feature selection and feature extraction from the received data;
[0077] Transform the time series into feature vectors through network transformation, and input them into the trained sepsis prediction model based on the feature vectors and current time stamp information to predict the probability of sepsis;
[0078] Wherein, the sepsis prediction model is formed by parallel connection of multiple classifiers, and the finally predicted probability of occurrence of sepsis is the mean value of the output probabilities of multiple classifiers.
Embodiment 3
[0080] This embodiment provides a computer device, including a memory, a processor, and a computer program stored on the memory and operable on the processor. When the processor executes the program, the following steps are implemented:
[0081] Obtain and preprocess the medical monitoring data of the person to be monitored in the intensive care unit;
[0082] Receive preprocessed medical monitoring data in chronological order and perform feature selection and feature extraction from the received data;
[0083] Transform the time series into feature vectors through network transformation, and input them into the trained sepsis prediction model based on the feature vectors and current time stamp information to predict the probability of sepsis;
[0084] Wherein, the sepsis prediction model is formed by parallel connection of multiple classifiers, and the finally predicted probability of occurrence of sepsis is the mean value of the output probabilities of multiple classifiers. ...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More