Operation opportunity prediction model for patient with acute necrotizing pancreatitis

A technique for acute pancreatitis, predictive models, applied in the field of neural networks

Pending Publication Date: 2020-04-28
SICHUAN UNIV
View PDF7 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Not all patients with acute pancreatitis and necrosis can wait until four weeks later for surgery, and patients with acu

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
  • Operation opportunity prediction model for patient with acute necrotizing pancreatitis
  • Operation opportunity prediction model for patient with acute necrotizing pancreatitis
  • Operation opportunity prediction model for patient with acute necrotizing pancreatitis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0041] LSTM, that is, Long short term network, refers to the long and short term neural network model.

[0042] HIS hospital information system hospital information system;

[0043] LIS laboratory information system laboratory information system;

[0044] RIS radiation information system Radiological information system;

[0045] CIS clinical information system Clinical information system.

[0046] Such as figure 1 , figure 2 As shown, the present invention collects the electronic medical record data of patients with acute pancreatitis in West China Hospital of Sichuan University for 10 years, and performs data cleaning.

[0047] use figure 2 The shown LSTM network structure performs time-series modeling on the electronic medical record data of patients wit...

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 discloses an operation opportunity prediction model for a patient with acute necrotizing pancreatitis, and the model comprises the following steps: S100, collecting and cleaning case data which comprises admission data and hospitalization data of the patient; S200, sorting the case data to obtain preprocessed data, wherein the sequence form of the preprocessed data is {Variables, Time}; S300, carrying out one-hot coding on the category type variables in the preprocessed data by using an Embedding mechanism, and then mapping the category type variables into a real vector space; S400, normalizing the data obtained in the step S300, introducing an LSTM model which is a multi-task model, wherein the output layer of the LSTM model is provided with four outcome indexes: 48-hour death after the patient is hospitalized, the number of remaining hospitalized days, whether organ failure occurs or not and whether an operation is performed or not. The optimal operation opportunity ofeach patient with acute pancreatitis necrosis can be determined according to the characteristics of the patient, so the prognosis condition of the patient is improved.

Description

technical field [0001] The invention relates to the field of neural networks, in particular to a model for predicting operation timing of patients with necrotizing acute pancreatitis. Background technique [0002] At present, there is almost no prediction model for the timing of surgery for patients with necrotizing acute pancreatitis in my country; as we all know, the time series characteristics and variable characteristics of different diseases are different. exists and cannot be applied directly. Previous models of disease prediction mainly focused on traditional statistical methods. Due to the heterogeneity of data, most of them were difficult to consider complex time information and simulate the real disease development status of patients. [0003] Domestic and foreign guidelines suggest that the timing of surgery for patients with acute pancreatitis and necrosis should be delayed as far as possible after four weeks, but they do not give specific recommendations on whic...

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
IPC IPC(8): G16H50/30G16H10/60G06F16/215
CPCG16H10/60G16H50/30G06F16/215
Inventor 兰蓝罗佳伟周小波
Owner SICHUAN UNIV
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