Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Explanatable acute kidney injury continuous early warning method and system, storage medium and electronic equipment

An acute kidney injury and electronic medical record technology, applied in the medical field, can solve the problems of alarm fatigue and clinical workers' inability to understand alarms effectively, and achieve the effects of improving recognition accuracy, alleviating alarm fatigue, and improving generalization ability

Pending Publication Date: 2022-04-29
SOUTHEAST UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the alarm fatigue problem based on the artificial intelligence early warning system and the inability of clinical workers to effectively understand the occurrence of the alarm make it impossible to interactively obtain effective information to evaluate the patient's condition to assist in the treatment. The current AKI intelligent early warning algorithm is far from meeting the clinical application standards. main problem

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
  • Explanatable acute kidney injury continuous early warning method and system, storage medium and electronic equipment
  • Explanatable acute kidney injury continuous early warning method and system, storage medium and electronic equipment
  • Explanatable acute kidney injury continuous early warning method and system, storage medium and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] This embodiment provides an interpretable method for continuous early warning of acute kidney injury, such as figure 1 shown, including the following steps:

[0050] Step 1: Acquisition of clinical electronic medical record data, constructing a tabular time series of patients with hourly steps, and selecting the creatinine and urine output standards in the KDIGO guidelines to define the occurrence and criticality of acute kidney injury ( figure 2 );

[0051] Step 2: Data preprocessing and feature extraction, clinical dynamic feature analysis, clinical information mining based on prior knowledge, and clinical experience feature extraction.

[0052] Step 3: Construction of deep learning method for continuous early warning of acute kidney injury, based on dilated causal convolution combined with residual network embedded in squeeze and excite (SE) module to perform multi-layer nonlinear mapping representation of patient time series information, and automatically mine pat...

Embodiment 2

[0056] This embodiment provides an interpretable continuous early warning system for acute kidney injury, including:

[0057] Clinical electronic medical record data acquisition and integration module, the acquired data information such as demographic data, vital signs and laboratory examinations are used as model training samples, and the tabular time of integrating multiple physiological parameter information of critically ill patients is constructed with the step size of hours sequence;

[0058] The data preprocessing and feature extraction module analyzes clinical dynamic features, mines clinical information based on prior knowledge, and extracts clinical experience features;

[0059] The acute kidney injury risk continuous warning method module, based on the dilated causal convolution combined with the residual network embedded in the extrusion and excitation (SE) module, performs multi-layer nonlinear mapping representation of patient time series information, and automat...

Embodiment 3

[0062] The purpose of this embodiment is to provide a computer-readable storage medium.

[0063] A computer-readable storage medium, on which a computer program is stored for calculating the similarity of fingerprints. When the program is executed by a processor, the following steps are performed:

[0064] Clinical electronic medical record data acquisition and integration module, the acquired data information such as demographic data, vital signs and laboratory examinations are used as model training samples, and the tabular time of integrating multiple physiological parameter information of critically ill patients is constructed with the step size of hours sequence;

[0065] The data preprocessing and feature extraction module analyzes clinical dynamic features, mines clinical information based on prior knowledge, and extracts clinical experience features;

[0066] The acute kidney injury risk continuous warning method module, based on the dilated causal convolution combine...

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 interpretable acute kidney injury continuous early warning method and system, a storage medium and electronic equipment. The method comprises the following steps: 1, acquiring clinical electronic medical record data, and constructing a patient tabular time sequence taking hour as unit step length; 2, data preprocessing and feature extraction are carried out, and clinical dynamic feature analysis is carried out to extract clinical experience features; 3, performing multi-layer nonlinear mapping representation on the time sequence information of the patient, and constructing an acute kidney injury continuous early warning deep learning method; a fourth step of providing an interpretable early warning model based on an improved integral gradient method to interpret an output result; and 5, constructing a clinical visual interaction interface to assist in clinical decision making. According to the method, an acute kidney injury depth representation early warning algorithm is constructed on the basis of fusing prior features, the accuracy of continuous patient risk tracking is effectively improved, and meanwhile, the usability of a system on which the algorithm depends is greatly improved through interpretable and visual interaction information.

Description

technical field [0001] The present invention relates to the field of medical technology, in particular to an interpretable acute kidney injury continuous warning method, system, storage medium and electronic equipment. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art. [0003] Acute kidney injury (Acute kidney injury, AKI) is a severe clinical syndrome characterized by a rapid decline in renal function caused by multiple etiologies and pathological mechanisms, with high morbidity and mortality. According to relevant statistics, there are about 13.3 million new cases of AKI every year in the world, and nearly 1.7 million people die from AKI and its complications. At present, there is still no effective treatment to reduce the course of AKI clinically, so the prevention and early diagnosis of AKI are the most important links in its prevention and tre...

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): G16H10/60G16H50/70G06N3/08G06N3/04
CPCG16H10/60G16H50/70G06N3/08G06N3/045
Inventor 刘澄玉杨美程李润发李建清
Owner SOUTHEAST UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com