Unlock instant, AI-driven research and patent intelligence for your innovation.

Artificial intelligence-based early prediction method and device for acute kidney injury

An acute kidney injury and artificial intelligence technology, applied in the medical field, can solve problems such as time lag, inability to specifically reflect renal function, and inability to predict the incidence of AKI early

Active Publication Date: 2021-07-06
戴松世
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] At present, for the diagnosis of AKI (Acute Kidney Injury, acute kidney injury), the creatinine and urine output used by DIGO, due to their limitations and the time lag relative to renal injury, cannot specifically reflect renal function and reflect renal function. nature of damage
[0003] With the development of medicine, through the use of biomarkers, FST (Furosemide Stress Test) functional models, the introduction of decision trees, deep learning and machine learning, the incidence of AKI cannot be predicted early

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
  • Artificial intelligence-based early prediction method and device for acute kidney injury
  • Artificial intelligence-based early prediction method and device for acute kidney injury
  • Artificial intelligence-based early prediction method and device for acute kidney injury

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] figure 1 Early prediction method for artificial intelligence of acute renal injury is provided in the embodiment of the present invention.

[0045] Refer figure 1 The method includes the following steps:

[0046] Step S101, acquire various types of raw parameters, perform data cleaning and feature extraction of various types of raw parameters, resulting in feature parameters;

[0047] Here, after obtaining various types of original parameters, various types of raw parameters are required, i.e., data cleaning and feature extraction, thereby obtaining useful information, ie feature parameters. For example, the doctor acquires feature parameters from the CT, B super or magnetic resonance, or acquires feature parameters from the blood test order, or the Chinese medicine has obtained the characteristics parameters through the pulse of the pulse and the tongue.

[0048] Further, feature parameters include feature values ​​corresponding to feature items and feature items.

[0049...

Embodiment 2

[0070] Figure 4 Early prediction devices of artificial intelligence of acute renal injury provided by the second embodiment of the present invention.

[0071] Refer Figure 4 The device includes:

[0072] The extraction unit 10 is used to obtain various types of raw parameters, and data cleaning and feature extraction of various types of original parameters is obtained.

[0073] The first development status acquisition unit 20 is used to obtain the development of the feature parameters through the genetic algorithm and the random forest algorithm, and the development state of each time periodic kidney injury;

[0074] Status point acquisition unit 30 for acquiring status points of AKI;

[0075] The determination unit 40 is configured to determine the reward value of each time period AKI according to the development of each time period AKI, and assign the reward value of each time period AKI to the status point of the AKI;

[0076] The second development status acquisition unit 50 ...

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 present invention provides an artificial intelligence early prediction method and device for acute kidney injury, including: obtaining various original parameters, performing data cleaning and feature extraction on various original parameters to obtain characteristic parameters; and obtaining characteristic parameters through genetic algorithm and random forest Algorithm to obtain the development status of acute kidney injury AKI in each time period; obtain the status points of AKI; determine the reward value of AKI in each time period through Monte Carlo tree and reinforcement learning algorithm according to the development status of AKI in each time period, and calculate the The reward value of segmental AKI is assigned to the state point of AKI; the reward value of AKI in each time segment and various original parameters are used through the random forest algorithm to predict the incidence probability of AKI after each time segment, which can be predicted earlier and more accurately The occurrence of AKI establishes an early prediction model for artificial intelligence intervention.

Description

Technical field [0001] The present invention relates to an early prediction method and apparatus for acute renal injury involving artificial intelligence. Background technique [0002] At present, the diagnosis of Aki (Acute Kidney Injury, Acute Kidney Injury), the amount of creatinine and urine used in DIGO, due to its limitations, relative to the time of renal injury, can not specifically reflect the kidney function, and reflect the kidney The nature of damage. [0003] With the development of medicine, by using biomarkers, FST (FROSEMIDE STRESS TEST) function model, introduction of decision trees, deep learning, and machine learning, etc., through the above means, it is not possible to predict the incidence of AKI. Inventive content [0004] In view of this, it is an object of the present invention to provide an early prediction method and apparatus for artificially intelligent acute renal injury, which can predict the occurrence of AKI earlier and accurately, establish an ea...

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 Patents(China)
IPC IPC(8): G16H50/50G06Q10/04G06N3/12
CPCG06N3/126G06Q10/04G16H50/50
Inventor 戴松世
Owner 戴松世