A method for scoring the cure probability of potential treatment options based on patient detection information

A treatment plan and technology for detecting information, applied in the field of deep learning analysis, can solve problems such as real-time update prediction methods without treatment plans

Active Publication Date: 2022-07-12
HUAZHONG UNIV OF SCI & TECH
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At the same time, there is currently no real-time update prediction method for the treatment plan. This invention hopes to use the patient's examination results and treatment plan to give a treatment plan with a higher probability of cure, and provide reasonable suggestions and references for doctors.

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
  • A method for scoring the cure probability of potential treatment options based on patient detection information
  • A method for scoring the cure probability of potential treatment options based on patient detection information
  • A method for scoring the cure probability of potential treatment options based on patient detection information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] The inventors collected a total of 340 cohorts of 340 patients with novel coronavirus pneumonia from Liyuan Hospital affiliated to Tongji Medical College of Huazhong University of Science and Technology, and collected their clinical examination information and CT results, treatment plans and final outcomes. Clinical information refers to the values ​​of various items of clinical testing, including routine test results such as blood test and urine test, and nucleic acid test results; treatment plan refers to the daily medication and treatment methods from admission to discharge, including antiviral drugs, traditional Chinese medicine and Chinese patent medicines, antibacterial drugs, anti-inflammatory factor storms, and ventilation schemes (for example, there can be thirty types shown in Table 1 below, each of which is recorded as a treatment method); the outcomes are divided into death and discharge from the hospital There are two categories. If a patient is transferred ...

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 belongs to the field of deep learning analysis, and discloses a method for scoring the cure probability of a potential treatment plan based on patient detection information. The method includes the following steps: (S1) collecting training data; (S2) establishing a logistic regression model and training; (S3) respectively establishing the unet model and the three-dimensional convolutional neural network model and training; (S4) complementing the training data, and obtaining the survival score of any patient corresponding to the training data in each day of the treatment process; (S5) Establish a long short-term memory network LSTM model and train it; (S6) Randomize a potential treatment plan, and predict the survival score on the N+2 day, so that the potential treatment plan can be scored. By improving the overall process design of the method and the system, the present invention can specifically quantify the patient's condition from the perspective of big data analysis, and score the cure probability of the potential treatment plan.

Description

technical field [0001] The invention belongs to the field of deep learning analysis, and more particularly, relates to a method for scoring the cure probability of a potential treatment plan based on patient detection information. A system corresponding to the method can also evaluate the cure probability of a potential treatment plan based on the patient detection information. score. Background technique [0002] For a type of disease, the detection values ​​of patients often contain a lot of information. At present, doctors' treatment for patients is based on experience and their own judgments on the patient's condition. Individual differences are large, and misdiagnosis may occur due to various reasons, and the diagnosis plan may also be given ill-considered. [0003] Pulmonary diseases, in addition to being reflected in clinical examination information (such as blood tests and urine tests), can often be judged by CT images of patients' lungs. Combining various data can...

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): G16H50/20G16H70/20G16H50/30G16H50/70G16H50/50G16H20/10G06N3/04G06N3/08
CPCG16H50/20G16H70/20G16H50/30G16H50/70G16H50/50G16H20/10G06N3/08G06N3/045
Inventor 薛宇苟宇杰宁万山
Owner HUAZHONG UNIV OF SCI & TECH
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