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

System for judging prognosis conditions of liver cancer patients based on artificial neural network model

An artificial neural network, liver cancer technology, applied in the medical field, can solve the problem of lack of an early warning model for progression-free survival of liver cancer patients, achieve good individualized prediction performance, improve treatment effect, and save social resources.

Active Publication Date: 2020-12-01
BEIJING DITAN HOSPITAL CAPITAL MEDICAL UNIV
View PDF3 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, there is still a lack of an early warning model that can use the technical advantages of artificial neural networks to perform progression-free survival in patients with liver cancer

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
  • System for judging prognosis conditions of liver cancer patients based on artificial neural network model
  • System for judging prognosis conditions of liver cancer patients based on artificial neural network model
  • System for judging prognosis conditions of liver cancer patients based on artificial neural network model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0091] Example 1 The study included patients with baseline characteristics and survival analysis

[0092] Retrospective consecutive incorporated in January 2008 to December 2016 to Capital Medical University, Beijing Ditan Hospital first diagnosed 2890 cases of patients with hepatitis B associated primary liver cancer. In this study, the Ditan hospital ethics committee approval.

[0093] Inclusion criteria: (1) patients diagnosed with primary liver cancer; (2) the age of 18-75 years old; (3) hepatitis B surface antigen positive> 6 months. Excluded: (1) patients with cholangiocarcinoma (n = 196); a patient (4) of the lost (n; (2) patients with metastatic liver cancer (n = 85); (3) combined with other types of tumors (n = 59) = 139); (5) associated with other patients with chronic liver disease (n = 172); (6) clinical data were incomplete (n = 122). The final included 2117 cases of patients. Asia-Pacific liver cancer diagnostic criteria in line with standard clinical guidelines for l...

Embodiment 2

[0101] Example 2 Construction of progression-free survival in patients with hepatocellular carcinoma independent risk factor screening and ANN model

[0102] Literature review and summarize the clinical experiences, identify factors associated with survival of patients with liver cancer include: tumor characteristics, focused on the size of the tumor, invasion, metastasis vessels, satellite nodules; liver function include: albumin, total bilirubin, glutamyl peptidase (r-GGT) and the like. But these indicators with little regard to immune function and inflammatory markers in patients with liver cancer death. Therefore, in this study, a comprehensive collection of clinical data, including:

[0103] (1) demographic characteristics: age, sex, smoking history, drinking history, family history of liver cancer;

[0104] (2) The combined history: diabetes mellitus, hypertension, coronary heart disease, hyperlipidemia, cirrhosis of the liver;

[0105] (3) HBV-related features: HBeAg, HBV-...

Embodiment 3

[0133] Example 3 Comparative discrimination ANN model, the calibration of the model and other

[0134] ANN model constructed using Example 2 1-year progression-free patient training and validation sets to predict survival.

[0135] As a result, in the training concentration, ANN predicted that the underlying PFS probability of PFS probability (AUC) was 0.866 (95% CI 0.848-0.884); C-index was 0.782 (95% Ci 0.767-0.797). In validation concentration, ANN predicts that the underlying PFS of PFS in patients with liver cancer is 0.730 (95% CI 0.690-0.770); the C-index is 0.704 (95% CI 0.675-0.732) (Table 3).

[0136] Table 3 ANN models and other models predict the area and C index comparison of ROC curves in patients with liver cancer in 1 year.

[0137]

[0138]

[0139] The predicted 1 year PFS probability and the corresponding calibration curve of the actual observation probability Figure 4 In 4A, 4B, indicating that the ANN model in the training set and the validation concentrati...

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 provides a device for judging prognosis conditions of liver cancer patients based on an artificial neural network model. The device comprises: (1) an input module configured to input tumor feature information of a to-be-discriminated liver cancer patient; (2) a prognosis discrimination module which is set to comprise an artificial neural network model used for calculating the prognosis condition of the to-be-discriminated liver cancer patient based on the input information; and (3) an output module, wherein the output module is set to output the obtained prognosis condition. Theinvention also provides a method for grouping prognosis conditions of liver cancer patients by adopting the device.

Description

Technical field [0001] The present invention relates to the field of medical, and Background technique [0002] Statistics show that the death caused by liver cancer in the globe accounted for the fourth place in all tumors. Despite the discovery of multiple early monitoring indicators and regular imaging inspections, liver cancer can be diagnosed early, and the treatment level of liver cancer is gradually improved, but due to population growth and aging, the number of liver cancer caused by 2016, the number of people lived in all tumors The third growth in 2006 has grown to the second, and there is research forecast to 2040, the number will continue to rise, more than 69.6%. China's new and death cases account for more than 50% of the world, most of which are caused by HBV infection. [0003] A variety of treatment methods have been seen for liver cancer for different periods, but the recurrence and metastasis of patients after treatment remains the severe problem facing clinica...

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): G16H50/80G16H50/70G06N3/04G06N3/08
CPCG16H50/80G16H50/70G06N3/084G06N3/045
Inventor 杨志云刘晓利侯艺鑫王宪波江宇泳
Owner BEIJING DITAN HOSPITAL CAPITAL MEDICAL 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