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

Cervical cancer precancerous early lesion stage diagnosis model and establishment method

A diagnostic model and method establishment technology, applied in the field of medical testing, can solve the problem of insufficient accuracy of the results, and achieve the effect of easy data and strong practicality

Inactive Publication Date: 2020-09-25
GUANGZHOU KINGMED TRANSFORMATIVE MEDICINE INST CO LTD +1
View PDF7 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The correlation between viral load and different stages of cervical precancerous lesions has been confirmed by research, and some studies have tried to use HPV viral load for auxiliary disease diagnosis, but there are problems such as insufficient accuracy of the results

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
  • Cervical cancer precancerous early lesion stage diagnosis model and establishment method
  • Cervical cancer precancerous early lesion stage diagnosis model and establishment method
  • Cervical cancer precancerous early lesion stage diagnosis model and establishment method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] A diagnostic model for the early stage of cervical cancer precancerous lesions, the process of which is as follows: figure 2 As shown, established by the following method:

[0041] S1: Obtain the HPV DNA test result data and cytological diagnosis result data of each subject sample, as data factors, evaluate as normal samples or cervical precancerous lesion samples according to the sample conditions, and construct data sets respectively. The specific method is as follows:

[0042] S11: Data collection.

[0043] HPV DNA of cervical smear cells and TCT cytology clinical detection data of 31954 cases. Extract HPV infection status (ie negative or positive), HPV viral load (VL), stage of cytological diagnosis (TCT cervical precancerous lesion stage, ie TCT stage), age (age), vaginitis (BV), fungal infection (fungus) and other diagnostic results.

[0044] S12: Build a data set.

[0045] Construct the data set, which is composed of the above-mentioned viral load (VL), cyt...

Embodiment 2

[0071] Validation of a diagnostic model for the precancerous early lesion stage of cervical cancer.

[0072] Collect new data set, specific content is with the S11 step in embodiment 1, as test set, its flow process is as follows image 3 shown.

[0073] The newly collected data is predicted by the cervical cancer precancerous early lesion stage diagnosis model obtained in Example 1, and the predicted probability values ​​of different precancerous lesion stages are compared, and the highest predicted probability value is selected as the diagnosis result of the disease stage, and the results are shown in the table 4. For the ROC curve of the model for different disease stages, see Figure 4 .

[0074] Table 4.

[0075]

[0076] It can be seen from the above results that the diagnostic model of the stage of early precancerous lesions of cervical cancer of the present invention is used to predict and evaluate the stage of early precancerous lesions of cervical cancer, and ...

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 relates to a cervical cancer precancerous early lesion stage diagnosis model and an establishment method, and belongs to the technical field of medical detection. The method comprises the following steps: S1, acquiring HPV DNA detection result data and cytological diagnosis result data of each subject sample, and respectively constructing data sets; S2, performing equalization processing on the data sets; S3, performing multi-factor logistic regression model construction on the equalized data sets in different data factor combination modes to obtain a model with an optimal AUC value of an ROC curve in different combination mode construction models; S4, carrying out machine learning training on the to-be-trained model obtained in the previous step according Xgboost, random forest, a decision tree, a neural network or an SVM algorithm to obtain a model with the optimal AUC value in different algorithm models. According to the invention, the positive prediction value of thefinally-obtained cervical cancer precancerous early lesion stage diagnosis model can reach 0.8706 for a patient with precancerous lesion stages as the key point, and the negative prediction value canreach 0.946.

Description

technical field [0001] The invention relates to the technical field of medical detection, in particular to a diagnostic model of cervical precancerous early lesion stages and a method for establishing it. Background technique [0002] Cervical cancer is a malignant disease that seriously infringes on women's health, with a high incidence rate and a growing trend. Existing strategies to prevent cervical cancer are screening of cytology and HPV DNA levels for women of appropriate age. However, due to the high requirements for testing equipment and doctor resources for cytology screening, the promotion of screening in areas with insufficient resources is largely limited. A growing body of research hopes to explore ways to infer disease status from DNA alone. [0003] However, due to the high false positive rate of pure HPV DNA test results, which leads to an excessively high colposcopy referral rate, therefore, it is necessary to combine other indicators to improve the accura...

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): G16H50/50G06N20/00
CPCG16H50/50G06N20/00
Inventor 孟博曾征宇李桂彬郑宝文于世辉
Owner GUANGZHOU KINGMED TRANSFORMATIVE MEDICINE INST CO LTD
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