Construction method and device of precancerous lesion prediction model of liver cancer and storage medium

By detecting the cfDNA peak map in body fluids, especially the peak value of the 450-550bp interval, a prediction model for precancerous liver cancer is constructed, and the problems of low sensitivity and dependence of precancerous liver cancer lesions screening in the prior art are solved, and non-invasiveness is achieved , high sensitivity and universal diagnosis improve the accuracy and efficiency of diagnosis.

CN119008022APending Publication Date: 2024-11-22GENETRON HEALTH (BEIJING) CO LTD +2
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202411078498.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-07
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

The prior art is difficult to achieve non-invasive, highly sensitive and universal screening methods for precancerous lesions with precancerous lesions below 2 cm, especially for precancerous lesions with low sensitivity and high dependence, which cannot meet clinical needs.

Method used

By detecting whether there is a peak in the cfDNA peak map in body fluids, especially the 450-550bp interval, a prediction model for precancerous liver cancer is constructed, and simple instruments and equipment and operating procedures are used to achieve the diagnosis of precancerous liver cancer.

Benefits of technology

It significantly improves the diagnostic sensitivity, specificity and accuracy of precancerous liver cancer lesions, is simple to operate, low cost, short detection cycle, and the effect is not inferior to the combined application of multiple biomarkers.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119008022A_ABST
    Figure CN119008022A_ABST
Patent Text Reader

Abstract

The invention provides a construction method and device of a liver cancer precancerous lesion prediction model and a storage medium, and belongs to the technical field of medical detection.The construction method comprises the steps that cfDNA in body fluid of healthy people and body fluid of liver cancer precancerous lesion patients is extracted; detecting the peak map of the cfDNA; and constructing a prediction model based on whether the peak graph has a peak value in a specific interval. The precancerous lesion of the liver cancer can be diagnosed only by detecting the cfDNA peak graph, complicated instrument equipment and experimental schemes are not needed, and the method is simple and rapid to operate, low in cost, short in detection period and high in universality.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of medical detection technology, and specifically to a method, device and storage medium for constructing a liver cancer precancerous lesion prediction model. Background Art

[0002] The incidence and mortality of liver cancer in my country are on the rise, and it has become a major threat to the health of the Chinese people. At present, there are about 90 million hepatitis patients and about 7 million cirrhosis patients in China, and the number of hepatocellular carcinoma (HCC)-related deaths is about 400,000 each year. The occurrence of liver cancer is closely related to the formation of precancerous lesions in the liver. The precancerous lesions of HCC usually occur on the basis of chronic hepatitis and cirrhosis. According to the current research progress in the field of clinical pathology, low-grade dysplastic nodules (LGDN) and high-grade dysplastic nodules (HGDN) are regarded as precancerous lesions of HCC.

[0003] The prognosis of liver cancer depends largely on the stage at which the tumor is detected. If liver cancer is found in the precancerous stage, radical treatment can prevent the occurrence of liver cancer, and its prognosis is significantly better than that of mid- and late-stage liver cancer. The 5-year survival rate will be greatly improved to 90% or more, while the cure rate of cancer found in the late stage is less than 10%. At present, pathological examination is the gold standard for diagnosing HCC precancerous lesions, but due to its invasiveness, patient compliance is very low and large-scale screening cannot be carried out. Routine clinical ultrasound examination, although it has the advantage of being non-invasive, has a low sensitivity of only 45% for detecting precancerous lesions below 2 cm, and is highly dependent on the operator, making it difficult to meet actual clinical needs.

[0004] Human body fluid samples contain various components such as cell-free DNA (cfDNA), proteins, cells, and vesicles (such as exosomes) from different tissues (including tumors). cfDNA refers to extracellular DNA molecules derived from any cell type found in body fluids. Therefore, plasma cfDNA is a mixture of DNA released by various tissues and organs. If it is cfDNA from tumor cells, it is usually called circulating tumor DNA (ctDNA). Studies have found that in healthy subjects, most of the cfDNA molecules in plasma come from the hematopoietic system, and the cfDNA fragment size distribution is mainly located at 167bp, usually present in low concentrations; however, in some cases, such as pregnancy, organ transplantation, or cancer (including precancerous lesions), the affected tissues will release additional DNA into the plasma, resulting in an increase in cfDNA concentration and a more complex pattern of fragment size distribution. The liver is an organ closely related to the blood. Cancer cells or precancerous lesions will quickly enter the blood after formation, which is very suitable for blood testing using liquid biopsy technology. Therefore, it is necessary to develop a new method for screening HCC precancerous lesions that is non-invasive, highly sensitive, and universal. Summary of the invention

[0005] To solve the above problems, the present invention provides a method, device and storage medium for constructing a prediction model for liver cancer precancerous lesions. Liver cancer precancerous lesions can be diagnosed by simply detecting the cfDNA peak graph, without the need for complex instruments and experimental schemes, with simple and fast operation, low cost, short detection cycle and strong universality.

[0006] In order to achieve the above object, the technical solution adopted by the present invention is as follows:

[0007] A method for constructing a prediction model for liver cancer precancerous lesions includes: extracting cfDNA from body fluids of healthy people and patients with liver cancer precancerous lesions; detecting a peak graph of cfDNA; and constructing a prediction model based on whether the peak graph has a peak in a specific interval.

[0008] Furthermore, the liver cancer precancerous lesions include: LGDN and HGDN.

[0009] Furthermore, the body fluid includes: urine, saliva, cerebrospinal fluid, blood, plasma and / or serum.

[0010] Furthermore, the specific interval is 450-550bp.

[0011] Furthermore, when there is a peak within 450-550bp, the test result is positive; when there is no peak within 450-550bp, the test result is negative.

[0012] A prediction model for liver cancer precancerous lesions, wherein the prediction model is constructed based on the above-mentioned construction method.

[0013] A diagnostic device for liver cancer precancerous lesions includes: a sample collection module, which is configured to extract cfDNA from the body fluid of a person to be tested; a data processing module, which is configured to detect the peak graph of cfDNA; and a discrimination module, which is configured to determine whether there is a precancerous lesion based on whether there is a peak in a specific interval of the peak graph.

[0014] Furthermore, the precancerous lesions of liver cancer include: LGDN and / or HGDN; the body fluids include: urine, saliva, cerebrospinal fluid, blood, plasma and / or serum.

[0015] Furthermore, the specific interval is 450-550bp; when there is a peak within 450-550bp, the test result is positive; when there is no peak within 450-550bp, the test result is negative.

[0016] A computer storage medium stores a computer program, wherein when the program is executed by a processor, the method for constructing the liver cancer precancerous lesion prediction model is implemented.

[0017] The beneficial effects of the technical solution provided by the embodiment of the present invention include: only one biomarker, namely cfDNA, combined with whether there is a peak value of cfDNA in a specific interval of the peak graph, can accurately predict liver cancer precancerous lesions. Compared with the prior art, the solution is simple, and only the cfDNA peak graph needs to be detected to diagnose HCC precancerous lesions, without puncture and complex instruments and experimental schemes, and the operation is simple and fast, low cost, short detection cycle, and strong universality. The prediction model of the present invention significantly improves the sensitivity, specificity and accuracy of diagnosing cancer, and the effect is not worse than the combined application of multiple biomarkers in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 The peak diagrams of different numbers of peaks in the 450-550 bp interval provided in the embodiment of the present invention, a represents 0 peaks, b represents 0 peaks, and c represents 1 peak. DETAILED DESCRIPTION

[0020] The present invention is further described in detail below by specific embodiments. However, it will be appreciated by those skilled in the art that the following examples are only used to illustrate the present invention and should not be considered as limiting the scope of the present invention. If specific techniques or conditions are not specified in the examples, they are carried out according to the techniques or conditions described in the literature in this area or according to the product instructions. If the manufacturer of the reagents or instruments used is not specified, they are all conventional products that can be obtained commercially.

[0021] As used herein, the words "comprises," "including," "having," or any other variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, article, or apparatus that includes listed elements is not necessarily limited to those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. The singular forms "a," "an," and "the" include plural referents unless the context clearly dictates otherwise.

[0022] Unless otherwise defined, all technical and scientific terms used in the present invention have the same meanings as those generally understood by those skilled in the art. In addition to the specific methods, equipment, and materials used in the embodiments, any methods, equipment, and materials of the prior art that are similar or equivalent to the methods, equipment, and materials in the embodiments of the present invention may be used to implement the present invention, based on the prior art mastery of those skilled in the art and the description of the present invention.

[0023] Unless otherwise stated, the experimental methods, detection methods, and preparation methods disclosed in the present invention all adopt conventional techniques in the field of molecular biology, immunology, laboratory science, gene sequencing technology, bioinformatics technology, and related fields.

[0024] The present invention provides a method for constructing a prediction model for liver cancer precancerous lesions, comprising:

[0025] S1. Extract cfDNA from body fluids of healthy people and patients with liver cancer precancerous lesions;

[0026] S2. Detect the peak graph of cfDNA;

[0027] S3. Construct a prediction model based on whether there is a peak in a specific interval of the peak graph.

[0028] The inventors collected a large number of clinical cases, and after large sample size analysis and in-depth research, revealed that only one biomarker, namely cfDNA, combined with whether there is a peak in a specific interval of the peak graph of cfDNA, can accurately predict liver cancer precancerous lesions. Compared with the prior art, the scheme is simple, and only the cfDNA peak graph needs to be detected to diagnose HCC precancerous lesions, without puncture and complex instruments and experimental schemes. The operation is simple and fast, the cost is low, the detection cycle is short, and the universality is strong. The prediction model of the present invention significantly improves the sensitivity, specificity and accuracy of diagnosing cancer, and the effect is not worse than the combined application of multiple biomarkers in the prior art.

[0029] Specifically, cfDNA is extracted from body fluids of healthy people and patients with liver cancer precancerous lesions, and the body fluids may be urine, saliva, cerebrospinal fluid, blood (whole blood), plasma, serum, etc., preferably blood. The liver cancer precancerous lesions include: LGDN and / or HGDN.

[0030] The extraction method can be a commercially available kit, such as the Apostle MiniMax from Nanke Zhengtu Company. TM The free DNA (cfDNA) separation and enrichment kit (Cat#: A17622-10, Version: P.27) was used to extract and purify free cfDNA from peripheral blood and collect it into a 1.5 mL centrifuge tube.

[0031] The peak graph of cfDNA was detected, and the extracted cfDNA was analyzed by electrophoresis using the Agilent 4200 TapeStation system (Agilent, USA) to generate a peak graph. Specifically:

[0032] (1) Take out the Genomic DNA Screen Tape and Genomic DNA Reagents from the 4°C refrigerator according to the number of samples, equilibrate them at room temperature for 5 min, vortex the Genomic DNA Reagents for 3-5 seconds, and centrifuge them for 3-5 seconds.

[0033] (2) Take a new 8-row plate and place it on a small yellow plate. Mark the tube wall as L, 0 (blank control), 1-6, and if there is a second row, mark it as 7-14. Add 10μL Genomic DNA Sample Buffer to each well, add 1μL Genomic DNA ladder to well L, do not add any reagents or samples to well 0, and add 1μL of the corresponding cfDNA sample to wells 1-14. After adding, cover the tube, vortex mix for 3-5s, and centrifuge for 3-5s. Open the tube cap and place it in the Agilent TapeStation. Check the gel image after the run. The system will automatically pop up the peak image results after the experiment.

[0034] A prediction model is constructed based on whether there is a peak in a specific interval of the peak graph. If a peak appears between 450-550 bp, the number of Peaks is counted as 1. If there is no Peak in this interval, the number of Peaks is counted as 0. Peaks in other length intervals are not counted in the number of Peaks, so the number of Peaks is also counted as 0. Figure 1 As shown, the cases where the effective peak numbers are 0 and 1 are respectively shown, and the peak is a "bell"-shaped vertex value between 450-550bp formed when the peak graph curve shows a trend of first increasing and then decreasing.

[0035] When the number of Peaks is 1, the test result is positive, which means that precancerous lesions of liver cancer have occurred; when the number of Peaks is 0, the test result is negative, which means that precancerous lesions of liver cancer have not occurred.

[0036] The present invention also provides a prediction model for liver cancer precancerous lesions, and the prediction model is constructed using the above-mentioned construction method.

[0037] The present invention also provides a diagnostic device for precancerous lesions of liver cancer, comprising: a sample collection module, which is configured to extract cfDNA from the body fluids of a person to be tested; a data processing module, which is configured to detect the peak graph of cfDNA; and a discrimination module, which is configured to determine whether there is a precancerous lesion based on whether there is a peak in a specific interval of the peak graph.

[0038] Specifically, the liver cancer precancerous lesions include: LGDN and / or HGDN; the body fluids include: urine, saliva, cerebrospinal fluid, blood, plasma and / or serum.

[0039] The specific interval is 450-550bp; when there is a peak within 450-550bp, the test result is positive; when there is no peak within 450-550bp, the test result is negative.

[0040] The present invention also includes an electronic device, comprising: one or more processors; a storage device, on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the above-mentioned method for constructing a liver cancer precancerous lesion prediction model.

[0041] The present invention also provides a computer storage medium on which a computer program is stored, wherein when the program is executed by a processor, the method for constructing the above-mentioned liver cancer precancerous lesion prediction model is implemented.

[0042] In order to better illustrate the embodiments of the present invention, the present invention is further described in detail below through specific examples.

[0043] Example 1

[0044] In this embodiment, the peak value of the peak graph is used for the diagnosis of liver cancer precancerous lesions in the general risk population. The present invention is used to detect plasma samples of 20 clinical LGDN patients, 23 clinical HGDN patients and 122 healthy people.

[0045] (1) The free cfDNA in peripheral blood was extracted and purified using the high-efficiency free DNA enrichment and separation kit of Nanke Zhengtu Company.

[0046] (2) The extracted cfDNA was subjected to Agilent 4200 peak analysis as described in the step instructions.

[0047] (3) If a peak appears between 450-550 bp, the number of peaks is counted as 1 and the test result is positive; otherwise, the result is negative. When analyzing performance, the following formula is used:

[0048] Sensitivity (%) = true positive / (true positive + false negative)

[0049] Specificity (%) = true negative / (true negative + false positive)

[0050] As shown in Table 1, the sensitivity of using Peaks to diagnose precancerous lesions is 37 / (37+6)=86%, and the specificity is 110 / (110+12)=90.2%. The sensitivity for low-grade dysplastic nodules is 17 / (17+3)=85%, and the sensitivity for high-grade dysplastic nodules is 20 / (20+3)=86.9%.

[0051] Table 1 Test results for general risk population

[0052]

[0053]

[0054]

[0055] Example 2

[0056] In this embodiment, the peak value of the peak graph is used for the diagnosis of liver cancer precancerous lesions in people with hepatitis and liver cirrhosis. The present invention is used to detect plasma samples of 20 clinical LGDN patients and 23 clinical HGDN patients and plasma samples of 51 hepatitis patients and 48 liver cirrhosis patients.

[0057] (1) The free cfDNA in peripheral blood was extracted and purified using the high-efficiency free DNA enrichment and separation kit of Nanke Zhengtu Company.

[0058] (2) The extracted cfDNA was subjected to Agilent 4200 peak analysis as described in the step instructions.

[0059] (3) If a peak appears between 450-550 bp, the number of peaks is counted as 1 and the test result is positive; otherwise, the result is negative.

[0060] The results are shown in Table 2. The sensitivity of using Peaks to diagnose precancerous lesions is 37 / (37+6)=86%, and the specificity is 78 / (78+22)=78.8%. Among them, the specificity in the hepatitis population is 41 / (41+10)=80.4%, and the specificity in the cirrhosis population is 36 / (36+12)=75%.

[0061] Table 2 Test results for hepatitis and cirrhosis populations

[0062]

[0063]

[0064] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for constructing a prediction model for liver cancer precancerous lesions, characterized in that: include: Extract cfDNA from body fluids of healthy people and patients with liver cancer precancerous lesions; Detection of the peak graph of cfDNA; A prediction model is constructed based on whether there is a peak in a specific interval of the peak graph.

2. The construction method according to claim 1, characterized in that: The liver precancerous lesions include: LGDN and / or HGDN.

3. The construction method according to claim 1, characterized in that: The body fluids include: urine, saliva, cerebrospinal fluid, blood, plasma and / or serum.

4. The construction method according to claim 1, characterized in that: The specific interval is 450-550 bp.

5. The construction method according to claim 4, characterized in that: When there is a peak within 450-550 bp, the test result is positive; When there is no peak within 450-550bp, the test result is negative.

6. A prediction model for liver cancer precancerous lesions, characterized in that: The prediction model is constructed based on the construction method described in any one of claims 1-5.

7. A diagnostic device for liver cancer precancerous lesions, characterized in that: include: A sample collection module, which is configured to extract cfDNA from the body fluid of the person to be tested; A data processing module, configured to detect a peak graph of cfDNA; A discrimination module is configured to determine whether there is a precancerous lesion based on whether there is a peak in a specific interval of the peak graph.

8. The diagnostic device according to claim 7, characterized in that The liver cancer precancerous lesions include: LGDN and / or HGDN; The body fluids include: urine, saliva, cerebrospinal fluid, blood, plasma and / or serum.

9. The diagnostic device according to claim 8, characterized in that The specific interval is 450-550bp; When there is a peak within 450-550 bp, the test result is positive; When there is no peak within 450-550bp, the test result is negative.

10. A computer storage medium, characterized in that: A computer program is stored thereon, wherein when the program is executed by a processor, the method for constructing a liver cancer precancerous lesion prediction model as described in any one of claims 1-5 is implemented.

Citation Information

Cited By

  • Multi-model fused lung squamous cell carcinoma survival probability prediction system

    CN120690451A