Application, construction method and system for preparing ALF early prediction product based on cfDNA concentration

By detecting cfDNA concentration and alpha-fetoprotein, an early prediction model of ALF was constructed, which solved the problem of insufficient early warning of ALF, and achieved high sensitivity and specific liver failure prediction, simplified the detection process and reduced costs.

CN119020482AActive Publication Date: 2024-11-26GENETRON HEALTH (BEIJING) CO LTD +3
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
CN202411256886.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-09
Publication Date
2024-11-26
Estimated Expiration
2044-09-09

AI Technical Summary

Technical Problem

The existing technology lacks effective early warning methods for ALF, which leads to rapid progress of liver failure and difficulty in treatment. The existing comprehensive internal medicine treatment and artificial liver treatment have limited effects, and there is a lack of early warning markers and models for ALF.

Method used

ALF early prediction products are prepared based on cfDNA concentration. By detecting the concentration of cfDNA and alpha-fetoprotein, a model is constructed to make early predictions of ALF, and the threshold is determined using the ROC curve and Yorden index, providing an early warning method with simple operation and low cost.

Benefits of technology

It has achieved high sensitivity and specificity early prediction of ALF, with a sensitivity of more than 73%, a specificity of 100%, no need for puncture and complex instruments, and a short detection cycle and strong universality.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119020482A_ABST
    Figure CN119020482A_ABST
Patent Text Reader

Abstract

The invention provides application, a construction method and a system for preparing an ALF early prediction product based on cfDNA concentration, and belongs to the technical field of medical detection, and the ALF early prediction product is used for carrying out acute hepatic failure early prediction of serious liver injury or rapid clinical deterioration on a to-be-detected person without previous liver diseases. According to the method, the hepatic failure can be early warned only by detecting the cfDNA concentration or increasing few indexes, puncture and complex instruments and equipment and experimental schemes are not needed, and the method is easy 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 belongs to the field of medical detection technology, and specifically relates to the use, construction method and system of preparing ALF early prediction products based on cfDNA concentration. Background Art

[0002] Liver failure is a serious liver damage caused by multiple factors, resulting in severe disorders or decompensation of synthesis, detoxification, metabolism and biotransformation functions, and a group of clinical syndromes with jaundice, coagulopathy, hepatorenal syndrome, hepatic encephalopathy and ascites as the main manifestations. Based on the medical history, onset characteristics and disease progression rate, my country divides liver failure into four categories: acute liver failure (ALF), subacute liver failure (SALF), acute on chronic liver failure (ACLF) and chronic liver failure (CLF). Among them, ALF refers to a type of liver failure with severe liver damage and rapid clinical deterioration in patients without previous liver disease.

[0003] It has become a clinical consensus that liver failure progresses rapidly, is difficult to treat, and has a high mortality rate. Once liver failure occurs, the existing comprehensive medical treatment and artificial liver treatment have limited effects. Liver transplantation is currently the most effective treatment, but it is subject to many restrictions such as scarce liver sources and high medical costs. If the risk of liver failure in patients can be predicted early and timely intervention can be made before liver failure occurs to prevent the progression of the disease, it will undoubtedly effectively improve the prognosis of patients and reduce the economic burden on patients. At present, scholars at home and abroad have carried out research on early warning models related to ACLF and have obtained good predictive capabilities. However, there are few studies on ALF and related early warning models at home and abroad, and most of the research focuses on ACLF.

[0004] Therefore, it is necessary to develop a new ALF early warning method that is simple to operate, cost-controlled, highly accurate and universal, so as to improve the level of liver failure prevention and treatment in my country and thereby increase the survival rate of patients. Summary of the invention

[0005] To solve the above problems, the present invention provides the use, construction method and system of preparing ALF early prediction products based on cfDNA concentration. Only by detecting cfDNA concentration or increasing a small number of indicators can early warning of liver failure be carried out, without puncture and complex instruments and equipment and experimental schemes. The operation is simple and fast, 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] The purpose of preparing an ALF early prediction product based on cfDNA concentration, wherein the ALF early prediction product is used for early prediction of acute liver failure with severe liver damage or rapid clinical deterioration in subjects without previous liver disease.

[0008] Furthermore, the cfDNA is extracted from the body fluid of the subject, and the body fluid includes urine, saliva, cerebrospinal fluid, blood, plasma or serum.

[0009] Furthermore, the first optimal threshold for distinguishing between acute liver failure and healthy individuals is determined by drawing ROC curves of patients with acute liver failure and healthy people in the training set, and using the Youden index as the first optimal threshold for distinguishing between patients with acute liver failure and healthy people.

[0010] A kit for early prediction of ALF, comprising: an alpha-fetoprotein detection reagent and a cfDNA extraction reagent; based on the concentrations of the alpha-fetoprotein and cfDNA, early prediction of severe liver damage and acute liver failure with rapid clinical deterioration is performed on a subject without previous liver disease.

[0011] Furthermore, the cfDNA is extracted from the body fluid of the subject, and the body fluid includes urine, saliva, cerebrospinal fluid, blood, plasma or serum.

[0012] A method for constructing an early prediction model for ALF comprises: determining a training set and a validation set, both of which include patients with acute liver failure and healthy people; collecting cfDNA concentration, alpha-fetoprotein concentration, age and gender information of samples in the training set and the validation set; constructing a model based on the cfDNA concentration of the training set or the cfDNA concentration, alpha-fetoprotein concentration, age and gender to obtain an optimal threshold; and performing validation in the validation set based on the model and the optimal threshold.

[0013] Furthermore, the cfDNA is extracted from the body fluid of the subject, which includes urine, saliva, cerebrospinal fluid, blood, plasma or serum; the alpha-fetoprotein concentration is detected through blood, plasma or serum.

[0014] Furthermore, when the model is constructed using cfDNA concentration, when the cfDNA concentration is not less than the first optimal threshold, the result is judged to be positive, otherwise it is negative; the first optimal threshold is determined by drawing the ROC curves of patients with acute liver failure and healthy people in the training set, and using the Youden index as the first optimal threshold for distinguishing patients with acute liver failure from healthy people.

[0015] Furthermore, when the model is constructed using cfDNA concentration, alpha-fetoprotein concentration, age and gender, gender is standardized by assigning a value of 1 to males and 0 to females; the model is:

[0016] ALFscreen=-6.04297-0.01424Age+0.46453Gender+0.11339AFP+6.55116Qubit; when the ALFscreen value is not less than the second optimal threshold, the result is judged to be positive, otherwise it is negative; the second optimal threshold is determined by drawing the ROC curves of patients with acute liver failure and healthy people in the training set, and using the Youden index as the second optimal threshold for distinguishing patients with acute liver failure from healthy people.

[0017] An ALF early prediction model system comprises: a processor and a memory, wherein the processor can construct an ALF early prediction model according to the construction method described in any one of claims 6 to 9 and perform sample information processing; the sample information processing comprises: inputting the cfDNA concentration or cfDNA concentration, alpha-fetoprotein concentration, age and gender information of the individual to be tested into the ALF early prediction model in the processor; the processor evaluates the risk assessment result of the sample to be tested based on the ALF early prediction model; and the memory is used to store the risk assessment result.

[0018] The technical solution provided by the present invention brings about the following beneficial effects: the prior art lacks early warning markers for ALF, and the present invention proposes corresponding biomarkers for early prediction of ALF and a corresponding model to achieve early prediction of ALT; secondly, the ALT early prediction model proposed in the present application has high sensitivity and specificity, with a sensitivity of more than 73% and a specificity of 100%; finally, only the detection of cfDNA concentration or a small increase in indicators is required to provide early warning of liver failure, without the need for puncture and complex instruments and equipment and experimental schemes, and the operation is simple and fast, the cost is low, the detection cycle is short, and the universality is strong. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] 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.

[0020] Figure 1 The ROC curve for early prediction of ALF based on cfDNA concentration provided in Example 1 of the present invention;

[0021] Figure 2 This is the ROC curve for early prediction of ALF based on the ALFscreen model provided in Example 2 of the present invention. DETAILED DESCRIPTION

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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.

[0026] The advance prediction time for early prediction of acute liver failure in the present invention is 1-2 weeks.

[0027] An embodiment of the present invention provides the use of preparing an ALF early prediction product based on cfDNA concentration, wherein the ALF early prediction product is used for early prediction of acute liver failure with severe liver damage or rapid clinical deterioration in a subject without previous liver disease.

[0028] After extensive and in-depth research, the present invention found that the mechanisms leading to ALF can be summarized into two categories: the first category is that pathogens or toxic substances directly damage organelles or trigger cell cascade pathways, disrupting cellular homeostasis. The second category is that the immune response (including innate and adaptive) ultimately converges on the liver cell death pathway, including apoptosis, autophagy, and necrosis (also known as programmed necrosis), leading to immune-mediated liver damage. Regardless of which of the above mechanisms, a large number of liver cells will cause apoptosis and necrosis, and the liver is an organ closely related to the blood. A large amount of cfDNA released by liver cell apoptosis or necrosis will quickly enter the blood, causing the cfDNA concentration in the blood to increase sharply, which is very suitable for blood testing using liquid biopsy technology. The present invention uses the concentration of cfDNA for early prediction of ALT, with high sensitivity and specificity.

[0029] Specifically, the cfDNA is extracted from the body fluid of the subject, and the body fluid includes urine, saliva, cerebrospinal fluid, blood, plasma or serum.

[0030] Specifically, the first optimal threshold for distinguishing between acute liver failure and healthy individuals is determined by drawing ROC curves of patients with acute liver failure and healthy people in the training set, and using the Youden index as the first optimal threshold for distinguishing between patients with acute liver failure and healthy people. Preferably, the first optimal threshold of the present invention is 0.823.

[0031] An embodiment of the present invention also provides a kit for early prediction of ALF, comprising: an alpha-fetoprotein detection reagent and a cfDNA extraction reagent; based on the concentrations of the alpha-fetoprotein and cfDNA, early prediction of severe liver damage and acute liver failure with rapid clinical deterioration is performed on a subject without previous liver disease.

[0032] Alpha-fetoprotein, or AFP, is a special protein in the blood during the embryonic period. It can only be synthesized in the liver cells and yolk sac of the fetus. Especially at 10-13 weeks of pregnancy, the content of this protein in the fetus is the highest, reaching 300-500 mg in 100 ml of blood, and then gradually decreases. After birth to 1 year old, most of the alpha-fetoprotein is replaced by albumin, and the alpha-fetoprotein level drops to the adult level (<20ng / ml). Because its concentration in the fetal blood is high and its content in the serum of healthy adults is very low, its full name is alpha-fetoprotein. When ALT occurs, it is often accompanied by the death and regeneration of a large number of liver cells. These new liver cells restore the ability to synthesize alpha-fetoprotein, so the concentration of alpha-fetoprotein in the blood can reach up to 2000ng / ml. This is the principle that the detection of alpha-fetoprotein can assist in the early prediction of ALT.

[0033] The cfDNA is extracted from the body fluid of the subject, and the body fluid includes urine, saliva, cerebrospinal fluid, blood, plasma or serum.

[0034] The extraction reagent adopts an existing commercially available product.

[0035] The embodiment of the present invention also provides a method for constructing an ALF early prediction model, comprising:

[0036] S1 determines a training set and a test set, both of which include patients with acute liver failure and healthy subjects.

[0037] Preferably, the training set and the test set are randomly divided in a ratio of 2:1.

[0038] S2 collects the cfDNA concentration, alpha-fetoprotein concentration, age, and gender information of samples in the training set and the test set.

[0039] The cfDNA is extracted from the body fluid of the subject, and the body fluid includes urine, saliva, cerebrospinal fluid, blood, plasma or serum. The alpha-fetoprotein concentration is detected by blood, plasma or serum.

[0040] AFP detection: Separate the plasma, draw 750 μl of plasma into a 1.5 ml EP tube, and use the AFP assay kit (chemiluminescent microparticle immunoassay, CMIA) to perform chemiluminescent labeling immunoassay of the AFP target protein molecule on the ARCHITECT i2000SR fully automatic immunoassay instrument (Abbott, USA).

[0041] cfDNA extraction: using Apostle MiniMax from Nanke Zhengtu TM The free DNA (cfDNA) separation and enrichment kit (Cat#: A17622-10, Version: P.27) extracts free cfDNA from plasma and collects it into a 1.5 mL centrifuge tube.

[0042] cfDNA concentration determination: The extracted cfDNA was measured using Qubit 4.0 (Life Technologies, Inc., USA) in a light-proof environment. According to the number of samples to be tested, 199 μL Qubit TM dsDNA HS buffer + 1μL Qubit TMPrepare the mixed solution of N+1 system according to the ratio of dsDNAHSreagent. Select 5mL, 15mL or 50mL centrifuge tube according to the volume of the mixed solution, add the above corresponding reagents to the centrifuge tube, mix it upside down 4-5 times, vortex mix it for 3-5s, and centrifuge it for 3-5s. Add 198μL of the mixed solution just prepared to each 0.5mL PCR thin-walled tube (flat cover), vortex mix the DNA product collected in step 1 in the 1.5mL centrifuge tube for 10s and then centrifuge it. After checking the sample number, take 2μL of DNA in turn and add it to the 198μL reaction system, vortex mix it for 3-5s, centrifuge it for 3-5s, and measure the DNA concentration after reacting in the dark for 2min.

[0043] S3 built a model based on the training set cfDNA concentration or cfDNA concentration, alpha-fetoprotein concentration, age, and gender. The ROC curves of patients with acute liver failure and healthy subjects were drawn in the training set, and the Youden index was used as the optimal threshold for distinguishing patients with acute liver failure from healthy subjects.

[0044] S4 performs validation in a validation set based on the model and the optimal threshold.

[0045] When the model is constructed using cfDNA concentration, when the cfDNA concentration is not less than the first optimal threshold, the result is judged to be positive, otherwise it is negative; the first optimal threshold is determined by drawing the ROC curves of patients with acute liver failure and healthy people in the training set, and using the Youden index as the first optimal threshold for distinguishing patients with acute liver failure from healthy people.

[0046] When the model is constructed using cfDNA concentration, alpha-fetoprotein concentration, age, and gender, gender is standardized by assigning a value of 1 to males and 0 to females; the model is:

[0047] ALFscreen=-6.04297-0.01424Age+0.46453Gender+0.11339AFP+6.55116Qubit;

[0048] When the ALFscreen value is not less than the second optimal threshold, the result is positive, otherwise it is negative;

[0049] The second optimal threshold is determined by drawing ROC curves of patients with acute liver failure and healthy people in the training set, and using the Youden index as the second optimal threshold for distinguishing patients with acute liver failure from healthy people. Preferably, the value of the second optimal threshold is 0.043.

[0050] The two models provided by the present invention can meet the requirements of a sensitivity greater than 73% and a specificity of 100%.

[0051] An embodiment of the present invention also provides an ALF early prediction model system, comprising: a processor and a memory, wherein the processor can construct an ALF early prediction model according to the above-mentioned construction method and perform sample information processing; the sample information processing comprises: inputting the cfDNA concentration or cfDNA concentration, alpha-fetoprotein concentration, age and gender information of the individual to be tested into the ALF early prediction model in the processor; the processor evaluates the risk assessment result of the sample to be tested based on the ALF early prediction model; and the memory is used to store the risk assessment result.

[0052] The electronic device of this embodiment may include a memory, a processor, a bus and a communication interface. The memory, the processor and the communication interface are electrically connected to each other directly or indirectly to achieve data interaction and transmission.

[0053] In this embodiment, the memory can be, but is not limited to, random access memory (RAM), read only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable read-only memory (EEPROM), etc.

[0054] In this embodiment, the processor can be an integrated circuit chip with signal processing capabilities. The processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FGPA) or other programmable logic devices, discrete gates or crystal logic devices, discrete hardware components.

[0055] In practical applications, the ALF early prediction model system can be an electronic device, which can be a server, a cloud platform, a mobile phone, a tablet computer, a laptop computer, an ultra-mobile personal computer (UMPC), a handheld computer, a netbook, a personal digital assistant (PDA), a wearable electronic device, a virtual reality device, and the like. Therefore, the embodiments of the present application do not limit the types of electronic devices.

[0056] In this embodiment, a device for detecting cfDNA and alpha-fetoprotein is also provided, which can simultaneously detect the concentrations of cfDNA and alpha-fetoprotein, including sample acquisition, a sample plasma concentration detection device, and a sample plasma cfDNA and alpha-fetoprotein concentration real-time display device.

[0057] In this embodiment, a computer readable medium is also provided, on which a computer program is stored, and when the computer is executed by a processor, the random forest model can be constructed. The computer readable medium includes: a USB flash drive, a mobile hard disk, a read-only memory, a random access memory, a magnetic disk, a floppy disk or an optical disk, and other media that can store program codes.

[0058] Example 1

[0059] Based on the application of cfDNA concentration in the early prediction of ALF, the present invention tested 53 plasma samples collected from patients with clinical acute liver failure and 60 plasma samples from healthy people. It includes:

[0060] 1. The test samples were extracted and purified from the free cfDNA in the peripheral blood using the high-efficiency free DNA enrichment and separation kit of Nanke Zhengtu Company.

[0061] 2. Perform Qubit concentration determination on the extracted cfDNA as described in the step instructions.

[0062] 3. The test samples are randomly divided into training set and validation set in a ratio of about 2:1. The sample conditions of the training set and validation set are shown in Tables 1 and 2.

[0063] Table 1. Division of training set and validation set

[0064] - Training set Validation set total Acute liver failure 34 19 53 Healthy people 42 18 60 total 76 37 113

[0065] The ROC curve was drawn using the samples of the training set to determine the optimal cut-off value of cfDNA concentration. Figure 1As shown in the figure, the AUC (area under the curve) of cfDNA concentration is 0.964, and the optimal cut off is 0.823. When the cfDNA concentration is not less than 0.823 ng / μL, the result is judged to be positive.

[0066] When analyzing performance, the following formula is used:

[0067] Sensitivity (%) = true positive / [true positive + false negative]

[0068] Specificity (%) = true negative / [true negative + false positive]

[0069] Therefore, in the training set, when cut off = 0.823, the sensitivity is 30 / (30+4) = 88.2% and the specificity is 41 / (41+1) = 97.6%.

[0070] 4. The performance of cfDNA concentration was verified using the validation set data, and the AUC was 0.918. When the cut off was 0.823, the sensitivity was 14 / (14+5)=73.7%, and the specificity was 18 / (18+0)=100%.

[0071] Table 2 Training set and validation set samples

[0072]

[0073]

[0074]

[0075]

[0076] Example 2

[0077] The embodiment of the present invention is based on the establishment of a multi-index ALT early prediction model and its application in ALT early prediction, and tests the collected plasma samples of 53 clinical acute liver failure patients and 60 healthy people. It includes:

[0078] 1. The division of samples, training sets and validation sets in Example 2 is the same as that in Example 1, and the detection data of age (Age), gender (Gender) and alpha-fetoprotein (AFP) are also included. Gender is assigned a value of 1 for males and 0 for females for standardization. The training set and validation set samples are shown in Table 3.

[0079] 2. Use the data of the training set to build a logistic regression model. The logistic regression model ALFscreen was developed using the logistic regression model package {glmnet} of R version 4.3.2. The model formula is:

[0080] ALFscreen=-6.04297-0.01424Age+0.46453Gender+0.11339AFP+6.55116Qubit

[0081] like Figure 2 As shown, the model AUC (area under the curve) is 0.980, and the optimal cut off = 0.043. When the model score is not less than 0.043, the result is positive, otherwise it is negative. The sensitivity of the model for comprehensive judgment of acute liver failure is 32 / (32+2) = 94.1%, and the specificity is 42 / (42+0) = 100%.

[0082] 3. The performance of the logistic regression model ALFscreen was verified using the data from the validation set. In the validation set, the AUC of the ALFscreen model was 0.974, and the sensitivity of the model for comprehensive judgment of acute liver failure was 16 / (16+3)=84.2%, and the specificity was 18 / (18+0)=100%.

[0083] Table 3 Training set and validation set samples

[0084]

[0085]

[0086]

[0087]

[0088] 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. Use of a product for early prediction of ALF based on cfDNA concentration, characterized in that: The ALF early prediction product is used for early prediction of acute liver failure with severe liver damage or rapid clinical deterioration in subjects without previous liver disease.

2. The use according to claim 1, characterized in that The cfDNA is extracted from the body fluid of the subject, and the body fluid includes urine, saliva, cerebrospinal fluid, blood, plasma or serum.

3. The use according to claim 1, characterized in that The first optimal threshold for distinguishing between acute liver failure and healthy individuals is determined by drawing ROC curves of acute liver failure patients and healthy subjects in the training set, and using the Youden index as the first optimal threshold for distinguishing between acute liver failure patients and healthy subjects.

4. A kit for early prediction of ALF, characterized in that: include: AFP detection reagents and cfDNA extraction reagents; Based on the concentrations of alpha-fetoprotein and cfDNA, early prediction of severe liver damage and acute liver failure with rapid clinical deterioration is performed in subjects without previous liver disease.

5. The kit according to claim 4, characterized in that The cfDNA is extracted from the body fluid of the subject, and the body fluid includes urine, saliva, cerebrospinal fluid, blood, plasma or serum.

6. A method for constructing an ALF early prediction model, characterized in that: include: Determining a training set and a validation set, wherein both the training set and the validation set include patients with acute liver failure and healthy subjects; The cfDNA concentration, alpha-fetoprotein concentration, age, and gender information of the samples in the training and validation sets were collected; Build a model based on the training set cfDNA concentration or cfDNA concentration, alpha-fetoprotein concentration, age, and gender to obtain the optimal threshold; Validation was performed in a validation set based on the model and the optimal threshold.

7. The construction method according to claim 6, characterized in that: The cfDNA is extracted from the body fluids of the subject, which include urine, saliva, cerebrospinal fluid, blood, plasma or serum; the alpha-fetoprotein concentration is detected by blood, plasma or serum.

8. The construction method according to claim 6, characterized in that: When the model is constructed using cfDNA concentration, if the cfDNA concentration is not less than the first optimal threshold, the result is judged as positive, otherwise it is negative; The first optimal threshold is determined by drawing ROC curves of patients with acute liver failure and healthy people in the training set, and using the Youden index as the first optimal threshold for distinguishing patients with acute liver failure from healthy people.

9. The construction method according to claim 6, characterized in that: When the model was constructed using cfDNA concentration, alpha-fetoprotein concentration, age, and sex; Gender is standardized by assigning 1 to male and 0 to female; The model is: ALFscreen=-6.04297-0.01424Age+0.46453Gender+0.11339AFP+6.55116Qubit; When the ALFscreen value is not less than the second optimal threshold, the result is positive, otherwise it is negative; The second optimal threshold is determined by drawing ROC curves of patients with acute liver failure and healthy people in the training set, and using the Youden index as the second optimal threshold for distinguishing patients with acute liver failure from healthy people.

10. An ALF early prediction model system, characterized in that: include: processor and memory, The processor may construct an ALF early prediction model and perform sample information processing according to the construction method described in any one of claims 6 to 9; The sample information processing includes: inputting the cfDNA concentration or cfDNA concentration, alpha-fetoprotein concentration, age and gender information of the individual to be tested into the ALF early prediction model in the processor; the processor evaluates the risk assessment result of the sample to be tested based on the ALF early prediction model; The memory is used to store the risk assessment result.

Citation Information

Patent Citations

  • Method for detecting necrosis degree of hepatic cells through level of plasma free DNA

    CN101955998A

  • Method for hepatitis B virus intrahepatic integration condition detection through peripheral blood of infected patient

    CN109082469A

  • Method for detecting peripheral blood of infected person with condition of hepatitis B virus intrahepatic integration

    CN110564855A

  • Use of HDAC2 in preparation of marker for evaluating progress of hepatic inflammation of acute hepatic failure

    CN112195236A

  • Early warning model, method and system for acute kidney injury of children

    CN115575634A