Non-invasive NASH scoring calculation and risk stratification methods, systems, devices and media

Abstract

This invention discloses a non-invasive method, system, device, and medium for calculating NASH diagnostic scores and risk stratification based on clinical and biochemical indicators. The method includes: collecting the target patient's age, height, weight, AST, ALT, and other information required for determining metabolic syndrome; calculating BMI, MetS values, and the AST / ALT ratio; calculating a NASH predictive score based on age, MetS, BMI, AST, and the AST / ALT ratio; and performing three-zone risk stratification of the target patient according to a dual threshold determined by the development cohort, where 0.37 is used as the rule-out cutoff point for 90% sensitivity, and 1.88 is used as the rule-in cutoff point for 90% specificity, classifying the target patient into a low-risk zone, a gray zone, or a high-risk zone. This invention can be used for non-invasive auxiliary screening, risk stratification, and clinical decision support for NASH.

Description

Technical Field

[0001] This invention relates to a method, system, device, and medium for non-invasive non-alcoholic steatohepatitis (NASH) diagnostic scoring calculation and risk stratification based on clinical and biochemical indicators. Background Technology

[0002] Currently, the gold standard for NASH is liver biopsy and pathological evaluation. While accurate, it is invasive, costly, has poor compliance, and is susceptible to sampling errors and observer variability, making it unsuitable for large-scale screening and dynamic follow-up. To address these shortcomings of existing liver biopsy and pathological evaluation methods, non-invasive scoring or models have been proposed. However, existing non-invasive scoring or models suffer from high variable acquisition costs, insufficient generalization, lack of external validation, emphasis on AUC while neglecting calibration and clinical decision benefits, and poor interpretability. Therefore, there is an urgent clinical need for an interpretable non-invasive auxiliary diagnostic and risk stratification tool for NASH that relies solely on readily available indicators, is easily embedded in information systems, and can achieve low-risk exclusion, gray-zone indication, and high-risk inclusion based on clearly defined thresholds. Summary of the Invention

[0003] The present invention aims to provide an implementable, low-cost, and interpretable technical solution for non-invasive auxiliary diagnostic scoring and risk stratification of NASH.

[0004] To achieve the above objectives, the first aspect of the present invention discloses a non-invasive method for calculating and risk stratifying NASH scores based on clinical and biochemical indicators, characterized by comprising the following steps:

[0005] Step 1: Collect age data of the target patients Height data, weight data, aspartate aminotransferase test value Alanine aminotransferase (ALT) test value And the information needed to diagnose metabolic syndrome; Step 2: Calculate the Body Mass Index (BMI) value based on height and weight data. ; Based on the information obtained for diagnosing metabolic syndrome, metabolic syndrome index values ​​are obtained. ; Calculate the aspartate aminotransferase detection value With alanine aminotransferase (ALT) test value ratio , ; Step 3: Calculate and obtain the NASH prediction score , .

[0006] Preferably, in step 2, the metabolic syndrome index values ​​are calculated. During calculation, if the metabolic syndrome index value meets the IDF criteria, then the metabolic syndrome index value will be used. Record it as 1; otherwise, set the metabolic syndrome index value as 1. Record it as 0.

[0007] Preferably, in step 3, the calculated NASH prediction score is obtained using the Logistic function. Conversion to NASH probability , .

[0008] Preferably, after step 3, the method further includes: Step 4: Based on the NASH prediction score Compared with the preset NASH prediction score threshold , The relationship between these factors determines whether the target patient is at high risk / prone to NASH, at low risk / prone to excluding NASH, or requires further evaluation.

[0009] Preferably, the two NASH prediction score thresholds , If we set them to 0.37 and 1.88 respectively, then we have: like If the target patient is located in a high-risk area, the conclusion that the target patient is at high risk of NASH / prone to NASH is given. like If the target patient is in the gray area, i.e. the uncertain area, then the conclusion that the target patient needs further evaluation is given. like If the target patient is located in a low-risk area, the conclusion that the target patient is at low risk of NASH / prone to excluding NASH is given.

[0010] Preferably, step 4 is followed by: Step 5: Generate a report for the target patient based on the judgment conclusions and related suggestions obtained in Step 4, or combine the NASH prediction score obtained in Step 3. or NASH probability The judgment conclusions and related suggestions obtained in step 4 are used to generate a report for the target patient.

[0011] The second aspect of the technical solution of this invention discloses a non-invasive NASH score calculation and risk stratification system based on clinical and biochemical indicators, used to implement the above-mentioned non-invasive NASH diagnostic score calculation method, characterized in that it includes: The data acquisition module is configured to implement the method described in step 1; An index construction module configured to implement the method described in step 2; A scoring calculation module configured to implement the method described in step 3; It is configured as a three-part hierarchical module for implementing the method described in step 4.

[0012] Preferred options also include: A report output module configured to implement the method described in step 5.

[0013] The third aspect of the technical solution of the present invention discloses an electronic device, comprising: One or more processors; A storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors perform the above-described non-intrusive NASH score calculation and risk stratification method.

[0014] The fourth aspect of the present invention discloses a computer-readable storage medium storing executable instructions thereon, which, when executed by a processor, cause the processor to perform the aforementioned non-intrusive NASH score calculation and risk stratification method.

[0015] The technical solution disclosed in this invention uses conventional clinical and biochemical indicators to construct a NASH diagnostic scoring formula, and maps the score to NASH risk probability or risk stratification results. Simultaneously, this invention introduces a dual-threshold, three-zone strategy, where 0.37 is the rule-out cutoff point with 90% sensitivity determined based on the Zhongshan cohort, and 1.88 is the rule-in cutoff point with 90% specificity determined based on the Zhongshan cohort, thus forming three zones: a low-risk zone, a gray zone, and a high-risk zone. Using the technical solution disclosed in this invention, a NASH predictive score or probability can be calculated based on the subject's conventional clinical and laboratory test indicators, achieving non-invasive auxiliary diagnosis and screening stratification of NASH, and providing a reference for whether further examination or follow-up is needed.

[0016] Compared with existing technical solutions, the present invention has the following beneficial effects: 1) Non-invasive, low-cost, and highly accessible: It relies only on routine clinical and blood biochemistry indicators, reducing the reliance on biopsies or expensive tests; 2) Clear and easy-to-deploy formulas: The scoring formulas are fixed, making it easy to quickly achieve automatic calculations in HIS / EMR, inspection systems, or mobile devices; 3) Clinical pathway friendly: dual thresholds and three-zone stratification, adapting to the actual process of screening—further evaluation—referral; 4) External validation supports generalization: Validation is performed in an independent external queue, reducing the risk of overfitting; 5) Can be embedded in clinical decision support systems: It can output scores, probabilities and three-zone results to support referral and further examination decisions. Attached Figure Description

[0017] Figure 1 This is a flowchart of a non-invasive NASH diagnostic score calculation and risk stratification method based on clinical and biochemical indicators disclosed in an embodiment of the present invention; Figure 2 This is a system block diagram of a non-invasive NASH score calculation system based on clinical and biochemical indicators disclosed in an embodiment of the present invention. Detailed Implementation

[0018] The present invention will be further illustrated below with reference to specific embodiments. It should be understood that these embodiments are for illustrative purposes only and are not intended to limit the scope of the invention. Furthermore, it should be understood that after reading the teachings of this invention, those skilled in the art can make various alterations or modifications to the invention, and these equivalent forms also fall within the scope defined by the appended claims.

[0019] The first aspect of this invention discloses a non-invasive method for calculating NASH diagnostic scores and risk stratification based on clinical and biochemical indicators, such as... Figure 1 As shown, it includes the following steps: Step S1, Data Acquisition: Collect age data of target patients (Unit: year), Height data (Unit: year) Weight data (unit: Aspartate aminotransferase detection value (Unit: U / L), Alanine aminotransferase (ALT) test value (Unit: U / L), and the information needed to diagnose metabolic syndrome. The target patients include individuals with fatty liver, metabolic abnormalities, abnormal liver enzymes, or suspected NASH risk.

[0020] Step S2, Metric Construction: The Body Mass Index (BMI) value is calculated based on height and weight data. (unit: ),in, ; Based on the information obtained for diagnosing metabolic syndrome, metabolic syndrome index values ​​are obtained. The information used to determine metabolic syndrome includes one or more of abdominal obesity, blood pressure, fasting blood glucose, triglycerides, and high-density lipoprotein cholesterol. In this embodiment of the invention, the determination can be made according to the International Diabetes Federation (IDF) diagnostic criteria for metabolic syndrome; if the IDF criteria are met, MetS is recorded as 1; otherwise, MetS is recorded as 0. In an optional implementation of this embodiment, if the IDF criteria are met, the metabolic syndrome index value is... Record it as 1; otherwise, record the metabolic syndrome index value as 1. Recorded as 0; Calculate the aspartate aminotransferase detection value With alanine aminotransferase (ALT) test value ratio , ; Step S3, Score Calculation: Calculate NASH prediction score As shown in the following formula: .

[0021] In another optional implementation of this invention, the calculated NASH prediction score can be obtained using the Logistic function. Conversion to NASH probability As shown in the following formula: .

[0022] Step S4: Three-part hierarchical division based on dual thresholds: Based on NASH prediction score The risk is stratified into three zones based on two preset NASH prediction score thresholds. The two NASH prediction score thresholds are 0.37 and 1.88, respectively; 0.37 is the rule-out cutoff point that meets 90% sensitivity based on the development cohort Zhongshancohort, and 1.88 is the rule-in cutoff point that meets 90% specificity based on the development cohort Zhongshancohort.

[0023] like If the target patient is located in the high-risk zone (Rule-in zone), the conclusion that the target patient is at high risk of NASH / prone to NASH is given. like If the target patient is in the gray zone (uncertain area), a conclusion is given that the target patient needs further evaluation. like If the target patient is located in the low-risk zone (Rule-out zone), the conclusion that the target patient is at low risk of NASH / prone to excluding NASH is given.

[0024] In another optional implementation of this invention, two NASH probability thresholds are set. , ,and Based on NASH probability With NASH probability threshold , The relationship between these factors is used to determine whether the target patient is at high risk / prone to NASH, at low risk / prone to excluding NASH, or requires further evaluation. The method is the same as above and will not be repeated here.

[0025] Step S5, Report Output: A report for the target patient is generated based on the risk stratification results and related recommendations obtained in step S4; or, it is generated by combining the NASH prediction score obtained in step S3. or NASH probability The risk stratification results and related recommendations obtained in step S4 are used to generate a report for the target patient. The report may include a NASH prediction score, NASH probability, stratification results for low-risk / grey / high-risk areas, and recommendations for further examination or follow-up.

[0026] NASH is closely related to metabolic abnormalities, obesity, and hepatocellular damage. Age, body mass index (BMI), and metabolic syndrome (MetS) reflect individual metabolic phenotypes and population differences, while AST and the AST / ALT ratio reflect biochemical characteristics related to hepatocellular damage. The method disclosed in this invention combines the aforementioned conventionally available indicators with specific weights to form a diagnostic score, which can achieve a quantitative estimate of NASH risk. Furthermore, the dual-threshold three-part strategy can take into account the different needs of "rule-in" and "rule-out" in clinical practice.

[0027] The above method was verified using the Zhongshan queue, and the following results were obtained: The area under the receiver operating characteristic (AUROC) curve was approximately 0.89 (95% confidence interval: 0.85–0.92). Specificity / positive predictive value (PPV) and sensitivity / negative predictive value (NPV) were reported at the two thresholds mentioned above, specifically: Rule-in percentage approximately 53.5%, Grey percentage approximately 25.1%, and Rule-out percentage approximately 21.4%. At a rule-in threshold ≥ 1.88, specificity was approximately 92.0%, and positive predictive value (PPV) was approximately 96.7%. At a rule-out threshold < 0.37, sensitivity was approximately 91.3%, and negative predictive value (NPV) was approximately 68.5%.

[0028] External validation of the above method using the PERSONS queue yielded the following results: The area under the receiver operating characteristic (AUROC) curve was approximately 0.77 (95% confidence interval: 0.72–0.81). Specificity / PPV and sensitivity / NPV were reported at the two thresholds of ≥1.88 and <0.37, respectively. The percentages of the three intervals (inclusion interval / grey interval / exclusion interval) were calculated as follows: Rule-in approximately 43.4%, Grey approximately 35.1%, and Rule-out approximately 21.6%. At the rule-in threshold ≥1.88, the specificity was approximately 71.6%, and the positive predictive value (PPV) was approximately 57.8%. At the rule-out threshold <0.37, the sensitivity was approximately 90.3%, and the negative predictive value (NPV) was approximately 83.9%.

[0029] The above verification results demonstrate that the method disclosed in the embodiments of the present invention is generalizable.

[0030] The second aspect of this invention discloses a non-invasive NASH diagnostic scoring system based on clinical and biochemical indicators, used to implement the aforementioned non-invasive NASH diagnostic scoring method, such as... Figure 2 As shown, it includes: The data acquisition module is used to collect age data of the target patients. Height data, weight data, aspartate aminotransferase test value Alanine aminotransferase (ALT) test value And the information needed to diagnose metabolic syndrome.

[0031] The indicator building module is used for: The Body Mass Index (BMI) value is calculated based on height and weight data. ; Based on the information obtained for diagnosing metabolic syndrome, metabolic syndrome index values ​​are obtained. In one optional implementation of this invention, if the metabolic syndrome index value meets the IDF standard, then... Record it as 1; otherwise, record the metabolic syndrome index value as 1. Recorded as 0; Calculate the aspartate aminotransferase detection value With alanine aminotransferase (ALT) test value ratio , .

[0032] The scoring calculation module is used to calculate the NASH prediction score. As shown in the following formula: .

[0033] In another optional implementation of this invention, the scoring calculation module further utilizes the Logistic function to calculate the NASH predicted score. Conversion to NASH probability : .

[0034] A three-part hierarchical module is used for NASH-based predictive scoring. With NASH prediction score threshold , The relationship between these factors determines whether the target patient is at high risk / prone to NASH, at low risk / prone to excluding NASH, or requires further evaluation.

[0035] In another optional implementation of this invention, the three-part hierarchical module can also be based on NASH probability. With NASH probability threshold , The relationship between these factors determines whether the target patient is at high risk / prone to NASH, at low risk / prone to excluding NASH, or requires further evaluation.

[0036] The report output module is used to generate a report for the target patient by combining the judgment conclusions and related suggestions obtained from the three-zone stratification module, or by combining the NASH prediction score obtained from the scoring calculation module. or NASH probability The judgment conclusions and related suggestions obtained from the three-part stratification module are used to generate a report for the target patient.

[0037] A third aspect of this invention discloses an electronic device including a processor capable of performing various appropriate actions and processes according to a program stored in a read-only memory (ROM) or loaded from a storage portion into a random access memory (RAM). The processor may include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor and / or an associated chipset and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor may also include onboard memory for caching purposes. The processor may include a single processing unit or multiple processing units for performing different actions of a non-invasive NASH diagnostic scoring and risk stratification method according to embodiments of this disclosure.

[0038] The RAM stores various programs and data required for the operation of the electronic device. The processor, ROM, and RAM are interconnected via a bus. The processor implements the aforementioned non-invasive NASH diagnostic scoring and risk stratification method by executing programs in the ROM and / or RAM. It should be noted that the programs may also be stored in one or more memories other than ROM and RAM. The processor may also perform various operations of the method according to embodiments of this disclosure by executing programs stored in said one or more memories.

[0039] According to embodiments of this disclosure, the electronic device may further include an input / output (I / O) interface, which is also connected to a bus. The electronic device may also include one or more of the following components connected to the I / O interface: an input section including a keyboard, mouse, etc.; an output section including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section including a hard disk, etc.; and a communication section including a network interface card such as a LAN card, modem, etc. The communication section performs communication processing via a network such as the Internet. A drive is also connected to the I / O interface as needed. Removable media, such as a magnetic disk, optical disk, magneto-optical disk, semiconductor memory, etc., are installed on the drive as needed so that computer programs read from them can be installed into the storage section as needed.

[0040] A fourth aspect of this invention also provides a computer-readable storage medium, which may be included in the device / apparatus described in the above embodiments; or it may exist independently and not assembled into the device / apparatus. The computer-readable storage medium carries one or more programs, which, when executed, implement the above-described non-invasive NASH diagnostic scoring and risk stratification method.

[0041] According to embodiments of this disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, such as including but not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM). The storage medium may be a ROM, an optical storage device, a magnetic storage device, or any suitable combination thereof. In embodiments of the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used or combined with an instruction execution system, apparatus, or device. For example, according to embodiments of the present disclosure, a computer-readable storage medium may include ROM 402 and / or RAM 403 and / or one or more memories other than ROM 402 and RAM 403 described above.

[0042] Those skilled in the art will understand that the features described in the various embodiments and / or claims of this invention can be combined or combined in various ways, even if such combinations or combinations are not explicitly described in this disclosure. In particular, the features described in the various embodiments and / or claims of this invention can be combined or combined in various ways without departing from the spirit and teachings of this disclosure. All such combinations and / or combinations fall within the scope of this disclosure.

[0043] The embodiments of the present invention have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of this disclosure. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. The scope of the present invention is defined by the appended claims and their equivalents. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of the present invention, and all such substitutions and modifications should fall within the scope of this disclosure.

Claims

1. A non-invasive method for calculating NASH scores and risk stratification based on clinical and biochemical indicators, characterized in that, Includes the following steps: Step 1: Collect age data of the target patients Height data, weight data, aspartate aminotransferase test value Alanine aminotransferase (ALT) test value And the information needed to diagnose metabolic syndrome; Step 2: Calculate the Body Mass Index (BMI) value based on height and weight data. ; Based on the information obtained for diagnosing metabolic syndrome, metabolic syndrome index values ​​are obtained. ; Calculate the aspartate aminotransferase detection value With alanine aminotransferase (ALT) test value ratio , ; Step 3: Calculate and obtain the NASH prediction score , .

2. The non-invasive NASH score calculation and risk stratification method based on clinical and biochemical indicators as described in claim 1, characterized in that, In step 2, the metabolic syndrome index values ​​are calculated. During calculation, if the metabolic syndrome index value meets the IDF criteria, then the metabolic syndrome index value will be used. Record it as 1; otherwise, set the metabolic syndrome index value as 1. Record it as 0.

3. The non-invasive NASH diagnostic scoring method based on clinical and biochemical indicators as described in claim 1, characterized in that, In step 3, the calculated NASH prediction score is obtained using the Logistic function. Conversion to NASH probability , .

4. The non-invasive NASH score calculation and risk stratification method based on clinical and biochemical indicators as described in claim 1, characterized in that, Following step 3, the following is also included: Step 4: Based on the NASH prediction score The risk is stratified into three zones based on a preset NASH prediction score threshold, wherein the two NASH prediction score thresholds are 0.37 and 1.88, respectively. like If the target patient is located in a high-risk area, the conclusion that the target patient is at high risk of NASH / prone to NASH is given. like If the target patient is in the gray area, i.e. the uncertain area, then the conclusion that the target patient needs further evaluation is given. like If the target patient is located in a low-risk area, the conclusion that the target patient is at low risk of NASH / prone to excluding NASH is given.

5. The non-invasive NASH score calculation and risk stratification method based on clinical and biochemical indicators as described in claim 4, characterized in that, The value of 0.37 is the rule-out cutoff point that satisfies 90% sensitivity, determined based on the development queue Zhongshan cohort, and the value of 1.88 is the rule-in cutoff point that satisfies 90% specificity, determined based on the development queue Zhongshan cohort.

6. A non-invasive NASH score calculation and risk stratification method based on clinical and biochemical indicators as described in claim 4 or 5, characterized in that, Step 4 is followed by: Step 5: Generate a report for the target patient based on the judgment conclusions and related suggestions obtained in Step 4, or combine the NASH prediction score obtained in Step 3. or NASH probability The risk stratification results and related recommendations obtained in step 4 are used to generate a report for the target patients.

7. A non-invasive NASH diagnostic scoring and risk stratification system based on clinical and biochemical indicators, used to implement the non-invasive NASH scoring and risk stratification method according to any one of claims 1 to 6, characterized in that, include: The data acquisition module is configured to implement the method described in step 1; An index construction module configured to implement the method described in step 2; A scoring calculation module configured to implement the method described in step 3; It is configured as a three-part hierarchical module for implementing the method described in step 4.

8. The non-invasive NASH diagnostic scoring system based on clinical and biochemical indicators as described in claim 7, characterized in that, Also includes: A report output module configured to implement the method described in step 5.

9. An electronic device, comprising: One or more processors; A storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors execute software to implement the non-invasive NASH diagnostic score calculation and risk stratification method according to any one of claims 1 to 6.

10. A computer-readable storage medium having stored executable instructions thereon, which, when executed by a processor, cause the processor to perform the non-invasive NASH diagnostic score calculation and risk stratification method according to any one of claims 1 to 6.

Images