CN116705286B - Prediction method based on metabolism-related fatty liver disease, electronic equipment and storage medium - Google Patents
Prediction method based on metabolism-related fatty liver disease, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN116705286B CN116705286B CN202310489636.6A CN202310489636A CN116705286B CN 116705286 B CN116705286 B CN 116705286B CN 202310489636 A CN202310489636 A CN 202310489636A CN 116705286 B CN116705286 B CN 116705286B
- Authority
- CN
- China
- Prior art keywords
- mafld
- risk
- fatty liver
- ccr
- hba1c
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 208000010706 fatty liver disease Diseases 0.000 title claims abstract description 28
- 230000004060 metabolic process Effects 0.000 title description 3
- 201000010099 disease Diseases 0.000 claims abstract description 29
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 29
- 230000002503 metabolic effect Effects 0.000 claims abstract description 22
- 238000012216 screening Methods 0.000 claims abstract description 17
- 238000007477 logistic regression Methods 0.000 claims abstract description 13
- DDRJAANPRJIHGJ-UHFFFAOYSA-N creatinine Chemical compound CN1CC(=O)NC1=N DDRJAANPRJIHGJ-UHFFFAOYSA-N 0.000 claims description 44
- 102000012192 Cystatin C Human genes 0.000 claims description 22
- 108010061642 Cystatin C Proteins 0.000 claims description 22
- 229940109239 creatinine Drugs 0.000 claims description 22
- 208000001072 type 2 diabetes mellitus Diseases 0.000 claims description 14
- 230000006870 function Effects 0.000 claims description 10
- 238000012502 risk assessment Methods 0.000 claims description 8
- 230000002596 correlated effect Effects 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- HVYWMOMLDIMFJA-DPAQBDIFSA-N cholesterol Chemical compound C1C=C2C[C@@H](O)CC[C@]2(C)[C@@H]2[C@@H]1[C@@H]1CC[C@H]([C@H](C)CCCC(C)C)[C@@]1(C)CC2 HVYWMOMLDIMFJA-DPAQBDIFSA-N 0.000 claims description 6
- 230000000875 corresponding effect Effects 0.000 claims description 6
- 108010003415 Aspartate Aminotransferases Proteins 0.000 claims description 3
- 102000004625 Aspartate Aminotransferases Human genes 0.000 claims description 3
- 102000017011 Glycated Hemoglobin A Human genes 0.000 claims description 3
- 108010014663 Glycated Hemoglobin A Proteins 0.000 claims description 3
- 238000000585 Mann–Whitney U test Methods 0.000 claims description 3
- 108090000992 Transferases Proteins 0.000 claims description 3
- 102000004357 Transferases Human genes 0.000 claims description 3
- 238000000546 chi-square test Methods 0.000 claims description 3
- 235000012000 cholesterol Nutrition 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 claims description 3
- 125000000291 glutamic acid group Chemical group N[C@@H](CCC(O)=O)C(=O)* 0.000 claims description 3
- 238000010832 independent-sample T-test Methods 0.000 claims description 3
- 230000003907 kidney function Effects 0.000 claims description 3
- QNAYBMKLOCPYGJ-REOHCLBHSA-N L-alanine Chemical compound C[C@H](N)C(O)=O QNAYBMKLOCPYGJ-REOHCLBHSA-N 0.000 claims description 2
- 235000004279 alanine Nutrition 0.000 claims description 2
- 230000024924 glomerular filtration Effects 0.000 claims description 2
- 230000008569 process Effects 0.000 claims description 2
- 238000000611 regression analysis Methods 0.000 claims description 2
- UFTFJSFQGQCHQW-UHFFFAOYSA-N triformin Chemical compound O=COCC(OC=O)COC=O UFTFJSFQGQCHQW-UHFFFAOYSA-N 0.000 claims description 2
- QGZKDVFQNNGYKY-UHFFFAOYSA-N Ammonia Chemical compound N QGZKDVFQNNGYKY-UHFFFAOYSA-N 0.000 claims 2
- 229910021529 ammonia Inorganic materials 0.000 claims 1
- 238000003745 diagnosis Methods 0.000 abstract description 8
- 230000006866 deterioration Effects 0.000 abstract 1
- 230000002349 favourable effect Effects 0.000 abstract 1
- 239000002699 waste material Substances 0.000 abstract 1
- 208000004930 Fatty Liver Diseases 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000000556 factor analysis Methods 0.000 description 4
- 208000008338 non-alcoholic fatty liver disease Diseases 0.000 description 4
- 206010019708 Hepatic steatosis Diseases 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000035945 sensitivity Effects 0.000 description 3
- 206010061818 Disease progression Diseases 0.000 description 2
- 239000000090 biomarker Substances 0.000 description 2
- 238000001574 biopsy Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000002405 diagnostic procedure Methods 0.000 description 2
- 235000005911 diet Nutrition 0.000 description 2
- 230000005750 disease progression Effects 0.000 description 2
- 206010073071 hepatocellular carcinoma Diseases 0.000 description 2
- 231100000844 hepatocellular carcinoma Toxicity 0.000 description 2
- 208000019423 liver disease Diseases 0.000 description 2
- 208000030159 metabolic disease Diseases 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 231100000240 steatosis hepatitis Toxicity 0.000 description 2
- 150000003626 triacylglycerols Chemical class 0.000 description 2
- 102100036475 Alanine aminotransferase 1 Human genes 0.000 description 1
- 108010082126 Alanine transaminase Proteins 0.000 description 1
- LFQSCWFLJHTTHZ-UHFFFAOYSA-N Ethanol Chemical compound CCO LFQSCWFLJHTTHZ-UHFFFAOYSA-N 0.000 description 1
- 206010018429 Glucose tolerance impaired Diseases 0.000 description 1
- 108010023302 HDL Cholesterol Proteins 0.000 description 1
- 206010061218 Inflammation Diseases 0.000 description 1
- 206010022489 Insulin Resistance Diseases 0.000 description 1
- 208000001280 Prediabetic State Diseases 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 208000037849 arterial hypertension Diseases 0.000 description 1
- 238000003766 bioinformatics method Methods 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 230000007211 cardiovascular event Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000037213 diet Effects 0.000 description 1
- 230000000378 dietary effect Effects 0.000 description 1
- 230000035622 drinking Effects 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007717 exclusion Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 208000006575 hypertriglyceridemia Diseases 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000004054 inflammatory process Effects 0.000 description 1
- 210000004185 liver Anatomy 0.000 description 1
- 238000002595 magnetic resonance imaging Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000006371 metabolic abnormality Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 201000009104 prediabetes syndrome Diseases 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
- 230000005180 public health Effects 0.000 description 1
- 238000013058 risk prediction model Methods 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000005891 transamination reaction Methods 0.000 description 1
- 238000002604 ultrasonography Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B20/00—ICT specially adapted for functional genomics or proteomics, e.g. genotype-phenotype associations
- G16B20/50—Mutagenesis
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B35/00—ICT specially adapted for in silico combinatorial libraries of nucleic acids, proteins or peptides
- G16B35/20—Screening of libraries
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
- G16B50/00—ICT programming tools or database systems specially adapted for bioinformatics
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Public Health (AREA)
- Biotechnology (AREA)
- Biophysics (AREA)
- Evolutionary Biology (AREA)
- Biomedical Technology (AREA)
- Databases & Information Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- Theoretical Computer Science (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Data Mining & Analysis (AREA)
- Library & Information Science (AREA)
- Molecular Biology (AREA)
- Epidemiology (AREA)
- Chemical & Material Sciences (AREA)
- Pathology (AREA)
- Primary Health Care (AREA)
- Analytical Chemistry (AREA)
- Proteomics, Peptides & Aminoacids (AREA)
- Bioethics (AREA)
- Genetics & Genomics (AREA)
- Biochemistry (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention provides a prediction method, electronic equipment and storage medium based on metabolic-related fatty liver disease, wherein indexes obviously related to MAFLD risks are obtained through single-factor and multi-factor Logistic regression analysis, and a prediction model with higher accuracy is established by using a nomogram method according to the indexes. The model is simple, quick and convenient to implement, can be used for large-scale MAFLD screening, improves the identification accuracy of people with higher MAFLD disease risk, can reduce the waste of medical resources, is favorable for improving the diagnosis efficiency of MAFLD, helps MAFLD patients to receive treatment in time, and prevents disease deterioration.
Description
Technical Field
The invention belongs to the field of bioinformatics analysis, and particularly relates to a prediction method based on metabolic-related fatty liver disease, electronic equipment and a storage medium.
Background
Nonalcoholic fatty liver disease (NAFLD) is a global public health problem with increasing prevalence, and the current definition of NAFLD requires the exclusion of heavy drinking and other secondary causes of chronic liver disease. However, fatty liver disease is not only focused on patients with or without excessive alcohol consumption, but may also be a disease driver in other forms of chronic liver disease patients. To better understand fatty liver disease, a new name and definition of adult NAFLD, a metabolic-related fatty liver disease (MAFLD), was proposed by an international panel of experts from 22 countries. MAFLD affects approximately one-fourth of adults worldwide, with prevalence of up to 50.7% in overweight and obese people.
The risk of cardiovascular events in MAFLD patients has increased significantly, as has the number of hepatocellular carcinoma (HCC) patients associated with MAFLD. Therefore, it is desirable to diagnose MAFLD patients as early as possible and to take appropriate intervention to prevent further disease progression. The diagnostic criteria for MAFLD were: histological (biopsy), imaging, or blood biomarkers confirm liver fat accumulation (i.e., liver steatosis) and meet at least one of three criteria: overweight or obese (caucasian body mass index [ BMI ] 25kg/m2 or Asian BMI 25kg/m 2), type 2 diabetes (T2 DM), metabolic disorders. Metabolic disorder refers to at least two of the following metabolic risk situations: increased waistline, arterial hypertension, hypertriglyceridemia, low high density lipoprotein cholesterol, pre-diabetes, subclinical inflammation and insulin resistance.
The diagnosis of MAFLD is complex, and the diagnosis of all people suspected to suffer from MAFLD by using the diagnosis standard can cost a lot of manpower and material resources, and can delay the real MAFLD patient from timely treatment. While some existing models or biomarkers for screening and diagnosing MAFLD are built in small sample populations, for example, MAFLD risk prediction models based on BMI and Waist Circumference (WC) are developed in 535 overweight or obese populations, are not suitable for general populations, and have an AUC of only 0.79. Therefore, there is a need to build MAFLD predictive models that can be used for large-scale crowd screening and are easy to implement.
Disclosure of Invention
Diagnosis of MAFLD as early as possible is helpful for patients to receive treatment in time, delay disease progression and prevent serious complications, but MAFLD prediction models which are suitable for large-scale people, convenient to implement and high in accuracy are still lacking at present. The invention aims to provide a prediction model of metabolic-related fatty liver disease based on creatinine and Cystatin C Ratio (CCR), a construction method and application thereof. The invention aims to provide a prediction model and a model construction method of metabolic-related fatty liver disease based on the ratio of creatinine to cystatin C, aiming at the defects existing at present.
The invention provides a method for predicting metabolic-related fatty liver disease based on the ratio of creatinine to cystatin C, which comprises the following steps:
(1) The following index data of the participants are obtained from the database: age, sex, race, BMI, T2DM, hbA1c, TG, CHOL, CCR, GGT, AST, ALT,
wherein, the whole names of the indexes are respectively: MAFLD: metabolic-related fatty liver disease, BMI: body mass index, GGT: glutamyl transferase, CCR: creatinine to cystatin C ratio, AST: aspartate aminotransferase, ALT: alanine transamination, T2DM: type 2 diabetes, hbA1c: glycosylated hemoglobin, TG: triglyceride, CHOL:
cholesterol;
(2) The correlation between each index and the MAFLD disease risk is analyzed by using single-factor Logistic regression, indexes which are obviously correlated with the MAFLD disease risk are screened out, and independent risk factors which are obviously correlated with the MAFLD disease risk are obtained by using multi-factor Logistic analysis, wherein the method comprises the following steps: age, gender, BMI, CCR, T DM, hbA1c, TG, CHOL, wherein age, gender, CCR, hbA1c, TG, CHOL are selected to build a predictive model;
(3) Scoring the independent risk factors by using a nomogram, wherein the scoring formula of each independent risk factor is as follows:
CCR score = -0.243736557 ccr+48.747311336;
age score = -0.09417962 age+7.0634471474;
gender scoring: male= 12.89266, female=0;
HbA1c score = 0.711006907 HbA1c-14.220138147;
TG score = 0.166666667 TG;
CHOL score = -1.302132565 x chol+12.370299771;
(4) Constructing a prediction model according to the scores, wherein the total risk assessment score (T) of the prediction model is the sum of scores of six indexes including age, gender and HbA1c, TG, CHOL, CCR;
(5) The calculation formula for obtaining the MAFLD disease risk (R) according to the risk assessment total score is as follows:
R＝-5.191e -06 *T3+0.001311815*T2-0.089010605*T+1.792531915；
(6) And inputting six index values of the detection crowd into a calculation formula of the MAFLD disease risk (R) to obtain the corresponding MAFLD disease risk.
Preferably, before the step of obtaining the following indexes of the participants from the database, the step of screening the participants meeting the conditions is further included:
(1) Excluding participants who were unable to diagnose whether they had MAFLD because of the lack of information;
(2) Excluding participants with missing study index (age, sex, race, BMI, T2DM, hbA1c, TG, CHOL, CCR) information;
(3) Since the level of creatinine to cystatin C ratio is affected by renal function, the glomerular filtration rate is excluded from being lower than 60ml/min/1.73m 2 Is a participant in the process.
Preferably, the single-factor Logistic regression analysis and the multi-factor Logistic regression analysis use R language for data analysis and glm function for regression analysis.
Preferably, the correlation between each index and the risk of MAFLD disease is analyzed using single factor Logistic regression, and the variability between MAFLD groups and non-MAFLD group classification or continuous variables in baseline data is assessed by independent sample t-test, chi-square test, or Mann-Whitney U test.
Preferably, when P < 0.05, this indicator is shown to be significantly correlated with risk of MAFLD disease; wherein, P is a statistical index for judging whether the result has statistical significance, namely whether the correlation is significant.
Preferably, after obtaining the calculation formula of the risk of the MAFLD according to the risk assessment total score, the method further comprises: a subject operating characteristic curve (ROC) is plotted and the accuracy of the predictive model is verified by the area under ROC curve (AUC). AUC, also known as C statistic, is mainly used to evaluate the accuracy of diagnostic tests, or the accuracy of binary regression model predictions. The range of AUC is 0.5-1.0, AUC is 0.5 and corresponds to random classification, 1.0 shows complete accuracy, 0.51-0.59 shows poor accuracy of the model, 0.60-0.69 shows poor accuracy, 0.70-0.79 shows moderate accuracy, 0.80-0.89 shows good accuracy, and 0.90 or more shows good accuracy. The AUC of the prediction model established by the invention for predicting the MAFLD risk is 0.841, which shows that the accuracy is higher.
Preferably, after six index values of the crowd to be detected are input into the prediction model to obtain corresponding MAFLD disease risks, the method further comprises the step of screening out crowds with high MAFLD disease risks, including:
and marking the people with MAFLD disease risks exceeding the reference value in the detected people, and reminding the people to seek medical attention in time.
The optimal cut-off value of the ROC curve is 0.637, and the specificity and the sensitivity of the model are 75.8% and 76.1% respectively, namely 63.7% can be used as reference values for distinguishing the risk of MAFLD.
Preferably, the present application further includes an electronic device, including:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to implement the method of predicting metabolic-related fatty liver disease based on a creatinine to cystatin C ratio when executing the instructions.
Also included is a computer readable storage medium comprising instructions that instruct a device to perform the method of predicting a metabolic-related fatty liver disease based on a creatinine to cystatin C ratio. Compared with the prior art, the invention has the following positive effects:
1. compared with the traditional prediction model, the invention additionally introduces 6 indexes of age, sex and HbA1c, TG, CHOL, CCR, namely BMI and Waistline (WC), and a nonogram method is used for scoring and establishing the prediction model according to the indexes, so that the accuracy of the prediction model is higher.
2. The traditional prediction is mainly carried out in specific crowds such as overweight or obese crowds, and is not suitable for most common crowds, and the prediction model established by the invention can be suitable for the prediction of the common crowds, and the screening range and the audience are wider.
3. The prediction model is simple and convenient to operate, the MAFLD disease risk can be obtained by inputting index information, the implementation is convenient, the prediction model can be used for large-scale MAFLD screening, and the recognition rate of people with high MAFLD disease risk is improved.
Drawings
The invention will be further understood from the following description taken in conjunction with the accompanying drawings. The components in the figures are not necessarily to scale, emphasis instead being placed upon illustrating the principles of the embodiments. Like reference numerals designate corresponding parts throughout the different views.
Fig. 1: flow chart for screening participants
Fig. 2: nomograms predicting MAFLD risk
Fig. 3: subject work characteristic curve of predictive model
Detailed Description
The following embodiments of the present invention are described in terms of specific examples, and those skilled in the art will appreciate the advantages and effects of the present invention from the disclosure herein. The invention is capable of other and different embodiments and its several details are capable of modification and variation in various respects, all without departing from the spirit of the present invention. The drawings of the present invention are merely schematic illustrations, and are not intended to be drawn to actual dimensions. The following embodiments will further illustrate the related art content of the present invention in detail, but the disclosure is not intended to limit the scope of the present invention.
The following describes in detail the embodiments of the present invention with reference to fig. 1-3.
Table 1 shows the index involved in the predictive model and its abbreviation control
| Abbreviations (abbreviations) | Terminology |
| MAFLD | Metabolism related fatty liver disease |
| BMI | Body mass index |
| WC | Waistline |
| GGT | Glutamyl transferase |
| CCR | Creatinine to cystatin C ratio |
| AST | Aspartate aminotransferase |
| ALT | Alanine aminotransferase |
| T2DM | Type 2 diabetes mellitus |
| HbA1c | Glycosylated hemoglobin |
| TG | Triglycerides (Triglycerides) |
| CHOL | Cholesterol |
The diagnostic basis for MAFLD is liver steatosis and the occurrence of any of the following 3 conditions: (1) overweight or obese, (2) T2DM, and (3) at least 2 metabolic abnormalities. Fatty Liver Index (FLI) is used to determine participants due to lack of tissue biopsy and ultrasound image dataIs a hepatic steatosis condition. The fatty liver index is calculated by the following formula: fli=100× (e 0.953 ×loge(TG)+0.139×BMI+0.718×loge(GGT)+0.053×WC-15.745)/(1+e 0.953 Xloge (TG) +0.139 XBMI+0.718 Xloge (GGT) +0.053 XWC-15.745), FLI.gtoreq.60 is defined as liver steatosis.
According to the diagnosis basis of MAFLD, the prediction model of the metabolic-related fatty liver disease based on the ratio of creatinine to cystatin C and the modeling method thereof comprise the following steps:
1. screening eligible participants
Based on the diagnostic criteria of MAFLD, portions of the participant data that do not meet diagnostic criteria are eliminated when screening the database for appropriate participant baseline data. The steps of screening participants are shown in fig. 1, and the screening for baseline data includes:
1) 35542 participants who were unable to diagnose whether they had MAFLD due to the lack of information were excluded;
2) The participants with 94344 study index (age, sex, race, BMI, T2DM, hbA1c, TG, CHOL, CCR) information missing were continuously excluded;
3) Since the levels of creatinine and cystatin C are affected by renal function, the filtration rate of 3861 glomeruli is lower than 60ml/min/1.73m 2 Is excluded from participants in the study.
Baseline data of 368634 participants were finally included for analysis, with a median age of 58 years and a female percentage of 54%. 139002 participants were diagnosed with MAFLD at baseline. Compared to the non-MAFLD population, MAFLD patients were mostly men, aged higher, higher BMI, GGT, hbA1c, TG, CHOL levels, lower CCR, ALB levels.
CCR is divided into three groups according to the triad of CCR levels: CCR tertile 1, CCR tertile 2, CCR tertile 3. Baseline data for participants are shown in the following table:
table 2: baseline characteristics of participants
Wherein n represents the number of people; and P is used for judging whether the statistical result has statistical significance.
The classifier variables in the baseline data of the present invention are expressed in numbers and percentages [ n (%) ], for example CCR tertile 1, as: 121649 (33); the continuous variable is expressed using a median and first and third quartiles [ medium (Q1, Q3) ] such as age expressed as: 58 (50,63). The independent sample t-test, chi-square test, or Mann-Whitney U test was used to evaluate the variability between the classification of the MAFLD group and the non-MAFLD group or continuous variable in the baseline data.
2. Independent risk factors related to MAFLD (magnetic resonance imaging) are obtained by adopting single-factor and multi-factor Logistic regression analysis
The data analysis was performed using the R language and the glm function was used for Logistic single and multi-factor analysis. Inclusion age, gender, race, BMI, CCR, T DM, hbA1c, TG, CHOL for single factor analysis; the analysis results are shown in the following table:
table 3: single-and multi-factor Logistic regression analysis
Wherein, OR: ratio (odds ratio), also known as odds ratio, is used to reflect the difference in exposure between cases and controls; or=1, indicating no correlation between exposure and disease; OR > 1, indicating that exposure is a risk factor for disease (positive correlation); OR < 1, indicating that the exposure factor is a protective factor (negative correlation) for the disease. The OR value is a point estimate, and the 95% confidence interval (95% CI) is an interval estimate, with the breadth of the confidence interval reflecting the accuracy of the parameter estimate, the narrower the confidence interval, the more accurate the estimate. The results are considered statistically significant, i.e., correlation is significant, when P < 0.05.
The present invention uses single and multi-factor Logistic regression analysis to determine variables that are significantly correlated (P < 0.05) to the risk of MAFLD. The variables P < 0.05 in the multifactor analysis were included in the predictive model. As shown in table 3, the single factor analysis results showed that age, gender, BMI, CCR, T DM, hbA1c, TG, CHOL were significantly correlated with risk of having MAFLD (P < 0.05), and these 8 indicators were included as covariates in the multi-factor analysis, and the results showed that age, gender, BMI, CCR, T DM, hbA1c, TG, CHOL were significantly correlated with risk of MAFLD (P < 0.05), thus determining that 8 indicators of age, gender, BMI, CCR, T DM, hbA1c, TG, CHO were independent risk factors of MAFLD.
3. Predictive model establishment by nomogram method scoring
Since BMI, T2DM are already included in the main diagnostic criteria of MAFLD, six indicators of age, gender, hbA1c, TG, CHOL, CCR were included, and R-package rms was used to build nomogram method scores to build a predictive model for predicting the risk of developing MAFLD in the population, and the model results are shown in FIG. 2.
Formula using R-package nomogram ex extraction model:
risk of MAFLD disease R= -5.191e -06 *T 3 +0.001311815*T 2 -0.089010605*T+
1.792531915, wherein the total risk assessment score T is the sum of the index scores.
The score for each index is:
CCR score = -0.243736557 ccr+48.747311336;
age score = -0.09417962 age+7.0634471474;
gender scoring: male= 12.89266, female=0;
HbA1c score = 0.711006907 HbA1c-14.220138147;
TG score = 0.166666667 TG;
CHOL score = -1.302132565 x chol+12.370299771.
For example, a 30 year old (4.238082874 score) male (12.89266 score) with a CCR of 64.6
(33.001929753 minutes), hbA1c of 37.9mmol/mol (12.7270236283 minutes), TG of 234.5mg/dL (39.0833334115 minutes), CHOL of 7.36mmol/L (2.7865636926 minutes), and calculating the sum of the scores of the indexes, namely, the total score T of 104.7295933602 minutes, to show that the MAFLD disease risk is 90%, and reminding the patient to take a definite diagnosis in time and take intervention measures. For the treatment of MAFLD, there is no approved drug specifically for MAFLD treatment, and the main treatment methods are to change life style, including adjustment of dietary structure and exercise enhancement.
A30 year old (4.238082874 score) female (0 score), CCR 86.7 (27.6153518441 score), hbA1c 29.7mmol/mol (7.6077738979 score), TG 165.5mg/dL (27.5833333885 score), CHOL 6.38mmol/L (4.0626536063 score), total T71.1071956108 score, and MAFLD risk 23%, indicating lower risk, no need for diagnosis, and regular monitoring.
4. Evaluating accuracy of predictive models
The efficacy of the predictive model was assessed by plotting the subject's working characteristics curve (Receiver Operating Characteristic Curve, ROC curve) and calculating the area under the ROC curve (AUC). ROC curves, which are a curve drawn by continuously measuring different observation tangent point values of a variable, can be used to evaluate the predictive performance of a statistical model to predict a classification result, the Y-axis of the curve being sensitivity and the X-axis being specificity. AUC, also known as C statistic, is mainly used to evaluate the accuracy of diagnostic tests, or the accuracy of binary regression model predictions. The range of AUC is 0.5-1.0, AUC is 0.5G to indicate corresponding random classification, 1.0 indicates complete accuracy, 0.51-0.59 indicates poor accuracy of the model, 0.60-0.69 indicates poor accuracy, 0.70-0.79 indicates moderate accuracy, 0.80-0.89 indicates good accuracy, and 0.90 or more indicates good accuracy.
According to the invention, an R packet pROC is adopted to draw an ROC curve, an AUC value is calculated, and an optimal cut-off value is found, as shown in figure 3, the AUC of the model prediction MAFLD risk is 0.841, which shows that the accuracy is higher; the cut-off value is 0.637, and the specificity and sensitivity of the model are 75.8% and 76.1% respectively, namely 63.7% can be used as reference values for distinguishing the risk of MAFLD.
5. Application of predictive model
The predictive model can be used for making a small program for a needed person, and the user can obtain the risk of the MAFLD by inputting the numerical values of six indexes including age, sex and HbA1c, TG, CHOL, CCR of the user or the family into the predictive model, and the small program can provide instruction in aspects of diet and exercise for the user with higher risk probability of the MAFLD. The predictive model may also be used to screen MAFLD patients during hospital physical examination or community screening.
Correspondingly, the electronic equipment is used for realizing a prediction method of metabolic-related fatty liver disease based on the ratio of creatinine to cystatin C, and the electronic equipment at least comprises a processor and a memory. The memory is for storing instructions executable by the processor 21, the processor being configured to implement a method of predicting metabolic-related fatty liver disease based on a creatinine to cystatin C ratio when the instructions are executed.
Also included is a computer readable storage medium comprising instructions that instruct a device to perform a method of predicting a metabolic-related fatty liver disease based on a creatinine to cystatin C ratio.
The program to be executed in the electronic device may be a program (a program for causing a computer to function) for controlling a central processing unit (Central Processing Unit, CPU) or the like to realize the functions of the above-described embodiment according to an aspect of the present invention. Information processed by these devices is temporarily stored in a random access Memory (Random Access Memory, RAM) when the processing is performed, and then stored in various ROMs such as a Read Only Memory (Flash ROM) and a Hard Disk Drive (HDD), and Read, corrected, and written by a CPU as necessary.
The electronic device according to the above embodiment may be partially implemented by a computer. In this case, the program for realizing the control function may be recorded on a computer-readable recording medium, and the program recorded on the recording medium may be read into a computer system and executed.
The term "computer system" as used herein refers to a computer system built in an electronic device, and uses hardware including an OS and peripheral devices. The term "computer-readable recording medium" refers to a removable medium such as a flexible disk, a magneto-optical disk, a ROM, or a CD-ROM, and a storage device such as a hard disk incorporated in a computer system.
Also, the "computer-readable recording medium" may include: a medium for dynamically storing a program in a short time, such as a communication line in the case of transmitting the program via a network such as the internet or a communication line such as a telephone line; a medium storing a program for a fixed time, such as a volatile memory in a computer system, which is a server or a client in this case. The program may be a program for realizing a part of the functions described above, or may be a program capable of realizing the functions described above by being combined with a program recorded in a computer system.
The electronic apparatus according to the above embodiment may be realized as an aggregate (device group) including a plurality of devices. Each device constituting the device group may include a part or all of each function or each functional block of the electronic apparatus according to the above embodiment. The device group may have all the functions or functional blocks of the electronic apparatus.
The above disclosure is only a preferred practical embodiment of the present invention and is not intended to limit the scope of the present invention, but various modifications and variations will be apparent to those skilled in the art. All equivalent technical changes, including various equivalent substitutions, improvements, etc. made in the description and the accompanying drawings of the present invention are included in the protection scope of the present invention.
Claims (10)
1. A method for predicting metabolic-related fatty liver disease based on creatinine to cystatin C ratio, comprising the steps of:
(1) The following index data of the participants are obtained from the database: age, sex, race, BMI, T2DM, hbA1c, TG, CHOL, CCR, GGT, AST, ALT,
wherein, the whole names of the indexes are respectively: MAFLD: metabolic-related fatty liver disease, BMI: body mass index, T2DM: type 2 diabetes, hbA1c: glycosylated hemoglobin, TG: triglyceride, CHOL: cholesterol, CCR: creatinine to cystatin C ratio, GGT: glutamyl transferase, AST: aspartate aminotransferase, ALT: converting alanine into ammonia;
(2) Analyzing the correlation between each index and the MAFLD disease risk by using single-factor Logistic regression, screening out indexes obviously related to the MAFLD disease risk, and obtaining independent risk factors obviously related to the MAFLD disease risk by using multi-factor Logistic regression, wherein the method comprises the following steps: age, gender, BMI, CCR, T DM, hbA1c, TG, CHOL, wherein age, gender, CCR, hbA1c, TG, CHOL are selected to build a predictive model;
(3) Scoring the independent risk factors by using a nomogram, wherein the scoring formula of each independent risk factor is as follows:
CCR score = -0.243736557 ccr+48.747311336;
age score = -0.09417962 age+7.063471474;
gender scoring: male= 12.89266, female=0;
HbA1c score = 0.711006907 HbA1c-14.220138147;
TG score = 0.166666667 TG;
CHOL score = -1.302132565 chol+12.370259371;
(4) Constructing a prediction model according to the scores, wherein the total risk assessment score of the prediction model is the sum of scores of six indexes including age, gender and HbA1c, TG, CHOL, CCR;
(5) The calculation formula for obtaining the MAFLD disease risk according to the risk assessment total score is as follows:
R=-5.191e -06 * T 3 + 0.001311815 * T 2 0.089010605 t+ 1.792531915, where T is the total score of risk assessment;
(6) And inputting six index values of the detected crowd into a calculation formula of the MAFLD disease risk to obtain a corresponding MAFLD disease risk.
2. The method for predicting metabolic-related fatty liver disease based on creatinine to cystatin C ratio of claim 1, further comprising the step of screening for eligible participants before the step of retrieving the following indicators of participants from the database in step (1), comprising:
(1) Excluding participants who were unable to diagnose whether they had MAFLD because of the lack of information;
(2) Excluding participants with missing study index information, wherein the study index includes age, gender, race, BMI, T2DM, hbA1c, TG, CHOL, CCR;
(3) Since the level of creatinine to cystatin C ratio is affected by renal function, the glomerular filtration rate is excluded from being lower than 60ml/min/1.73m 2 Is a participant in the process.
3. The method for predicting metabolic-related fatty liver disease based on creatinine to cystatin C ratio of claim 1, wherein the single factor Logistic regression analysis and the multi-factor Logistic regression analysis in step (2) use R language for data analysis and glm function for regression analysis.
4. The method according to claim 1, wherein the analyzing the correlation between each of the indicators and the risk of developing MAFLD using single factor Logistic regression in step (2) comprises: the variability between the MAFLD group and the non-MAFLD group classification variables or continuous variables in the baseline data was assessed by independent sample t-test, chi-square test, or Mann-Whitney U test.
5. The method according to claim 1, wherein for the screening of the index significantly associated with risk of developing MAFLD in step (2), the method comprises:
when (when)PWhen < 0.05, it is shown that the index is significantly correlated with risk of MAFLD disease, wherein,Pthe statistical index is used for judging whether the result has statistical significance, namely whether the correlation is obvious.
6. The method according to claim 1, wherein after obtaining the calculation formula of the risk of developing MAFLD according to the total score of risk assessment in step (5), further comprising: a subject work characteristic curve ROC is plotted and the accuracy of the predictive model is assessed by the area under ROC curve AUC.
7. The method for predicting metabolic-related fatty liver disease based on creatinine and cystatin C ratio according to claim 1, wherein in step (6), six index values of the detected population are input into the prediction model, and after obtaining the corresponding risk of suffering from MAFLD, the method further comprises a step of screening out a population at high risk of suffering from MAFLD, comprising:
and marking the people with MAFLD disease risks exceeding the reference value in the detected people, and reminding the people to seek medical attention in time.
8. The method for predicting metabolic-related fatty liver disease based on the ratio of creatinine to cystatin C according to claim 7, wherein the reference value is 63.7%.
9. An electronic device, comprising:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to implement the method for predicting metabolic-related fatty liver disease based on the creatinine to cystatin C ratio of any one of claims 1 to 8 when executing the instructions.
10. A computer-readable storage medium comprising instructions that instruct a device to perform the method of predicting a metabolic-related fatty liver disease based on a creatinine to cystatin C ratio of any one of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310489636.6A CN116705286B (en) | 2023-05-04 | 2023-05-04 | Prediction method based on metabolism-related fatty liver disease, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310489636.6A CN116705286B (en) | 2023-05-04 | 2023-05-04 | Prediction method based on metabolism-related fatty liver disease, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116705286A CN116705286A (en) | 2023-09-05 |
| CN116705286B true CN116705286B (en) | 2024-03-08 |
Family
ID=87834757
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310489636.6A Active CN116705286B (en) | 2023-05-04 | 2023-05-04 | Prediction method based on metabolism-related fatty liver disease, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116705286B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3296744A1 (en) * | 2016-09-16 | 2018-03-21 | Biopredictive | Method of diagnosis of non-alcoholic fatty liver diseases |
| CN111063440A (en) * | 2019-12-31 | 2020-04-24 | 苏州和锐生物科技有限公司 | Early non-alcoholic fatty liver disease evaluation model, construction method and application thereof |
| CN113160983A (en) * | 2021-04-09 | 2021-07-23 | 南京医科大学附属逸夫医院 | Metabolism-related fatty liver disease clinical prediction model |
| CN115910334A (en) * | 2022-10-31 | 2023-04-04 | 浙江大学 | Dynamic prediction model for risk of early new-onset hypertriglyceridemia after liver transplantation of recipients |
| CN115910322A (en) * | 2022-11-06 | 2023-04-04 | 集美大学 | Non-alcoholic fatty liver disease diagnosis model and construction method and system thereof |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3599615A1 (en) * | 2018-07-27 | 2020-01-29 | Biopredictive | Method of diagnosis of liver steatosis |
| US20210298638A1 (en) * | 2020-03-27 | 2021-09-30 | Hygieia Sciences LLC | Method of Detection of Fatty Liver Diseases by Breath Analysis |
-
2023
- 2023-05-04 CN CN202310489636.6A patent/CN116705286B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3296744A1 (en) * | 2016-09-16 | 2018-03-21 | Biopredictive | Method of diagnosis of non-alcoholic fatty liver diseases |
| CN111063440A (en) * | 2019-12-31 | 2020-04-24 | 苏州和锐生物科技有限公司 | Early non-alcoholic fatty liver disease evaluation model, construction method and application thereof |
| CN113160983A (en) * | 2021-04-09 | 2021-07-23 | 南京医科大学附属逸夫医院 | Metabolism-related fatty liver disease clinical prediction model |
| CN115910334A (en) * | 2022-10-31 | 2023-04-04 | 浙江大学 | Dynamic prediction model for risk of early new-onset hypertriglyceridemia after liver transplantation of recipients |
| CN115910322A (en) * | 2022-11-06 | 2023-04-04 | 集美大学 | Non-alcoholic fatty liver disease diagnosis model and construction method and system thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116705286A (en) | 2023-09-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | ZJU index: a novel model for predicting nonalcoholic fatty liver disease in a Chinese population | |
| JP6235583B2 (en) | Method for detecting and staging liver fibrosis from image acquisition data | |
| US20210208147A1 (en) | Method of prognosis and follow up of primary liver cancer | |
| Choi et al. | Magnetic resonance-based assessments better capture pathophysiologic profiles and progression in nonalcoholic fatty liver disease | |
| Atta et al. | Sonography as a predictor of human immunodeficiency virus–associated nephropathy | |
| Tang et al. | Among simple non-invasive scores, Pro-C3 and ADAPT best exclude advanced fibrosis in Asian patients with MAFLD | |
| Shen et al. | Relationship between obesity, metabolic syndrome, and nonalcoholic fatty liver disease in the elderly agricultural and fishing population of Taiwan | |
| US20190265241A1 (en) | Method of diagnosis of non-alcoholic fatty liver diseases | |
| Schulz et al. | Identifying high-risk NASH patients: what we know so far | |
| Procino et al. | Reducing NAFLD‐screening time: A comparative study of eight diagnostic methods offering an alternative to ultrasound scans | |
| Hong et al. | Reader agreement and accuracy of ultrasound features for hepatic steatosis | |
| Zhang et al. | A newly noninvasive model for prediction of non-alcoholic fatty liver disease: utility of serum prolactin levels | |
| Festi et al. | Non-invasive diagnostic approach to non-alcoholic fatty liver disease: current evidence and future perspectives | |
| Tang et al. | N-terminal propeptide of type 3 collagen-based sequential algorithm can identify high-risk steatohepatitis and fibrosis in MAFLD | |
| RU2523661C1 (en) | Method of screening hepatic disorders, and system for implementing method | |
| JP7170368B2 (en) | Disease risk assessment method, disease risk assessment device, and disease risk assessment program | |
| Lu et al. | Adiponectin–leptin ratio for the early detection of lean non-alcoholic fatty liver disease independent of insulin resistance | |
| Frankland et al. | Diagnostic performance of ultrasound hepatorenal index for the diagnosis of hepatic steatosis in children | |
| Sourianarayanane et al. | Accuracy of ultrasonographic fatty liver index using point-of-care ultrasound in stratifying non-alcoholic fatty liver disease patients | |
| CN116705286B (en) | Prediction method based on metabolism-related fatty liver disease, electronic equipment and storage medium | |
| CN115602319B (en) | Noninvasive hepatic fibrosis assessment device | |
| JP2018512208A (en) | Computerized optical analysis method of MR (magnetic resonance) images for quantifying or determining liver lesions | |
| LU504525B1 (en) | Prediction method, electronic device and storage medium for metabolic associated fatty liver disease based on creatinine to cystatin c ratio | |
| Qiu et al. | The newly proposed alanine aminotransferase to high-density lipoprotein cholesterol ratio has shown effectiveness in identifying non-alcoholic fatty liver disease | |
| De Almeida et al. | Evaluation of an instrument for screening patients at risk for chronic kidney disease: testing SCORED (Screening for Occult Renal Disease) in a Portuguese population |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |