CN116030963A - Alpha fetoprotein negative primary hepatocellular carcinoma nomogram diagnosis model, construction method and application thereof - Google Patents
Alpha fetoprotein negative primary hepatocellular carcinoma nomogram diagnosis model, construction method and application thereof Download PDFInfo
- Publication number
- CN116030963A CN116030963A CN202211742555.4A CN202211742555A CN116030963A CN 116030963 A CN116030963 A CN 116030963A CN 202211742555 A CN202211742555 A CN 202211742555A CN 116030963 A CN116030963 A CN 116030963A
- Authority
- CN
- China
- Prior art keywords
- hepatocellular carcinoma
- alpha fetoprotein
- primary hepatocellular
- model
- negative primary
- 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.)
- Pending
Links
- 206010073071 hepatocellular carcinoma Diseases 0.000 title claims abstract description 69
- 231100000844 hepatocellular carcinoma Toxicity 0.000 title claims abstract description 69
- 102000013529 alpha-Fetoproteins Human genes 0.000 title claims abstract description 65
- 108010026331 alpha-Fetoproteins Proteins 0.000 title claims abstract description 65
- 238000003745 diagnosis Methods 0.000 title claims abstract description 40
- 238000010276 construction Methods 0.000 title claims abstract description 12
- 238000007477 logistic regression Methods 0.000 claims abstract description 13
- 108010094028 Prothrombin Proteins 0.000 claims description 35
- 102100027378 Prothrombin Human genes 0.000 claims description 35
- 229940039716 prothrombin Drugs 0.000 claims description 35
- 108010063628 acarboxyprothrombin Proteins 0.000 claims description 22
- 230000002159 abnormal effect Effects 0.000 claims description 18
- 210000003743 erythrocyte Anatomy 0.000 claims description 13
- 102000002260 Alkaline Phosphatase Human genes 0.000 claims description 11
- 108020004774 Alkaline Phosphatase Proteins 0.000 claims description 11
- WQZGKKKJIJFFOK-GASJEMHNSA-N Glucose Natural products OC[C@H]1OC(O)[C@H](O)[C@@H](O)[C@@H]1O WQZGKKKJIJFFOK-GASJEMHNSA-N 0.000 claims description 11
- 102000001554 Hemoglobins Human genes 0.000 claims description 11
- 108010054147 Hemoglobins Proteins 0.000 claims description 11
- 102000012406 Carcinoembryonic Antigen Human genes 0.000 claims description 9
- 108010022366 Carcinoembryonic Antigen Proteins 0.000 claims description 9
- 210000004369 blood Anatomy 0.000 claims description 9
- 239000008280 blood Substances 0.000 claims description 9
- BPYKTIZUTYGOLE-IFADSCNNSA-N Bilirubin Chemical compound N1C(=O)C(C)=C(C=C)\C1=C\C1=C(C)C(CCC(O)=O)=C(CC2=C(C(C)=C(\C=C/3C(=C(C=C)C(=O)N\3)C)N2)CCC(O)=O)N1 BPYKTIZUTYGOLE-IFADSCNNSA-N 0.000 claims description 8
- 208000019425 cirrhosis of liver Diseases 0.000 claims description 8
- 210000001616 monocyte Anatomy 0.000 claims description 8
- 102100036475 Alanine aminotransferase 1 Human genes 0.000 claims description 7
- 108010082126 Alanine transaminase Proteins 0.000 claims description 7
- 108010088751 Albumins Proteins 0.000 claims description 7
- 102000009027 Albumins Human genes 0.000 claims description 7
- 108010003415 Aspartate Aminotransferases Proteins 0.000 claims description 7
- 102000004625 Aspartate Aminotransferases Human genes 0.000 claims description 7
- 102000004420 Creatine Kinase Human genes 0.000 claims description 7
- 108010042126 Creatine kinase Proteins 0.000 claims description 7
- 108020004206 Gamma-glutamyltransferase Proteins 0.000 claims description 7
- 102000003855 L-lactate dehydrogenase Human genes 0.000 claims description 7
- 108700023483 L-lactate dehydrogenases Proteins 0.000 claims description 7
- 102000006640 gamma-Glutamyltransferase Human genes 0.000 claims description 7
- 239000008103 glucose Substances 0.000 claims description 7
- 208000002672 hepatitis B Diseases 0.000 claims description 7
- 238000000611 regression analysis Methods 0.000 claims description 7
- 238000000034 method Methods 0.000 claims description 6
- 102000006395 Globulins Human genes 0.000 claims description 5
- 108010044091 Globulins Proteins 0.000 claims description 5
- 206010042135 Stomatitis necrotising Diseases 0.000 claims description 5
- 210000000265 leukocyte Anatomy 0.000 claims description 5
- 210000004698 lymphocyte Anatomy 0.000 claims description 5
- 210000000440 neutrophil Anatomy 0.000 claims description 5
- 201000008585 noma Diseases 0.000 claims description 5
- 239000000427 antigen Substances 0.000 claims description 4
- 102000036639 antigens Human genes 0.000 claims description 4
- 108091007433 antigens Proteins 0.000 claims description 4
- 150000001720 carbohydrates Chemical class 0.000 claims description 4
- 238000005534 hematocrit Methods 0.000 claims description 4
- OYPRJOBELJOOCE-UHFFFAOYSA-N Calcium Chemical compound [Ca] OYPRJOBELJOOCE-UHFFFAOYSA-N 0.000 claims description 3
- 108010049003 Fibrinogen Proteins 0.000 claims description 3
- 102000008946 Fibrinogen Human genes 0.000 claims description 3
- 108010044467 Isoenzymes Proteins 0.000 claims description 3
- 108090000190 Thrombin Proteins 0.000 claims description 3
- 210000003651 basophil Anatomy 0.000 claims description 3
- 239000011575 calcium Substances 0.000 claims description 3
- 229910052791 calcium Inorganic materials 0.000 claims description 3
- 210000003979 eosinophil Anatomy 0.000 claims description 3
- 229940012952 fibrinogen Drugs 0.000 claims description 3
- 235000018102 proteins Nutrition 0.000 claims description 3
- 102000004169 proteins and genes Human genes 0.000 claims description 3
- 108090000623 proteins and genes Proteins 0.000 claims description 3
- 229960004072 thrombin Drugs 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 238000008789 Direct Bilirubin Methods 0.000 claims description 2
- FYYHWMGAXLPEAU-UHFFFAOYSA-N Magnesium Chemical compound [Mg] FYYHWMGAXLPEAU-UHFFFAOYSA-N 0.000 claims description 2
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 claims description 2
- 238000008050 Total Bilirubin Reagent Methods 0.000 claims description 2
- 230000036541 health Effects 0.000 claims description 2
- 239000011777 magnesium Substances 0.000 claims description 2
- 229910052749 magnesium Inorganic materials 0.000 claims description 2
- 239000011574 phosphorus Substances 0.000 claims description 2
- 229910052698 phosphorus Inorganic materials 0.000 claims description 2
- DDRJAANPRJIHGJ-UHFFFAOYSA-N creatinine Chemical compound CN1CC(=O)NC1=N DDRJAANPRJIHGJ-UHFFFAOYSA-N 0.000 claims 2
- DGAQECJNVWCQMB-PUAWFVPOSA-M Ilexoside XXIX Chemical compound C[C@@H]1CC[C@@]2(CC[C@@]3(C(=CC[C@H]4[C@]3(CC[C@@H]5[C@@]4(CC[C@@H](C5(C)C)OS(=O)(=O)[O-])C)C)[C@@H]2[C@]1(C)O)C)C(=O)O[C@H]6[C@@H]([C@H]([C@@H]([C@H](O6)CO)O)O)O.[Na+] DGAQECJNVWCQMB-PUAWFVPOSA-M 0.000 claims 1
- ZLMJMSJWJFRBEC-UHFFFAOYSA-N Potassium Chemical compound [K] ZLMJMSJWJFRBEC-UHFFFAOYSA-N 0.000 claims 1
- LEHOTFFKMJEONL-UHFFFAOYSA-N Uric Acid Chemical compound N1C(=O)NC(=O)C2=C1NC(=O)N2 LEHOTFFKMJEONL-UHFFFAOYSA-N 0.000 claims 1
- TVWHNULVHGKJHS-UHFFFAOYSA-N Uric acid Natural products N1C(=O)NC(=O)C2NC(=O)NC21 TVWHNULVHGKJHS-UHFFFAOYSA-N 0.000 claims 1
- PNNCWTXUWKENPE-UHFFFAOYSA-N [N].NC(N)=O Chemical compound [N].NC(N)=O PNNCWTXUWKENPE-UHFFFAOYSA-N 0.000 claims 1
- 229940109239 creatinine Drugs 0.000 claims 1
- 239000011591 potassium Substances 0.000 claims 1
- 229910052700 potassium Inorganic materials 0.000 claims 1
- 239000011734 sodium Substances 0.000 claims 1
- 229910052708 sodium Inorganic materials 0.000 claims 1
- 229940116269 uric acid Drugs 0.000 claims 1
- 238000001514 detection method Methods 0.000 abstract description 4
- 230000000694 effects Effects 0.000 abstract description 3
- 230000000007 visual effect Effects 0.000 abstract description 2
- 210000003494 hepatocyte Anatomy 0.000 abstract 1
- 238000012216 screening Methods 0.000 description 9
- 238000010200 validation analysis Methods 0.000 description 9
- 230000008901 benefit Effects 0.000 description 7
- 238000012549 training Methods 0.000 description 6
- 206010016654 Fibrosis Diseases 0.000 description 5
- 206010028980 Neoplasm Diseases 0.000 description 5
- 230000007882 cirrhosis Effects 0.000 description 5
- 230000035945 sensitivity Effects 0.000 description 5
- 208000000419 Chronic Hepatitis B Diseases 0.000 description 4
- 238000004820 blood count Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 238000011088 calibration curve Methods 0.000 description 3
- 210000000170 cell membrane Anatomy 0.000 description 3
- 230000003908 liver function Effects 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 102000004190 Enzymes Human genes 0.000 description 2
- 108090000790 Enzymes Proteins 0.000 description 2
- 102000004641 Fetal Proteins Human genes 0.000 description 2
- 108010003471 Fetal Proteins Proteins 0.000 description 2
- -1 IBIL Proteins 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 201000011510 cancer Diseases 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 230000015271 coagulation Effects 0.000 description 2
- 238000005345 coagulation Methods 0.000 description 2
- 229940088598 enzyme Drugs 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000002107 myocardial effect Effects 0.000 description 2
- 238000010827 pathological analysis Methods 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 206010008909 Chronic Hepatitis Diseases 0.000 description 1
- 238000011394 anticancer treatment Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005773 cancer-related death Effects 0.000 description 1
- 231100000504 carcinogenesis Toxicity 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 238000013524 data verification Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000013399 early diagnosis Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000002489 hematologic effect Effects 0.000 description 1
- 208000006454 hepatitis Diseases 0.000 description 1
- 230000003907 kidney function Effects 0.000 description 1
- 238000009533 lab test Methods 0.000 description 1
- 210000004185 liver Anatomy 0.000 description 1
- 208000014018 liver neoplasm Diseases 0.000 description 1
- 230000036210 malignancy Effects 0.000 description 1
- 230000001394 metastastic effect Effects 0.000 description 1
- 206010061289 metastatic neoplasm Diseases 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011119 multifactor regression analysis Methods 0.000 description 1
- 238000011369 optimal treatment Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000001356 surgical procedure Methods 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Images
Classifications
-
- 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
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention discloses a alpha fetoprotein negative primary hepatocellular carcinoma nomographic diagnosis model, a construction method and application thereof. According to the invention, clinical characteristic data of a patient with alpha fetoprotein negative primary hepatocytes is collected, independent predictors related to alpha fetoprotein negative primary hepatocellular carcinoma are screened out by utilizing a single factor logistics, LASSO, the independent predictors are incorporated into multi-factor logistic regression analysis, the joint diagnosis effect of a plurality of indexes is analyzed, a probability prediction model with better performance is selected, and a alpha fetoprotein negative primary hepatocellular carcinoma nomogram diagnosis model is established. The alpha fetoprotein negative primary hepatocellular carcinoma nomogram diagnosis model is simple and visual, only needs clinical common detection results, does not need to increase the burden of patients, and is suitable for clinical rapid application.
Description
Technical Field
The invention belongs to the technical field of diagnosis, and relates to a alpha fetoprotein negative primary hepatocellular carcinoma diagnosis model, a construction method and application thereof.
Background
Primary hepatocellular carcinoma (HCC) accounts for 75% -85% of liver cancers, and is the predominant type. HCC has become the sixth largest cancer worldwide as a rapidly advancing, relapsing and metastatic malignancy, and is the third leading cause of cancer-related death. Due to the hidden onset and the lack of effective early diagnosis means, a plurality of patients reach late stage when diagnosis is confirmed, so that the optimal treatment opportunity is missed. Therefore, searching for more effective screening and diagnostic markers can effectively improve the diagnosis efficiency of HCC and improve the survival outcome of patients.
Currently, alpha Fetoprotein (AFP) is the most widely used hematological screening means for HCC, but data indicate that about 30% of HCC patients appear to be free of AFP elevation, and therefore a fraction of AFP-negative primary hepatocellular carcinoma becomes the screening "blind zone". Furthermore, benign diseases of the liver such as cirrhosis, chronic hepatitis may also manifest as elevated AFP. Several other single indicators have been found to aid in the diagnosis of HCC, such as abnormal prothrombin (PIVKA-II), alpha fetoprotein heterosomes (AFP-L3%), etc. The PIVKA-II single index still has the problem of low sensitivity when being used for assisting in diagnosing HCC. There is enough evidence that combining multiple indicators can effectively improve diagnostic sensitivity and specificity and diagnostic efficacy. Various models have been currently constructed for the diagnosis of HCC, but most of the utility in diagnosing AFP-negative HCC is not validated based on the collocation between AFP and different markers. In addition, the disadvantages include: the part of the models adopt novel indexes which are not widely applied in clinic, and are not easy to popularize and apply in clinic; also part of the model is not verified by multi-center large-scale data; when most models are used, complex calculation is needed according to a formula, and the operation is complicated.
The alignment chart (Alignment Diagram), also called Nomogram chart, is based on multi-factor regression analysis, integrates a plurality of predictors, and then adopts line segments with scales to draw on the same plane according to a certain proportion so as to express the interrelationship between various variables in the predictive model.
Disclosure of Invention
In order to overcome the defects of the existing markers and diagnostic models, the invention aims to provide a diagnostic model combined by clinical conventional detection indexes and aiming at alpha fetoprotein negative primary hepatocellular carcinoma, and a construction method and application thereof.
In order to achieve the above purpose, the invention adopts the following technical scheme:
a method for constructing a diagnosis model of alpha fetoprotein negative primary hepatocellular carcinoma comprises the following steps:
(1) The data of relevant clinical characteristics before primary hepatocellular carcinoma after surgical excision and pathological diagnosis is collected, including demographic data (sex, age), average hemoglobin concentration (MCHC), red blood cell distribution width (RDW), platelet count (PLT), tumor markers such as Alpha Fetoprotein (AFP), carcinoembryonic antigen (CEA), carbohydrate antigen 199 (CA), abnormal prothrombin (PIVKA-II), liver function index such as alanine Aminotransferase (ALT), aspartate Aminotransferase (AST), gamma-glutamyltransferase (GGT), alkaline phosphatase (ALC), red blood cell count (RBC), hemoglobin content (HGB), red blood cell pressure volume (HCT), average red blood cell volume (MCV), average hemoglobin content (MCH), average hemoglobin concentration (MCHC), red blood cell distribution width (RDW), platelet count (PLT), tumor markers such as Alpha Fetoprotein (AFP), carcinoembryonic antigen (CEA), carbohydrate antigen 199 (PIVKA-II), liver function index such as alanine Aminotransferase (ALT), aspartate Aminotransferase (AST), gamma-glutamyltransferase (GGT), alkaline phosphatase (ALP), total hemoglobin (IL), direct magnesium bilirubin (UK), and direct bilirubin (UA (UK) are collected, blood phosphorus (P), blood Calcium (CA); myocardial enzyme index: creatine Kinase (CK), creatine kinase isozymes (CKMB), lactate Dehydrogenase (LDH); coagulation function index: prothrombin Time (PT), partial prothrombin time (APTT), international Normalized Ratio (INR), fibrinogen (Fg), thrombin Time (TT); blood Glucose (GLU), total Protein (TP), albumin (ALB), globulin (GLO)); meanwhile, collecting relevant clinical characteristic data of the people with hepatitis B, liver cirrhosis and health physical examination as a control group; the final training set was incorporated into 294 patients with alpha fetoprotein negative hepatocellular carcinoma, 63 patients with chronic hepatitis B, 64 patients with cirrhosis, and 159 healthy physical examination groups for model construction; an external validation set from another hospital included 227 patients with fetoprotein negative hepatocellular carcinoma, 47 patients with chronic hepatitis b, 45 patients with cirrhosis, and 137 healthy physical examination populations for model validation;
(2) Carrying out single-factor logistic regression analysis on the clinical characteristic data in the step (1), primarily screening out single-factor prediction variables related to primary hepatocellular carcinoma of alpha fetoprotein negative, and screening out 17P<Incorporating 0.05 single factor predictive variables (gender, age, CEA, PIVKA-II, lymphocyte counts, monocyte counts, neutrophil counts, PLT, WBC, ALB, ALP, GLU, IBIL, LDH, TP, APTT, fg, PT) into LASSO regression analysis, and further performing dimension reduction screening to obtain 8 independent predictors (gender, age, PIVKA-II, monocyte counts, PLT, ALP, PT, MCHC) related to alpha fetoprotein-negative primary hepatocellular carcinoma;
(3) Incorporating the independent predictors determined by LASSO regression analysis in (2) into multi-factor logistic regression analysis, analyzing the joint diagnosis effect of a plurality of indexes to obtain 4 key factors (age, PT, PLT, PIVKA-II) and constructing a diagnosis model of alpha fetoprotein negative primary hepatocellular carcinoma, wherein the prediction formula of the diagnosis model of alpha fetoprotein negative primary hepatocellular carcinoma is as follows:
wherein ,Prepresenting a predicted probability value, age representing Age, PIVKA-ii representing abnormal prothrombin (abnormal prothrombin variable is required to undergo level transformation according to the number of squares of the numerical distribution, wherein less than or equal to 20 mAU/ml=1, 20.1-30 mAU/ml=2, 301-178 mAU/ml=3; gtoreq 178.1 mAU/ml=4), PT represents prothrombin time, PLT represents platelet count;
(4) Drawing a nomographic diagnosis model based on the primary hepatocellular carcinoma diagnosis model of alpha fetoprotein negative in the step (3) by adopting a DynNom package of R language;
(5) Assessing the discriminatory power of the alignment diagnostic model by a subject work curve (ROC) and calculating the area under the curve (AUC); evaluating the degree of offset between the predicted value and the actual value by drawing a calibration curve; evaluating clinical practicality of the alignment diagnostic model by a Decision Curve (DCS) and a Clinical Impact Curve (CIC); meanwhile, the alignment chart diagnosis model is further verified in an external verification set with different sources, and finally the AUC (area under curve) of the model for distinguishing the AFP negative HCC from the control group is 0.937.
A model for diagnosing the alignment chart of primary hepatocellular carcinoma of alpha fetoprotein negative is obtained by the construction method.
Further, the above-mentioned a alpha fetoprotein negative primary hepatocellular carcinoma noma diagnostic model consists of 11 scales; the first scale is a score scale, and the score range is 0-100 minutes; the second scale is a platelet number scale, and the value range is 0-800 multiplied by 10 9 L, corresponding to 30-80 minutes; the third scale is an age scale, the value range is 24-90 years old, and the corresponding score is 40-100 minutes; the fourth scale is a prothrombin time scale, the value range is 9.8-23.4 seconds, and the corresponding score is 0-88 minutes; the fifth scale is an abnormal prothrombin scale, and after the abnormal prothrombin scale is converted into a grade variable according to the quartile of the numerical distribution, the numerical values of 1, 2, 3 and 4 respectively correspond to 40, 60, 80 and 100 minutes.
Further, the diagnosis model of the alpha fetoprotein negative primary hepatocellular carcinoma nomogram further comprises a total score value scoring formula, specifically:
total score = platelet count corresponding score + age corresponding score + prothrombin time corresponding score + abnormal prothrombin corresponding score.
The application of the alignment chart diagnosis model in preparing products for diagnosing or assisting in diagnosing alpha fetoprotein negative primary hepatocellular carcinoma.
The beneficial effects of the invention are as follows: the alpha fetoprotein negative primary hepatocellular carcinoma noma diagnostic model constructed by 4 clinical conventional detection indexes (age and PT, PLT, PIVKA-II) is simple and visual, has good diagnostic efficiency in the aspect of diagnosing AFP negative HCC, has higher sensitivity and specificity, and is favorable for clinical diagnosis through external data verification.
Drawings
Fig. 1: the invention discloses a diagnosis model of alpha fetoprotein negative primary hepatocellular carcinoma nomogram.
Fig. 2: the invention evaluates the distinguishing capability of the alpha fetoprotein negative primary hepatocellular carcinoma nomographic diagnostic model by drawing an ROC curve and calculating AUC and cut-off values. A: in the training set, the AUC of the model was 0.937, the cut-off value was 0.366, the corresponding Specificity was 0.902, and the sensitivity was 0.854.B: in the validation set, the AUC of the model was 0.942, the cut-off value was 0.290, the corresponding Specificity was 0.921, and the sensitivity was 0.882.
Fig. 3: according to the invention, the degree of coincidence between the predicted probability value and the true observed value of the primary hepatocellular carcinoma nomogram diagnostic model of alpha fetoprotein negative is estimated by drawing a calibration curve, and the diagnostic accuracy of the model is judged. The abscissa in the graph corresponds to the predicted probability value of the model for the primary hepatocellular carcinoma of the alpha fetoprotein negative patient, and the ordinate corresponds to the actual probability of the patient. The ideal prediction result is that the model prediction probability value is completely matched with the actual occurrence rate; the dotted line of the application is the actual representation of the model; the Bais-corrected actual representation of the sample after repeated self-sampling corrects the over-fitting condition. The actual performance of the model is close to the Idea line, which means that the model has better fitting degree between the prediction probability and the actual occurrence probability.
Fig. 4: the present invention evaluates its clinical utility by plotting the net gain of DCA and CIC (G-H) through the model. A: the model applies a Decision Curve (DCA) in the training set. B: the model applies a Decision Curve (DCA) in the validation set. The horizontal axis represents risk probability of illness (High Risk Threshold), and the vertical axis is Net gain after the Benefit minus the fraud (Net Benefit). When the risk probability is at a certain value, the model is adopted to predict, and the difference value between the benefit value of the detected true positive patient and the loss value of the detected false positive patient is the net benefit rate. The lower horizontal axis is the loss to gain Ratio (Cost: benefit Ratio). The curved diagonal lines in the figure represent the behavior of the diagnostic model in the training set (red) and the validation set (blue), respectively, the other two black lines represent the two extremes, the black horizontal lines represent that all patients did not apply the model, and the net benefit is 0; the black dashed line represents the change in net benefit as the threshold probability changes, using the model, for all patients to predict. The curve of the model in the graph is higher than two extreme cases in a larger risk probability range, and has a larger application value. C: the model applied Clinical Impact Curve (CIC) (red) in the training set. D: the model was applied to the Clinical Impact Curve (CIC) (blue) in the validation set. The ordinate represents the number of patients in 1000 using the model predicted at different risk probabilities. Red and blue curves (Number high risk) in the figure represent the Number of persons that are divided into positives (high risk) by the model at each threshold probability; the black curve (Number high risk with outcome) is the number of people who are truly positive at each threshold probability.
Detailed Description
In order to make the contents of the present invention more easily understood, the technical scheme of the present invention will be further described with reference to the specific embodiments, but the present invention is not limited thereto.
EXAMPLE 1 construction of a model for diagnosis of a primary hepatocellular carcinoma nomogram negative for alpha fetoprotein
1. Collecting HCC patient and control data
The group entering requirements are as follows: the primary hepatocellular carcinoma patient is obtained by surgical excision and pathological diagnosis; AFP negative (< 20 ng/mL); no other anti-cancer treatment was received prior to surgery; the clinical data are complete.
Collecting preoperative relevant demographic data (sex, age) of a patient meeting the conditions, and 48 common clinical laboratory test indicators (blood routine: neutrophil count (Neutrophil counts), monocyte count (Monocyte count), lymphocyte count (Lymphocyte counts), eosinophil count (Eosinophils counts), basophil count (Basophil count), white blood cell count (WBC), red blood cell count (RBC), hemoglobin content (HGB), hematocrit (HCT), mean red blood cell volume (MCV), mean hemoglobin content (MCH), mean hemoglobin concentration (MCHC), red blood cell distribution width (RDW), platelet count (PLT), tumor markers: alpha Fetoprotein (AFP), carcinoembryonic antigen (CEA), carbohydrate antigen 199 (CA 199), abnormal prothrombin (PIVKA-II), liver function indicators: alanine Aminotransferase (ALT), aspartate Aminotransferase (AST), gamma-glutamyltransferase (GGT), alkaline phosphatase (ALP), total bilirubin (DBIL), bilirubin (il), indirect bilirubin (il), renal function indicators (MG), plasma membrane (ea), plasma membrane (NA), and plasma membrane (NA), blood Calcium (CA); myocardial enzyme index: creatine Kinase (CK), creatine kinase isozymes (CKMB), lactate Dehydrogenase (LDH); coagulation function index: prothrombin Time (PT), partial prothrombin time (APTT), international Normalized Ratio (INR), fibrinogen (Fg), thrombin Time (TT); blood Glucose (GLU), total Protein (TP), albumin (ALB), globulin (GLO)).
And meanwhile, collecting relevant data of the hepatitis B, liver cirrhosis and healthy physical examination crowd as a control group.
The final training set was incorporated into 294 patients with alpha fetoprotein negative hepatocellular carcinoma, 63 patients with chronic hepatitis B, 64 patients with cirrhosis, and 159 healthy physical examination groups for model construction; an external validation set from another hospital included 227 patients with fetoprotein negative hepatocellular carcinoma, 47 patients with chronic hepatitis b, 45 patients with cirrhosis, and 137 healthy physical examination groups for model validation.
2. Logistic regression and LASSO regression analysis screening independent variables
The SPSS 22.0 software is adopted to carry out single factor logistic regression analysis on 50 clinical variables, and the result shows that 17 indexes of gender, age, CEA, PIVKA-II, lymphocyte counts, monocyte counts, neutrophil counts and PLT, WBC, ALB, ALP, GLU, IBIL, LDH, TP, APTT, fg, PT have statistical differencesP< 0.05) (table 1), a single factor predictive variable associated with alpha fetoprotein negative primary hepatocellular carcinoma; for further screening and dimension reduction, the single factor logistic regression analysisPVariables < 0.05 were included in the LASSO regression analysis to finally yield 8 independent predictors of sex, age, PIVKA-II, monocyte counts, PLT, ALP, PT, MCHC associated with alpha fetoprotein negative primary hepatocellular carcinoma (Table 2).
Table 1 single factor logistic regression results (n=17)
TABLE 2 LASSO regression results
3. Multi-factor logistic regression construction final model and model visualization
The 8 indexes (sex, age, PIVKA-II, monocyte counts and PLT, ALP, PT, MCHC) obtained by screening are taken into multi-factor logistic regression, the combined diagnosis effect of the multiple indexes is analyzed, and the final result shows that the age, PT, PLT, PIVKA-II and the total of 4 key indexes areP< 0.05) with maximum diagnostic efficacy, the results are expressed as OR values and 95% CI (Table 3).
TABLE 3 multifactor logistic regression results
The final logistic regression equation is
f(x)=-0.247+0.079（Age）+1.843（PIVKA-II）-0.588(PT)-0.006(PLT)
In order to facilitate calculation and application, age, prothrombin time and platelet count are directly substituted into calculation for numerical variables, and abnormal prothrombin variables are subjected to grade conversion according to the number of squares of numerical distribution, wherein the ratio of less than or equal to 20 mAU/mL=1; 20.1-30mAU/mL = 2;30.1-178mAU/mL = 3; gtoreq 178.1 mAU/ml=4.
The predicted probability value calculated from this equation is:
The application of this equation in clinic requires a number of complex operations, for which the equation is converted into a nomogram using the DynNom package in R software (FIG. 1). When the method is applied, the patient index is used for finding a corresponding point position (PIVKA-II needs to perform grade variable conversion) on a numerical axis, meanwhile, the scores projected to the uppermost scale line are recorded, the four variable scores are added to obtain a total score, and finally, a predicted probability value corresponding to the position of the total score is found, namely the possibility that the patient obtained through the nomogram has HCC. In the nomogram, a first behavior score scale is used, and the score range is 0-100 minutes; a second behavior platelet count (PLT) scale with a value ranging from 0 to 800 x 10 9 L, the corresponding score is 30-80 minutes; the third action Age (Age) scale is 24-90 years old, and the corresponding score is 40-100 minutes; a fourth action Prothrombin Time (PT) scale, wherein the value range is 9.8-23.4 seconds, and the corresponding score is 0-88 minutes; the fifth behavior is abnormal prothrombin (PIVKA-II) scale, and after the quartile of the numerical distribution is converted into a grade variable, the numerical values of 1, 2, 3 and 4 respectively correspond to 40, 60, 80 and 100 minutes. And obtaining a single score corresponding to the single score above each index, and adding to obtain a total score, wherein a predicted probability value corresponding to the lower total score is the probability that the model predicts the patient suffers from HCC. Such as a 65 year old patient corresponding score(corresponding score: 79 points) with a PLT of 195X 10 9 With a score of 66 per liter, a score of 11.8s (79 per liter) for PT and a score of 322mAU/mL for PIVKA-II (4 for a score of 100), the patient adds up a total score of 324 in the model with a corresponding predicted probability value of 0.989.
4. Model verification
(1) The constructed alpha fetoprotein negative primary hepatocellular carcinoma noma diagnostic model was evaluated by ROC curve and AUC (area under curve) was calculated, the ability of the model to distinguish alpha fetoprotein negative primary hepatocellular carcinoma (AFPN-HCC) from the control group was evaluated (fig. 2A), resulting in AUC:0.937 (95% CI: 0.892-0.938) while validated by an external validation set (FIG. 2B), see AUC:0.942 The results show that the diagnosis model of the alpha fetoprotein negative primary hepatocellular carcinoma nomogram constructed by the invention has better diagnosis efficiency.
(2) The deviation between the predicted value and the actual observed value of the diagnosis of the established alpha fetoprotein negative primary hepatocellular carcinoma nomogram is evaluated by drawing a calibration curve, and a relatively good agreement is found between the predicted value and the actual observed value (figure 3).
(3) The clinical practicality of the established alpha fetoprotein negative primary hepatocellular carcinoma nomographic diagnosis model is evaluated by drawing DCA and CIC, and the model can be seen to obtain better net benefit (figure 4).
From the above verification it can be concluded that: the alpha fetoprotein negative primary hepatocellular carcinoma diagnosis model built based on 4 clinical common laboratory detection indexes including age, platelet count (PLT), prothrombin Time (PT) and abnormal prothrombin (PIVKA-II) has higher application value for diagnosis of AFP negative HCC, and has clinical practicability after being visually converted into a nomogram.
The foregoing description is only of the preferred embodiments of the invention, and all changes and modifications that come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.
Claims (6)
1. A construction method of a alpha fetoprotein negative primary hepatocellular carcinoma nomographic diagnosis model is characterized by comprising the following steps: the method comprises the following steps: s1: collecting clinical profile data of a patient with alpha fetoprotein negative primary hepatocellular carcinoma, including sex, age, neutrophil count, monocyte count, lymphocyte count, eosinophil count, basophil, leukocyte count, erythrocyte count, hemoglobin content, hematocrit, mean red blood cell volume, mean hemoglobin content, mean hemoglobin concentration, distribution width of red blood cells, platelet count, alpha fetoprotein, carcinoembryonic antigen, carbohydrate antigen 199, abnormal prothrombin, alanine aminotransferase, aspartate aminotransferase, gamma-glutamyl transferase, alkaline phosphatase, total bilirubin, direct bilirubin, indirect bilirubin, creatinine, uric acid, urea nitrogen, potassium, sodium, magnesium, blood phosphorus, blood calcium, creatine kinase isozyme, lactate dehydrogenase, prothrombin time, partial prothrombin time, international normalized ratio, fibrinogen, thrombin time, blood glucose, total protein, albumin and globulin, while collecting clinical profile data of a patient with hepatitis B, liver cirrhosis patient, and health physical examination population as a control;
s2: regression analysis is carried out on the clinical characteristic data collected in S1 by utilizing single-factor logistic regression analysis, and single-factor prediction variables related to primary hepatocellular carcinoma of alpha fetoprotein negative are primarily screened outP <0.05 variable is included in LASSO regression analysis, and independent predictors related to alpha fetoprotein negative primary hepatocellular carcinoma are screened out;
s3: and (3) incorporating the independent predictors determined according to the LASSO regression analysis in the S2 into a multi-factor logistic regression analysis, and finally selecting the age, the prothrombin time, the platelet count and the abnormal prothrombin to construct a diagnosis model of alpha fetoprotein negative primary hepatocellular carcinoma, wherein the prediction formula of the diagnosis model of alpha fetoprotein negative primary hepatocellular carcinoma is as follows:
wherein ,Prepresenting pre-emphasisA probability value, age, PIVKA-II, abnormal prothrombin, PT, prothrombin time and PLT, platelet count; the PIVKA-II is subjected to grade transformation according to the four directions of numerical distribution, wherein the grade transformation is less than or equal to 20 mAU/mL=1, 20.1-30 mAU/mL=2, 30.1-178 mAU/mL=3, and more than or equal to 178.1 mAU/mL=4;
s4: and drawing a nomographic model based on the diagnosis model of alpha fetoprotein negative primary hepatocellular carcinoma in S3 by adopting a DynNom package of R language.
2. The method for constructing a diagnosis model of alpha fetoprotein negative primary hepatocellular carcinoma nomogram, according to claim 1, wherein the method comprises the following steps: the method also comprises the steps of:
s5: and (4) evaluating the alignment chart model drawn in the step (S4) by adopting an ROC curve, a DCA curve and a CIC curve.
3. A model for diagnosis of a primary hepatocellular carcinoma noma negative for alpha fetoprotein, characterized in that: obtained by the construction method according to claim 1.
4. A alpha fetoprotein negative primary hepatocellular carcinoma nomographic model according to claim 3, characterized in that: the alpha fetoprotein negative primary hepatocellular carcinoma noma diagnosis model consists of 11 scales; wherein the first scale is a score scale, and the score range is 0-100 minutes; the second scale is platelet number scale with value range of 0-800×10 9 L, corresponding score of 30-80; the third scale is an age scale, the value range is 24-90 years old, and the corresponding score is 40-100 minutes; the fourth scale is a prothrombin time scale, the value range is 9.8-23.4 seconds, and the corresponding score is 0-88 minutes; the fifth scale is an abnormal prothrombin scale, and after the abnormal prothrombin scale is converted into a grade variable according to the quartile of the numerical distribution, the numerical values of 1, 2, 3 and 4 respectively correspond to 40, 60, 80 and 100 minutes.
5. The diagnostic model of alpha fetoprotein negative primary hepatocellular carcinoma nomogram according to claim 4, wherein: the alpha fetoprotein negative primary hepatocellular carcinoma nomogram diagnosis model also comprises a total score scoring formula, which specifically comprises the following steps:
total score = platelet count corresponding score + age corresponding score + prothrombin time corresponding score + abnormal prothrombin corresponding score.
6. Use of the alignment diagnostic model of claim 3 for the preparation of a product for diagnosis or assisted diagnosis of alpha fetoprotein negative primary hepatocellular carcinoma.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211742555.4A CN116030963A (en) | 2022-12-30 | 2022-12-30 | Alpha fetoprotein negative primary hepatocellular carcinoma nomogram diagnosis model, construction method and application thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211742555.4A CN116030963A (en) | 2022-12-30 | 2022-12-30 | Alpha fetoprotein negative primary hepatocellular carcinoma nomogram diagnosis model, construction method and application thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116030963A true CN116030963A (en) | 2023-04-28 |
Family
ID=86090742
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211742555.4A Pending CN116030963A (en) | 2022-12-30 | 2022-12-30 | Alpha fetoprotein negative primary hepatocellular carcinoma nomogram diagnosis model, construction method and application thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116030963A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116825362A (en) * | 2023-08-29 | 2023-09-29 | 北京回龙观医院(北京心理危机研究与干预中心) | Diagnostic prediction model for alcoholic liver injury and construction method and application method thereof |
-
2022
- 2022-12-30 CN CN202211742555.4A patent/CN116030963A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116825362A (en) * | 2023-08-29 | 2023-09-29 | 北京回龙观医院(北京心理危机研究与干预中心) | Diagnostic prediction model for alcoholic liver injury and construction method and application method thereof |
| CN116825362B (en) * | 2023-08-29 | 2024-01-02 | 北京回龙观医院(北京心理危机研究与干预中心) | Diagnostic prediction model for alcoholic liver injury and construction method and application method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107153774A (en) | The disease forecasting system of the structure and application of chronic disease risk assessment the hyperbolic model model | |
| JP2009535644A (en) | Method and apparatus for identifying disease status using biomarkers | |
| CN113327679A (en) | Pulmonary embolism clinical risk and prognosis scoring method and system | |
| CN109830264B (en) | Method for classifying tumor patients based on methylation sites | |
| CN113851185B (en) | Prognosis evaluation method for immunotherapy of non-small cell lung cancer patient | |
| CN111584082A (en) | Establishment and application of primary hepatocellular carcinoma microvascular invasion regression prediction model based on clinical examination multidimensional data | |
| CN116030963A (en) | Alpha fetoprotein negative primary hepatocellular carcinoma nomogram diagnosis model, construction method and application thereof | |
| CN109585011A (en) | The Illnesses Diagnoses method and machine readable storage medium of chest pain patients | |
| CN114864080A (en) | Method, system, equipment and medium for establishing liver cancer diagnosis model C-GALAD II | |
| CN114093517A (en) | Cancer screening method and system based on blood indexes and cfDNA | |
| CN112201318A (en) | Application method of laboratory index model in risk stratification of COVID-19 patients | |
| CN114141371B (en) | System for predicting prognosis of liver cancer associated with tumor-related anemia patient caused by hepatitis B virus infection | |
| CN111613324A (en) | Method for predicting liver cancer risk by high-throughput analysis of hepatitis B virus genome RT/S region sequence characteristics through machine learning model | |
| CN110911008A (en) | Method for establishing biliary tract occluded alignment chart prediction model and application thereof | |
| CN110148471A (en) | Liver and gallbladder tumor patient survival rate prediction data collection system and model building method | |
| CN111192687A (en) | Line graph prediction model for advanced appendicitis and application thereof | |
| CN114496210A (en) | ST-segment-elevation-type myocardial infarction prognosis scoring system | |
| Castaldo et al. | Differential diagnosis between hepatocellular carcinoma and cirrhosis through a discriminant function based on results for serum analytes | |
| Sheng et al. | Higher mean corpuscular hemoglobin concentration is associated with worse prognosis of hepatorenal syndrome: a multicenter retrospective study | |
| CN114252612B (en) | Liver cancer metastasis prediction system and method based on nerve cell adhesion molecules | |
| CN105671179A (en) | Application of serum microRNA in liver cancer diagnosis and diagnosis kit | |
| CN110993092B (en) | NGFP diagnostic index acquisition method and high-risk HCC prediction model construction method | |
| Han et al. | Development and validation of a nomogram for predicting death within 2 days after intracerebral hemorrhage | |
| CN108417267B (en) | System for determining short-term prognosis of patient with liver cirrhosis hepatorenal syndrome | |
| Cao et al. | Construction and evaluation of a risk prediction model for pulmonary infection‐associated acute kidney injury in intensive care units |
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 |