CN117133439A - Ovarian malignancy and juncture tumor diagnosis model construction method - Google Patents
Ovarian malignancy and juncture tumor diagnosis model construction method Download PDFInfo
- Publication number
- CN117133439A CN117133439A CN202310602283.6A CN202310602283A CN117133439A CN 117133439 A CN117133439 A CN 117133439A CN 202310602283 A CN202310602283 A CN 202310602283A CN 117133439 A CN117133439 A CN 117133439A
- Authority
- CN
- China
- Prior art keywords
- tumor
- model
- reference range
- ovarian
- malignancy
- 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
- 206010028980 Neoplasm Diseases 0.000 title claims abstract description 215
- 201000011510 cancer Diseases 0.000 title claims abstract description 89
- 230000036210 malignancy Effects 0.000 title claims abstract description 78
- 230000002611 ovarian Effects 0.000 title claims abstract description 78
- 238000003745 diagnosis Methods 0.000 title claims abstract description 36
- 238000010276 construction Methods 0.000 title description 2
- 238000000034 method Methods 0.000 claims abstract description 46
- 206010061535 Ovarian neoplasm Diseases 0.000 claims abstract description 44
- 206010033128 Ovarian cancer Diseases 0.000 claims abstract description 27
- 238000011282 treatment Methods 0.000 claims abstract description 19
- 230000035945 sensitivity Effects 0.000 claims abstract description 15
- 230000002980 postoperative effect Effects 0.000 claims abstract description 11
- 206010061336 Pelvic neoplasm Diseases 0.000 claims abstract description 4
- 210000002966 serum Anatomy 0.000 claims description 44
- 238000012795 verification Methods 0.000 claims description 23
- 208000031513 cyst Diseases 0.000 claims description 22
- 230000003902 lesion Effects 0.000 claims description 22
- 238000012360 testing method Methods 0.000 claims description 22
- 238000012549 training Methods 0.000 claims description 22
- 238000011156 evaluation Methods 0.000 claims description 21
- 238000000926 separation method Methods 0.000 claims description 21
- 206010003445 Ascites Diseases 0.000 claims description 20
- 101000650344 Homo sapiens RecQ-mediated genome instability protein 1 Proteins 0.000 claims description 20
- 102100027431 RecQ-mediated genome instability protein 1 Human genes 0.000 claims description 20
- 230000003211 malignant effect Effects 0.000 claims description 19
- 230000007170 pathology Effects 0.000 claims description 19
- 239000007787 solid Substances 0.000 claims description 18
- 238000013058 risk prediction model Methods 0.000 claims description 17
- 238000002604 ultrasonography Methods 0.000 claims description 15
- 206010011732 Cyst Diseases 0.000 claims description 14
- 230000017531 blood circulation Effects 0.000 claims description 14
- 238000007477 logistic regression Methods 0.000 claims description 13
- 238000001514 detection method Methods 0.000 claims description 12
- 238000007689 inspection Methods 0.000 claims description 12
- 210000004698 lymphocyte Anatomy 0.000 claims description 12
- 230000008901 benefit Effects 0.000 claims description 11
- 230000001575 pathological effect Effects 0.000 claims description 10
- 230000001788 irregular Effects 0.000 claims description 9
- 206010061289 metastatic neoplasm Diseases 0.000 claims description 9
- 238000010827 pathological analysis Methods 0.000 claims description 9
- 210000000601 blood cell Anatomy 0.000 claims description 8
- 238000011088 calibration curve Methods 0.000 claims description 8
- 210000000440 neutrophil Anatomy 0.000 claims description 8
- 230000009245 menopause Effects 0.000 claims description 7
- 239000000523 sample Substances 0.000 claims description 7
- 208000030507 AIDS Diseases 0.000 claims description 6
- 102000009027 Albumins Human genes 0.000 claims description 6
- 108010088751 Albumins Proteins 0.000 claims description 6
- 208000023275 Autoimmune disease Diseases 0.000 claims description 6
- 102000004420 Creatine Kinase Human genes 0.000 claims description 6
- 108010042126 Creatine kinase Proteins 0.000 claims description 6
- 102000006395 Globulins Human genes 0.000 claims description 6
- 108010044091 Globulins Proteins 0.000 claims description 6
- 108010023302 HDL Cholesterol Proteins 0.000 claims description 6
- 108010028554 LDL Cholesterol Proteins 0.000 claims description 6
- 230000001746 atrial effect Effects 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
- 208000026278 immune system disease Diseases 0.000 claims description 6
- 238000003018 immunoassay Methods 0.000 claims description 6
- 210000001616 monocyte Anatomy 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 238000004393 prognosis Methods 0.000 claims description 6
- 238000001356 surgical procedure Methods 0.000 claims description 6
- 210000001519 tissue Anatomy 0.000 claims description 6
- 230000004069 differentiation Effects 0.000 claims description 5
- 230000007717 exclusion Effects 0.000 claims description 5
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 claims description 5
- 230000000306 recurrent effect Effects 0.000 claims description 5
- 238000005070 sampling Methods 0.000 claims description 5
- 206010027476 Metastases Diseases 0.000 claims description 4
- 230000003187 abdominal effect Effects 0.000 claims description 4
- 210000004369 blood Anatomy 0.000 claims description 4
- 239000008280 blood Substances 0.000 claims description 4
- 230000009401 metastasis Effects 0.000 claims description 4
- 210000002445 nipple Anatomy 0.000 claims description 4
- PGOHTUIFYSHAQG-LJSDBVFPSA-N (2S)-6-amino-2-[[(2S)-5-amino-2-[[(2S)-2-[[(2S)-2-[[(2S)-2-[[(2S)-4-amino-2-[[(2S)-2-[[(2S)-2-[[(2S)-2-[[(2S)-2-[[(2S)-5-amino-2-[[(2S)-5-amino-2-[[(2S)-2-[[(2S)-2-[[(2S)-2-[[(2S,3R)-2-[[(2S)-5-amino-2-[[(2S)-2-[[(2S)-2-[[(2S,3R)-2-[[(2S)-2-[[(2S)-2-[[(2S)-2-[[(2S)-2-[[(2S)-5-amino-2-[[(2S)-1-[(2S,3R)-2-[[(2S)-2-[[(2S)-2-[[(2R)-2-[[(2S)-2-[[(2S)-2-[[2-[[(2S)-2-[[(2S)-2-[[(2S)-2-[[(2S)-1-[(2S)-2-[[(2S)-2-[[(2S)-2-[[(2S)-2-amino-4-methylsulfanylbutanoyl]amino]-3-(1H-indol-3-yl)propanoyl]amino]-5-carbamimidamidopentanoyl]amino]propanoyl]pyrrolidine-2-carbonyl]amino]-3-methylbutanoyl]amino]-4-methylpentanoyl]amino]-4-methylpentanoyl]amino]acetyl]amino]-3-hydroxypropanoyl]amino]-4-methylpentanoyl]amino]-3-sulfanylpropanoyl]amino]-4-methylsulfanylbutanoyl]amino]-5-carbamimidamidopentanoyl]amino]-3-hydroxybutanoyl]pyrrolidine-2-carbonyl]amino]-5-oxopentanoyl]amino]-3-hydroxypropanoyl]amino]-3-hydroxypropanoyl]amino]-3-(1H-imidazol-5-yl)propanoyl]amino]-4-methylpentanoyl]amino]-3-hydroxybutanoyl]amino]-3-(1H-indol-3-yl)propanoyl]amino]-5-carbamimidamidopentanoyl]amino]-5-oxopentanoyl]amino]-3-hydroxybutanoyl]amino]-3-hydroxypropanoyl]amino]-3-carboxypropanoyl]amino]-3-hydroxypropanoyl]amino]-5-oxopentanoyl]amino]-5-oxopentanoyl]amino]-3-phenylpropanoyl]amino]-5-carbamimidamidopentanoyl]amino]-3-methylbutanoyl]amino]-4-methylpentanoyl]amino]-4-oxobutanoyl]amino]-5-carbamimidamidopentanoyl]amino]-3-(1H-indol-3-yl)propanoyl]amino]-4-carboxybutanoyl]amino]-5-oxopentanoyl]amino]hexanoic acid Chemical compound CSCC[C@H](N)C(=O)N[C@@H](Cc1c[nH]c2ccccc12)C(=O)N[C@@H](CCCNC(N)=N)C(=O)N[C@@H](C)C(=O)N1CCC[C@H]1C(=O)N[C@@H](C(C)C)C(=O)N[C@@H](CC(C)C)C(=O)N[C@@H](CC(C)C)C(=O)NCC(=O)N[C@@H](CO)C(=O)N[C@@H](CC(C)C)C(=O)N[C@@H](CS)C(=O)N[C@@H](CCSC)C(=O)N[C@@H](CCCNC(N)=N)C(=O)N[C@@H]([C@@H](C)O)C(=O)N1CCC[C@H]1C(=O)N[C@@H](CCC(N)=O)C(=O)N[C@@H](CO)C(=O)N[C@@H](CO)C(=O)N[C@@H](Cc1cnc[nH]1)C(=O)N[C@@H](CC(C)C)C(=O)N[C@@H]([C@@H](C)O)C(=O)N[C@@H](Cc1c[nH]c2ccccc12)C(=O)N[C@@H](CCCNC(N)=N)C(=O)N[C@@H](CCC(N)=O)C(=O)N[C@@H]([C@@H](C)O)C(=O)N[C@@H](CO)C(=O)N[C@@H](CC(O)=O)C(=O)N[C@@H](CO)C(=O)N[C@@H](CCC(N)=O)C(=O)N[C@@H](CCC(N)=O)C(=O)N[C@@H](Cc1ccccc1)C(=O)N[C@@H](CCCNC(N)=N)C(=O)N[C@@H](C(C)C)C(=O)N[C@@H](CC(C)C)C(=O)N[C@@H](CC(N)=O)C(=O)N[C@@H](CCCNC(N)=N)C(=O)N[C@@H](Cc1c[nH]c2ccccc12)C(=O)N[C@@H](CCC(O)=O)C(=O)N[C@@H](CCC(N)=O)C(=O)N[C@@H](CCCCN)C(O)=O PGOHTUIFYSHAQG-LJSDBVFPSA-N 0.000 claims description 3
- 108010050201 2-hydroxybutyrate dehydrogenase Proteins 0.000 claims description 3
- 102100036475 Alanine aminotransferase 1 Human genes 0.000 claims description 3
- 108010082126 Alanine transaminase Proteins 0.000 claims description 3
- 102000002260 Alkaline Phosphatase Human genes 0.000 claims description 3
- 108020004774 Alkaline Phosphatase Proteins 0.000 claims description 3
- 102000005666 Apolipoprotein A-I Human genes 0.000 claims description 3
- 108010059886 Apolipoprotein A-I Proteins 0.000 claims description 3
- 101710095342 Apolipoprotein B Proteins 0.000 claims description 3
- 102100040202 Apolipoprotein B-100 Human genes 0.000 claims description 3
- 102000012406 Carcinoembryonic Antigen Human genes 0.000 claims description 3
- 108010022366 Carcinoembryonic Antigen Proteins 0.000 claims description 3
- 102000009123 Fibrin Human genes 0.000 claims description 3
- 108010073385 Fibrin Proteins 0.000 claims description 3
- BWGVNKXGVNDBDI-UHFFFAOYSA-N Fibrin monomer Chemical compound CNC(=O)CNC(=O)CN BWGVNKXGVNDBDI-UHFFFAOYSA-N 0.000 claims description 3
- 108010049003 Fibrinogen Proteins 0.000 claims description 3
- 102000008946 Fibrinogen Human genes 0.000 claims description 3
- 101710107035 Gamma-glutamyltranspeptidase Proteins 0.000 claims description 3
- 101710173228 Glutathione hydrolase proenzyme Proteins 0.000 claims description 3
- 108010044467 Isoenzymes Proteins 0.000 claims description 3
- CKLJMWTZIZZHCS-REOHCLBHSA-N L-aspartic acid Chemical compound OC(=O)[C@@H](N)CC(O)=O CKLJMWTZIZZHCS-REOHCLBHSA-N 0.000 claims description 3
- 102000003855 L-lactate dehydrogenase Human genes 0.000 claims description 3
- 108700023483 L-lactate dehydrogenases Proteins 0.000 claims description 3
- 208000007433 Lymphatic Metastasis Diseases 0.000 claims description 3
- 108010094028 Prothrombin Proteins 0.000 claims description 3
- 102100027378 Prothrombin Human genes 0.000 claims description 3
- 101150017781 RMI1 gene Proteins 0.000 claims description 3
- 108090000190 Thrombin Proteins 0.000 claims description 3
- 108010000499 Thromboplastin Proteins 0.000 claims description 3
- 102000002262 Thromboplastin Human genes 0.000 claims description 3
- 108090000340 Transaminases Proteins 0.000 claims description 3
- 230000004913 activation Effects 0.000 claims description 3
- 102000013529 alpha-Fetoproteins Human genes 0.000 claims description 3
- 108010026331 alpha-Fetoproteins Proteins 0.000 claims description 3
- 239000000427 antigen Substances 0.000 claims description 3
- 102000036639 antigens Human genes 0.000 claims description 3
- 108091007433 antigens Proteins 0.000 claims description 3
- 210000003567 ascitic fluid Anatomy 0.000 claims description 3
- 235000003704 aspartic acid Nutrition 0.000 claims description 3
- 230000002238 attenuated effect Effects 0.000 claims description 3
- OQFSQFPPLPISGP-UHFFFAOYSA-N beta-carboxyaspartic acid Natural products OC(=O)C(N)C(C(O)=O)C(O)=O OQFSQFPPLPISGP-UHFFFAOYSA-N 0.000 claims description 3
- 230000002146 bilateral effect Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 239000002775 capsule Substances 0.000 claims description 3
- 230000000747 cardiac effect Effects 0.000 claims description 3
- 238000002512 chemotherapy Methods 0.000 claims description 3
- 238000000546 chi-square test Methods 0.000 claims description 3
- 230000015271 coagulation Effects 0.000 claims description 3
- 238000005345 coagulation Methods 0.000 claims description 3
- 239000007857 degradation product Substances 0.000 claims description 3
- 239000000539 dimer Substances 0.000 claims description 3
- 210000003743 erythrocyte Anatomy 0.000 claims description 3
- 229950003499 fibrin Drugs 0.000 claims description 3
- 229940012952 fibrinogen Drugs 0.000 claims description 3
- 102000006640 gamma-Glutamyltransferase Human genes 0.000 claims description 3
- 230000002489 hematologic effect Effects 0.000 claims description 3
- 230000037356 lipid metabolism Effects 0.000 claims description 3
- 238000002504 lithotomy Methods 0.000 claims description 3
- 230000000877 morphologic effect Effects 0.000 claims description 3
- 229940099990 ogen Drugs 0.000 claims description 3
- 210000005259 peripheral blood Anatomy 0.000 claims description 3
- 239000011886 peripheral blood Substances 0.000 claims description 3
- 229940039716 prothrombin Drugs 0.000 claims description 3
- 238000001959 radiotherapy Methods 0.000 claims description 3
- 238000001228 spectrum Methods 0.000 claims description 3
- 108010088201 squamous cell carcinoma-related antigen Proteins 0.000 claims description 3
- 238000000528 statistical test Methods 0.000 claims description 3
- 210000002784 stomach Anatomy 0.000 claims description 3
- 230000002522 swelling effect Effects 0.000 claims description 3
- 238000012353 t test Methods 0.000 claims description 3
- 229960004072 thrombin Drugs 0.000 claims description 3
- 102000014898 transaminase activity proteins Human genes 0.000 claims description 3
- UFTFJSFQGQCHQW-UHFFFAOYSA-N triformin Chemical compound O=COCC(OC=O)COC=O UFTFJSFQGQCHQW-UHFFFAOYSA-N 0.000 claims description 3
- 239000000439 tumor marker Substances 0.000 claims description 3
- 210000001015 abdomen Anatomy 0.000 claims 1
- 238000002592 echocardiography Methods 0.000 claims 1
- 210000001215 vagina Anatomy 0.000 claims 1
- 206010004433 Benign ovarian tumour Diseases 0.000 abstract description 8
- 238000003759 clinical diagnosis Methods 0.000 abstract description 2
- 238000010200 validation analysis Methods 0.000 description 8
- 230000004083 survival effect Effects 0.000 description 5
- 238000002591 computed tomography Methods 0.000 description 4
- 238000002595 magnetic resonance imaging Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 208000034176 Neoplasms, Germ Cell and Embryonal Diseases 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 3
- 238000003748 differential diagnosis Methods 0.000 description 3
- 238000000556 factor analysis Methods 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 3
- 238000005192 partition Methods 0.000 description 3
- 108010010234 HDL Lipoproteins Proteins 0.000 description 2
- 102000015779 HDL Lipoproteins Human genes 0.000 description 2
- 238000012274 Preoperative evaluation Methods 0.000 description 2
- 210000004027 cell Anatomy 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000000684 flow cytometry Methods 0.000 description 2
- 230000036541 health Effects 0.000 description 2
- 201000008016 ovarian benign neoplasm Diseases 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000002271 resection Methods 0.000 description 2
- 206010061692 Benign muscle neoplasm Diseases 0.000 description 1
- 208000007690 Brenner tumor Diseases 0.000 description 1
- 208000001490 Dengue Diseases 0.000 description 1
- 206010012310 Dengue fever Diseases 0.000 description 1
- 206010014759 Endometrial neoplasm Diseases 0.000 description 1
- 208000021309 Germ cell tumor Diseases 0.000 description 1
- 206010061218 Inflammation Diseases 0.000 description 1
- 206010025323 Lymphomas Diseases 0.000 description 1
- 201000004458 Myoma Diseases 0.000 description 1
- 208000007571 Ovarian Epithelial Carcinoma Diseases 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000004791 biological behavior Effects 0.000 description 1
- 230000023555 blood coagulation Effects 0.000 description 1
- 230000005773 cancer-related death Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 208000025729 dengue disease Diseases 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000013399 early diagnosis Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 206010016629 fibroma Diseases 0.000 description 1
- 206010049444 fibromatosis Diseases 0.000 description 1
- 238000002513 implantation Methods 0.000 description 1
- 230000008595 infiltration Effects 0.000 description 1
- 238000001764 infiltration Methods 0.000 description 1
- 230000004054 inflammatory process Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 208000011937 ovarian epithelial tumor Diseases 0.000 description 1
- 208000016517 ovarian serous tumor Diseases 0.000 description 1
- 210000001672 ovary Anatomy 0.000 description 1
- 231100000915 pathological change Toxicity 0.000 description 1
- 230000036285 pathological change Effects 0.000 description 1
- 201000002628 peritoneum cancer Diseases 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000011896 sensitive detection Methods 0.000 description 1
- 230000000405 serological effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 210000004881 tumor cell Anatomy 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- 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
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Landscapes
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Data Mining & Analysis (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Epidemiology (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention relates to the technical field of ovarian cancer, and discloses a method for constructing a diagnosis model of ovarian malignancy and juncture tumor, which comprises the following steps: s1: the case-control study is adopted to analyze the patients who are hospitalized for 'pelvic tumor and ovarian tumor' and complete the operation treatment, and the patients with ovarian malignancy or borderline tumor confirmed by the postoperative histopathological examination are taken as case groups. The method for constructing the ovarian malignancy and juncture tumor diagnosis model optimizes and judges the ovarian tumor benign and malignancy diagnosis model based on the prior clinical case data, establishes the related nomograms thereof, establishes a clinical-ultrasonic nomogram model combining clinical risk factors and other diagnosis model characteristics, and can be used as a clinical tool for noninvasively predicting the ovarian tumor benign and malignancy before individuation operation, thereby providing scientific basis for diagnosis and treatment of patients and carrying out auxiliary decision making, achieving the aim of 'accurate medical treatment' and further improving the sensitivity and specificity of the ovarian tumor benign and malignancy in clinical diagnosis and treatment.
Description
Invention of the invention
The invention relates to the technical field of ovarian cancer, in particular to a method for constructing an ovarian malignancy and juncture tumor diagnosis model.
Background
Ovarian cancer is the third most common gynecological malignancy which causes gynecological cancer-related death, the anatomical position of the ovary is in the deep pelvic cavity, so that effective examination means are often lacking in clinic, more than 60% of ovarian cancer patients reach late stage when they visit, the survival rate of the early stage ovarian cancer patients is less than 30%, however, the survival rate of the early stage ovarian cancer patients can reach 90%, the early stage ovarian cancer has already progressed in diagnosis and treatment, but the prognosis of the late stage patients is still not ideal, the survival rate of the early stage ovarian cancer is only 5% -21% in 10 years, therefore, diagnosis and treatment of the ovarian cancer are still one of the most troublesome problems faced by gynecologist, the diagnosis of the ovarian cancer is indeed based on histopathology, and the main pathological types of the ovarian cancer comprise ovarian epithelial tumors with the proportion of more than 90%; germ cell tumor accounting for 2% -3%; in epithelial ovarian cancer, high-grade serous cancer accounts for 70%, endometrium-like cancer accounts for 10%, mucinous cancer accounts for 3%, transparent cell cancer accounts for 10%, low-grade serous cancer is less than 5%, ovarian juncture tumor is an ovarian tumor with low malignant potential, and is not easy to metastasize due to lack of obvious malignant tumor characteristics of tumor cells growing toward interstitial infiltration, so that the ovarian tumor is different from invasive ovarian cancer, overall prognosis is relatively ideal, but according to the tissue pathological classification of the ovarian tumor of the world health tissue in 2020, the characteristic of the invasive implantation of juncture tumor is more similar to LGSC from the aspects of tissue morphology and biological behaviors, so that low malignant potential tumor is not recommended to be used, in clinic, because lack of sensitive detection means leads to no clear diagnosis, so that part of ovarian tumor can possibly progress to IOC, early evaluation of ovarian tumor properties is particularly important for improving survival rate of patients, and is often difficult to reduce occurrence of surgical complications and unnecessary surgical treatment for asymptomatic ovarian tumor patients, but also can be used for judging whether or not to have a great treatment potential for the malignant tumor, or not have a great treatment, but also can be judged by the following the diagnosis of the malignant tumor, or the potential tumor.
At present, the preoperative evaluation of the ovarian tumor properties is the key point and the difficulty of research in clinic, the related preoperative auxiliary inspection mainly comprises the qualitative diagnosis and differential diagnosis of imaging inspection such as ultrasonic inspection, MRI (magnetic resonance imaging) and CT (computed tomography), clinical characteristics, serum markers related to ovarian cancer, laparoscopic exploration and the like, and although the auxiliary inspection methods have certain value in clinic, the auxiliary inspection methods are often independent of each other and have limitations of different degrees, and the conventional imaging inspection such as ultrasonic inspection, MRI (magnetic resonance imaging) and CT (computed tomography) can be influenced by subjective factors and clinical experience of testers, so that an accurate and noninvasive ovarian malignancy and juncture tumor risk prediction model is established, and the auxiliary inspection method has important significance for early diagnosis and identification of ovarian malignancy and juncture, has important value for the accurate preoperative evaluation and the selection of treatment schemes, and becomes a research increasingly.
Disclosure of Invention
(one) solving the technical problems
The invention aims to provide a method for constructing an ovarian malignancy and juncture tumor diagnosis model, which aims to solve the problems in the background technology.
(II) technical scheme
In order to achieve the above purpose, the present invention provides the following technical solutions: a method for constructing an ovarian malignancy and juncture tumor diagnosis model comprises the following steps:
S1: the patients in which the "pelvic tumor and ovarian tumor" are hospitalized and the operation treatment is completed are analyzed by adopting a case-control study, the patients with ovarian malignancy or borderline tumor confirmed by the postoperative histopathological examination are taken as case groups, and the cases with ovarian benign tumor confirmed by the postoperative histopathological examination are taken as control groups according to age and menopausal condition matching.
S2: demographic, clinical pathological data and ultrasonic image information of the cases are collected, ultrasonic examination is carried out, and morphological indexes such as maximum diameter line of tumor, character of tumor, maximum diameter of solid component, number of cyst rooms, separation condition, number of papillary processes, sound accompanying shadow, presence or absence of blood flow signals, presence or absence of ascites and the like are mainly observed.
S3: CA125, ovarian cancer risk prediction model (ROMA), malignancy risk index scoring system (RMI 1), simple rule risk prediction model (SRRisk), assessment of different tumors of the Accessory (ADNEX), sensitivity, specificity, positive predictive value, negative predictive value, about index and Kappa value of the model are calculated and the differences among different indexes are compared.
S4: comparing the general demographics data with the clinical pathology data between the two groups, and further analyzing clinically relevant variables through logistics multi-factor regression to obtain independent risk factors.
S5: randomly dividing a study population into a training set and a verification set according to a ratio of 8:2, and constructing a clinical related variable diagnosis alignment chart model COM of ovarian malignancy and borderline tumor by using a logistic regression model in the training set.
S6: and in the verification set, the degree of distinction of the model is checked through the working characteristic curve and the consistency index of the test subject, the degree of calibration is checked through the calibration curve, and the performance of the clinical benefit verification model is evaluated through the clinical decision curve.
S7: and constructing clinical relevant indexes of ovarian malignancy and borderline tumor by using logistics regression model in training set, and constructing alignment pattern model COM+ADNEX by combining ADNEX model.
S8: the model performance is verified in verifying differentiation, calibration, and clinical benefit of the centralized test model.
Preferably, the inclusion criteria for the case group in S1 is those older than 18 years, those with ovarian malignancy and borderline tumor confirmed by surgical pathology, and those not receiving radiation therapy, chemotherapy, and other treatments prior to surgery, and the exclusion criteria for the case group in S1 are those with insufficient medical history and pathological diagnosis, those with recurrent tumor, metastatic tumor, those with other tumor history or precancerous lesions, those with immune system diseases (such as autoimmune disease, acquired immunodeficiency syndrome, etc.), and pregnant women.
Preferably, the inclusion criteria of the control group in S1 are those who are first diagnosed with pathological changes in ovarian tissue through surgery and have no malignant lesions, and the clinical data of all subjects are complete, and the exclusion criteria of the control group in S2 are those who have insufficient medical history and pathological diagnosis, those who have recurrent tumors, metastatic tumors, those who have other tumor histories or precancerous lesions, those who have immune system diseases (such as autoimmune diseases, acquired immunodeficiency syndrome, etc.), and pregnant women.
Preferably, the clinical pathology data in S2 includes age, menopause, body mass index, gynecological color ultrasound index of the hospital collected in 3 months before operation, serum tumor marker level in 3 months before operation, blood cell related parameter before operation, blood coagulation function related parameter before operation, FIGO stage, lymph node metastasis, etc., and each measured value of gynecological color ultrasound ovarian tumor of the gynecological is semi-quantitatively converted according to report results of gynecological color ultrasound of the hospital collected before operation: (1) tumor maximum diameter line (mm); (2) swelling properties: the solid tumor is regular, irregular, cystic and cystic; (3) maximum diameter (mm) of the solid component; (4) cyst number of rooms: the solidity, single room, 2-10 rooms, more than 10 rooms; (5) separation conditions: no separation, smooth separation and unsmooth separation; (6) number of papillae: 1, 2, 3, greater than 3; (7) whether to accompany sound shadow: yes, no; (8) blood flow signal: no, level 1, level 2, level 3; (9) ascites: is; no, according to literature reports, 35 hematological indices with clear relationship to ovarian cancer were selected and classified into 5 categories: (1) serum tumor markers 7, including CA125: the reference range is 0.00-35.00U/ml; CA153: the reference range is 0.00-31.30U/ml; cancer antigen 199: the reference range is 0.00-37.00U/ml; squamous cell carcinoma antigen: the reference range is 0.00-1.50ng/ml; alpha fetoprotein: the reference range is 0.00-8.78ng/ml; carcinoembryonic antigen: the reference range is 0.00-5.00ng/ml; HE4: the reference range is that the pre-menopause of normal people is less than 68.96pmol/L, and the post-menopause of normal people is less than 114.9pmol/L; (2) blood cell-related parameter 6: neutrophil count: the reference range is 1.80-6.30X10-9/L; lymphocyte count: the reference range is 1.1-3.20X10-9/L; monocyte count: the reference range is 0.10-0.60 x 10-9/L; platelet count: the reference range is 125-350 x 10-9/L; width of distribution of erythrocytes: the reference range is 12.1-14.3%; average platelet volume: the reference range is 7.20-12.00fL; (3) serum lipid metabolism index 6: triglyceride level: the reference range is 0.00-1.70mmol/L; total cholesterol level: the reference range is 0.00-5.20mmol/L; apolipoprotein-A1 level: the reference range is 1.20-1.60g/L; apolipoprotein-B levels: the reference range is 0.60-1.20g/L; high density lipoprotein cholesterol levels: the reference range is 1.29-1.55mmol/L; low density lipoprotein cholesterol level: the reference range is 0.00-3.10mmol/L; (4) other serum biochemistry general related parameters 10: albumin level: the reference range is 40.00-55.00mmol/L; globulin level: the reference range is 20.00-40.00mmol/L; lactate dehydrogenase level: the reference range is 120.00-250.00mmol/L; creatine kinase level: the reference range is 40.00-200.00mmol/L; creatine kinase isoenzyme levels: the reference range is 0.00-25mmol/L; alanine aminotransferase level: the reference range is 7.00-40.00mmol/L; aspartic acid aminotransferase level: the reference range is 13.00-35.00mmol/L; gamma-glutamyl transpeptidase level: reference range is 7.00-45.00mmol/L, alkaline phosphatase level: the reference range is 50.00-135.00mmol/L; alpha-hydroxybutyrate dehydrogenase level: the reference range is 72.00-182.00U/L; (5) 6 parameters related to coagulation function: prothrombin time: the reference range is 9.80-12.10sec; activation of partial thromboplastin time: the reference range is 23.30-32.50sec; thrombin time: the reference range is 14.00-21.00sec; fibrinogen: the reference range is 1.80-3.50g/L; d-dimer: the reference range is 0.00-0.55mg/LFEU; fibrin (ogen) degradation products: the reference range is 0.00-5.00mg/L; and converting some of the indices into ratios including neutrophil count/lymphocyte count ratio, platelet count/lymphocyte count ratio, monocyte count/lymphocyte count ratio, albumin/globulin ratio, and low density lipoprotein cholesterol/high density lipoprotein cholesterol ratio.
Preferably, the main instruments in S2 include an ultrasonic instrument and a serum detection index detection instrument, wherein the ultrasonic instrument specifically adopts a GE volume 730Pro color ultrasonic instrument, a non-married female takes a supine position in an inspection process, a convex array probe has a frequency of 25MHz, a married female takes a lithotomy position through abdominal scanning, an intracavity probe has a frequency of 47.5MHz, a vaginal ultrasonic inspection or joint abdominal scanning is performed, a dual accessory is conventionally scanned, a tumor is found, the position, the shape, the size, the internal echo, the presence or absence of a solid component and its sound shadow, the presence or absence of a partition, the number of the partition, whether the partition is smooth, the presence or absence of nipple-shaped protrusions, the number of protrusions, the presence or absence of ascites, the tumor interior and peripheral color blood flow signals are obtained, when detecting the blood flow conditions, a spectrum pattern of more than 3 cardiac cycles is obtained, the serum detection is detected by a chemiluminescent immunoassay method by an acquisition hospital clinical laboratory, the instrument specifically adopts a rogowski type 601 fully automatic immunoassay analyzer, and the blood routine is detected by an acquisition hospital clinical laboratory instrument specifically adopts a flow cytometry technique, and BC-6800 and a full blood cell analyzer is used in the clinical laboratory.
Preferably, in the step S3, 3mL of peripheral blood is drawn in the morning on an empty stomach, 35U and mL are taken as cutoff values of CA125, that is, the cutoff values are positive, and the cutoff values are less than or equal to the cutoff values, and the cutoff values are negative, and the evaluation standard of the ovarian cancer risk prediction model in the step S3 is premenopausal: pi= -12+2.38 x in (HE 4) +0.0626 x in (CA 125), postmenopausal: pi= -8.09+1.04 x In (HE 4) +0.732 x In (CA 125), ROMA (%) =exp (PI) and [1+exp (PI) ]%, where In is the natural logarithm, exp is an exponential function based on a natural constant, and premenopausal and postmenopausal women have ROMA index values > 13.1% and 22.7%, which are considered to be at high risk of ovarian malignancy.
Preferably, the evaluation criteria of the malignancy risk index scoring system in S3 is rmi1=ca125 (U and mL) ×u×m, where U represents total ultrasound score of each patient, M represents menopausal status, ultrasound scoring criteria is 5 indexes of bilateral lesions, multi-atrial cysts, papillary or solid lesions, ascites, metastasis, and the evaluation criteria of the simple rule risk prediction model in S3 is benign features (B features): (1) a sheet Fang Nangzhong; (2) the maximum diameter of the solid component is less than 7mm; (3) sound shadow is accompanied behind the tumor; (4) smooth multi-atrial cysts with a maximum diameter <10 cm; (5) grade 1 of tumor color blood flow score; malignancy characteristics (M characteristics): (1) an irregular solid tumor; (2) peritoneal effusion; (3) more than or equal to 4 nipple-shaped protrusions; (4) irregular multi-atrial cyst solid tumor with the maximum diameter of more than or equal to 10 cm; (5) CS stage 4; wherein stage 1: very low risk, there are more than 2B features, no M features; 2 stages: low risk, presence of 2B-features or single atrial cysts in B-features only, no M-features; 3 stages: medium risk, with other B features than 1 single atrial cyst, no M features; 4 stages: the risk is high, B features or M features are not generated, and the number of the B features is more than or equal to the number of the M features; 5 stages: very high risk, M feature number > B feature number; SRRisk grades 1 to 3 are classified as benign, and SRRisk grades 4 and 5 are classified as malignant.
Preferably, the model evaluation criteria of ADNEX in S3 are 3 clinical indexes: (1) age (age) of the patient; (2) serum CA125 levels; (3) diagnosis center (whether it is tumor transfer center); the 6 ultrasonic indexes are as follows: (1) maximum lesion diameter (mm); (2) diameter (mm) of the solid component in the lesion; (3) whether more than 10 pockets; (4) the number of nipple projections on the wall of the capsule; (5) whether sound and shadow are attenuated or not is judged; (6) whether there is ascites; the use method of the model is that the required 9 predictors (the value of serum CA125 can be applied even if the value is missing) are respectively input into the IOTA ADNEX online website: www.iotagroup.org and adnexmodel, click calculations, the percentage of ovarian tumor properties and stage will automatically be generated, the IOTA ADNEX model divides ovarian tumor nest tumors into five stages, respectively: benign, borderline, early malignant (stage I), late malignant (stage ii to V), metastatic tumors, were considered malignant with 10% as cutoff, at risk > 10%, and benign with < 10%. The results are directly displayed in the form of charts such as percentage charts, bar charts, radar charts and the like, and the preoperative stage results are calculated.
Preferably, all data in the S4-S8 are statistically processed by using SPSS24.0 statistical software package, and the metering data conforming to normal distribution are expressed as x+/-S; the comparison between the two groups adopts t test; the data which do not accord with normal distribution are represented by a quarter bit distance (IQR), the comparison between two groups adopts a nonparametric rank sum test, the counting data adopts an example number and a percentage to represent, the comparison between two groups adopts a chi square test, the classification variable is represented by a percentage, the classification variable is subjected to a single-factor Logistic regression test, on the basis, the influence factors of ovarian malignancy and juncture tumor are analyzed by adopting a multi-factor Logistic regression model, the postoperative pathological diagnosis result is taken as a gold standard, a subject working characteristic (ROC) curve is drawn, the sensitivity, the specificity, the positive prediction value, the negative prediction value and the about sign index of different diagnosis prediction models under a standard cut-off value are calculated, the efficacy sizes of the ovarian benign malignancy are identified by comparing serum CA125, ROMA, SSRisk, ADNEX models, RMI1 and a diagnosis alignment line graph model COM, and the five methods are respectively subjected to consistency test with the pathological result to obtain a Kappa value, and the Kappa value is more than or equal to 0.75; a kappa value of 0.75> 0.4 is considered to be common to both; kappa value <0.4 considers that the consistency of the two is poor, R software is utilized to draw a nomogram by a logic regression model and calculate a consistency index (C-index) of the nomogram model, the C index is also called C index, the C index represents the ability of a model to predict that an individual achieves an expected result, the C index is 0.5 and has no prediction ability, the C index is 1 and can perfectly distinguish different prognosis of a patient, the C index is lower than 0.7 and considers relatively poor prediction ability, the model is internally verified by a Bootstrap self-sampling method, a calibration curve, a clinical Decision Curve (DCA) and a ROC curve of the nomogram model are drawn by the R software, the degree of distinction, the degree of calibration and the clinical application value of the nomogram model are evaluated, the using method of the degree of calibration is that the holmer-lemeshomerhneshowsoffit figure is checked, if the checking result shows statistical significance (P < 0.05), a certain difference exists between the model prediction value and the actual observation value, and the degree of calibration is general; if P >0.05, it shows that the predicted value and the observed value have no significant difference, so the model fitting degree is good, and all statistical tests in the study adopt that when P <0.05, the difference is considered to have statistical significance.
Compared with the prior art, the invention has the beneficial effects that: the method for constructing the ovarian malignancy and juncture tumor diagnosis model optimizes and judges the ovarian tumor benign and malignancy diagnosis model based on the prior clinical case data, establishes the related nomograms thereof, establishes a clinical-ultrasonic nomogram model combining clinical risk factors and other diagnosis model characteristics, and can be used as a clinical tool for noninvasively predicting the ovarian tumor benign and malignancy before individuation operation, thereby providing scientific basis for diagnosis and treatment of patients and carrying out auxiliary decision making, achieving the aim of 'accurate medical treatment' and further improving the sensitivity and specificity of the ovarian tumor benign and malignancy in clinical diagnosis and treatment.
Drawings
FIG. 1 is a flow chart of the diagnostic nomographic model for ovarian malignancy and junctional tumors according to the present invention;
FIG. 2 is a statistical plot of general clinical data for the case group and the control group of the present invention;
FIG. 3 is a statistical plot of general clinical data for the case group and the control group of the present invention;
FIG. 4 is a demographic, clinical pathology, serum CA125 and HE4 level statistical plot of patients according to the invention;
FIG. 5 is a statistical chart of the results of single-factor logistic regression analysis of risk factors for ovarian malignancy and borderline tumor onset according to the present invention;
FIG. 6 is a statistical graph of the results of a multi-factor logistic regression analysis of risk factors for ovarian malignancy and borderline tumor onset according to the present invention;
FIG. 7 is a statistical chart of the results of a multi-factor logistic regression analysis of risk factors for ovarian malignancy and borderline tumor onset according to the present invention;
FIG. 8 is a statistical plot of sensitivity, specificity, positive predictive value, negative predictive value, about dengue index, and kappa values for serum CA125, ROMA, RMI1, SRRisk, and ADNEX models of the invention;
FIG. 9 is a graph of diagnostic performance versus statistics for the CA125, ROMA, RMI1, SRRisk and ADNEX models of the invention.
FIG. 10 is a graph of ROC for serum CA125, ROMA, RMI1, SRRisk and ADNEX models of the invention;
FIG. 11 is a graph of decision making for predicting ovarian malignancy and borderline tumors using the serum CA125, ROMA, RMI1, SRRisk and ADNEX models of the invention;
FIG. 12 is a schematic diagram of a nomographic model for predicting risk of ovarian malignancy and borderline tumor onset in accordance with the present invention;
FIG. 13 is a calibration graph (training set) of the evaluation and verification alignment pattern model COM of the present invention;
fig. 14 is a calibration graph (verification set) of the evaluation and verification alignment chart model COM of the present invention;
FIG. 15 is a clinical decision graph (training set) of the evaluation and verification nomogram model COM of the present invention;
FIG. 16 is a clinical decision graph (validation set) of the evaluation and validation nomogram model COM of the present invention;
FIG. 17 is a ROC graph (training set) of the present invention evaluating and verifying the discrimination of a nomogram model COM;
FIG. 18 is a ROC graph (validation set) of the present invention evaluating and validating the COM differentiation of a nomogram model;
FIG. 19 is a schematic diagram of an alignment model of the present invention COM+ADNEX predicting risk of ovarian malignancy and borderline tumor;
FIG. 20 is a calibration graph of the training set evaluation and verification alignment model COM+ADNEX of the present invention;
FIG. 21 is a graph of clinical decisions for evaluating and validating a nomogram model COM+ADNEX in a training set of the present invention;
FIG. 22 is a calibration graph of the verification concentrate evaluation and verification nomogram model COM+ADNEX of the present invention;
FIG. 23 is a graph of clinical decisions for validating a centralized assessment and validation nomogram model COM+ADNEX of the present invention;
FIG. 24 is a ROC graph (training set) of the present invention evaluating and verifying the discrimination of the alignment pattern COM+ADNEX;
fig. 25 is a ROC graph (validation set) of the present invention evaluating and validating the alignment pattern com+adnex differentiation.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1-24, the present invention provides a technical solution: a method for constructing an ovarian malignancy and juncture tumor diagnosis model comprises the following steps:
s1: the patients in which the "pelvic tumor and ovarian tumor" are hospitalized and the operation treatment is completed are analyzed by adopting a case-control study, the patients with ovarian malignancy or borderline tumor confirmed by the postoperative histopathological examination are taken as case groups, and the cases with ovarian benign tumor confirmed by the postoperative histopathological examination are taken as control groups according to age and menopausal condition matching.
S2: demographic, clinical pathological data and ultrasonic image information of the cases are collected, ultrasonic examination is carried out, and morphological indexes such as maximum diameter line of tumor, character of tumor, maximum diameter of solid component, number of cyst rooms, separation condition, number of papillary processes, sound accompanying shadow, presence or absence of blood flow signals, presence or absence of ascites and the like are mainly observed.
S3: CA125, ovarian cancer risk prediction model (ROMA), malignancy risk index scoring system (RMI 1), simple rule risk prediction model (SRRisk), assessment of different tumors of the Accessory (ADNEX), sensitivity, specificity, positive predictive value, negative predictive value, about index and Kappa value of the model are calculated and the differences among different indexes are compared.
S4: comparing the general demographics data with the clinical pathology data between the two groups, and further analyzing clinically relevant variables through logistics multi-factor regression to obtain independent risk factors.
S5: randomly dividing a study population into a training set and a verification set according to a ratio of 8:2, and constructing a clinical related variable diagnosis alignment chart model COM of ovarian malignancy and borderline tumor by using a logistic regression model in the training set.
S6: and in the verification set, the degree of distinction of the model is checked through the working characteristic curve and the consistency index of the test subject, the degree of calibration is checked through the calibration curve, and the performance of the clinical benefit verification model is evaluated through the clinical decision curve.
S7: and constructing clinical relevant indexes of ovarian malignancy and borderline tumor by using logistics regression model in training set, and constructing alignment pattern model COM+ADNEX by combining ADNEX model.
S8: the model performance is verified in verifying differentiation, calibration, and clinical benefit of the centralized test model.
The inclusion criteria for the S1 case group are those older than 18 years, those with ovarian malignancy and borderline tumor confirmed by surgical pathology, and those who did not receive radiotherapy, chemotherapy, and other treatments before surgery, and the exclusion criteria for the S1 case group are those with medical history and insufficient pathological diagnosis data, those with recurrent tumor, metastatic tumor, those with other tumor histories or precancerous lesions, those with immune system diseases (such as autoimmune diseases, acquired immunodeficiency syndrome, etc.), and pregnant women.
The inclusion standard of the control group in S1 is the first time the ovarian tissue is diagnosed with the pathological condition through operation, and the clinical data of all study subjects are complete, and the exclusion standard of the control group in S2 is the case history and the pathological condition diagnosis data insufficiency, the recurrence tumor, the metastatic tumor, the other tumor history or the precancerous lesion, the immune system disease (such as autoimmune disease, acquired immunodeficiency syndrome and the like) and the pregnant women.
S2, clinical pathology data comprise age, menopause, body mass index, gynecological color Doppler ultrasound index acquired in a hospital in 3 months before operation, serum tumor marker level in 3 months before operation, blood cell related parameters before operation, FIGO stage, lymph node metastasis and the like, and according to report results of gynecological color Doppler ultrasound acquired in the hospital before operation, each measured value of the gynecological color Doppler ultrasound ovarian tumor is subjected to semi-quantitative conversion: (1) tumor maximum diameter line (mm); (2) swelling properties: the solid tumor is regular, irregular, cystic and cystic; (3) maximum diameter (mm) of the solid component; (4) cyst number of rooms: the solidity, single room, 2-10 rooms, more than 10 rooms; (5) separation conditions: no separation, smooth separation and unsmooth separation; (6) number of papillae: 1, 2, 3, greater than 3; (7) whether to accompany sound shadow: yes, no; (8) blood flow signal: no, level 1, level 2, level 3; (9) ascites: is; no, according to literature reports, 35 hematological indices with clear relationship to ovarian cancer were selected and classified into 5 categories: (1) serum tumor markers 7, including CA125: the reference range is 0.00-35.00U/ml; CA153: the reference range is 0.00-31.30U/ml; cancer antigen 199: the reference range is 0.00-37.00U/ml; squamous cell carcinoma antigen: the reference range is 0.00-1.50ng/ml; alpha fetoprotein: the reference range is 0.00-8.78ng/ml; carcinoembryonic antigen: the reference range is 0.00-5.00ng/ml; HE4: the reference range is that the pre-menopause of normal people is less than 68.96pmol/L, and the post-menopause of normal people is less than 114.9pmol/L; (2) blood cell-related parameter 6: neutrophil count: the reference range is 1.80-6.30X10-9/L; lymphocyte count: the reference range is 1.1-3.20X10-9/L; monocyte count: the reference range is 0.10-0.60 x 10-9/L; platelet count: the reference range is 125-350 x 10-9/L; width of distribution of erythrocytes: the reference range is 12.1-14.3%; average platelet volume: the reference range is 7.20-12.00fL; (3) serum lipid metabolism index 6: triglyceride level: the reference range is 0.00-1.70mmol/L; total cholesterol level: the reference range is 0.00-5.20mmol/L; apolipoprotein-A1 level: the reference range is 1.20-1.60g/L; apolipoprotein-B levels: the reference range is 0.60-1.20g/L; high density lipoprotein cholesterol levels: the reference range is 1.29-1.55mmol/L; low density lipoprotein cholesterol level: the reference range is 0.00-3.10mmol/L; (4) other serum biochemistry general related parameters 10: albumin level: the reference range is 40.00-55.00mmol/L; globulin level: the reference range is 20.00-40.00mmol/L; lactate dehydrogenase level: the reference range is 120.00-250.00mmol/L; creatine kinase level: the reference range is 40.00-200.00mmol/L; creatine kinase isoenzyme levels: the reference range is 0.00-25mmol/L; alanine aminotransferase level: the reference range is 7.00-40.00mmol/L; aspartic acid aminotransferase level: the reference range is 13.00-35.00mmol/L; gamma-glutamyl transpeptidase level: reference range is 7.00-45.00mmol/L, alkaline phosphatase level: the reference range is 50.00-135.00mmol/L; alpha-hydroxybutyrate dehydrogenase level: the reference range is 72.00-182.00U/L; (5) 6 parameters related to coagulation function: prothrombin time: the reference range is 9.80-12.10sec; activation of partial thromboplastin time: the reference range is 23.30-32.50sec; thrombin time: the reference range is 14.00-21.00sec; fibrinogen: the reference range is 1.80-3.50g/L; d-dimer: the reference range is 0.00-0.55mg/LFEU; fibrin (ogen) degradation products: the reference range is 0.00-5.00mg/L; and converting some of the indices into ratios including neutrophil count/lymphocyte count ratio, platelet count/lymphocyte count ratio, monocyte count/lymphocyte count ratio, albumin/globulin ratio, and low density lipoprotein cholesterol/high density lipoprotein cholesterol ratio.
The main instruments in S2 comprise ultrasonic instruments and serum detection index detection instruments, wherein the ultrasonic instruments specifically adopt GE Voluson 730Pro color ultrasonic instruments, an unmatched female is in a supine position in the detection process, a convex array probe has the frequency of 25MHz, a matched female is in a lithotomy position, an intracavity probe has the frequency of 47.5MHz, the matched female is subjected to vaginal ultrasonic detection or combined abdominal scanning, a tumor is found by conventional scanning double accessories, the parts, the shape, the size, the internal echo, the presence or absence of a solid component and the sound shadow thereof, the presence or absence of separation, the separation number, whether the separation is smooth, the presence or absence of nipple-shaped protrusions and the protrusion number are detected, ascites is detected in the tumor and peripheral color blood flow signals, when the blood flow condition is detected, a spectrum graph of more than 3 cardiac cycles is obtained, the serum detection is detected by a chemiluminescent immunoassay method by an acquisition hospital clinical laboratory, the instrument specifically adopts a Rogowski Cobase601 type full-automatic immunoassay instrument of Roche company, the blood routine is detected by an acquisition clinical laboratory department by a flow cytometry technique, and the whole blood cell analyzer of BC-6900 is specifically adopted.
In S3, when CA125 is calculated, 3mL of peripheral blood is extracted from all patients in the morning on an empty stomach, 35U and mL are taken as cutoff values of CA125, namely, the cutoff values are positive, the value is less than or equal to the cutoff values, the value is negative, and the evaluation standard of the ovarian cancer risk prediction model in S3 is premenopausal: pi= -12+2.38 x in (HE 4) +0.0626 x in (CA 125), postmenopausal: pi= -8.09+1.04 x In (HE 4) +0.732 x In (CA 125), ROMA (%) =exp (PI) and [1+exp (PI) ]%, where In is the natural logarithm, exp is an exponential function based on a natural constant, and premenopausal and postmenopausal women have ROMA index values > 13.1% and 22.7%, which are considered to be at high risk of ovarian malignancy.
The evaluation criteria of the malignancy risk index scoring system in S3 is rmi1=ca125 (U and mL) ×u×m, where U represents the total ultrasound score of each patient, M represents the menopausal status, the ultrasound scoring criteria is 5 indexes of bilateral lesions, multi-atrial cysts, papillary or solid lesions, ascites, metastasis, and the evaluation criteria of the simple rule risk prediction model in S3 is benign features (B features): (1) a sheet Fang Nangzhong; (2) the maximum diameter of the solid component is less than 7mm; (3) sound shadow is accompanied behind the tumor; (4) smooth multi-atrial cysts with a maximum diameter <10 cm; (5) grade 1 of tumor color blood flow score; malignancy characteristics (M characteristics): (1) an irregular solid tumor; (2) peritoneal effusion; (3) more than or equal to 4 nipple-shaped protrusions; (4) irregular multi-atrial cyst solid tumor with the maximum diameter of more than or equal to 10 cm; (5) CS stage 4; wherein stage 1: very low risk, there are more than 2B features, no M features; 2 stages: low risk, presence of 2B-features or single atrial cysts in B-features only, no M-features; 3 stages: medium risk, with other B features than 1 single atrial cyst, no M features; 4 stages: the risk is high, B features or M features are not generated, and the number of the B features is more than or equal to the number of the M features; 5 stages: very high risk, M feature number > B feature number; SRRisk grades 1 to 3 are classified as benign, and SRRisk grades 4 and 5 are classified as malignant.
Model evaluation criteria for ADNEX in S3 were 3 clinical indices: (1) age (age) of the patient; (2) serum CA125 levels; (3) diagnosis center (whether it is tumor transfer center); the 6 ultrasonic indexes are as follows: (1) maximum lesion diameter (mm); (2) diameter (mm) of the solid component in the lesion; (3) whether more than 10 pockets; (4) the number of nipple projections on the wall of the capsule; (5) whether sound and shadow are attenuated or not is judged; (6) whether there is ascites; the use method of the model is that the required 9 predictors (the value of serum CA125 can be applied even if the value is missing) are respectively input into the IOTA ADNEX online website: www.iotagroup.org and adnexmodel, click calculations, the percentage of ovarian tumor properties and stage will automatically be generated, the IOTA ADNEX model divides ovarian tumor nest tumors into five stages, respectively: benign, borderline, early malignant (stage I), late malignant (stage ii to V), metastatic tumors, were considered malignant with 10% as cutoff, at risk > 10%, and benign with < 10%. The results are directly displayed in the form of charts such as percentage charts, bar charts, radar charts and the like, and the preoperative stage results are calculated.
All data in S4-S8 are statistically processed by using SPSS24.0 statistical software package, and the metering data conforming to normal distribution is expressed by x+/-S; the comparison between the two groups adopts t test; the data which do not accord with normal distribution are represented by a quarter bit distance (IQR), the comparison between two groups adopts a nonparametric rank sum test, the counting data adopts an example number and a percentage to represent, the comparison between two groups adopts a chi square test, the classification variable is represented by a percentage, the classification variable is subjected to a single-factor Logistic regression test, on the basis, the influence factors of ovarian malignancy and juncture tumor are analyzed by adopting a multi-factor Logistic regression model, the postoperative pathological diagnosis result is taken as a gold standard, a subject working characteristic (ROC) curve is drawn, the sensitivity, the specificity, the positive prediction value, the negative prediction value and the about sign index of different diagnosis prediction models under a standard cut-off value are calculated, the efficacy sizes of the ovarian benign malignancy are identified by comparing serum CA125, ROMA, SSRisk, ADNEX models, RMI1 and a diagnosis alignment line graph model COM, and the five methods are respectively subjected to consistency test with the pathological result to obtain a Kappa value, and the Kappa value is more than or equal to 0.75; a kappa value of 0.75> 0.4 is considered to be common to both; kappa value <0.4 considers that the consistency of the two is poor, R software is utilized to draw a nomogram by a logic regression model and calculate a consistency index (C-index) of the nomogram model, the C index is also called C index, the C index represents the ability of a model to predict that an individual achieves an expected result, the C index is 0.5 and has no prediction ability, the C index is 1 and can perfectly distinguish different prognosis of a patient, the C index is lower than 0.7 and considers relatively poor prediction ability, the model is internally verified by a Bootstrap self-sampling method, a calibration curve, a clinical Decision Curve (DCA) and a ROC curve of the nomogram model are drawn by the R software, the degree of distinction, the degree of calibration and the clinical application value of the nomogram model are evaluated, the using method of the degree of calibration is that the holmer-lemeshomerhneshowsoffit figure is checked, if the checking result shows statistical significance (P < 0.05), a certain difference exists between the model prediction value and the actual observation value, and the degree of calibration is general; if P >0.05, it shows that the predicted value and the observed value have no significant difference, so the model fitting degree is good, and all statistical tests in the study adopt that when P <0.05, the difference is considered to have statistical significance.
To sum up: firstly, retrospective analysis is carried out on 8880 cases of pelvic cavity and accessory tumor total population of women and young health care hospitals in Fujian province in 2013 and 2016, wherein 3730 cases of hospitalizers, 1217 cases of patients with ovarian tumor specimens obtained through laboratory examination and imaging examination, and 96 cases of clinical pathology data of patients with ovarian malignancy and juncture tumor are confirmed by gynecological oncology through operation pathology, and the clinical pathology data are defined as case groups; and receiving clinical pathology data of patients suffering from ovarian malignant lesions and subjected to side ovarian tumor stripping or side ovarian resection in the period of hospitalization of the oncology, wherein the clinical pathology data of patients suffering from ovarian malignant lesions and subjected to side ovarian resection are consistent with the inclusion standard of ovarian benign tumors and 1121 cases, 109 cases of ovarian benign tumor cases are matched according to age and menopausal condition and are defined as a control group, the study is a case-control study, the whole flow is shown in figure 1, and the median age is 44 years (35-54 years) in 96 patients suffering from ovarian malignant and borderline tumor; 16 cases with ascites and 80 cases without ascites; type of pathology: 46 cases of ovarian serous cancers, 18 cases of mucinous cancers, 9 cases of endometrial cancers, 5 cases of germ cell cancers, 7 cases of sex cord interstitial cancers, 3 cases of transparent cell cancers, 6 cases of metastasis and 2 cases of other (including malignant Brenner tumors, undifferentiated cancers, mixed cancers and peritoneal cancers); stage of surgical pathology: according to the international gynaecology and obstetrics alliance 2014 FIGO staging standard: 46 cases of phase I, 6 cases of phase II, 25 cases of phase III and 3 cases of phase V, and 16 cases of phase not being segmented; in 7 cases, 89 cases were not lymphomatous, and in 109 cases, the median age was 42 years (32-51 years); type of pathology: the cases of 22 cases of ovarian serous tumors, 16 cases of mucous tumors, 41 cases of endometrium-like tumors and 23 cases of germ cell tumors, 4 cases of sex cord interstitial tumors and 3 other cases (including ovarian smooth myoma, ovarian fibromatosis and simple cyst) are shown in fig. 2-3, the cases and the control patients have statistical differences in terms of histological types, serum CA125 and serum HE4, compared with the control patients, the serum CA125 and HE4 levels of the cases are obviously increased (20.3vs 77.95,P<0.001;38.57vs 62.73,P<0.001), the two groups of patients have no statistical differences (P > 0.05) in terms of age, body mass index and menopause, the results of single-factor and multi-factor analysis of the study population are shown in fig. 5-7 in detail, and the single-factor analysis results show that the factors related to ovarian malignancy and borderline tumor comprise: serum CA125, serum HE4, serum CA153, apoA1, HDL, α -HBDH, LDH, CK, FDP, fib, D-D, neu, NLR, PLR (P all < 0.05), multi-factor logistics regression analysis results showed that high serum CA125, serum HE4, serum CA153, apoA1, HDL, LDH, CK, FDP, fib, D-D, neu, NLR, PLR levels were independent risk factors for ovarian malignancy and borderline tumor onset, as shown in fig. 7, with post-operative pathological diagnosis as gold standard, sensitivity, specificity, positive predictive value, negative predictive value, about log index (Youden index) and Kappa value for ovarian malignancy and borderline tumor diagnosis were calculated for each model according to the positive decision criteria described in the study methods, with serum CA125, ROMA, RMI1, SRRisk and ADNEX models as gold standard: ADNEX model > SRRisk > CA125> ROMA > RMI1 (91.7%, 87.5%, 63.5%, 54.2%, 46.9%), specificity: RMI1> ROMA > srrisk=adnex model > CA125 (98.2%, 94.5%, 81.7%, 73.4%), about log index: ADNEX model > SRRisk > ROMA > RMI1> CA125 (73.3%, 69.2%, 48.7%, 45.0%, 36.9%), sensitivity, specificity, accuracy, kappa value results between diagnostic models compared by chi-square segmentation test two-phase (see fig. 9), CA125 sensitivity higher than ROMA and RMI1 (P < 0.05), lower than SRRisk and ADNEX models (P < 0.05); ROMA sensitivity is higher than RMI1 (P < 0.05); RMI1 sensitivity is lower than SRRisk (P < 0.05); ADNEX model sensitivity is higher than SRRisk (P < 0.05), serum CA125, ROMA, RMI1, SRRisk and ADNEX model specificity are not significantly different, accuracy of each model is found to be higher than that of SRRisk, ROMA, RMI and CA125 (P is < 0.05), consistency test results of two-by-two of five types of diagnosis models show that consistency between RMI1 and CA125 and ROMA is general (Kappa values are 0.551 and 0.579 respectively), consistency between SRRisk and ADNEX is general (Kappa values are 0.746), consistency between SRRisk and RMOA and ADNEX 1 is general (Kappa values are 0.418 and 0.410 respectively), consistency between the rest models is poor (Kappa values are all < 0.4), and ROC curves (figure 10) of serum CA125, ROMA, RMI1, SRRisk and ADNEX models are drawn, and AUC of CA125 is 0.775:0.711 to 95:0.838; the AUC of the ROMA is 0.794 (95% CI: 0.728-0.860); AUC of RMI1 is 0.841 (95% CI:0.787 to 0.895); AUC of SRRisk is 0.897 (95% CI: 0.853-0.940); AUC of ADNEX model was 0.936 (95% CI: 0.903-0.969), as shown in Table 3.1.6, by comparing AUC between diagnostic models in pairs, AUC of each of RMI1, SRRisk, ADNEX model was higher than CA125 (Z values 2.55, 3.47 and 5.21, respectively, P < 0.01); AUC was higher for both SRRisk and ADNEX models than ROMA (Z values 2.97 and 4.28, respectively, p < 0.01); AUC of SRRisk and ADNEX models is higher than RMI1 (Z18 values of 2.17 and 4.42, respectively, p < 0.05); the AUC of ADNEX model is higher than SRRisk (Z value is 2.49, P < 0.05), the decision curves corresponding to the above five models are drawn, see FIG. 11, the analysis of the decision curves shows that compared with other models, ADNEX model and SRRisk model have higher net benefit rate in most threshold range, relatively better clinical application value, the establishment and evaluation of the second part of ovarian malignancy and juncture tumor diagnosis risk prediction model are in view of multiple collinearity possibly existing between variables, in order to improve the problem, we use R software to re-screen the variables by using gradual logistic regression on the basis of multi-factor analysis result, use the screened clinical variables for constructing risk prediction model and drawing the alignment, divide the study population into training set and verification set (8:2) according to random principle, establish the alignment model COM for predicting the risk of ovarian malignancy/benign malignancy according to the training set, FIG. 3.2.1, CA125, HE4, CA153, neutrophil count as final predictors are incorporated into the present nomogram model, clinical benefit and validation model performance is evaluated using C-index, calibration curve and decision curve, in training and validation sets, nomogram C-index values for predicting ovarian malignancy and juncture tumors are 0.821 (95% CI: 0.755-0.887) and 0.838 (95% CI: 0.781-0.895), bootstrap self-sampling 1000 times method is employed to internally validate the nomogram model to show good compliance of the model, according to calibration curves of predicted and actual values drawn in training and validation sets, performance of the nomogram model for predicting ovarian malignancy and juncture tumor risk is good through consistency test, goodness-of-fit test P values are 0.9980 and 0.9740, all >0.05, see figures 13-14, can draw corresponding decision curves according to established nomogram models, find that the nomogram models have ideal net benefit rate within a larger threshold range no matter in a verification set or a training set, represent that the established nomogram models COM have good clinical application potential, draw ROC curves for differential diagnosis of benign and malignant ovarian tumors by other models and the nomogram models COM, and have maximum AUC for differential diagnosis of benign and malignant ovarian tumors in the nomogram models COM no matter in the verification set or the training set, are higher than that of the risk prediction models for single detection CA125, CA153, HE4 and Neu, see figures 17-18 in detail, the optimization and evaluation of the risk prediction models for ovarian malignancy and juncture tumor diagnosis are based on the above, and we select the prediction model to combine with the ADNEX model to construct a novel nomogram model COM+ADNEX, see figure 19, the Bootstrap self-sampling 1000 times method is adopted to carry out internal verification on the alignment chart model, the alignment chart model has good conformity, the distinguishing degree test result shows that the C index of the alignment chart model is 0.917 ((95%CI: 0.874-0.961), the correction curve of the model predicted value and the actual value is drawn, the consistency test is carried out, the result indicates that the alignment chart model has good efficacy of predicting ovarian malignancy and juncture tumor risk, the goodness-of-fit test P= 0.6930, see figure 20, the analysis of decision curve drawn according to the established alignment chart model shows that the alignment chart model has ideal net benefit rate in most threshold ranges, see figure 21, similar results are obtained in verification sets, see figures 22 and 23, the ADNEX model, the prediction model COM+ADNEX are respectively drawn in training sets and verification sets, the AUC of the COM+ADNEX model for identifying ovarian malignancy and boundary tumor is higher than that of the ADNEX model and the prediction model COM, and the detail is shown in figures 24-25, and the study has the following advantages: firstly, the data of the risk factors in the nomogram are common and easy to obtain clinically, the clinical operability is strong, the method is convenient and not complicated, particularly, the cost of neutrophil count is low, the method has repeatability, and the clinical popularization is more convenient; secondly, the nomogram can intuitively judge the proportion of each factor in the morbidity risk, provide specific risk values, and is objective and accurate; finally, the model integrates serological tumor markers, combines inflammation indexes and ultrasonic indexes, has high C index, has good prediction capability and clinical application value, however, the research also has the defects, firstly, the model is used as a case-control research, and some potential biases are unavoidable; secondly, due to the limitation of the number of cases, the study fails to further group and count the ovarian boundary tumor and the ovarian malignant tumor, in the follow-up work, the sample size is enlarged, meanwhile, the malignancy/boundary property is brought into the grouping condition for carrying out the refinement study, in addition, the model does not carry out the verification of external clinical data, the credibility of the model can be verified by the practical case data in the future, the recommendation is that patients with higher risk of the ovarian malignant tumor/boundary tumor are screened out by using a nomogram, and the patients are used as possible surgical treatment objects for carrying out the strict follow-up monitoring so as to prolong the survival time, and the nomogram is applied to clinic, so that the method has important significance for making a more reasonable and effective treatment method and preventing and improving the prognosis of the patients.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (9)
1. The method for constructing the ovarian malignancy and juncture tumor diagnosis model is characterized by comprising the following steps:
s1: the patients in which the "pelvic tumor and ovarian tumor" are hospitalized and the operation treatment is completed are analyzed by adopting a case-control study, the patients with ovarian malignancy or borderline tumor confirmed by the postoperative histopathological examination are taken as case groups, and the cases with ovarian benign tumor confirmed by the postoperative histopathological examination are taken as control groups according to age and menopausal condition matching.
S2: demographic, clinical pathological data and ultrasonic image information of the cases are collected, ultrasonic examination is carried out, and morphological indexes such as maximum diameter line of tumor, character of tumor, maximum diameter of solid component, number of cyst rooms, separation condition, number of papillary processes, sound accompanying shadow, presence or absence of blood flow signals, presence or absence of ascites and the like are mainly observed.
S3: CA125, ovarian cancer risk prediction model (ROMA), malignancy risk index scoring system (RMI 1), simple rule risk prediction model (SRRisk), assessment of different tumors of the Accessory (ADNEX), sensitivity, specificity, positive predictive value, negative predictive value, about index and Kappa value of the model are calculated and the differences among different indexes are compared.
S4: comparing the general demographics data with the clinical pathology data between the two groups, and further analyzing clinically relevant variables through logistics multi-factor regression to obtain independent risk factors.
S5: randomly dividing a study population into a training set and a verification set according to a ratio of 8:2, and constructing a clinical related variable diagnosis alignment chart model COM of ovarian malignancy and borderline tumor by using a logistic regression model in the training set.
S6: and in the verification set, the degree of distinction of the model is checked through the working characteristic curve and the consistency index of the test subject, the degree of calibration is checked through the calibration curve, and the performance of the clinical benefit verification model is evaluated through the clinical decision curve.
S7: and constructing clinical relevant indexes of ovarian malignancy and borderline tumor by using logistics regression model in training set, and constructing alignment pattern model COM+ADNEX by combining ADNEX model.
S8: the model performance is verified in verifying differentiation, calibration, and clinical benefit of the centralized test model.
2. The method for constructing a diagnostic model of ovarian malignancy and borderline tumor according to claim 1, wherein: the inclusion criteria for the case group in S1 are those aged over 18 years, those with ovarian malignancy and borderline tumor confirmed by surgical pathology, and those who did not receive radiotherapy, chemotherapy, and other treatments before surgery, and those with insufficient medical history and pathological diagnosis, those with recurrent tumor, metastatic tumor, those with other tumor history or precancerous lesions, those with immune system diseases (such as autoimmune disease, acquired immunodeficiency syndrome, etc.), and pregnant women.
3. The method for constructing a diagnostic model of ovarian malignancy and borderline tumor according to claim 1, wherein: the inclusion standard of the control group in the S1 is the first time the ovarian tissue is confirmed to be not malignant lesions by the operation pathology, and the clinical data of all study subjects are complete, and the exclusion standard of the control group in the S2 is the case history and the pathological diagnosis data are incomplete, the recurrent tumor, the metastatic tumor, the other tumor history or precancerous lesions, the immune system diseases (such as autoimmune diseases, acquired immunodeficiency syndrome and the like) and pregnant women.
4. The method for constructing a diagnostic model of ovarian malignancy and borderline tumor according to claim 1, wherein: the clinical pathology data in the S2 comprises age, menopause, body mass index, gynecological color Doppler ultrasound index acquired in a hospital in 3 months before operation, serum tumor marker level in 3 months before operation, blood cell related parameters before operation, FIGO stage, lymph node metastasis and the like, and each measured value of the gynecological color Doppler ultrasound ovarian tumor is semi-quantitatively converted according to the report result of gynecological color Doppler ultrasound acquired in the hospital before operation: (1) tumor maximum diameter line (mm); (2) swelling properties: the solid tumor is regular, irregular, cystic and cystic; (3) maximum diameter (mm) of the solid component; (4) cyst number of rooms: the solidity, single room, 2-10 rooms, more than 10 rooms; (5) separation conditions: no separation, smooth separation and unsmooth separation; (6) number of papillae: 1, 2, 3, greater than 3; (7) whether to accompany sound shadow: yes, no; (8) blood flow signal: no, level 1, level 2, level 3; (9) ascites: is; no, according to literature reports, 35 hematological indices with clear relationship to ovarian cancer were selected and classified into 5 categories: (1) serum tumor markers 7, including CA125: the reference range is 0.00-35.00U/ml; CA153: the reference range is 0.00-31.30U/ml; cancer antigen 199: the reference range is 0.00-37.00U/ml; squamous cell carcinoma antigen: the reference range is 0.00-1.50ng/ml; alpha fetoprotein: the reference range is 0.00-8.78ng/ml; carcinoembryonic antigen: the reference range is 0.00-5.00ng/ml; HE4: the reference range is that the pre-menopause of normal people is less than 68.96pmol/L, and the post-menopause of normal people is less than 114.9pmol/L; (2) blood cell-related parameter 6: neutrophil count: the reference range is 1.80-6.30X10-9/L; lymphocyte count: the reference range is 1.1-3.20X10-9/L; monocyte count: the reference range is 0.10-0.60 x 10-9/L; platelet count: the reference range is 125-350 x 10-9/L; width of distribution of erythrocytes: the reference range is 12.1-14.3%; average platelet volume: the reference range is 7.20-12.00fL; (3) serum lipid metabolism index 6: triglyceride level: the reference range is 0.00-1.70mmol/L; total cholesterol level: the reference range is 0.00-5.20mmol/L; apolipoprotein-A1 level: the reference range is 1.20-1.60g/L; apolipoprotein-B levels: the reference range is 0.60-1.20g/L; high density lipoprotein cholesterol levels: the reference range is 1.29-1.55mmol/L; low density lipoprotein cholesterol level: the reference range is 0.00-3.10mmol/L; (4) other serum biochemistry general related parameters 10: albumin level: the reference range is 40.00-55.00mmol/L; globulin level: the reference range is 20.00-40.00mmol/L; lactate dehydrogenase level: the reference range is 120.00-250.00mmol/L; creatine kinase level: the reference range is 40.00-200.00mmol/L; creatine kinase isoenzyme levels: the reference range is 0.00-25mmol/L; alanine aminotransferase level: the reference range is 7.00-40.00mmol/L; aspartic acid aminotransferase level: the reference range is 13.00-35.00mmol/L; gamma-glutamyl transpeptidase level: reference range is 7.00-45.00mmol/L, alkaline phosphatase level: the reference range is 50.00-135.00mmol/L; alpha-hydroxybutyrate dehydrogenase level: the reference range is 72.00-182.00U/L; (5) 6 parameters related to coagulation function: prothrombin time: the reference range is 9.80-12.10sec; activation of partial thromboplastin time: the reference range is 23.30-32.50sec; thrombin time: the reference range is 14.00-21.00sec; fibrinogen: the reference range is 1.80-3.50g/L; d-dimer: the reference range is 0.00-0.55mg/LFEU; fibrin (ogen) degradation products: the reference range is 0.00-5.00mg/L; and converting some of the indices into ratios including neutrophil count/lymphocyte count ratio, platelet count/lymphocyte count ratio, monocyte count/lymphocyte count ratio, albumin/globulin ratio, and low density lipoprotein cholesterol/high density lipoprotein cholesterol ratio.
5. The method for constructing a diagnostic model of ovarian malignancy and borderline tumor according to claim 1, wherein: the main instruments in S2 comprise ultrasonic instruments and serum detection index detection instruments, wherein the ultrasonic instruments specifically adopt GE Voluson 730Pro color ultrasonic instruments, in the inspection process, a non-married female is in a supine position, a convex array probe is arranged at the frequency of 25MHz, a married female is in a lithotomy position through abdominal scanning, an intracavity probe is arranged at the frequency of 47.5MHz, the ultrasonic inspection of vagina or the combined scanning of abdomen is carried out, double accessories are conventionally scanned, tumors are found, the positions, the shapes, the sizes, the internal echoes, the existence of solid components and sound shadows, the existence of separation, the separation number, whether the separation is smooth, the existence of nipple-shaped protrusions and the protrusion number are carried out, ascites is formed or not, and when blood flow conditions are detected, spectrum patterns of more than 3 cardiac cycles are obtained in the tumor, serum detection is detected by a chemiluminescent immunoassay method by an acquisition hospital clinical laboratory, the instrument specifically adopts a Rogowski Cobase601 type full-automatic immunoassay analyzer, blood is conventionally detected by an acquisition hospital laboratory, and the instrument specifically adopts a Rayleigh BC-6800 and a full-automatic Mitsubishi 6900 full-cell blood analyzer.
6. The method for constructing a diagnostic model of ovarian malignancy and borderline tumor according to claim 1, wherein: in the step S3, 3mL of peripheral blood is drawn from all patients in the morning on an empty stomach, 35U and mL are taken as cutoff values of CA125, namely positive values are taken as the cutoff values, and negative values are taken as the values, wherein the evaluation standard of the ovarian cancer risk prediction model in the step S3 is that the model is premenopausal: pi= -12+2.38 x in (HE 4) +0.0626 x in (CA 125), postmenopausal: pi= -8.09+1.04 x In (HE 4) +0.732 x In (CA 125), ROMA (%) =exp (PI) and [1+exp (PI) ]%, where In is the natural logarithm, exp is an exponential function based on a natural constant, and premenopausal and postmenopausal women have ROMA index values > 13.1% and 22.7%, which are considered to be at high risk of ovarian malignancy.
7. The method for constructing a diagnostic model of ovarian malignancy and borderline tumor according to claim 1, wherein: the evaluation criteria of the malignancy risk index scoring system in S3 is rmi1=ca 125 (U and mL) ×u×m, where U represents total ultrasound score of each patient, M represents menopausal status, ultrasound scoring criteria is 5 indexes of bilateral lesions, multi-atrial cyst, nipple or solid lesion, ascites, metastasis, and the evaluation criteria of the simple rule risk prediction model in S3 is benign characteristics (B characteristics): (1) a sheet Fang Nangzhong; (2) the maximum diameter of the solid component is less than 7mm; (3) sound shadow is accompanied behind the tumor; (4) smooth multi-atrial cysts with a maximum diameter <10 cm; (5) grade 1 of tumor color blood flow score; malignancy characteristics (M characteristics): (1) an irregular solid tumor; (2) peritoneal effusion; (3) more than or equal to 4 nipple-shaped protrusions; (4) irregular multi-atrial cyst solid tumor with the maximum diameter of more than or equal to 10 cm; (5) CS stage 4; wherein stage 1: very low risk, there are more than 2B features, no M features; 2 stages: low risk, presence of 2B-features or single atrial cysts in B-features only, no M-features; 3 stages: medium risk, with other B features than 1 single atrial cyst, no M features; 4 stages: the risk is high, B features or M features are not generated, and the number of the B features is more than or equal to the number of the M features; 5 stages: very high risk, M feature number > B feature number; SRRisk grades 1 to 3 are classified as benign, and SRRisk grades 4 and 5 are classified as malignant.
8. The method for constructing a diagnostic model of ovarian malignancy and borderline tumor according to claim 1, wherein: the model evaluation standard of ADNEX in S3 is that 3 clinical indexes are as follows: (1) age (age) of the patient; (2) serum CA125 levels; (3) diagnosis center (whether it is tumor transfer center); the 6 ultrasonic indexes are as follows: (1) maximum lesion diameter (mm); (2) diameter (mm) of the solid component in the lesion; (3) whether more than 10 pockets; (4) the number of nipple projections on the wall of the capsule; (5) whether sound and shadow are attenuated or not is judged; (6) whether there is ascites; the use method of the model is that the required 9 predictors (the value of serum CA125 can be applied even if the value is missing) are respectively input into the IOTA ADNEX online website: www.iotagroup.org and adnexmodel, click calculations, the percentage of ovarian tumor properties and stage will automatically be generated, the IOTA ADNEX model divides ovarian tumor nest tumors into five stages, respectively: benign, borderline, early malignant (stage I), late malignant (stage ii to V), metastatic tumors, were considered malignant with 10% as cutoff, at risk > 10%, and benign with < 10%. The results are directly displayed in the form of charts such as percentage charts, bar charts, radar charts and the like, and the preoperative stage results are calculated.
9. The method for constructing a diagnostic model of ovarian malignancy and borderline tumor according to claim 1, wherein: all data in the S4-S8 are statistically processed by using an SPSS24.0 statistical software package, and metering data conforming to normal distribution are expressed by x+/-S; the comparison between the two groups adopts t test; the data which do not accord with normal distribution are represented by a quarter bit distance (IQR), the comparison between two groups adopts a nonparametric rank sum test, the counting data adopts an example number and a percentage to represent, the comparison between two groups adopts a chi square test, the classification variable is represented by a percentage, the classification variable is subjected to a single-factor Logistic regression test, on the basis, the influence factors of ovarian malignancy and juncture tumor are analyzed by adopting a multi-factor Logistic regression model, the postoperative pathological diagnosis result is taken as a gold standard, a subject working characteristic (ROC) curve is drawn, the sensitivity, the specificity, the positive prediction value, the negative prediction value and the about sign index of different diagnosis prediction models under a standard cut-off value are calculated, the efficacy sizes of the ovarian benign malignancy are identified by comparing serum CA125, ROMA, SSRisk, ADNEX models, RMI1 and a diagnosis alignment line graph model COM, and the five methods are respectively subjected to consistency test with the pathological result to obtain a Kappa value, and the Kappa value is more than or equal to 0.75; a kappa value of 0.75> 0.4 is considered to be common to both; kappa value <0.4 considers that the consistency of the two is poor, R software is utilized to draw a nomogram by a logic regression model and calculate a consistency index (C-index) of the nomogram model, the C index is also called C index, the C index represents the ability of a model to predict that an individual achieves an expected result, the C index is 0.5 and has no prediction ability, the C index is 1 and can perfectly distinguish different prognosis of a patient, the C index is lower than 0.7 and considers relatively poor prediction ability, the model is internally verified by a Bootstrap self-sampling method, a calibration curve, a clinical Decision Curve (DCA) and a ROC curve of the nomogram model are drawn by the R software, the degree of distinction, the degree of calibration and the clinical application value of the nomogram model are evaluated, the using method of the degree of calibration is that the holmer-lemeshomerhneshowsoffit figure is checked, if the checking result shows statistical significance (P < 0.05), a certain difference exists between the model prediction value and the actual observation value, and the degree of calibration is general; if P >0.05, it shows that the predicted value and the observed value have no significant difference, so the model fitting degree is good, and all statistical tests in the study adopt that when P <0.05, the difference is considered to have statistical significance.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310602283.6A CN117133439A (en) | 2023-05-26 | 2023-05-26 | Ovarian malignancy and juncture tumor diagnosis model construction method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310602283.6A CN117133439A (en) | 2023-05-26 | 2023-05-26 | Ovarian malignancy and juncture tumor diagnosis model construction method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN117133439A true CN117133439A (en) | 2023-11-28 |
Family
ID=88857155
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310602283.6A Pending CN117133439A (en) | 2023-05-26 | 2023-05-26 | Ovarian malignancy and juncture tumor diagnosis model construction method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117133439A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118039070A (en) * | 2024-04-11 | 2024-05-14 | 四川省肿瘤医院 | Clinical care system for interventional operation |
-
2023
- 2023-05-26 CN CN202310602283.6A patent/CN117133439A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118039070A (en) * | 2024-04-11 | 2024-05-14 | 四川省肿瘤医院 | Clinical care system for interventional operation |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Cao et al. | Validation of American college of radiology ovarian-adnexal reporting and data system ultrasound (O-RADS US): analysis on 1054 adnexal masses | |
Tanase et al. | Factors that differentiate between endometriosis-associated ovarian cancer and benign ovarian endometriosis with mural nodules | |
Ionescu et al. | Correlation of ultrasound features and the Risk of Ovarian Malignancy Algorithm score for different histopathological subtypes of benign adnexal masses | |
Zhang et al. | Diagnostic performance of the Gynecology Imaging Reporting and Data System for malignant adnexal masses | |
Koneczny et al. | The use of sonographic subjective tumor assessment, IOTA logistic regression model 1, IOTA Simple Rules and GI-RADS system in the preoperative prediction of malignancy in women with adnexal masses | |
CN117133439A (en) | Ovarian malignancy and juncture tumor diagnosis model construction method | |
Hu et al. | Preoperative nomogram for predicting sentinel lymph node metastasis risk in breast cancer: a potential application on omitting sentinel lymph node biopsy | |
Guo et al. | A novel diagnostic nomogram based on serological and ultrasound findings for preoperative prediction of malignancy in patients with ovarian masses | |
Li et al. | Assessing CT imaging features combined with CEA and CA125 levels to identify endometriosis-associated ovarian cancer | |
Zhao et al. | Clinical and pathologic predictors of lymph node metastasis in papillary thyroid microcarcinomas | |
Niemi et al. | Reliability of preoperative evaluation of postmenopausal ovarian tumors | |
Jung et al. | Differentiating thymoma from thymic cyst in anterior mediastinal abnormalities smaller than 3 cm | |
Lee et al. | Ultrasonographic ovarian mass scoring system for predicting malignancy in pregnant women with ovarian mass | |
Rodriguez-Lopez et al. | Impaired immune reaction and increased lactate and C-reactive protein for early prediction of severe morbidity and pancreatic fistula after pancreatoduodenectomy | |
Xuan et al. | Application of contrast-enhanced ultrasound in the pathological grading and prognosis prediction of hepatocellular carcinoma | |
Wang et al. | Evaluating the risk of malignancy in adnexal masses: validation of O-RADS and comparison with ADNEX model, SA, and RMI | |
CN104251906A (en) | Tumor marker | |
RU2695758C1 (en) | Method for prediction of clinical course in patients with brain metastases | |
Saito et al. | Multiple regression analysis for assessing the growth of small hepatocellular carcinoma: the MIB-1 labeling index is the most effective parameter | |
Jordan et al. | Ovarian cancer biomarkers as diagnostic triage tests | |
Fadare et al. | The diagnosis of mucinous lesions in endometrial samplings by gynaecological pathologists: An analysis of diagnostic reproducibility | |
Fredericks et al. | Science Repository | |
Wu et al. | Prediction of VEGF and EGFR expression in peripheral lung cancer based on the radiomics model of spectral CT enhanced images | |
Velayo et al. | Improving diagnostic strategies for ovarian cancer in Filipino women using ultrasound imaging and a multivariate index assay | |
Guerriero et al. | Transvaginal ultrasonography in the diagnosis of extrauterine pelvic diseases |
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 |