CN113658696A - Prediction system for jointly predicting gastric cancer prognosis based on patient age, nutritional indexes, tumor stages and tumor markers - Google Patents
Prediction system for jointly predicting gastric cancer prognosis based on patient age, nutritional indexes, tumor stages and tumor markers Download PDFInfo
- Publication number
- CN113658696A CN113658696A CN202110832843.8A CN202110832843A CN113658696A CN 113658696 A CN113658696 A CN 113658696A CN 202110832843 A CN202110832843 A CN 202110832843A CN 113658696 A CN113658696 A CN 113658696A
- Authority
- CN
- China
- Prior art keywords
- scale
- value
- corresponding score
- patient
- score
- 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.)
- Granted
Links
- 208000005718 Stomach Neoplasms Diseases 0.000 title claims abstract description 111
- 206010017758 gastric cancer Diseases 0.000 title claims abstract description 111
- 201000011549 stomach cancer Diseases 0.000 title claims abstract description 111
- 238000004393 prognosis Methods 0.000 title claims abstract description 102
- 206010028980 Neoplasm Diseases 0.000 title claims abstract description 74
- 235000016709 nutrition Nutrition 0.000 title claims abstract description 70
- 230000004083 survival effect Effects 0.000 claims abstract description 97
- 238000010276 construction Methods 0.000 claims abstract description 9
- 238000002271 resection Methods 0.000 claims abstract description 9
- 238000012795 verification Methods 0.000 claims description 18
- 238000011088 calibration curve Methods 0.000 claims description 10
- 238000012800 visualization Methods 0.000 claims description 5
- 238000004519 manufacturing process Methods 0.000 claims 1
- 230000009286 beneficial effect Effects 0.000 abstract description 5
- 230000000875 corresponding effect Effects 0.000 description 136
- 238000000034 method Methods 0.000 description 15
- 239000000439 tumor marker Substances 0.000 description 15
- 230000000052 comparative effect Effects 0.000 description 11
- 230000000694 effects Effects 0.000 description 6
- 238000012549 training Methods 0.000 description 6
- 201000011510 cancer Diseases 0.000 description 5
- 108010088751 Albumins Proteins 0.000 description 4
- 102000009027 Albumins Human genes 0.000 description 4
- 238000013211 curve analysis Methods 0.000 description 3
- 238000010200 validation analysis Methods 0.000 description 3
- 102100032752 C-reactive protein Human genes 0.000 description 2
- 238000011226 adjuvant chemotherapy Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 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 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 210000004698 lymphocyte Anatomy 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000009897 systematic effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 108010074051 C-Reactive Protein Proteins 0.000 description 1
- 230000004544 DNA amplification Effects 0.000 description 1
- 101150054472 HER2 gene Proteins 0.000 description 1
- 206010061218 Inflammation Diseases 0.000 description 1
- 108020005198 Long Noncoding RNA Proteins 0.000 description 1
- 206010058467 Lung neoplasm malignant Diseases 0.000 description 1
- 238000001358 Pearson's chi-squared test Methods 0.000 description 1
- JAWMENYCRQKKJY-UHFFFAOYSA-N [3-(2,4,6,7-tetrahydrotriazolo[4,5-c]pyridin-5-ylmethyl)-1-oxa-2,8-diazaspiro[4.5]dec-2-en-8-yl]-[2-[[3-(trifluoromethoxy)phenyl]methylamino]pyrimidin-5-yl]methanone Chemical compound N1N=NC=2CN(CCC=21)CC1=NOC2(C1)CCN(CC2)C(=O)C=1C=NC(=NC=1)NCC1=CC(=CC=C1)OC(F)(F)F JAWMENYCRQKKJY-UHFFFAOYSA-N 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000037396 body weight Effects 0.000 description 1
- 238000007475 c-index Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000002512 chemotherapy Methods 0.000 description 1
- 238000000546 chi-square test Methods 0.000 description 1
- 235000012000 cholesterol Nutrition 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 239000002537 cosmetic Substances 0.000 description 1
- 238000011498 curative surgery Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000035622 drinking Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 108700020302 erbB-2 Genes Proteins 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000004054 inflammatory process Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 201000005202 lung cancer Diseases 0.000 description 1
- 208000020816 lung neoplasm Diseases 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035764 nutrition Effects 0.000 description 1
- 235000003715 nutritional status Nutrition 0.000 description 1
- 230000007170 pathology Effects 0.000 description 1
- 230000002980 postoperative effect Effects 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000011470 radical surgery Methods 0.000 description 1
- 239000002994 raw material Substances 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000000391 smoking effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000001356 surgical procedure Methods 0.000 description 1
- 238000012353 t test Methods 0.000 description 1
- 230000001225 therapeutic effect Effects 0.000 description 1
- 230000004580 weight loss Effects 0.000 description 1
Images
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
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention provides a prediction system for joint prediction of gastric cancer prognosis based on patient age, nutritional indicators, tumor stages and tumor markers, wherein the prediction system is constructed by taking the age, tumor TNM stages, AFP, CA153, CA724 and nutritional indicators of patients as prediction indicators, and belongs to the field of prediction models. The prediction system can accurately predict the prognosis of gastric cancer patients (particularly patients who undergo gastric cancer resection operation in stage I-IV), and accurately predict the survival rate of the patients. The prediction system for predicting the gastric cancer prognosis provided by the invention is simple in construction method, high in prediction accuracy and discrimination, has important significance for clinically and auxiliarily judging the prognosis condition and survival rate of gastric cancer patients, and is beneficial to individual accurate treatment of clinical patients.
Description
Technical Field
The invention belongs to the field of prediction models, and particularly relates to a prediction system for jointly predicting gastric cancer prognosis based on patient age, nutritional indexes, tumor stages and tumor markers.
Background
Although the incidence of gastric cancer is reduced in some countries in recent years, the absolute value of the number of new cases is increased when the global overall incidence of gastric cancer is reduced due to the increase of the overall population and the aging of the population in high incidence areas. Currently, surgery is the primary method of treating gastric cancer. However, the long-term therapeutic effect of the gastric cancer patients who are operated is different. Accurate prediction of the prognosis of gastric cancer patients is of great importance in guiding the treatment of patients and improving the prognosis.
The TNM staging is one of the most important factors influencing the prognosis of the gastric cancer, and currently, the TNM staging can objectively and accurately predict the prognosis of the gastric cancer. The TNM staging provides scientific basis for accurately judging prognosis, can better reflect the consistency of staging and prognosis, is beneficial to making a reasonable treatment scheme, evaluating the treatment effect and reflecting the treatment level. However, some patients with the same TNM stage and basically the same treatment means still have the same long-term curative effect, and some patients can survive for a long time but some patients cannot.
In fact, it is far from sufficient to use a single index to infer a patient's prognosis in clinical work, since these indices only provide a stratified risk for the population and do not allow individualized prediction for each patient's specific situation. It has been found that the prognosis of cancer patients depends not only on tumor-related factors but also on host-related factors. There are many systems for prognosis scoring of gastric cancer that involve host-related factors, which have been reported. These scoring systems include a system for predicting the survival time of a patient after radical gastric cancer resection, which is constructed based on a neutrophil-to-lymphocyte ratio (NLR), a platelet-to-lymphocyte ratio (PLR), and a lymphocyte-to-monocyte ratio (LMR), an improved glasgow prognosis scoring system (mGPS) based on an inflammation index, a gene-related gastric cancer prognosis risk scoring system based on HER2 gene amplification and lncRNA profile, and a scoring system based on physical fitness status (ECOG PS), and the like. Nutritional indicators are also considered to be closely related to gastric cancer prognosis. Xuechao Liu et al (systematic cosmetic score and nonbiological marker prediction cancer-specific subset in cancer II-III scientific cancer patients with ad juvant chemotherapy, Clinical Nutrition, Volume 38, Issue 4, August 2019, Pages 1853 1860) constructed a gastric cancer prognosis scoring system based on C-reactive protein/albumin ratio (CRP/Alb), post-operative nutritional index (PNI), pre-operative weight loss, and CA199, which was found by internal validation to be able to predict 1-year, 3-year, and 5-year cancer specific survival rates (CSS) in a patient who underwent adjuvant chemotherapy after receiving curative surgery for stage II-III gastric cancer in an ideal model. However, the system is a scoring system established by data training of patients who undergo adjuvant chemotherapy after undergoing radical surgery on stage II-III gastric cancer, and cannot be widely applied to survival rate prediction of stage I-IV (particularly I, IV) gastric cancer patients; moreover, the C-index of the system is 0.714 (95% CI:0.680-0.749), and the prediction accuracy and the discrimination are still further improved.
Therefore, there is a need to develop a prediction system suitable for patients with stage I-IV gastric cancer, which can provide a more accurate prognosis for patients with lung cancer.
Disclosure of Invention
The invention aims to provide a prediction system for jointly predicting gastric cancer prognosis based on patient age, nutritional indexes, tumor stages and tumor markers.
The invention provides a prediction system for predicting the prognosis of a gastric cancer patient, which is constructed by taking the age, the tumor TNM stage, AFP, CA153, CA724 and nutritional indexes of the patient as prediction indexes.
Further, the prediction system is an alignment chart which comprises straight lines 1-11, wherein the straight lines 1-11 are sequentially arranged from top to bottom and are parallel to each other; each straight line represents a scale, and scales are carved on the scale;
the 1 st scale represents a scale with a score corresponding to the scale on the 2 nd to 7 th scales; the scale value of the 1 st scale is 0-100, 0 is at the leftmost end, 100 is at the rightmost end, and the scale of the scale is divided equally;
the 7 th scale represents the nutritional index of the patient;
the 8 th scale represents the sum of the scores corresponding to the scales on the 2 nd to 7 th scales;
the 9 th scale represents the predicted value of the 3-year survival rate of the patient, and the predicted value of the 3-year survival rate of the patient is the value of the score on the 8 th scale corresponding to the 9 th scale;
the 10 th scale shows the predicted value of the 5-year survival rate of the patient, and the predicted value of the 5-year survival rate of the patient is the value of the score on the 8 th scale corresponding to the 10 th scale;
the 11 th scale represents the predicted value of the 8-year survival rate of the patient, and the predicted value of the 8-year survival rate of the patient is the corresponding value of the score on the 8 th scale on the 11 th scale.
Further, the nutritional index is CONUT;
the scale value of the 2 nd scale is 20-90, 20 is at the leftmost end, 90 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 2 nd scale is 20, the corresponding score on the 1 st scale is 0, and when the scale of the 2 nd scale is 90, the corresponding score on the 1 st scale is 65;
the scale value of the 3 rd scale is 1-4, 1 is at the leftmost end, 4 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 3 rd scale is 1, the corresponding score on the 1 st scale is 0, and when the scale of the 3 rd scale is 4, the corresponding score on the 1 st scale is 100;
the 4 th scale is 0-1000, 0 is at the leftmost end, 1000 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 4 th scale is 0, the corresponding score on the 1 st scale is 0, and when the scale of the 4 th scale is 1000, the corresponding score on the 1 st scale is 86;
the scale value of the 5 th scale is 0-300, 0 is at the leftmost end, 300 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 5 th scale is 0, the corresponding score on the 1 st scale is 0, and when the scale of the 5 th scale is 300, the corresponding score on the 1 st scale is 42.5;
the 6 th scale has a scale value of 0-1000, wherein 0 is at the leftmost end, 1000 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 6 th scale is 0, the corresponding score on the 1 st scale is 0, and when the scale of the 6 th scale is 1000, the corresponding score on the 1 st scale is 90;
the scale value of the 7 th scale is 1-12, 1 is at the leftmost end, 12 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 7 th scale is 1, the corresponding score on the 1 st scale is 0, and when the scale of the 7 th scale is 12, the corresponding score on the 1 st scale is 92.5;
the scale of the 8 th scale is 0-260, 0 is at the leftmost end, 260 is at the rightmost end, and the scale of the scale is divided equally; when the scale of 8 th scale is 0, it corresponds the 0 scale of first scale, and when the scale of 8 th scale is 260, it corresponds the 100 scales of first scale.
Further, when the nutritional indicator is CONUT, the nomogram is shown in fig. 1.
In fig. 1:
when the value of the score on the 8 th scale on the 9 th scale is at the left end of 0.95, the predicted value of the 3-year survival rate is more than 0.95, and when the value of the score on the 8 th scale on the 9 th scale is at the right end of 0.3, the predicted value of the 3-year survival rate is less than 0.3;
when the value corresponding to the score on the 8 th scale on the 10 th scale is at the left end of 0.95, the predicted value of the 5-year survival rate is greater than 0.95, and when the value corresponding to the score on the 8 th scale on the 10 th scale is at the right end of 0.1, the predicted value of the 5-year survival rate is less than 0.1;
when the value corresponding to the score on the 8 th scale on the 11 th scale is at the left end of 0.95, the predicted value of the survival rate per 8 years is greater than 0.95, and when the value corresponding to the score on the 8 th scale on the 11 th scale is at the right end of 0.05, the predicted value of the survival rate per 8 years is less than 0.05.
Further, the nutritional index is NRI;
the scale value of the 2 nd scale is 20-90, 20 is at the leftmost end, 90 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 2 nd scale is 20, the corresponding score on the 1 st scale is 0, and when the scale of the 2 nd scale is 90, the corresponding score on the 1 st scale is 33.5;
the scale value of the 3 rd scale is 1-4, 1 is at the leftmost end, 4 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 3 rd scale is 1, the corresponding score on the 1 st scale is 0, and when the scale of the 3 rd scale is 4, the corresponding score on the 1 st scale is 61;
the 4 th scale is 0-1000, 0 is at the leftmost end, 1000 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 4 th scale is 0, the corresponding score on the 1 st scale is 0, and when the scale of the 4 th scale is 1000, the corresponding score on the 1 st scale is 56;
the scale value of the 5 th scale is 0-300, 0 is at the leftmost end, 300 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 5 th scale is 0, the corresponding score on the 1 st scale is 0, and when the scale of the 5 th scale is 300, the corresponding score on the 1 st scale is 21.25;
the 6 th scale has a scale value of 0-1000, wherein 0 is at the leftmost end, 1000 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 6 th scale is 0, the corresponding score on the 1 st scale is 0, and when the scale of the 6 th scale is 1000, the corresponding score on the 1 st scale is 60;
the scale value of the 7 th scale is 120-62, 120 is at the leftmost end, 65 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 7 th scale is 120, the corresponding score on the 1 st scale is 0, and when the scale of the 7 th scale is 65, the corresponding score on the 1 st scale is 100;
the 8 th scale is 0-200, 0 is at the leftmost end, 200 is at the rightmost end, and the scale of the scale is divided equally; when the scale of 8 th scale is 0, it corresponds the 0 scale of first scale, and when the scale of 8 th scale is 200, it corresponds the 100 scales of first scale.
Further, when the nutritional index is NRI, the nomogram is shown in fig. 2.
In fig. 2:
when the value of the score on the 8 th scale on the 9 th scale is at the left end of 0.95, the predicted value of the 3-year survival rate is more than 0.95, and when the value of the score on the 8 th scale on the 9 th scale is at the right end of 0.3, the predicted value of the 3-year survival rate is less than 0.3;
when the value corresponding to the score on the 8 th scale on the 10 th scale is at the left end of 0.95, the predicted value of the 5-year survival rate is greater than 0.95, and when the value corresponding to the score on the 8 th scale on the 10 th scale is at the right end of 0.1, the predicted value of the 5-year survival rate is less than 0.1;
when the value corresponding to the score on the 8 th scale on the 11 th scale is at the left end of 0.95, the predicted value of the survival rate per 8 years is greater than 0.95, and when the value corresponding to the score on the 8 th scale on the 11 th scale is at the right end of 0.05, the predicted value of the survival rate per 8 years is less than 0.05.
Further, the nutritional index is PNI;
the scale value of the 2 nd scale is 20-90, 20 is at the leftmost end, 90 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 2 nd scale is 20, the corresponding score on the 1 st scale is 0, and when the scale of the 2 nd scale is 90, the corresponding score on the 1 st scale is 21.25;
the scale value of the 3 rd scale is 1-4, 1 is at the leftmost end, 4 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 3 rd scale is 1, the corresponding score on the 1 st scale is 0, and when the scale of the 3 rd scale is 4, the corresponding score on the 1 st scale is 52.5;
the 4 th scale is 0-1000, 0 is at the leftmost end, 1000 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 4 th scale is 0, the corresponding score on the 1 st scale is 0, and when the scale of the 4 th scale is 1000, the corresponding score on the 1 st scale is 45;
the scale value of the 5 th scale is 0-300, 0 is at the leftmost end, 300 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 5 th scale is 0, the corresponding score on the 1 st scale is 0, and when the scale of the 5 th scale is 300, the corresponding score on the 1 st scale is 24.5;
the 6 th scale has a scale value of 0-1000, wherein 0 is at the leftmost end, 1000 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 6 th scale is 0, the corresponding score on the 1 st scale is 0, and when the scale of the 6 th scale is 1000, the corresponding score on the 1 st scale is 57.5;
the scale value of the 7 th scale is 70-20, 70 is at the leftmost end, 20 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 7 th scale is 70, the corresponding score on the 1 st scale is 0, and when the scale of the 7 th scale is 20, the corresponding score on the 1 st scale is 100;
the scale of the 8 th scale is 0-160, 0 is at the leftmost end, 160 is at the rightmost end, and the scale of the scale is divided equally; when the scale of 8 th scale is 0, it corresponds the 0 scale of first scale, and when the scale of 8 th scale is 160, it corresponds the 100 scales of first scale.
Further, when the nutritional indicator is PNI, the nomogram is as shown in fig. 3.
In fig. 3:
when the value of the score on the 8 th scale on the 9 th scale is at the left end of 0.95, the predicted value of the 3-year survival rate is more than 0.95, and when the value of the score on the 8 th scale on the 9 th scale is at the right end of 0.3, the predicted value of the 3-year survival rate is less than 0.3;
when the value corresponding to the score on the 8 th scale on the 10 th scale is at the left end of 0.95, the predicted value of the 5-year survival rate is greater than 0.95, and when the value corresponding to the score on the 8 th scale on the 10 th scale is at the right end of 0.1, the predicted value of the 5-year survival rate is less than 0.1;
when the value corresponding to the score on the 8 th scale on the 11 th scale is at the left end of 0.95, the predicted value of the survival rate per 8 years is greater than 0.95, and when the value corresponding to the score on the 8 th scale on the 11 th scale is at the right end of 0.1, the predicted value of the survival rate per 8 years is less than 0.1.
Further, the construction method of the nomogram comprises the following steps:
(1) collecting the indexes of the patient and inputting the indexes into an input module;
the indices include age, tumor TNM staging, AFP, CA153, CA724, and nutritional indices of the patient;
(2) and constructing a cox regression model by using the indexes in the input module, finishing the nomogram visualization of the cox regression model by using an RMS (root mean square) operation package, and finishing the nomogram verification of the cox regression model by using a calibration Curve and precision currve operation package to obtain the product.
Further, the age is 20-95 years, the TNM stage is 1, 2, 3 or 4, the AFP is 0-1000 ng/mL, the CA153 is 0-1000U/mL, and the CA724 is 0-300U/mL.
Further, when the nutritional index is CONUT, the CONUT is 1-12; when the nutritional index is NRI, the NRI is 120-62; and when the nutritional index is PNI, the PNI is 70-20.
The invention also provides equipment for predicting the prognosis of a gastric cancer patient, which is characterized in that: the device comprises the prediction system.
The invention also provides application of the prediction system in preparing equipment for predicting the prognosis of a gastric cancer patient.
Further, the gastric cancer patient is a patient with stage I-IV gastric cancer resection operation;
and/or the gastric cancer patient prognosis is 3, 5, 8 year survival rate of gastric cancer patients.
The invention constructs a nomogram for predicting gastric cancer prognosis based on multiple indexes of patient age, nutritional indexes (CONUT, NRI or PNI), tumor TNM stage and tumor markers (AFP, CA153 and CA 724). The nomogram can be used for accurately predicting the prognosis of a gastric cancer patient (particularly a patient with stage I-IV gastric cancer resection operation), and the survival rate of the patient can be accurately predicted.
Compared with the existing gastric cancer prognosis prediction model, the nomogram for predicting gastric cancer prognosis provided by the invention has the following advantages:
1. the system of the application is suitable for patients with stage I-IV gastric cancer resection operation;
2. the indexes adopted by the application are all indexes which are convenient for a clinician to obtain and use;
3. compared with a gastric cancer prognosis prediction system based on a single index (constructed in a comparison example 1-8), the gastric cancer prognosis prediction system constructed based on multiple indexes of patient age, nutritional index (CONUT, NRI or PNI), tumor TNM stage and tumor markers (AFP, CA153 and CA724) has the advantages that the area under the ROC curve and the C-index are obviously increased, and the prediction result is more accurate.
4. In addition, in the gastric cancer prognosis prediction system based on multiple indexes, which is constructed in embodiments 1 to 3 of the present invention, the gastric cancer prognosis prediction system constructed in embodiment 3 has the best prediction effect. The result shows that the multi-index gastric cancer prognosis prediction system constructed by selecting PNI as the nutritional index has better prediction effect on gastric cancer prognosis.
The nomogram for predicting the gastric cancer prognosis provided by the invention is simple in construction method, high in prediction accuracy and discrimination, has important significance for clinically and auxiliarily judging the prognosis condition and survival rate of gastric cancer patients, and is beneficial to individual accurate treatment of clinical patients.
Obviously, many modifications, substitutions, and variations are possible in light of the above teachings of the invention, without departing from the basic technical spirit of the invention, as defined by the following claims.
The present invention will be described in further detail with reference to the following examples. This should not be understood as limiting the scope of the above-described subject matter of the present invention to the following examples. All the technologies realized based on the above contents of the present invention belong to the scope of the present invention.
Drawings
FIG. 1 is a nomogram for predicting the prognosis of gastric cancer based on age, nutritional index CONUT, tumor stage and tumor marker multi-index combination.
FIG. 2 is a nomogram for predicting gastric cancer prognosis based on age, nutritional index NRI, tumor stage and tumor marker multi-index combination.
FIG. 3 is a nomogram for predicting gastric cancer prognosis based on age, nutritional index PNI, tumor stage and tumor marker multi-index combination.
FIG. 4 is a comparison of the ROC curves for prognosis of the multi-index prediction system constructed in example 1 and the single-index prediction systems constructed in the control example.
FIG. 5 is a comparison of the ROC curves for prognosis of the multi-index prediction system constructed in example 2 and the single-index prediction systems constructed in the control example.
FIG. 6 is a comparison of the ROC curves for prognosis of the multi-index prediction system constructed in example 3 and the single-index prediction systems constructed in the control example.
FIG. 7 shows the results of the verification of the 3-year survival rate (A, C, E) and the 5-year survival rate (B, D, F) of the patients predicted by the multi-index prediction systems constructed in embodiments 1 to 3 of the present invention using a decision curve analysis method.
FIG. 8 is a verification result of patient 3, 5, and 8 year survival rates predicted by the multi-index prediction system constructed in embodiments 1-3 of the present invention using a calibration curve.
Detailed Description
The raw materials and equipment used in the invention are known products and are obtained by purchasing commercial products.
The patient data adopted in the embodiment of the invention are all from 937 patients who have undergone gastric cancer resection operation in stages I-IV (the hospital for treatment is Sichuan university Hospital in Waisia, the time for treatment is from 3 months to 7 months in 2020 in 2006, the disease is primarily diagnosed gastric cancer, and the treatment scheme is surgical resection). After the systematic treatment of all patients is finished, outpatient follow-up visits, hospitalization follow-up visits and telephone follow-up visits are adopted.
Collecting the basic preoperative conditions (including sex, age, ethnicity, smoking and drinking) of 937 patients, tumor markers (including AFP, unit ng/mL; CA153, unit U/mL; CA724, unit U/mL), TNM staging conditions and CONUT (Controlling Nutritional Status), NRI (Nutritional risk index) and PNI (Nutritional nuclear index) of 3 Nutritional indexes for single-factor and multi-factor cox regression analysis, C-index calculation and screening, and screening out the prognosis indexes which are related to gastric cancer and are convenient for a clinician to use:
wherein, the TNM staging condition is subjected to pathology inspection and comprehensive analysis and judgment of a clinician; the CONUT is calculated by albumin, total cholesterol and lymphocyte count; NRI was calculated from albumin and body weight (preoperative and ideal); PNI is calculated by albumin and lymphocyte counts.
937 patients were randomized into two groups: one 649 cases are used as a model training set; and the other 288 cases as model verification groups.
Example 1: the invention relates to a construction method of a nomogram for jointly predicting gastric cancer prognosis based on age, nutritional index CONUT, tumor stage and tumor marker multi-index
Input module
Age (Age), tumor TNM stage (stage), tumor markers AFP, CA153 and CA724, and a nutritional index CONUT of 649 patients in the model training group are collected as indexes related to the prognosis of the gastric cancer of the patients. And inputting the indexes into an input module.
Second, building gastric cancer prognosis prediction model
And (3) constructing a cox regression model by using indexes in the input module, finishing nomogram visualization of the cox regression model by using an RMS (root mean square) operation package, and finishing nomogram verification of the cox regression model by using a calibration Curve and precision currve operation package to obtain a nomogram 1 shown in the figure 1.
The alignment contains 11 scales:
the 1 st scale represents a scale with a score corresponding to the scale on the 2 nd to 7 th scales; the scale value of the 1 st scale is 0-100, 0 is at the leftmost end, 100 is at the rightmost end, and the scale of the scale is divided equally;
the 7 th scale represents the patient's nutritional indicator, CONUT;
the 8 th scale represents the Total risk score (Total Points), wherein the Total risk score is the risk score corresponding to age, the risk score corresponding to the stage of the tumor TNM, the risk score corresponding to AFP, the risk score corresponding to CA153, the risk score corresponding to CA724 and the risk score corresponding to CONUT, namely the sum of the scores corresponding to the scales on the 2 nd to 7 th scales;
the 9 th scale shows the predicted value of 3-year survival rate of the patient, and the predicted value of the 3-year survival rate of the patient is the value of the score on the 8 th scale corresponding to the 9 th scale;
the 10 th scale shows the predicted value of the 5-year survival rate of the patient, and the predicted value of the 5-year survival rate of the patient is the value of the score on the 8 th scale corresponding to the 10 th scale;
the 11 th scale represents the predicted value of the 8-year survival rate of the patient, and the predicted value of the 8-year survival rate of the patient is the value of the score on the 8 th scale corresponding to the 11 th scale;
the scale value of the 2 nd scale is 20-90, 20 is at the leftmost end, 90 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 2 nd scale is 20, the corresponding score on the 1 st scale is 0, and when the scale of the 2 nd scale is 90, the corresponding score on the 1 st scale is 65;
the scale value of the 3 rd scale is 1-4, 1 is at the leftmost end, 4 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 3 rd scale is 1, the corresponding score on the 1 st scale is 0, and when the scale of the 3 rd scale is 4, the corresponding score on the 1 st scale is 100;
the 4 th scale is 0-1000, 0 is at the leftmost end, 1000 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 4 th scale is 0, the corresponding score on the 1 st scale is 0, and when the scale of the 4 th scale is 1000, the corresponding score on the 1 st scale is 86;
the scale value of the 5 th scale is 0-300, 0 is at the leftmost end, 300 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 5 th scale is 0, the corresponding score on the 1 st scale is 0, and when the scale of the 5 th scale is 300, the corresponding score on the 1 st scale is 42.5;
the 6 th scale has a scale value of 0-1000, wherein 0 is at the leftmost end, 1000 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 6 th scale is 0, the corresponding score on the 1 st scale is 0, and when the scale of the 6 th scale is 1000, the corresponding score on the 1 st scale is 90;
the scale value of the 7 th scale is 1-12, 1 is at the leftmost end, 12 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 7 th scale is 1, the corresponding score on the 1 st scale is 0, and when the scale of the 7 th scale is 12, the corresponding score on the 1 st scale is 92.5;
the scale of the 8 th scale is 0-260, 0 is at the leftmost end, 260 is at the rightmost end, and the scale of the scale is divided equally; when the scale of 8 th scale is 0, it corresponds the 0 scale of first scale, and when the scale of 8 th scale is 260, it corresponds the 100 scales of first scale.
In fig. 1:
when the value of the score on the 8 th scale on the 9 th scale is at the left end of 0.95, the predicted value of the 3-year survival rate is more than 0.95, and when the value of the score on the 8 th scale on the 9 th scale is at the right end of 0.3, the predicted value of the 3-year survival rate is less than 0.3;
when the value corresponding to the score on the 8 th scale on the 10 th scale is at the left end of 0.95, the predicted value of the 5-year survival rate is greater than 0.95, and when the value corresponding to the score on the 8 th scale on the 10 th scale is at the right end of 0.1, the predicted value of the 5-year survival rate is less than 0.1;
when the value corresponding to the score on the 8 th scale on the 11 th scale is at the left end of 0.95, the predicted value of the survival rate per 8 years is greater than 0.95, and when the value corresponding to the score on the 8 th scale on the 11 th scale is at the right end of 0.05, the predicted value of the survival rate per 8 years is less than 0.05.
Third, the gastric cancer prognosis prediction model is used for predicting the survival rate of the patient
And collecting the ages, tumor TNM stages, tumor markers AFP, CA153 and CA724 and a nutritional index CONUT of 288 patients in the model verification group, and obtaining the 3-year survival rate, the 5-year survival rate and the 8-year survival rate predicted by each patient according to the nomogram 1.
Example 2: the invention relates to a construction method of a nomogram for jointly predicting gastric cancer prognosis based on age, nutritional index NRI, tumor stage and tumor marker multi-index
Input module
The age, tumor TNM stage, tumor markers AFP, CA153 and CA724 and a nutritional index NRI of 649 patients in the model training group are collected to be used as indexes related to the gastric cancer prognosis of the patients. And inputting the indexes into an input module.
Second, building gastric cancer prognosis prediction model
And constructing a cox regression model by using the indexes in the input module, finishing the nomogram visualization of the cox regression model by using an RMS (root mean square) operation package, and finishing the nomogram verification of the cox regression model by using a calibration Curve and precision currve operation package to obtain the nomogram 2 shown in the figure 2.
The alignment contains 11 scales:
the 1 st scale represents a scale with a score corresponding to the scale on the 2 nd to 7 th scales; the scale value of the 1 st scale is 0-100, 0 is at the leftmost end, 100 is at the rightmost end, and the scale of the scale is divided equally;
the 7 th scale represents the patient's nutritional index NRI;
the 8 th represents the Total risk score (Total Points), wherein the Total risk score is the sum of the risk score corresponding to age, the risk score corresponding to tumor TNM stage, the risk score corresponding to AFP, the risk score corresponding to CA153, the risk score corresponding to CA724 and the risk score corresponding to NRI, namely the score corresponding to the scale on the 2 nd to 7 th scales;
the 9 th scale shows the predicted value of 3-year survival rate of the patient, and the predicted value of the 3-year survival rate of the patient is the value of the score on the 8 th scale corresponding to the 9 th scale;
the 10 th scale shows the predicted value of the 5-year survival rate of the patient, and the predicted value of the 5-year survival rate of the patient is the value of the score on the 8 th scale corresponding to the 10 th scale;
the 11 th scale represents the predicted value of the 8-year survival rate of the patient, and the predicted value of the 8-year survival rate of the patient is the corresponding value of the score on the 8 th scale on the 11 th scale.
The scale value of the 2 nd scale is 20-90, 20 is at the leftmost end, 90 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 2 nd scale is 20, the corresponding score on the 1 st scale is 0, and when the scale of the 2 nd scale is 90, the corresponding score on the 1 st scale is 33.5;
the scale value of the 3 rd scale is 1-4, 1 is at the leftmost end, 4 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 3 rd scale is 1, the corresponding score on the 1 st scale is 0, and when the scale of the 3 rd scale is 4, the corresponding score on the 1 st scale is 61;
the 4 th scale is 0-1000, 0 is at the leftmost end, 1000 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 4 th scale is 0, the corresponding score on the 1 st scale is 0, and when the scale of the 4 th scale is 1000, the corresponding score on the 1 st scale is 56;
the scale value of the 5 th scale is 0-300, 0 is at the leftmost end, 300 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 5 th scale is 0, the corresponding score on the 1 st scale is 0, and when the scale of the 5 th scale is 300, the corresponding score on the 1 st scale is 21.25;
the 6 th scale has a scale value of 0-1000, wherein 0 is at the leftmost end, 1000 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 6 th scale is 0, the corresponding score on the 1 st scale is 0, and when the scale of the 6 th scale is 1000, the corresponding score on the 1 st scale is 60;
the scale value of the 7 th scale is 120-62, 120 is at the leftmost end, 65 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 7 th scale is 120, the corresponding score on the 1 st scale is 0, and when the scale of the 7 th scale is 65, the corresponding score on the 1 st scale is 100;
the 8 th scale is 0-200, 0 is at the leftmost end, 200 is at the rightmost end, and the scale of the scale is divided equally; when the scale of 8 th scale is 0, it corresponds the 0 scale of first scale, and when the scale of 8 th scale is 200, it corresponds the 100 scales of first scale.
In fig. 2:
when the value of the score on the 8 th scale on the 9 th scale is at the left end of 0.95, the predicted value of the 3-year survival rate is more than 0.95, and when the value of the score on the 8 th scale on the 9 th scale is at the right end of 0.3, the predicted value of the 3-year survival rate is less than 0.3;
when the value corresponding to the score on the 8 th scale on the 10 th scale is at the left end of 0.95, the predicted value of the 5-year survival rate is greater than 0.95, and when the value corresponding to the score on the 8 th scale on the 10 th scale is at the right end of 0.1, the predicted value of the 5-year survival rate is less than 0.1;
when the value corresponding to the score on the 8 th scale on the 11 th scale is at the left end of 0.95, the predicted value of the survival rate per 8 years is greater than 0.95, and when the value corresponding to the score on the 8 th scale on the 11 th scale is at the right end of 0.05, the predicted value of the survival rate per 8 years is less than 0.05.
Third, the gastric cancer prognosis prediction model is used for predicting the survival rate of the patient
And collecting the ages, tumor TNM stages, tumor markers AFP, CA153 and CA724 and a nutritional index NRI of 288 patients in the model verification group, and obtaining the 3-year survival rate, the 5-year survival rate and the 8-year survival rate predicted by each patient according to the nomogram 2.
Example 3: the invention relates to a construction method of a nomogram for jointly predicting gastric cancer prognosis based on age, nutritional index PNI, tumor stage and tumor marker multi-index
Input module
The age, tumor TNM stage, tumor markers AFP, CA153 and CA724 and nutritional index PNI of 649 patients in the model training group are collected as indexes related to the prognosis of the gastric cancer of the patients. And inputting the indexes into an input module.
Second, building gastric cancer prognosis prediction model
And (3) constructing a cox regression model by using indexes in the input module, finishing the nomogram visualization of the cox regression model by using an RMS (root mean square) operation package, and finishing the nomogram verification of the cox regression model by using a calibration Curve and precision currve operation package to obtain the nomogram 3 shown in the figure 3.
The alignment contains 11 scales:
the 1 st scale represents a scale with a score corresponding to the scale on the 2 nd to 7 th scales; the scale value of the 1 st scale is 0-100, 0 is at the leftmost end, 100 is at the rightmost end, and the scale of the scale is divided equally;
the 7 th scale indicates the nutritional index PNI of the patient;
the 8 th scale represents the Total risk score (Total Points), wherein the Total risk score is the risk score corresponding to age, the risk score corresponding to tumor TNM stage, the risk score corresponding to AFP, the risk score corresponding to CA153, the risk score corresponding to CA724 and the risk score corresponding to PNI, namely the sum of the scores corresponding to the scales on the 2 nd to 7 th scales;
the 9 th scale shows the predicted value of 3-year survival rate of the patient, and the predicted value of the 3-year survival rate of the patient is the value of the score on the 8 th scale corresponding to the 9 th scale;
the 10 th scale shows the predicted value of the 5-year survival rate of the patient, and the predicted value of the 5-year survival rate of the patient is the value of the score on the 8 th scale corresponding to the 10 th scale;
the 11 th scale represents the predicted value of the 8-year survival rate of the patient, and the predicted value of the 8-year survival rate of the patient is the corresponding value of the score on the 8 th scale on the 11 th scale.
The scale value of the 2 nd scale is 20-90, 20 is at the leftmost end, 90 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 2 nd scale is 20, the corresponding score on the 1 st scale is 0, and when the scale of the 2 nd scale is 90, the corresponding score on the 1 st scale is 21.25;
the scale value of the 3 rd scale is 1-4, 1 is at the leftmost end, 4 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 3 rd scale is 1, the corresponding score on the 1 st scale is 0, and when the scale of the 3 rd scale is 4, the corresponding score on the 1 st scale is 52.5;
the 4 th scale is 0-1000, 0 is at the leftmost end, 1000 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 4 th scale is 0, the corresponding score on the 1 st scale is 0, and when the scale of the 4 th scale is 1000, the corresponding score on the 1 st scale is 45;
the scale value of the 5 th scale is 0-300, 0 is at the leftmost end, 300 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 5 th scale is 0, the corresponding score on the 1 st scale is 0, and when the scale of the 5 th scale is 300, the corresponding score on the 1 st scale is 24.5;
the 6 th scale has a scale value of 0-1000, wherein 0 is at the leftmost end, 1000 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 6 th scale is 0, the corresponding score on the 1 st scale is 0, and when the scale of the 6 th scale is 1000, the corresponding score on the 1 st scale is 57.5;
the scale value of the 7 th scale is 70-20, 70 is at the leftmost end, 20 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 7 th scale is 70, the corresponding score on the 1 st scale is 0, and when the scale of the 7 th scale is 20, the corresponding score on the 1 st scale is 100;
the scale of the 8 th scale is 0-160, 0 is at the leftmost end, 160 is at the rightmost end, and the scale of the scale is divided equally; when the scale of 8 th scale is 0, it corresponds the 0 scale of first scale, and when the scale of 8 th scale is 160, it corresponds the 100 scales of first scale.
In fig. 3:
when the value of the score on the 8 th scale on the 9 th scale is at the left end of 0.95, the predicted value of the 3-year survival rate is more than 0.95, and when the value of the score on the 8 th scale on the 9 th scale is at the right end of 0.3, the predicted value of the 3-year survival rate is less than 0.3;
when the value corresponding to the score on the 8 th scale on the 10 th scale is at the left end of 0.95, the predicted value of the 5-year survival rate is greater than 0.95, and when the value corresponding to the score on the 8 th scale on the 10 th scale is at the right end of 0.1, the predicted value of the 5-year survival rate is less than 0.1;
when the value corresponding to the score on the 8 th scale on the 11 th scale is at the left end of 0.95, the predicted value of the survival rate per 8 years is greater than 0.95, and when the value corresponding to the score on the 8 th scale on the 11 th scale is at the right end of 0.1, the predicted value of the survival rate per 8 years is less than 0.1.
Third, the gastric cancer prognosis prediction model is used for predicting the survival rate of the patient
And collecting the ages, tumor TNM stages, tumor markers AFP, CA153 and CA724 and a nutritional index PNI of 288 patients in the model verification group, and obtaining the 3-year survival rate, the 5-year survival rate and the 8-year survival rate predicted by each patient according to the nomogram 3.
The following is a method of establishing a gastric cancer prognosis control prediction system.
Comparative example 1: establishment of Age (Age) -based single-index gastric cancer prognosis prediction system
A single index gastric cancer prognosis prediction system based on Age (Age) was established with reference to the method of example 1, except that the collected indices correlated with the prognosis of gastric cancer of a patient were replaced from 6 items of Age, tumor TNM staging, tumor markers AFP, CA153 and CA724, nutritional index NRI to 1 item of Age.
Comparative example 2: establishment of single-index gastric cancer prognosis prediction system based on tumor TNM staging (stage)
A single-index gastric cancer prognosis prediction system based on tumor TNM staging is established by referring to the method of example 1, and the difference is that the collected indexes related to the gastric cancer prognosis of the patient are replaced by 1 tumor TNM staging from 6 items of age, tumor TNM staging, tumor markers AFP, CA153 and CA724 and nutritional indicator NRI.
Comparative example 3: establishment of single-index gastric cancer prognosis prediction system based on tumor marker AFP
A single-index gastric cancer prognosis prediction system based on a tumor marker AFP is established by referring to the method of example 1, and the difference is only that 6 collected indexes related to gastric cancer prognosis of a patient are replaced by 1 tumor marker AFP from 6 items of age, tumor TNM stage, tumor markers AFP, CA153 and CA724 and nutritional index NRI.
Comparative example 4: establishment of single-index gastric cancer prognosis prediction system based on tumor marker CA153
A single-index gastric cancer prognosis prediction system based on a tumor marker CA153 is established by referring to the method of example 1, and the difference is only that the collected indexes related to the gastric cancer prognosis of a patient are replaced by 1 tumor marker CA153 from 6 items of age, tumor TNM stage, tumor markers AFP, CA153 and CA724 and nutritional indicator NRI.
Comparative example 5: establishment of single-index gastric cancer prognosis prediction system based on tumor marker CA724
A single-index gastric cancer prognosis prediction system based on a tumor marker CA724 is established by referring to the method of example 1, and the difference is only that the collected indexes related to the gastric cancer prognosis of a patient are replaced by 1 tumor marker CA724 from 6 items of age, tumor TNM stage, tumor markers AFP, CA153 and CA724 and nutritional index NRI.
Comparative example 6: establishment of single-index gastric cancer prognosis prediction system based on nutritional index CONUT
A single-index gastric cancer prognosis prediction system based on a nutritional index CONUT is established by referring to the method of example 1, and the difference is only that the collected indexes related to the gastric cancer prognosis of the patient are replaced by 1 nutritional index CONUT from 6 items of age, tumor TNM stage, tumor markers AFP, CA153 and CA724 and the nutritional index NRI.
Comparative example 7: establishment of single-index gastric cancer prognosis prediction system based on nutritional index NRI
A single-index gastric cancer prognosis prediction system based on the nutritional index NRI is established by referring to the method of example 1, and the difference is only that the collected indexes related to the gastric cancer prognosis of the patient are replaced by 1 nutritional index NRI from 6 items of age, tumor TNM stage, tumor markers AFP, CA153 and CA724 and the nutritional index NRI.
Comparative example 8: establishment of single-index gastric cancer prognosis prediction system based on nutritional index PNI
A single-index gastric cancer prognosis prediction system based on the nutritional index PNI is established by referring to the method of example 1, and the difference is that the collected indexes related to the gastric cancer prognosis of the patient are replaced by 1 nutritional index PNI from 6 items of age, tumor TNM stage, tumor markers AFP, CA153 and CA724 and the nutritional index NRI.
The beneficial effects of the prediction system of the invention are demonstrated by experimental examples below.
Experimental example 1: efficacy verification of nomograms for predicting gastric cancer prognosis
1. Verification method
The predicted outcome of 3, 5, 8 year survival for patients with the system described in examples 1-3 was compared to the actual survival of the patients. The prediction models constructed in comparative examples 1 to 8 were used for comparison.
Internal verification is performed through a training set, and the internal verification comprises a Decision Curve Analysis (DCA) and a Calibration Curve (Calibration Curve), and indexes such as AUC and C-index of the Analysis method are analyzed at the same time. The validation set performs an external validation of the calibration curve.
Nomogram performance is evaluated based on discriminative (distinguishing between patients with and without events) and calibration (accuracy of nomogram prediction probability) capabilities. Quantification was done using the area under the subject's working characteristic curve (AUC) and C-index. The 95% confidence interval for each AUC and C-index was calculated. Generally, the AUC has lower accuracy when being 0.5-0.7, certain accuracy when being 0.7-0.9, higher accuracy when being more than 0.9, and no diagnosis value when being 0.5, which indicates that the diagnosis method does not work at all; generally, a C-index greater than 0.75 is considered to be better discrimination. The calibration capability of the nomogram was evaluated by plotting the observed predicted probability and the actual probability of occurrence using a cox regression model. The curve along the 45 ° line illustrates that the predicted probability is the same as the observed probability, indicating perfect calibration. A P value of > 0.05 of Hosmer-Lemeshow (H-L) is considered to be well calibrated, meaning that there is no significant difference between the actual and predicted prognosis. To fairly evaluate the predicted performance of nomograms for future new patients, 1000 bootstrap evaluations were used to obtain model performance.
Statistical significance was set as p-value < 0.05 in the two-tailed experiment. Statistical normal distribution data are expressed as mean ± sd, and non-normal distribution data are expressed as median (interquartile range). The measured data passes t test or rank sum test, and the counting data adopts pearson chi-square test or continuous correction chi-square test or fisher accurate test.
2. Verification result
TABLE 1 comparison of prediction abilities of various gastric cancer prognosis systems
Table 1 shows the areas under the ROC curves of the gastric cancer prognosis prediction systems constructed in examples 1 to 3 and comparative examples 1 to 8 of the present invention and their corresponding 95% confidence intervals, C-indexes and their corresponding 95% confidence intervals, sensitivities, and positive prediction values. FIGS. 4 to 6 show comparative graphs of prognosis ROC curves for each prediction system. Compared with the gastric cancer prognosis prediction systems based on single indexes and constructed in the comparison examples 1-8, the gastric cancer prognosis prediction systems based on multiple indexes of age, nutritional indexes, tumor stages and tumor markers, which are constructed in the embodiments 1-3 of the invention, have the advantages that the ROC curve lower area and the C-index are obviously increased, the prediction result is more accurate, and the discrimination is higher.
Fig. 7 is a verification result of the calibration curve, and it can be seen that the curves of 3 and 5-year survival rates (red) are close to the ideal curve (blue); fig. 8 is a verification result of the decision curve analysis method, and it can be seen that the curves of 3, 5, and 8 years survival rates are far from two extreme curves (blue and green slopes). The results show that the gastric cancer prognosis prediction system based on multiple indexes, which is constructed in the embodiments 1-3 of the invention, has high accuracy of prediction results of 3, 5 and 8-year survival rates of patients.
In addition, as can be seen from comparison of the c-index values, the gastric cancer prognosis prediction system constructed in example 3 has the best prediction effect in the gastric cancer prognosis prediction system constructed according to the present invention based on multiple indexes. The method shows that the multi-index gastric cancer prognosis prediction system constructed by selecting PNI as the nutritional index has the best prediction effect on gastric cancer prognosis.
In conclusion, the invention provides a prediction system for jointly predicting gastric cancer prognosis based on patient age, nutritional indicators, tumor stages and tumor markers and a construction method thereof. The prediction system can accurately predict the prognosis of gastric cancer patients (particularly patients who undergo gastric cancer resection operation in stage I-IV), and accurately predict the survival rate of the patients. The prediction system for predicting the gastric cancer prognosis provided by the invention is simple in construction method, high in prediction accuracy and discrimination, has important significance for clinically and auxiliarily judging the prognosis condition and survival rate of gastric cancer patients, and is beneficial to individual accurate treatment of clinical patients.
Claims (10)
1. A prediction system for predicting the prognosis of a patient with gastric cancer, characterized by: the prediction system is constructed by taking the age, the tumor TNM stage, AFP, CA153, CA724 and nutritional indexes of a patient as prediction indexes.
2. The prediction system of claim 1, wherein: the prediction system is an alignment chart which comprises straight lines 1-11, wherein the straight lines 1-11 are sequentially arranged from top to bottom and are parallel to each other; each straight line represents a scale, and scales are carved on the scale;
the 1 st scale represents a scale with a score corresponding to the scale on the 2 nd to 7 th scales; the scale value of the 1 st scale is 0-100, 0 is at the leftmost end, 100 is at the rightmost end, and the scale of the scale is divided equally;
scale 2 indicates the age of the patient;
scale 3 indicates the tumor TNM stage of the patient;
scale 4 indicates AFP of the patient;
scale 5 indicates CA724 of the patient;
scale 6 indicates the patient's CA 153;
the 7 th scale represents the nutritional index of the patient;
the 8 th scale represents the sum of the scores corresponding to the scales on the 2 nd to 7 th scales;
the 9 th scale shows the predicted value of 3-year survival rate of the patient, and the predicted value of the 3-year survival rate of the patient is the value of the score on the 8 th scale corresponding to the 9 th scale;
the 10 th scale shows the predicted value of the 5-year survival rate of the patient, and the predicted value of the 5-year survival rate of the patient is the value of the score on the 8 th scale corresponding to the 10 th scale;
the 11 th scale represents the predicted value of the 8-year survival rate of the patient, and the predicted value of the 8-year survival rate of the patient is the corresponding value of the score on the 8 th scale on the 11 th scale.
3. The prediction system of claim 2, wherein: the nutritional index is CONUT;
the scale value of the 2 nd scale is 20-90, 20 is at the leftmost end, 90 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 2 nd scale is 20, the corresponding score on the 1 st scale is 0, and when the scale of the 2 nd scale is 90, the corresponding score on the 1 st scale is 65;
the scale value of the 3 rd scale is 1-4, 1 is at the leftmost end, 4 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 3 rd scale is 1, the corresponding score on the 1 st scale is 0, and when the scale of the 3 rd scale is 4, the corresponding score on the 1 st scale is 100;
the 4 th scale is 0-1000, 0 is at the leftmost end, 1000 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 4 th scale is 0, the corresponding score on the 1 st scale is 0, and when the scale of the 4 th scale is 1000, the corresponding score on the 1 st scale is 86; the scale value of the 5 th scale is 0-300, 0 is at the leftmost end, 300 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 5 th scale is 0, the corresponding score on the 1 st scale is 0, and when the scale of the 5 th scale is 300, the corresponding score on the 1 st scale is 42.5;
the 6 th scale has a scale value of 0-1000, wherein 0 is at the leftmost end, 1000 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 6 th scale is 0, the corresponding score on the 1 st scale is 0, and when the scale of the 6 th scale is 1000, the corresponding score on the 1 st scale is 90;
the scale value of the 7 th scale is 1-12, 1 is at the leftmost end, 12 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 7 th scale is 1, the corresponding score on the 1 st scale is 0, and when the scale of the 7 th scale is 12, the corresponding score on the 1 st scale is 92.5;
the scale of the 8 th scale is 0-260, 0 is at the leftmost end, 260 is at the rightmost end, and the scale of the scale is divided equally; when the scale of 8 th scale is 0, it corresponds the 0 scale of first scale, and when the scale of 8 th scale is 260, it corresponds the 100 scales of first scale.
4. The prediction system of claim 2, wherein: the nutritional index is NRI;
the scale value of the 2 nd scale is 20-90, 20 is at the leftmost end, 90 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 2 nd scale is 20, the corresponding score on the 1 st scale is 0, and when the scale of the 2 nd scale is 90, the corresponding score on the 1 st scale is 33.5;
the scale value of the 3 rd scale is 1-4, 1 is at the leftmost end, 4 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 3 rd scale is 1, the corresponding score on the 1 st scale is 0, and when the scale of the 3 rd scale is 4, the corresponding score on the 1 st scale is 61;
the 4 th scale is 0-1000, 0 is at the leftmost end, 1000 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 4 th scale is 0, the corresponding score on the 1 st scale is 0, and when the scale of the 4 th scale is 1000, the corresponding score on the 1 st scale is 56; the scale value of the 5 th scale is 0-300, 0 is at the leftmost end, 300 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 5 th scale is 0, the corresponding score on the 1 st scale is 0, and when the scale of the 5 th scale is 300, the corresponding score on the 1 st scale is 21.25;
the 6 th scale has a scale value of 0-1000, wherein 0 is at the leftmost end, 1000 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 6 th scale is 0, the corresponding score on the 1 st scale is 0, and when the scale of the 6 th scale is 1000, the corresponding score on the 1 st scale is 60;
the scale value of the 7 th scale is 120-62, 120 is at the leftmost end, 65 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 7 th scale is 120, the corresponding score on the 1 st scale is 0, and when the scale of the 7 th scale is 65, the corresponding score on the 1 st scale is 100;
the 8 th scale is 0-200, 0 is at the leftmost end, 200 is at the rightmost end, and the scale of the scale is divided equally; when the scale of 8 th scale is 0, it corresponds the 0 scale of first scale, and when the scale of 8 th scale is 200, it corresponds the 100 scales of first scale.
5. The prediction system of claim 2, wherein: the nutritional index is PNI;
the scale value of the 2 nd scale is 20-90, 20 is at the leftmost end, 90 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 2 nd scale is 20, the corresponding score on the 1 st scale is 0, and when the scale of the 2 nd scale is 90, the corresponding score on the 1 st scale is 21.25;
the scale value of the 3 rd scale is 1-4, 1 is at the leftmost end, 4 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 3 rd scale is 1, the corresponding score on the 1 st scale is 0, and when the scale of the 3 rd scale is 4, the corresponding score on the 1 st scale is 52.5;
the 4 th scale is 0-1000, 0 is at the leftmost end, 1000 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 4 th scale is 0, the corresponding score on the 1 st scale is 0, and when the scale of the 4 th scale is 1000, the corresponding score on the 1 st scale is 45; the scale value of the 5 th scale is 0-300, 0 is at the leftmost end, 300 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 5 th scale is 0, the corresponding score on the 1 st scale is 0, and when the scale of the 5 th scale is 300, the corresponding score on the 1 st scale is 24.5;
the 6 th scale has a scale value of 0-1000, wherein 0 is at the leftmost end, 1000 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 6 th scale is 0, the corresponding score on the 1 st scale is 0, and when the scale of the 6 th scale is 1000, the corresponding score on the 1 st scale is 57.5;
the scale value of the 7 th scale is 70-20, 70 is at the leftmost end, 20 is at the rightmost end, and the scale of the scale is divided equally; when the scale of the 7 th scale is 70, the corresponding score on the 1 st scale is 0, and when the scale of the 7 th scale is 20, the corresponding score on the 1 st scale is 100;
the scale of the 8 th scale is 0-160, 0 is at the leftmost end, 160 is at the rightmost end, and the scale of the scale is divided equally; when the scale of 8 th scale is 0, it corresponds the 0 scale of first scale, and when the scale of 8 th scale is 160, it corresponds the 100 scales of first scale.
6. The prediction system according to any one of claims 1 to 5, wherein: the construction method of the prediction system comprises the following steps:
(1) collecting the prediction indexes and inputting the prediction indexes into an input module;
(2) and constructing a cox regression model by using the indexes in the input module, finishing the nomogram visualization of the cox regression model by using an RMS (root mean square) operation package, and finishing the nomogram verification of the cox regression model by using a calibration Curve and precision currve operation package to obtain the product.
7. The prediction system of claim 6, wherein: the age is 20-95 years, the TNM stage is 1, 2, 3 or 4, the AFP is 0-1000 ng/mL, the CA153 is 0-1000U/mL, and the CA724 is 0-300U/mL;
and/or when the nutritional index is CONUT, the CONUT is 1-12; when the nutritional index is NRI, the NRI is 120-62; and when the nutritional index is PNI, the PNI is 70-20.
8. An apparatus for predicting the prognosis of a patient with gastric cancer, characterized by: the apparatus comprising a prediction system as claimed in any one of claims 1 to 7.
9. Use of the prediction system of any one of claims 1 to 7 in the manufacture of a device for predicting the prognosis of a patient with gastric cancer.
10. Use according to claim 9, characterized in that: the gastric cancer patient is a patient who undergoes gastric cancer resection operation in stage I-IV;
and/or the gastric cancer patient prognosis is 3, 5, 8 year survival rate of gastric cancer patients.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110832843.8A CN113658696B (en) | 2021-07-22 | 2021-07-22 | Prediction system for predicting prognosis of gastric cancer based on combination of patient age, nutrition index, tumor stage and tumor marker |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110832843.8A CN113658696B (en) | 2021-07-22 | 2021-07-22 | Prediction system for predicting prognosis of gastric cancer based on combination of patient age, nutrition index, tumor stage and tumor marker |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113658696A true CN113658696A (en) | 2021-11-16 |
| CN113658696B CN113658696B (en) | 2023-07-14 |
Family
ID=78477713
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110832843.8A Active CN113658696B (en) | 2021-07-22 | 2021-07-22 | Prediction system for predicting prognosis of gastric cancer based on combination of patient age, nutrition index, tumor stage and tumor marker |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113658696B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114141360A (en) * | 2021-12-02 | 2022-03-04 | 山东大学 | Breast cancer prediction method based on punished COX regression |
| CN115295126A (en) * | 2022-09-29 | 2022-11-04 | 浙江省肿瘤医院 | Model for predicting mismatch repair gene defect of gastric cancer |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101965514A (en) * | 2008-01-03 | 2011-02-02 | 艾博特生物技术有限公司 | Predicting long-term efficacy of a compound in the treatment of psoriasis |
| CN101970685A (en) * | 2007-01-16 | 2011-02-09 | Musc研究发展基金会 | Compositions and methods for diagnosing, treating, and preventing prostate conditions |
| CN106055898A (en) * | 2016-05-27 | 2016-10-26 | 石河子大学 | Prognosis method for patients with gastric carcinoma |
| CN107563134A (en) * | 2017-08-30 | 2018-01-09 | 中山大学 | A kind of system for being used to precisely predict patients with gastric cancer prognosis |
| CN108676881A (en) * | 2018-05-24 | 2018-10-19 | 江苏大学附属医院 | Purposes of the reagent of specific recognition CHAF1A in preparing gastric cancer prognosis evaluation reagent kit |
| CN110305964A (en) * | 2019-07-26 | 2019-10-08 | 安徽医科大学第一附属医院 | A kind of foundation of patients with prostate cancer prognosis recurrence risk profile mark tool and its risk evaluation model |
| CN110931134A (en) * | 2019-12-03 | 2020-03-27 | 南通大学 | Method for predicting hospitalization pressure injury healing based on big data mining model |
| CN112185569A (en) * | 2020-09-11 | 2021-01-05 | 中山大学孙逸仙纪念医院 | Breast cancer patient disease-free survival period prediction model and construction method thereof |
| CN112259231A (en) * | 2020-10-20 | 2021-01-22 | 华中科技大学同济医学院附属协和医院 | High-risk gastrointestinal stromal tumor patient postoperative recurrence risk assessment method and system |
-
2021
- 2021-07-22 CN CN202110832843.8A patent/CN113658696B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101970685A (en) * | 2007-01-16 | 2011-02-09 | Musc研究发展基金会 | Compositions and methods for diagnosing, treating, and preventing prostate conditions |
| CN101965514A (en) * | 2008-01-03 | 2011-02-02 | 艾博特生物技术有限公司 | Predicting long-term efficacy of a compound in the treatment of psoriasis |
| CN106055898A (en) * | 2016-05-27 | 2016-10-26 | 石河子大学 | Prognosis method for patients with gastric carcinoma |
| CN107563134A (en) * | 2017-08-30 | 2018-01-09 | 中山大学 | A kind of system for being used to precisely predict patients with gastric cancer prognosis |
| CN108676881A (en) * | 2018-05-24 | 2018-10-19 | 江苏大学附属医院 | Purposes of the reagent of specific recognition CHAF1A in preparing gastric cancer prognosis evaluation reagent kit |
| CN110305964A (en) * | 2019-07-26 | 2019-10-08 | 安徽医科大学第一附属医院 | A kind of foundation of patients with prostate cancer prognosis recurrence risk profile mark tool and its risk evaluation model |
| CN110931134A (en) * | 2019-12-03 | 2020-03-27 | 南通大学 | Method for predicting hospitalization pressure injury healing based on big data mining model |
| CN112185569A (en) * | 2020-09-11 | 2021-01-05 | 中山大学孙逸仙纪念医院 | Breast cancer patient disease-free survival period prediction model and construction method thereof |
| CN112259231A (en) * | 2020-10-20 | 2021-01-22 | 华中科技大学同济医学院附属协和医院 | High-risk gastrointestinal stromal tumor patient postoperative recurrence risk assessment method and system |
Non-Patent Citations (2)
| Title |
|---|
| 任文豪: "预后营养指数与胃肠癌手术患者预后的关系" * |
| 黄颖鹏: "胃癌患者的肿瘤免疫学特征及其对术后临床结局的影响" * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114141360A (en) * | 2021-12-02 | 2022-03-04 | 山东大学 | Breast cancer prediction method based on punished COX regression |
| CN115295126A (en) * | 2022-09-29 | 2022-11-04 | 浙江省肿瘤医院 | Model for predicting mismatch repair gene defect of gastric cancer |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113658696B (en) | 2023-07-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113658696A (en) | Prediction system for jointly predicting gastric cancer prognosis based on patient age, nutritional indexes, tumor stages and tumor markers | |
| Zhang et al. | Seven genes for the prognostic prediction in patients with glioma | |
| CN104046624B (en) | Gene and application thereof for lung cancer for prognosis | |
| CN112626218A (en) | Gene expression classifier and in-vitro diagnosis kit for predicting pancreatic cancer metastasis risk | |
| CN116525005A (en) | Application of macrophage marker gene in liver cancer prognosis and risk assessment model thereof | |
| Luo et al. | Establishment of a nomogram-based prognostic model (LASSO-COX regression) for predicting progression-free survival of primary non-small cell lung cancer patients treated with adjuvant chinese herbal medicines therapy: A retrospective study of case series | |
| Ye et al. | An online survival predictor in glioma patients using machine learning based on WHO CNS5 data | |
| CN104975082A (en) | Gene group to assess prognosis of lung cancer and application thereof | |
| Wang et al. | Identification of prognostic biomarkers of breast cancer based on the immune-related gene module | |
| CN113436673A (en) | Molecular marker for liver cancer prognosis prediction and application thereof | |
| CN113345589A (en) | Construction method and application method of liver cancer prognosis model and electronic equipment | |
| CN113470813A (en) | Survival rate prognosis model for liver cancer patient | |
| CN111471773A (en) | Diagnostic biomarker for predicting prognosis of gastric adenocarcinoma patient and determination method and application thereof | |
| Liu et al. | Landscape and construction of a novel N6-methyladenosine-related LncRNAs in cervical cancer | |
| Zhang et al. | A novel metabolism-related prognostic gene development and validation in gastric cancer | |
| CN113241181A (en) | Prognosis risk assessment model and assessment device for liver cancer patient | |
| CN113450917A (en) | Application of biomarker in prediction of liver cancer prognosis | |
| CN112259231A (en) | High-risk gastrointestinal stromal tumor patient postoperative recurrence risk assessment method and system | |
| Mamoor | Differential expression of collagen type III alpha 1 chain in human epithelial ovarian cancer. | |
| Mamoor | Differential expression of tubulin tyrosine ligase-like 7 in human epithelial ovarian cancer. | |
| Mamoor | Differential expression of glutamic-oxaloacetic transaminase 1-like 1 in human epithelial ovarian cancer. | |
| Mamoor | Differential expression of protein phosphatase 1 regulatory subunit 12A in human epithelial ovarian cancer. | |
| Mamoor | Differential expression of tweety family member 3 in human epithelial ovarian cancer. | |
| Mamoor | Differential expression of diacylglycerol kinase beta in human epithelial ovarian cancer. | |
| Mamoor | Differential expression of syncoilin, intermediate filament protein in human epithelial ovarian cancer. |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |