CN107563134A - A kind of system for being used to precisely predict patients with gastric cancer prognosis - Google Patents
A kind of system for being used to precisely predict patients with gastric cancer prognosis Download PDFInfo
- Publication number
- CN107563134A CN107563134A CN201710765129.5A CN201710765129A CN107563134A CN 107563134 A CN107563134 A CN 107563134A CN 201710765129 A CN201710765129 A CN 201710765129A CN 107563134 A CN107563134 A CN 107563134A
- Authority
- CN
- China
- Prior art keywords
- living
- year
- probability
- points
- patients
- 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
- 206010017758 gastric cancer Diseases 0.000 title claims abstract description 88
- 208000005718 Stomach Neoplasms Diseases 0.000 title claims abstract description 83
- 201000011549 stomach cancer Diseases 0.000 title claims abstract description 83
- 238000004393 prognosis Methods 0.000 title claims abstract description 31
- 206010028980 Neoplasm Diseases 0.000 claims description 52
- 230000004083 survival effect Effects 0.000 claims description 27
- 208000007433 Lymphatic Metastasis Diseases 0.000 claims description 15
- HEVGGTGPGPKZHF-UHFFFAOYSA-N Epilaurene Natural products CC1C(=C)CCC1(C)C1=CC=C(C)C=C1 HEVGGTGPGPKZHF-UHFFFAOYSA-N 0.000 claims description 13
- 238000012360 testing method Methods 0.000 claims description 13
- 201000011510 cancer Diseases 0.000 claims description 12
- 208000005189 Embolism Diseases 0.000 claims description 6
- 208000010749 gastric carcinoma Diseases 0.000 claims description 6
- 201000000498 stomach carcinoma Diseases 0.000 claims description 6
- 201000011531 vascular cancer Diseases 0.000 claims description 6
- 210000002784 stomach Anatomy 0.000 claims description 4
- 206010034647 Peristalsis visible Diseases 0.000 claims description 3
- 230000000968 intestinal effect Effects 0.000 claims description 3
- 230000008855 peristalsis Effects 0.000 claims description 3
- 208000022534 visible peristalsis Diseases 0.000 claims description 3
- 238000011282 treatment Methods 0.000 description 13
- 230000002980 postoperative effect Effects 0.000 description 8
- 210000001165 lymph node Anatomy 0.000 description 7
- 210000001365 lymphatic vessel Anatomy 0.000 description 7
- 230000009790 vascular invasion Effects 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 6
- 238000000034 method Methods 0.000 description 6
- 206010027476 Metastases Diseases 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 238000003745 diagnosis Methods 0.000 description 3
- 201000010099 disease Diseases 0.000 description 3
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 3
- 238000002224 dissection Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000001225 therapeutic effect Effects 0.000 description 3
- 230000018199 S phase Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000002651 drug therapy Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 210000002751 lymph Anatomy 0.000 description 2
- 230000001575 pathological effect Effects 0.000 description 2
- 206010061309 Neoplasm progression Diseases 0.000 description 1
- 238000009098 adjuvant therapy Methods 0.000 description 1
- 230000000118 anti-neoplastic effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000000747 cardiac effect Effects 0.000 description 1
- 229940121657 clinical drug Drugs 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 238000000205 computational method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 210000002599 gastric fundus Anatomy 0.000 description 1
- 238000011337 individualized treatment Methods 0.000 description 1
- 210000000936 intestine Anatomy 0.000 description 1
- 238000002386 leaching Methods 0.000 description 1
- 230000003211 malignant effect Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 239000002547 new drug Substances 0.000 description 1
- 230000007170 pathology Effects 0.000 description 1
- 210000002826 placenta Anatomy 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 239000004575 stone Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000002560 therapeutic procedure Methods 0.000 description 1
- 238000003325 tomography Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000011269 treatment regimen Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Landscapes
- Investigating Or Analysing Biological Materials (AREA)
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
Abstract
The invention provides a kind of system for being used to precisely predict patients with gastric cancer prognosis, the Nomogram prognostic predictive models that the system is built based on the present invention, compared to traditional TNM stage system, the system has accuracy height, individuation prediction, and possesses the stomach cancer prognosis prediction feature for meeting distinct Chinese characteristics.
Description
Technical field
The present invention relates to a kind of system for being used to precisely predict patients with gastric cancer prognosis.
Background technology
At present, prognostic system Main Basiss International Union Against Cancer/american cancer of malignant tumour in the world
Tumor-infiltrated-lymphatic metastasis-DISTANT METASTASES IN (TNM) Staging System that association (UICC/AJCC) formulates, this Staging System are based on
The biological characteristics of tumour, by the invasive depth (T) of tumour, lymphatic metastasis situation (N) and whether there is DISTANT METASTASES IN (M) three
Individual essential characteristic is integrated, to evaluate the progress extent of tumour, first in the age in last century 40-50 by French scientist
Pierre Denoix are proposed, and arrange the TNM stage for foring the first edition by AJCC in 1977.Then every several years, AJCC
It can be improved and updated by stages and with reference to newest clinical information based on previous version.At the beginning of 2017, the 8th edition TNM stage
System has come out.For malignant entity tumor (including stomach cancer), this system is existing evaluation tumor patient tumour progression degree
And the foundation stone and goldstandard of guiding clinical treatment.
However, also there is the defects of corresponding and inferior position in the system.First, with the mankind malignant tumour is recognized it is increasingly deep
Enter, more and more clinical pathology (including gene) parameters have been found the biological behaviour that can reflect tumour and and then influence patient
Treatment and prognosis, and TNM stage system only includes tri- most basic clinical parameters of T, N, M, therefore its accuracy of forecast has
Treat further to improve；Secondly, the system is that the retrospective materials based on large tumor patients are analyzed and clustered and obtained
, treatment is and guided to evaluate the prognosis situation of same class patient, is not for the individual forecasting system of single tumour, many institutes
The biological characteristics of known tumor patient varies, therefore seems particularly heavy for the individuation prediction of single tumor patient
Will；In addition, although China is stomach cancer big country, annual new cases account for the 40-50% of global new cases, right existing stomach cancer
Chinese gastric cancer patients are very few (only accounting for 4%) in the crowd for being used to analyze that TNM stage system is adopted, therefore existing TNM
The prediction whether Staging System is applied to Chinese stomach cancer crowd is not understood especially.
At present, the U.S., South Korea, that Japan has successively delivered the large sample of three state stomach cancer crowds, individuation based on more than is accurate
The method (i.e. Nomogram methods, also known as nomogram, nomogram) of prediction, precision of prediction 68%-80% are not waited and (are all remarkably higher than
TNM stage), it is also different to adopt clinicopathologic features.Large sample, individuation, accurate prediction so based on Chinese stomach cancer crowd
Stomach cancer prognostic model there is not yet large report.
Due to ethnic group, biological characteristics, by stages and Therapeutic mode difference, the above-mentioned stomach cancer based on other countries
Nomogram forecast models include parameter and precision of prediction is different.If U.S.'s stomach cancer is with proximal gastric carcinoma, progressive stage stomach
Cancer, the operation of D0/1 lymph node dissections are main feature, and Japan and Korea S are with distal gastric cancer, early carcinoma of stomach, the operation of D2 lymph node dissections
Main feature, and women patients with gastric cancer prognosis is significantly better than male patient in above-mentioned three states crowd.And Chinese stomach cancer crowd with
Based on distal gastric cancer, advanced gastric carcinoma, D2 lymph node dissections are performed the operation, and women patients with gastric cancer prognosis is not better than male patient.
Therefore, the accurate forecast model of individuation based on Chinese stomach cancer crowd is established to be particularly important.
The content of the invention
At present, prognostic system Main Basiss International Union Against Cancer/American Cancer Society of stomach cancer in the world
(UICC/AJCC) tumor-infiltrated-lymphatic metastasis-DISTANT METASTASES IN (TNM) Staging System formulated, and the postoperative of patients with gastric cancer is controlled
Treatment all relies on the system.However, most literature reports the accuracy about 60-70% of the system prediction patients with gastric cancer prognosis, and
This assessment system is the Prediction based on stomach cancer crowd, rather than individuation prediction.The present invention is based on domestic multicenter, large sample
Stomach cancer crowd (amount to 6753) carry out statistical analysis, for the biological characteristics of Chinese stomach cancer crowd, and combine Chinese stomach
Cancer crowd's main flow modus operandi, the clinicopathological characteristics of Chinese stomach cancer crowd are adapted to by selecting, and foundation is based on Chinese stomach cancer people
The individuation of group, accurate prognostic predictive model, and use external certificate method verifies the accuracy of the model.Thus, the present invention carries
For a kind of system for being used to precisely predict patients with gastric cancer prognosis, in favor of instructing the postoperative adjuvant therapy of patients with gastric cancer and prognosis to comment
Estimate.
To achieve the above object, the technical scheme taken：A kind of system for being used to precisely predict patients with gastric cancer prognosis, bag
Include：
Data input module, for by the age of Stomach Carcinomas patient, tumor size, tumor locus, vascular cancer embolus, Lauren
Parting, T the testing result input model computing module with rate of lymph-node metastasis by stages；
In model computation module, including 3 probability of living in a year models, 5 probability of living in a year models, 10 probability of living in a year models
It is at least one；
The 3 probability of living in a year model is used for according to patients with gastric cancer points scoring values and 3 probability of living in a year models
The probability of living in a year of patients with gastric cancer 3 is calculated, the 3 probability of living in a year model includes 3 probability of living in a year formula, and 3 probabilities of living in a year are public
Formula：3 probabilities of living in a year=2.3e-07*points3-0.000142141*points2+0.0225317*points-
0.165042369；
The 5 probability of living in a year model, for according to patients with gastric cancer points scoring values and 5 probability of living in a year models
The probability of living in a year of patients with gastric cancer 5 is calculated, the 5 probability of living in a year model includes 5 probability of living in a year formula, and 5 probabilities of living in a year are public
Formula：5 probabilities of living in a year=2.3e-07*points3-0.000116593*points2+0.012943284*points+
0.486444498；
The 10 probability of living in a year model, for according to patients with gastric cancer points scoring values and 10 probability of living in a year moulds
Type calculates the probability of living in a year of patients with gastric cancer 10, and the 10 probability of living in a year model includes 10 probability of living in a year formula, survives within 10 years
New probability formula：10 probabilities of living in a year=2.3e-07*points3-9.7445e-05*points2+0.006998258*points+
0.760926131；
Wherein, the patients with gastric cancer points=ages score+tumor size score+tumor locus score+vascular cancer embolus
Score+Lauren parting scores+T score+rate of lymph-node metastasis scores by stages；
The age score formula is 1.224*age-12.237, and age is the age of patients with gastric cancer；
The tumor size score formula is 1.443*size, and size is the tumor size of patients with gastric cancer；
The rule of tumor locus score：Gastric cancer=0 point；Orifice of the stomach stomach bottom cancer=23.656 point；Body of stomach cancer=20.447 point；
Full stomach cancer=35.753 point；
The rule of vascular cancer embolus score：Without=0 point, there are=11.780 points；
The rule of Lauren parting scores：Visible peristalsis visible intestinal peristalsis=0 point, diffusion-type=13.506 point；
The rule of T scores by stages：T2=0 points；T3=18.028 points；T4a=36.055 points；T4b=54.083 points；
Rate of lymph-node metastasis score formula is 100*LNR；
As a result output module, for being survived according to the probability of living in a year result of patients with gastric cancer 3,5 probability of living in a year results, 10 years
At least one of probability results judge patients with gastric cancer prognosis situation；The survival probability of patients with gastric cancer is higher, then prompts the stomach
Cancer patient prognosis bona, the possibility of life cycle length are bigger.
Stomach cancer is one of most common malignant tumour in global range, and China is (every for the maximum incidence gastric cancer country in the whole world
Year new cases account for the whole world 45%).With nearly twenty or thirty year, the popularization of stomach cancer Normalized Treatment and new antineoplastic
Continuous research and development, the cure rate and survival rate of stomach cancer improve year by year, how precisely to predict that the survival probability of patients with gastric cancer turns into and grinds
Study carefully the key scientific problems of personnel's concern.Nomogram prognostic predictive models constructed by the present invention are based in current global range
The advanced gastric carcinoma case-data of maximum sample number, be medical worker and it is public understand the disease epidemiology background,
Innovation clinical practice diagnosis and treatment method, development basic research and Study on Transformation have established solid foundation.It is each involved by the present invention
Parameter is the data variable obtained by basic Clinicopathologic Diagnosis method, with collection is quick, judge is unified, intuitively accurate
Feature, the computational methods of its model are simple and easy, and the more existing conventional TNM stage system of prediction accuracy is high.
In the application aspect of clinical practice, the composite can be widely applied in Chinese major comprehensive and cancer department diagnosis and treatment
The patients with gastric cancer of the heart (including teaching hospital and non-teaching hospital).Can clinically the model be applied to be directed to individual patient more accurately
3,5,10 years estimated survival rates are calculated, the objective concrete numerical value contributes to clinician, patient and family members to state of an illness stage and life
Deposit prognosis and make more intuitive judgement.On the one hand, clinician can be according to more accurately estimated survival rate recommends individualized treatment
Scheme, such as palliative excision, the selection of drug therapy, complex treatment different schemes order：Such as screen out survival rate it is low,
The high patient of the death rate, the drug therapy that wound is small, risk is low is selected as far as possible, to avoid over-treatment；It is and high, dead to survival rate
The low patient of rate is died, the operative treatment of relative active may be selected, to avoid insufficient therapy.On the other hand, patient and family members can be more
Recognize coincident with severity degree of condition well, there is the true hope based on concrete numerical value to therapeutic effect, with prevent it is too high estimation curative effect and
Cause obvious psychological gap and medical resource to waste, also or underestimation curative effect and cause to be reluctant to receive treatment and miss treatment
Opportunity.The present invention to patients with gastric cancer precision individuation prognosis prediction, help doctor and patient have to disease correctly understanding and
It is expected that the selection to complex treatment strategy plays an important role.
In terms of clinical drug trial new technology clinical test related to operation, the present invention can more accurate evaluation survival of patients
Prognosis, so as to improve the uniformity of the accuracy of clinical test sample size calculating and specification clinical test patient in group.On the one hand,
In the clinical trial design stage of any newtype drug, clinic examination is calculated according to the survival region situation of target patient population
Sample size needed for testing is vital, and influences whether the experiment can reach the key link of positive findings, structure of the present invention
The system built can be that firm base is established in the sample size calculating of clinical test to the high precision of patient's prognosis prediction.The opposing party
The related clinical test of new technology is still performed the operation often for the specific patient by stages of the disease in face, either new drug, then
The homogenieity of patient in group crowd how should be ensured, and avoid the negative knot for selecting skew to cause clinical test because of patient in group
FruitThe present invention is assessed patient accurate survival rate, and specification, which is included, to be studied the baseline values of patient and be consistent, and is
The smooth development of clinical test provides safeguard, and reduces influence of the selection skew to result of the test during into group clinical test as far as possible.
The Nomogram prognostic predictive models that the present invention is built will be precisely predicted stomach cancer individuation, the choosing of therapeutic strategy
Select, the propulsion of clinical test etc. provides important reference, give data and side to improve the treatment curative effect of China's patients with gastric cancer
The science of law is supported.
The beneficial effects of the present invention are：It is used for the accurate system for predicting patients with gastric cancer prognosis the invention provides a kind of,
The Nomogram prognostic predictive models that the system is built based on the present invention, compared to traditional TNM stage system, the system has essence
Exactness is high, individuation prediction, and possesses the stomach cancer prognosis prediction feature for meeting distinct Chinese characteristics.
Brief description of the drawings
Fig. 1 is the Nomogram prognostic predictive models that the present invention is built.
Embodiment
To better illustrate the object, technical solutions and advantages of the present invention, below in conjunction with specific embodiment to the present invention
It is described further.
Embodiment 1
The present invention has initially set up a domestic multicenter, large sample, clinical and pathological data and the perfect stomach of Follow-up Data
Cancer clinical database, by picking out satisfactory 6753 patients from the basic data of 10213 Chinese gastric cancer patients
As building the basis of this forecast model, and it is divided into a model training collection and two external certificate collection are predicted and counted respectively
Its precision of prediction is calculated, finally the survival of patients situation predicted is compared with the actual Survival of patient, it is pre- to evaluate
Survey efficiency.Detailed results are described below：
First, by the way that 10213 patients with gastric cancer are carried out into conditional filtering, remnant gastric cancer, Multiple primary cancers, staging tomography is excluded and is suffered from
Person, DISTANT METASTASES IN patient, infantile tumour patient, non-D2 radical excisions patient, non-R0 excisions patient, perioperative mortality are suffered from
Person, clinical and pathological data and Follow-up Data deletion patients, 6753 patients of final residue enter modeling statistics；
2nd, 6753 patients are divided into model training collection by three centers (being respectively 2169,2353 and 2231)
And external certificate collection, independent prognostic factor is screened by COX regression models, finally filters out age, tumor size, tumour portion
Position, Lauren partings, lymphatic vessel/vascular invasion, T by stages, 7 variables of rate of lymph-node metastasis enter model training, with R softwares
(2.13.2 versions) (http://www.r-project.org) modeling statistics is carried out, and attempt to use respectively for each class variable
Classified variable and continuous variable count maximum predicted accuracy, and finally establish Nomogram prognostic predictive models and suffered from predicting
Person's survival rate of postoperative 3,5,10 years, as shown in table 1 and Fig. 1, the Nomogram prognostic predictive models that the present invention establishes include 3 years
Survival probability model, 5 probability of living in a year models, 10 probability of living in a year models, the Nomogram models established can be used for individual
The prognosis prediction of patient, classification accuracy is up to 0.82 (95% confidential interval, 0.79-0.85), and newest the 8th edition
The prediction accuracy of TNM stage is only 0.74 (95% confidential interval, 0.72-0.77), and both prediction accuracy differences have aobvious
Write statistical significance (P values<0.001)；
The Nomogram prognostic predictive models that the present invention of table 1 is built
3rd, two external certificate collection are predicted according to the Nomogram models of above-mentioned foundation, it is found that two outsides are tested
The prediction accuracy of card collection respectively reaches 0.83 (95% confidential interval, 0.80-0.86) and 0.81 (95% confidential interval, 0.78-
0.83), and the prediction accuracy of the 8th edition TNM stage is respectively 0.75 (95% confidential interval, 0.72-0.77) and 0.74
(95% confidential interval, 0.71-0.76), both prediction accuracy differences are respectively provided with notable statistical significance, and (P values are equal<0.001)；
4th, by the Nomogram models of foundation to predict patient's survival rate of postoperative 3,5,10 years, and it is true with patient
Postoperative 3,5,10 years survival rates carry out model calibration, find no matter training set or checking collection, the accuracy of model prediction is equal
In 10% section of true Survival, the good precision of prediction of model is embodied.
So far, the present invention establishes a large sample based on Chinese stomach cancer crowd, high accuracy, individuation prognosis prediction mould
Type.Compared to traditional TNM stage system, the Nomogram models that the present invention is built have accuracy height, individuation prediction, and have
The standby stomach cancer prognosis prediction feature for meeting distinct Chinese characteristics.
The present invention illustrates the prognosis prediction advantage of the more traditional TNM stage of the present invention by taking following three patients as an example：
First, antrum portion being located at 38 years old patient, postoperative tumor size 4cm, tumour, Lauren partings are visible peristalsis visible intestinal peristalsis,
It is tumor-infiltrated to placenta percreta (T4a) without lymphatic vessel/vascular invasion, 7 pieces of lymphatic metastasis, clean 70 pieces of (i.e. lymph nodes of lymph node
The rate of transform 10%) exemplified by (being the III B phases according to the 8th edition TNM stage)：
And the Nomogram models that patient's prognosis prediction is built according to the present invention assign point calculation formula (as above the 5th part institute
Show) carry out every score, i.e. the age counts 45.257 (=1.224 × 38-12.237) points, tumor size meter 5.772 (=1.443
× 4) divide, tumor locus meter 0 divides, and Lauren partings meter 0 divides, and lymphatic vessel/vascular invasion meter 0 divides, and T counts 36.055 points by stages, leaching
Rate of transform meter 10 (=100 × 10%) point is fawned on, amounts to 97.084 points (items score is added summations), substitute into 3 respectively with total score,
" points " in 5 years and 10 probability of living in a year calculation formula, the value finally calculated according to formula is that single patient is corresponding
Survival probability., then the 3 of the patient, the survival rate of 5,10 years is respectively 89.32%, 85.45% and 73.24%.
Secondly, with 60 years old patient, postoperative tumor size 10cm, tumour is located at body of stomach, and Lauren partings are to diffuse,
It is tumor-infiltrated to subserosa (T3) without lymphatic vessel/vascular invasion, 6 pieces of lymphatic metastasis, clean 15 pieces of (i.e. lymphs of lymph node
Tie the rate of transform 40%) exemplified by (being the III A phases according to the 8th edition TNM stage)：
And the Nomogram models that patient's prognosis prediction is built according to the present invention assign the progress (as shown in table 1) of point calculation formula
Items score, i.e. age count 61.203 (=1.224 × 60-12.237) points, and tumor size meter 14.43 (=1.443 × 4) divides,
Tumor locus meter 20.447 divides, and Lauren partings meter 13.506 divides, and lymphatic vessel/vascular invasion meter 0 divides, and T counts 13.028 points by stages,
Rate of lymph-node metastasis meter 40 (=100 × 40%) point, 162.614 points (items score is added summation) are amounted to, respectively with total score generation
Enter 3,5 years and 10 probability of living in a year calculation formula in " points ", the value finally calculated according to formula is single patient's phase
The survival probability answered.Then the 3 of the patient, the survival rate of 5,10 years is respectively 72.93%, 49.71% and 31.12%.
3rd, with 80 years old patient, postoperative tumor size 8cm, tumour is located at gastric fundus and cardiac part, and Lauren partings are intestines
Type, with lymphatic vessel/vascular invasion, tumor-infiltrated to shallow muscle layer (T2), 6 pieces of lymphatic metastasis, clean 10 pieces of (i.e. lymphs of lymph node
Tie the rate of transform 60%) exemplified by (being the II B phases according to the 8th edition TNM stage)：
And the Nomogram models that patient's prognosis prediction is built according to the present invention assign point calculation formula (as above the 5th part institute
Show) carry out every meter, i.e. the age counts 85.683 (=1.224 × 38-12.237) and divided, tumor size meter 11.544 (=1.443 ×
8) dividing, tumor locus meter 23.656 divides, and Lauren partings meter 0 divides, and lymphatic vessel/vascular invasion meter 11.780 divides, and T counts 0 point by stages,
Rate of lymph-node metastasis meter 60 (=100 × 60%) point, 192.659 points (items score is added summation) are amounted to, respectively with total score generation
Enter 3,5 years and 10 probability of living in a year calculation formula in " points ", the value finally calculated according to formula is single patient's phase
The survival probability answered., then the 3 of the patient, the survival rate of 5,10 years is respectively 54.47%, 29.72% and 13.70%.
By above-mentioned three patients by stages and it is expected that such as according to TNM stage it can be seen from survival rate, three patients' is estimated
Survival rate is followed successively by II B (the 3rd), III A (second case), III B phases (first case) from high to low, and such as according to the present invention
Predictive model algorithm, 3,5 and 10 years of three patients estimated survival rates from high to low on the contrary for first case (89.32%,
85.45% and 73.24%), second case (72.93%, 49.71% and 31.12%), the 3rd (54.47%, 29.72% and
13.70%) statistical result, and based on above two method compared, the present invention are provided pre- by clinician and patient
It is more reliable to survey accuracy.
Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention rather than the present invention is protected
The limitation of scope is protected, although being explained in detail with reference to preferred embodiment to the present invention, one of ordinary skill in the art should
Understand, technical scheme can be modified or equivalent substitution, without departing from the essence of technical solution of the present invention
And scope.
Claims (1)
- A kind of 1. system for being used to precisely predict patients with gastric cancer prognosis, it is characterised in that including：Data input module, for the age of Stomach Carcinomas patient, tumor size, tumor locus, vascular cancer embolus, Lauren to be divided Type, T the testing result input model computing module with rate of lymph-node metastasis by stages；In model computation module, including 3 probability of living in a year models, 5 probability of living in a year models, 10 probability of living in a year models at least It is a kind of；The 3 probability of living in a year model is used to be calculated according to patients with gastric cancer points scoring values and 3 probability of living in a year models The probability of living in a year of patients with gastric cancer 3, the 3 probability of living in a year model include 3 probability of living in a year formula, 3 probability of living in a year formula：3 Probability of living in a year=2.3e-07*points3-0.000142141*points2+0.0225317*points-0.165042369；The 5 probability of living in a year model, for according to patients with gastric cancer points scoring values and the calculating of 5 probability of living in a year models The probability of living in a year of patients with gastric cancer 5, the 5 probability of living in a year model include 5 probability of living in a year formula, 5 probability of living in a year formula：5 Probability of living in a year=2.3e-07*points3-0.000116593*points2+0.012943284*points+ 0.486444498；The 10 probability of living in a year model, based on according to patients with gastric cancer points scoring values and 10 probability of living in a year models The probability of living in a year of patients with gastric cancer 10 is calculated, the 10 probability of living in a year model includes 10 probability of living in a year formula, 10 probabilities of living in a year Formula：10 probabilities of living in a year=2.3e-07*points3-9.7445e-05*points2+0.006998258*points+ 0.760926131；Wherein, the patients with gastric cancer points=ages score+tumor size score+tumor locus score+vascular cancer embolus score+ Lauren parting scores+T score+rate of lymph-node metastasis scores by stages；The age score formula is 1.224*age-12.237, and age is the age of patients with gastric cancer；The tumor size score formula is 1.443*size, and size is the tumor size of patients with gastric cancer；The rule of tumor locus score：Gastric cancer=0 point；Orifice of the stomach stomach bottom cancer=23.656 point；Body of stomach cancer=20.447 point；Full stomach Cancer=35.753 point；The rule of vascular cancer embolus score：Without=0 point, there are=11.780 points；The rule of Lauren parting scores：Visible peristalsis visible intestinal peristalsis=0 point, diffusion-type=13.506 point；The rule of T scores by stages：T2=0 points；T3=18.028 points；T4a=36.055 points；T4b=54.083 points；Rate of lymph-node metastasis score formula is 100*LNR；As a result output module, for according to the probability of living in a year result of patients with gastric cancer 3,5 probability of living in a year results, 10 probabilities of living in a year At least one of as a result patients with gastric cancer prognosis situation is judged；The survival probability of patients with gastric cancer is higher, then prompts the stomach cancer to suffer from Person prognosis bona, the possibility of life cycle length are bigger.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710765129.5A CN107563134A (en) | 2017-08-30 | 2017-08-30 | A kind of system for being used to precisely predict patients with gastric cancer prognosis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710765129.5A CN107563134A (en) | 2017-08-30 | 2017-08-30 | A kind of system for being used to precisely predict patients with gastric cancer prognosis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107563134A true CN107563134A (en) | 2018-01-09 |
Family
ID=60978314
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710765129.5A Pending CN107563134A (en) | 2017-08-30 | 2017-08-30 | A kind of system for being used to precisely predict patients with gastric cancer prognosis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107563134A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109493969A (en) * | 2018-09-11 | 2019-03-19 | 中山大学孙逸仙纪念医院 | Assess model and its application of the Paget`s disease with invasive ductal carcinoma patient prognosis |
| CN110993110A (en) * | 2019-10-23 | 2020-04-10 | 中山大学附属第六医院 | Intestinal cancer peritoneal metastasis prediction model and construction method thereof |
| CN111128328A (en) * | 2019-10-25 | 2020-05-08 | 中山大学肿瘤防治中心（中山大学附属肿瘤医院、中山大学肿瘤研究所） | Nasopharyngeal carcinoma structured image report and data processing system and method |
| CN112120790A (en) * | 2020-09-23 | 2020-12-25 | 常州市第一人民医院 | Mild ischemic stroke patient prediction model based on index scoring |
| CN112365948A (en) * | 2020-10-27 | 2021-02-12 | 沈阳东软智能医疗科技研究院有限公司 | Cancer stage prediction system |
| CN112837815A (en) * | 2021-02-04 | 2021-05-25 | 复旦大学附属中山医院 | Model for evaluating gastric cancer prognosis based on Lauren typing and postoperative residual lymph node and application |
| CN113658696A (en) * | 2021-07-22 | 2021-11-16 | 四川大学华西医院 | Prediction system for jointly predicting gastric cancer prognosis based on patient age, nutritional indexes, tumor stages and tumor markers |
| CN114420291A (en) * | 2022-01-14 | 2022-04-29 | 安徽省肿瘤医院 | Lymph node metastasis risk assessment system and equipment for gastric cancer based on machine learning and storage medium |
| CN114496306A (en) * | 2022-01-28 | 2022-05-13 | 北京大学口腔医学院 | Machine learning-based prognosis survival stage prediction method and system |
-
2017
- 2017-08-30 CN CN201710765129.5A patent/CN107563134A/en active Pending
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109493969A (en) * | 2018-09-11 | 2019-03-19 | 中山大学孙逸仙纪念医院 | Assess model and its application of the Paget`s disease with invasive ductal carcinoma patient prognosis |
| CN109493969B (en) * | 2018-09-11 | 2022-03-08 | 中山大学孙逸仙纪念医院 | Model for evaluating prognosis of patients with Paget's disease complicated with invasive ductal carcinoma and application of model |
| CN110993110B (en) * | 2019-10-23 | 2023-06-02 | 中山大学附属第六医院 | Intestinal cancer peritoneal metastasis prediction model and construction method thereof |
| CN110993110A (en) * | 2019-10-23 | 2020-04-10 | 中山大学附属第六医院 | Intestinal cancer peritoneal metastasis prediction model and construction method thereof |
| CN111128328A (en) * | 2019-10-25 | 2020-05-08 | 中山大学肿瘤防治中心（中山大学附属肿瘤医院、中山大学肿瘤研究所） | Nasopharyngeal carcinoma structured image report and data processing system and method |
| CN112120790A (en) * | 2020-09-23 | 2020-12-25 | 常州市第一人民医院 | Mild ischemic stroke patient prediction model based on index scoring |
| CN112365948A (en) * | 2020-10-27 | 2021-02-12 | 沈阳东软智能医疗科技研究院有限公司 | Cancer stage prediction system |
| CN112365948B (en) * | 2020-10-27 | 2023-07-18 | 沈阳东软智能医疗科技研究院有限公司 | Cancer stage prediction system |
| CN112837815A (en) * | 2021-02-04 | 2021-05-25 | 复旦大学附属中山医院 | Model for evaluating gastric cancer prognosis based on Lauren typing and postoperative residual lymph node and application |
| CN113658696A (en) * | 2021-07-22 | 2021-11-16 | 四川大学华西医院 | Prediction system for jointly predicting gastric cancer prognosis based on patient age, nutritional indexes, tumor stages and tumor markers |
| CN114420291B (en) * | 2022-01-14 | 2023-04-07 | 安徽省肿瘤医院 | Lymph node metastasis risk assessment system and equipment for gastric cancer based on machine learning and storage medium |
| CN114420291A (en) * | 2022-01-14 | 2022-04-29 | 安徽省肿瘤医院 | Lymph node metastasis risk assessment system and equipment for gastric cancer based on machine learning and storage medium |
| CN114496306B (en) * | 2022-01-28 | 2022-12-20 | 北京大学口腔医学院 | Machine learning-based prognosis survival stage prediction method and system |
| CN114496306A (en) * | 2022-01-28 | 2022-05-13 | 北京大学口腔医学院 | Machine learning-based prognosis survival stage prediction method and system |
| WO2023143232A1 (en) * | 2022-01-28 | 2023-08-03 | 北京大学口腔医学院 | Prognosis survival stage prediction method and system based on machine learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107563134A (en) | A kind of system for being used to precisely predict patients with gastric cancer prognosis | |
| Bendifallah et al. | A nomogram for predicting lymph node metastasis of presumed stage I and II endometrial cancer | |
| Gur et al. | Validation of breast cancer nomograms for predicting the non-sentinel lymph node metastases after a positive sentinel lymph node biopsy in a multi-center study | |
| Jajroudi et al. | Prediction of survival in thyroid cancer using data mining technique | |
| CN105319364B (en) | For predicting that the Combining diagnosis of microhepatia cancer recurrence is marked | |
| CN112542247B (en) | Method and system for predicting complete remission probability of pathology after breast cancer neoadjuvant chemotherapy | |
| Chen et al. | Objective palliative prognostic score among patients with advanced cancer | |
| Huang et al. | Development and validation of a nomogram for preoperative prediction of perineural invasion in colorectal cancer | |
| Mahar et al. | Refining prognosis in lung cancer: a report on the quality and relevance of clinical prognostic tools | |
| Cirkovic et al. | Prediction models for estimation of survival rate and relapse for breast cancer patients | |
| CN105209631A (en) | A method for improving disease diagnosis using measured analytes | |
| CN113270188A (en) | Method and device for constructing prognosis prediction model of patient after esophageal squamous carcinoma radical treatment | |
| CN111383765A (en) | Esophageal squamous carcinoma onset risk information prediction model, construction method and application | |
| Hague et al. | Cutaneous T-cell lymphoma: Diagnosing subtypes and the challenges | |
| Polash et al. | Functionality testing of machine learning algorithms to anticipate life expectancy of stomach cancer patients | |
| Lora et al. | Prognostic models for locally advanced cervical cancer: external validation of the published models | |
| Grover et al. | Multistate Markov modelling for disease progression of breast cancer patients based on CA15-3 marker | |
| Tamiya et al. | Evaluation of the efficacy and safety of chemotherapy for patients with wet stage IIIB/IV non-small-cell lung cancer aged 80 years old or more | |
| Qu et al. | Validation of predictors for lymph node status in penile cancer: Results from a population-based cohort | |
| Yap et al. | Predictors of early mortality after radical nephrectomy with renal vein or inferior vena cava thrombectomy-a population-based study. | |
| CN112768060A (en) | Liver cancer postoperative recurrence prediction method based on random survival forest and storage medium | |
| Houri et al. | Prediction of endometrial cancer recurrence by using a novel machine learning algorithm: An Israeli gynecologic oncology group study | |
| Yun et al. | A nomogram for predicting recurrence after complete resection for thymic epithelial tumors based on the TNM classification: A multi‐institutional retrospective analysis | |
| Panda et al. | Role of Predictive Modeling in Healthcare Research: A Scoping Review | |
| CN110021433A (en) | A kind of system for precisely predicting gastro-entero-pancreatic tumor patient's prognosis |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180109 |
|
| WD01 | Invention patent application deemed withdrawn after publication |