CN116013528B - Bladder cancer postoperative recurrence risk prediction method, device and medium combining with FISH detection - Google Patents
Bladder cancer postoperative recurrence risk prediction method, device and medium combining with FISH detection Download PDFInfo
- Publication number
- CN116013528B CN116013528B CN202310032705.0A CN202310032705A CN116013528B CN 116013528 B CN116013528 B CN 116013528B CN 202310032705 A CN202310032705 A CN 202310032705A CN 116013528 B CN116013528 B CN 116013528B
- Authority
- CN
- China
- Prior art keywords
- recurrence
- clinical
- target patient
- fish detection
- risk
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 74
- 208000007097 Urinary Bladder Neoplasms Diseases 0.000 title claims abstract description 33
- 206010005003 Bladder cancer Diseases 0.000 title claims abstract description 32
- 230000002980 postoperative effect Effects 0.000 title claims abstract description 32
- 201000005112 urinary bladder cancer Diseases 0.000 title claims abstract description 30
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000012216 screening Methods 0.000 claims abstract description 18
- 210000002700 urine Anatomy 0.000 claims abstract description 17
- 238000013517 stratification Methods 0.000 claims abstract description 9
- 206010028980 Neoplasm Diseases 0.000 claims description 31
- 239000000523 sample Substances 0.000 claims description 23
- 238000012549 training Methods 0.000 claims description 18
- 238000001356 surgical procedure Methods 0.000 claims description 14
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 230000002159 abnormal effect Effects 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 9
- 230000007170 pathology Effects 0.000 claims description 9
- 238000011088 calibration curve Methods 0.000 claims description 8
- 238000012360 testing method Methods 0.000 claims description 8
- 201000011510 cancer Diseases 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 6
- 238000001325 log-rank test Methods 0.000 claims description 5
- 238000010824 Kaplan-Meier survival analysis Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 238000011065 in-situ storage Methods 0.000 claims description 3
- 210000004027 cell Anatomy 0.000 description 14
- 230000005856 abnormality Effects 0.000 description 10
- 230000000875 corresponding effect Effects 0.000 description 8
- 208000009458 Carcinoma in Situ Diseases 0.000 description 7
- 210000000349 chromosome Anatomy 0.000 description 7
- 101100222091 Arabidopsis thaliana CSP3 gene Proteins 0.000 description 5
- 230000004083 survival effect Effects 0.000 description 5
- QTBSBXVTEAMEQO-UHFFFAOYSA-N Acetic acid Chemical compound CC(O)=O QTBSBXVTEAMEQO-UHFFFAOYSA-N 0.000 description 3
- OKKJLVBELUTLKV-UHFFFAOYSA-N Methanol Chemical compound OC OKKJLVBELUTLKV-UHFFFAOYSA-N 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 239000003298 DNA probe Substances 0.000 description 2
- WCUXLLCKKVVCTQ-UHFFFAOYSA-M Potassium chloride Chemical compound [Cl-].[K+] WCUXLLCKKVVCTQ-UHFFFAOYSA-M 0.000 description 2
- 238000000546 chi-square test Methods 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- MHMNJMPURVTYEJ-UHFFFAOYSA-N fluorescein-5-isothiocyanate Chemical compound O1C(=O)C2=CC(N=C=S)=CC=C2C21C1=CC=C(O)C=C1OC1=CC(O)=CC=C21 MHMNJMPURVTYEJ-UHFFFAOYSA-N 0.000 description 2
- 238000009396 hybridization Methods 0.000 description 2
- 201000004933 in situ carcinoma Diseases 0.000 description 2
- 230000036210 malignancy Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000001114 myogenic effect Effects 0.000 description 2
- 230000001575 pathological effect Effects 0.000 description 2
- 108090000623 proteins and genes Proteins 0.000 description 2
- 238000000611 regression analysis Methods 0.000 description 2
- PYWVYCXTNDRMGF-UHFFFAOYSA-N rhodamine B Chemical compound [Cl-].C=12C=CC(=[N+](CC)CC)C=C2OC2=CC(N(CC)CC)=CC=C2C=1C1=CC=CC=C1C(O)=O PYWVYCXTNDRMGF-UHFFFAOYSA-N 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 238000011282 treatment Methods 0.000 description 2
- 238000010200 validation analysis Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 108020004635 Complementary DNA Proteins 0.000 description 1
- 108020003215 DNA Probes Proteins 0.000 description 1
- 238000009098 adjuvant therapy Methods 0.000 description 1
- 208000036878 aneuploidy Diseases 0.000 description 1
- 231100001075 aneuploidy Toxicity 0.000 description 1
- 230000001093 anti-cancer Effects 0.000 description 1
- 238000010804 cDNA synthesis Methods 0.000 description 1
- 210000002230 centromere Anatomy 0.000 description 1
- 239000002299 complementary DNA Substances 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007717 exclusion Effects 0.000 description 1
- 239000000834 fixative Substances 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 230000027939 micturition Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000008188 pellet Substances 0.000 description 1
- 230000010412 perfusion Effects 0.000 description 1
- 239000008363 phosphate buffer Substances 0.000 description 1
- 235000011164 potassium chloride Nutrition 0.000 description 1
- 239000001103 potassium chloride Substances 0.000 description 1
- 238000004393 prognosis Methods 0.000 description 1
- 238000002271 resection Methods 0.000 description 1
- 238000011272 standard treatment Methods 0.000 description 1
- 230000002485 urinary effect Effects 0.000 description 1
- 238000005406 washing Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Abstract
The application discloses a bladder cancer postoperative recurrence risk prediction method, device and medium combined with FISH detection, wherein the method comprises the following steps: screening a plurality of predictors from the candidate clinical factors; constructing a clinical prediction model according to the plurality of predictors and the FISH detection result; obtaining the value of each predictive factor according to the clinical data of the target patient; confirming a FISH detection value according to the urine sample of the target patient; inputting the values of the predictive factors and the FISH detection values into the clinical predictive model to obtain a recurrence risk score of the target patient; and predicting the postoperative recurrence risk of the target patient according to the recurrence risk score to obtain the risk stratification of the target patient. By adopting the application, the prediction of the recurrence risk after bladder cancer operation is carried out by combining with FISH detection, and more accurate and reliable prediction results are obtained.
Description
Technical Field
The application relates to the technical field of bladder cancer prognosis evaluation, in particular to a bladder cancer postoperative recurrence risk prediction method, device and medium combining with FISH detection.
Background
Bladder cancer is the tenth most common malignancy worldwide, with the 13 th in the mortality associated with cancer being the second largest urinary malignancy in china. Bladder cancer is called the "most expensive" tumor, and brings a heavy economic burden to patients and society due to its high recurrence rate and complicated treatment modes such as surgery. About 75% of newly diagnosed bladder cancer cases are non-myogenic invasive bladder cancer (NMIBC), which is higher for young patients. Transurethral bladder tumor electroresections (transurethral resection of bladder tumor, TURBT) and post-operative adjuvant therapy are standard treatment regimens for NMIBC, however, up to 70% of patients still relapse within one year after diagnosis. Therefore, predicting risk of recurrence in NMIBC patients is of great clinical importance.
At present, the EAU guidelines recommend CUETO and EORTC models for predicting postoperative recurrence risk of NMIBC patients, and the two models are used for dangerous stratification by using clinical factors of patients, wherein the CUETO model comprises six predictors of tumor number, tumor size, past recurrence frequency, T stage, whether in-situ cancer is complicated and G stage; the EORTC model is specially used for patients with postoperative BCG bladder perfusion treatment and comprises six predictors including gender, age, whether the patients relapse, tumor number, whether in-situ cancers are accompanied and G classification. However, these two models have a C index of 0.636-0.644, which has been externally validated by researchers, and the C index is only between 0.51 and 0.57, suggesting that the prediction accuracy of the models is still to be improved, and a need for finding more efficient predictors is urgent.
Disclosure of Invention
The application provides a bladder cancer postoperative recurrence risk prediction method, device and medium combining with FISH detection, and the accuracy of bladder cancer postoperative recurrence risk prediction of a patient is improved by introducing a FISH detection result.
To achieve the above object, a first aspect of the embodiments of the present application provides a method for predicting risk of recurrence after bladder cancer surgery in combination with FISH detection, including:
screening a plurality of predictors from the candidate clinical factors;
constructing a clinical prediction model according to the plurality of predictors and the FISH detection result;
obtaining the value of each predictive factor according to the clinical data of the target patient;
confirming a FISH detection value according to the urine sample of the target patient;
inputting the values of the predictive factors and the FISH detection values into the clinical predictive model to obtain a recurrence risk score of the target patient;
and predicting the postoperative recurrence risk of the target patient according to the recurrence risk score to obtain the risk stratification of the target patient.
In a possible implementation manner of the first aspect, the screening a plurality of predictors from candidate clinical factors specifically includes:
performing correlation screening on candidate clinical factors in a training group by using a LASSO Cox regression algorithm, and taking clinical factors with regression coefficients not being 0 as prediction factors; the training set is obtained by grouping data of a clinical pathology database and is used for training a clinical prediction model.
In a possible implementation manner of the first aspect, the plurality of predictors includes tumor grading, T-staging, whether cancer in situ is accompanied, whether recurrence is past.
In a possible implementation manner of the first aspect, the constructing a clinical prediction model according to the plurality of predictors and FISH detection results specifically includes:
in Cox regression, performing shrinkage punishment on the plurality of predictors and the FISH detection result by using a Lasso regression algorithm according to a preset norm, and adjusting regression coefficients corresponding to the plurality of predictors and the FISH detection result to obtain a calculation formula of recurrence risk scores;
enabling the C index score of the recurrence risk score calculation formula and the consistency of the calibration curve to reach an expected target;
under different cut-off points, kaplan-Meier survival analysis and log rank test are carried out, and selection is carried outMaximum χ 2 The cut-off point corresponding to the value serves as the best cut-off point for recurrence risk scoring.
In a possible implementation manner of the first aspect, the determining a FISH detection value according to the urine sample of the target patient specifically includes:
testing a urine sample using a set of dual-targeting FISH probes to obtain +3 index, +7 index, +17 index, and P16 index for the target patient;
if two or more indexes of the +3 index, the +7 index and the +17 index are abnormal or the single P16 index is abnormal, the FISH detection value is positive.
In a possible implementation manner of the first aspect, the predicting the postoperative recurrence risk of the target patient according to the recurrence risk score, to obtain a risk stratification of the target patient, specifically includes:
if the recurrence risk score is greater than or equal to the optimal cutoff point, the target patient belongs to a high risk group;
if the recurrence risk score is less than the optimal cutoff point, the target patient belongs to a low risk group.
In a possible implementation manner of the first aspect, after the inputting the values of the respective predictors and the FISH detection values into the clinical prediction model, obtaining the recurrence risk score of the target patient, the method further includes:
predicting the risk of recurrence of the patient in the future 1 year, the future 2 years and the future 3 years respectively according to the clinical prediction model, and establishing a nomogram corresponding to the clinical prediction model;
combining the relapse risk score of the target patient with the nomogram, predicting the relapse risk of the target patient within 1 year, 2 years and 3 years of the future.
A second aspect of embodiments of the present application provides a bladder cancer postoperative recurrence risk prediction apparatus in combination with FISH detection, comprising:
a screening module for screening a plurality of predictors from the candidate clinical factors;
the model construction module is used for constructing a clinical prediction model according to the plurality of predictors and the FISH detection result;
the factor value taking module is used for obtaining the value of each prediction factor according to the clinical data of the target patient;
the FISH value module is used for confirming a FISH detection value according to the urine sample of the target patient;
the scoring module is used for inputting the values of the predictive factors and the FISH detection values into the clinical predictive model to obtain the recurrence risk score of the target patient;
and the prediction module is used for predicting the postoperative recurrence risk of the target patient according to the recurrence risk score to obtain the risk stratification of the target patient.
A third aspect of embodiments of the present application provides a computer readable storage medium storing a computer program which when executed by a processor implements a method of predicting risk of recurrence after a bladder cancer surgery as described above in connection with FISH detection.
Compared with the prior art, the bladder cancer postoperative recurrence risk prediction method, device and medium combining with FISH detection provided by the embodiment of the application are used for screening prediction factors related to RFS (recurrence free survival) of an NMIBC patient after operation from candidate clinical factors (including age, gender, tumor size, tumor number, tumor grading, T stage, whether in-situ cancer is accompanied or not and whether recurrence is occurring or not in the past), and then combining with the prediction factors and FISH detection values to construct a novel clinical prediction model for predicting the postoperative recurrence risk of the NMIBC patient. According to a regression formula in the clinical prediction model, the recurrence risk score of each patient can be calculated, so that the postoperative recurrence risk of each patient is predicted.
Compared with CUETO and EORTC models recommended by EAU guidelines, the clinical prediction model provided by the application has a higher C index, which means that the bladder cancer postoperative recurrence risk prediction method combined with FI SH detection provided by the application is more accurate.
Drawings
FIG. 1 is a schematic flow chart of a method for predicting risk of recurrence after bladder cancer surgery in combination with FI SH detection according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a calibration curve used for prediction performance evaluation of a clinical prediction model in an embodiment of the present application;
fig. 3 is a schematic illustration of a nomogram corresponding to a clinical predictive model according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Referring to fig. 1, an embodiment of the present application provides a method for predicting risk of recurrence after bladder cancer surgery in combination with FI SH detection, including:
s10, screening out a plurality of predictive factors from candidate clinical factors.
S11, constructing a clinical prediction model according to the plurality of predictors and the FISH detection result.
S12, obtaining the value of each prediction factor according to the clinical data of the target patient.
S13, confirming FI SH detection value according to the urine sample of the target patient.
S14, inputting the values of the predictive factors and the FI SH detection values into the clinical predictive model to obtain the recurrence risk score of the target patient.
S15, predicting postoperative recurrence risk of the target patient according to the recurrence risk score to obtain risk stratification of the target patient.
The focus of this example is on the construction of the clinical predictive model in S11, which requires the use of a clinical pathology database during construction. The clinical pathology database adopted in this example was derived from 240 NMI BC patients hospitalized in a commemorative hospital, and the clinical pathology data inclusion criteria were: (a) pathologically diagnosing non-myogenic invasive bladder cancer; (b) transurethral bladder tumor electroresection; (c) preoperatively performed urine shed cells FI SH detection. The exclusion criteria were: (a) absence of clinical pathology data and follow-up information; (b) patients with additional cancers. When the model is constructed, the whole study queue is randomly divided into a training group and a verification group according to the proportion of 7:3.
Baseline characteristics of the patient including age, sex, whether the past tumor recurred, tumor number, tumor size, pathological T stage, whether carcinoma in situ was accompanied, tumor grade, and preoperative FI SH test results (each probe index result, number of abnormal probes, and FI SH result) were obtained from the case data. Tumor pathology stage was determined according to the international anticancer alliance, version 8 TNM staging system. The outcome non-recurrence survival (RFS) in this example refers to the time from the date of surgery to the date of recurrence or last follow-up.
In both S10 and S11, the LASSO algorithm and Cox regression model are used, but the emphasis of S10 and S11 is different. In S10, the Lasso regression algorithm uses a preset norm to perform shrinkage penalty, performs penalty correction on variable coefficients with little contribution to dependent variables, compresses coefficients of some less important variables to 0, and keeps coefficients of important variables to be larger than 0 so as to reduce the number of covariates in Cox regression. In S11, the shrinkage degree is different when the Lasso regression algorithm is used to perform shrinkage penalty by using the preset norm, the shrinkage degree in S11 is smaller than the shrinkage degree in S10, the coefficient of each variable is not normalized to 0, the coefficient of each variable is only used to adjust the coefficient of each variable, and the number of covariates in Cox regression is not reduced.
And S11, when a clinical prediction model is constructed, a training group is required to be used for adjusting the recurrence risk score expression, and then a verification group is used for verifying the recurrence risk score calculation formula and the optimal cut-off point of the recurrence risk score, so that the accuracy and the reliability of the clinical prediction model which introduces the FISH detection result are further evaluated. The FI SH detection value is related to the states of the sites of CSP3, CSP7, CSP17 and p16 and the positive numbers of the four sites.
Illustratively, S10 specifically includes:
performing correlation screening on candidate clinical factors in a training group by using a LASSO Cox regression algorithm, and taking clinical factors with regression coefficients not being 0 as prediction factors; the training set is obtained by grouping data of a clinical pathology database and is used for training a clinical prediction model.
In the training group, a LASSO Cox regression algorithm is used to screen out the predictive factors related to the postoperative RFS of the NMIBC patient from the variables of candidate clinical factors (including age, sex, tumor size, tumor number, tumor grade, T stage, whether in-situ cancer is accompanied or not, whether recurrence is past or not) and to construct a new clinical predictive model for predicting the postoperative recurrence risk of the NMIBC patient in S11.
Illustratively, the plurality of predictors includes tumor grade, T-grade, whether concomitant carcinoma in situ, whether previous recurrence.
In the embodiment, 4 prediction factors related to postoperative recurrence are selected from 13 candidate clinical pathological factors according to the correlation size by using LASSO Cox regression analysis, wherein the prediction factors comprise tumor grading, T grading, whether in-situ cancer is accompanied or not, and whether recurrence is past or not.
Illustratively, S11 specifically includes:
in Cox regression, performing shrinkage punishment on the plurality of predictors and the FISH detection result by using a Lasso regression algorithm according to a preset norm, and adjusting regression coefficients corresponding to the plurality of predictors and the FISH detection result to obtain a calculation formula of recurrence risk scores;
enabling the C index score of the recurrence risk score calculation formula and the consistency of the calibration curve to reach an expected target;
under different cut-off points, kaplan-Meier survival analysis and log rank test are carried out, and the cut-off point corresponding to the highest χ2 value is selected as the best cut-off point of recurrence risk score.
In this example, the expression of the new clinical predictive model for predicting risk of postoperative recurrence in NMIBC patients is an expression of recurrence risk score. The 4 predictor values in the expression and the FISH detection values can be referred to in table 1, and the values (regression coefficients) in table 1 are obtained according to the result of LASSO Cox regression analysis. Taking FISH test values as an example, in the case database, the incidence of aneuploidy of CSP3, 7, and 17 in the cohort patients was 41%, 40%, 44%, respectively, and the incidence of p16 site loss was 21%. Of these, the most common combination types are CSP3, 7 and 17 sites positive, with no abnormalities in the absence of the p16 site.
The chi-square test and logistic regression analysis results show that CSP3, 7, 17 sites, the number of positive detection sites and the FISH detection result are obviously related to the tumor stage and grade of NMIBC patients (the chi-square test and the P value are all < 0.001). Furthermore, GLP-P16 site deletion and FISH detection correlated with tumor recurrence (P values 0.044, 0.007, respectively). Kaplan-Meier survival curves showed that GLP-16 positive group patients had shorter RFS than GLP-16 negative group patients (p=0.041) and FISH test positive group patients had shorter RFS than FISH test negative group patients (p=0.006) throughout the cohort.
Table 1 regression coefficients for each predictor
The meaning of the predictive model discrimination is as follows: in the predicted value of the model, whether a intercept point can be found or not is judged, so that one group can be correctly distinguished from the other group, and if the distinguishing degree is more separated and is more consistent with the actual situation, the distinguishing degree of the model is more prompted. The C index is a common index for evaluating the discrimination of a prognostic prediction model, ranging from 0 to 1, and is usually greater than 0.6, suggesting that the model has good discrimination.
The meaning of the prediction model calibration degree is: and evaluating whether the size of the predicted value of the model is consistent with the size of the occurrence probability of the ending event, and if the predicted value of the model is close to the actual occurrence probability of the ending event, prompting that the calibration degree of the model is higher. The evaluation uses a calibration curve as shown in fig. 2, and when the calibration curve of the model is closer to the 45-degree diagonal (i.e., the ideal model reference line), the prediction accuracy is higher.
Finally, in the training set, the present example uses X-tile software (version 3.6.1, university of yersil medical school, new jersey, ct, usa) to select the best cut-off point for recurrence risk score (optimal cutoff value), dividing patients into high risk and low risk groups. The log-rank test was used to evaluate the difference in survival curves for the high-risk and low-risk groups and to analyze the subgroups in subgroups of different ages and sexes. Other statistical analyses were performed using R statistical software version 4.0.4 (https:// www.r-project. Org /) except that the optimal cut-off points were chosen using X-tile software. All statistical analyses were double-sided, with P <0.05 considered statistically different.
Illustratively, S13 specifically includes:
testing a urine sample using a set of dual-targeting FISH probes to obtain +3 index, +7 index, +17 index, and P16 index for the target patient; the dual-targeting FISH probe includes chromosome centromere specific probes, locus specific probe-p 16 sites for 3, 7 and 17;
if two indexes of the +3 index, the +7 index and the +17 index are abnormal or the P16 index is abnormal, the FISH detection takes a value.
Illustratively, the +3 index abnormality refers to the occurrence of three or more +3 signal points within a single cell; the +7 index abnormality refers to the occurrence of three or more than three +7 signal points in a single cell; the +17 index abnormality refers to the occurrence of three or more than three +17 signal points in a single cell; the P16 index abnormality refers to the occurrence of one or zero P16 signal points in a single cell.
In this example, the patient's morning urine (first urination of the day) is collected preoperatively as a urine sample for FISH testing. Urine samples were centrifuged at 1500rpm for 10min and cell pellet was collected for FISH analysis. Cells were resuspended in phosphate buffer, incubated in hypotonic potassium chloride solution (0.075 mol/L) and then fixed with fixative (methanol: acetic acid=3:1). Slides made of urine samples were used for FISH analysis (GP Medical Technologies, ltd, beijing, china).
Chromosome-specific probes (CSP) 3, 7 and 17 and a locus-specific probe (GLP) -p16 site (9 p 21) were used in the FISH analysis. Two DNA probes were mixed together as a set of dual-targeting FISH probes paired as follows: chromosome 3 and chromosome 7, chromosome 17 and p16. Labeling with rhodamine and fluorescein isothiocyanate (fluorescein isothiocyanate, FITC) produced red (rhodamine) and green (FITC) fluorescent signals in the hybridized samples. The steps of pretreatment of the sample slide, hybridization of the fluorescent marked DNA probe and the complementary DNA, washing and counterstaining after hybridization and the like are carried out according to the operation flow of the instruction book of the kit. The signals were observed and photographed using a computer imaging system (IMSTAR s.a., paris, france).
100 non-overlapping and well-signaled cells were observed using each probe combination. Counting the percentage of the number of cells with different types of abnormal conditions, and establishing a threshold value; threshold = mean (M) +3 x Standard Deviation (SD); thresholds were established for the following 5 indices, expressed as +3, +7, +17, -P16 (-1), and-P16 (-2), respectively:
(1) the +3 index abnormality refers to the occurrence of three or more green signal points in a single cell, suggesting chromosome 3 multimers;
(2) the +7 index abnormality refers to the occurrence of three or more red signal points in a single cell, suggesting chromosome 7 multimers;
(3) the +17 index abnormality refers to the occurrence of three or more green signal points in a single cell, suggesting chromosome 17 multimers;
(4) -abnormal P16 (-1) index means that a red signal point appears in a single cell, which indicates the heterozygosity deficiency of the P16 gene;
(5) the P16 (-2) index abnormality refers to no red signal point in single cell, which suggests that the P16 gene is homozygous for the deficiency, and belongs to complex abnormality.
Firstly judging the condition of the index, and judging that the detection index is positive if the detection index value is more than or equal to the respective threshold value. And judging the FISH result according to the principle, and judging that the FISH detection result is positive if two or more indexes are abnormal at the same time or single-P16 is abnormal.
Illustratively, S15 specifically includes:
if the recurrence risk score is greater than or equal to the optimal cutoff point, the target patient belongs to a high risk group;
if the recurrence risk score is less than the optimal cutoff point, the target patient belongs to a low risk group.
Illustratively, after S14, further comprising:
predicting the risk of recurrence of the patient in the future 1 year, the future 2 years and the future 3 years respectively according to the clinical prediction model, and establishing a nomogram corresponding to the clinical prediction model;
combining the relapse risk score of the target patient with the nomogram, predicting the relapse risk of the target patient within 1 year, 2 years and 3 years of the future.
Referring to fig. 3, an FI SH-clinical prediction model is constructed according to the regression result, and is used for predicting RFS of NMI BC patients after operation, and providing a nomogram, which is convenient for clinical use. The model has good discrimination in the training set, C index up to 0.683 (95% CI, 0.611-0.756), and is validated in the validation set with C index of 0.665 (95% CI, 0.565-0.765). The calibration curve of the model, whether in the training set or the validation set, suggests that the model has good calibration (see fig. 2).
Compared with the prior art, the bladder cancer postoperative recurrence risk prediction method, device and medium combining with FISH detection provided by the embodiment of the application are used for jointly constructing a novel clinical prediction model for predicting the postoperative recurrence risk of NMI BC patients by combining with FISH detection results (comprising CSP3, CSP7, CSP17 and p16 site states and four site positive numbers) after screening prediction factors related to RFS (recurrence-free survival) of NMI BC patients from candidate clinical factors (comprising age, sex, tumor size, tumor number, tumor grading, T stage, whether cancer is accompanied with in situ or not and recurrence or not in the past). According to a regression formula in the clinical prediction model, the recurrence risk score of each patient can be calculated, so that the postoperative recurrence risk of each patient is predicted.
Compared with CUETO and EORTC models recommended by EAU guidelines, the clinical prediction model provided by the application has a higher C index, which means that the bladder cancer postoperative recurrence risk prediction method combined with FISH detection provided by the application is more accurate.
An embodiment of the present application provides a device for predicting risk of recurrence after bladder cancer surgery in combination with FISH detection, including: the system comprises a screening module, a model construction module, a factor value module, a FISH value module, a scoring module and a prediction module.
And the screening module is used for screening a plurality of predictive factors from the candidate clinical factors.
And the model construction module is used for constructing a clinical prediction model according to the plurality of predictors and the FISH detection result.
And the factor value taking module is used for obtaining the value of each predictive factor according to the clinical data of the target patient.
And the FISH detection value module is used for confirming the FISH detection value according to the urine sample of the target patient.
And the scoring module is used for inputting the values of the predictive factors and the FISH detection values into the clinical predictive model to obtain the recurrence risk score of the target patient.
And the prediction module is used for predicting the postoperative recurrence risk of the target patient according to the recurrence risk score to obtain the risk stratification of the target patient.
It will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the bladder cancer postoperative recurrence risk prediction device described above may refer to the corresponding process in the foregoing method embodiment, and will not be described herein again 。
An embodiment of the present application provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements a method for predicting risk of recurrence after a bladder cancer surgery in combination with FISH detection as described above.
In several embodiments provided by the present application, it will be understood that each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
While the foregoing is directed to the preferred embodiments of the present application, it will be appreciated by those skilled in the art that changes and modifications may be made without departing from the principles of the application, such changes and modifications are also intended to be within the scope of the application.
Claims (7)
1. A method for predicting risk of recurrence after bladder cancer surgery in combination with FISH detection, comprising:
screening a plurality of predictors from candidate clinical factors, specifically including: performing correlation screening on candidate clinical factors in a training group by using a LASOCox regression algorithm, and taking clinical factors with regression coefficients not being 0 as prediction factors; the training group is obtained by grouping data of a clinical pathology database and is used for training a clinical prediction model;
constructing a clinical prediction model according to the plurality of predictors and the FISH detection result, wherein the method specifically comprises the following steps: in Cox regression, performing shrinkage punishment on the plurality of predictors and the FISH detection result by using a Lasso regression algorithm according to a preset norm, and adjusting regression coefficients corresponding to the plurality of predictors and the FISH detection result to obtain a calculation formula of recurrence risk scores; enabling the C index score of the recurrence risk score calculation formula and the consistency of the calibration curve to reach an expected target; under different cut-off points, kaplan-Meier survival analysis and log rank test are carried out, and the cut-off point corresponding to the highest χ2 value is selected as the optimal cut-off point of recurrence risk score;
obtaining the value of each predictive factor according to the clinical data of the target patient;
confirming a FISH detection value according to the urine sample of the target patient;
inputting the values of the predictive factors and the FISH detection values into the clinical predictive model to obtain a recurrence risk score of the target patient;
predicting the postoperative recurrence risk of bladder cancer of the target patient according to the recurrence risk score to obtain risk stratification of the target patient.
2. The method of claim 1, wherein the plurality of predictors comprises tumor grade, T-stage, whether cancer in situ is concomitant, whether recurrence is past.
3. The method for predicting risk of recurrence after surgery of bladder cancer in combination with FISH detection according to claim 1, wherein said determining FISH detection value from urine samples of said target patient specifically comprises:
testing a urine sample using a set of dual-targeting FISH probes to obtain +3 index, +7 index, +17 index, and P16 index for the target patient;
if two or more indexes of the +3 index, the +7 index and the +17 index are abnormal or the single P16 index is abnormal, the FISH detection value is positive.
4. The method for predicting risk of recurrence after surgery for bladder cancer in combination with FISH detection according to claim 1, wherein predicting the risk of recurrence after surgery for the target patient based on the recurrence risk score, comprises:
if the recurrence risk score is greater than or equal to the optimal cutoff point, the target patient belongs to a high risk group;
if the recurrence risk score is less than the optimal cutoff point, the target patient belongs to a low risk group.
5. The method for predicting risk of recurrence after a bladder cancer surgery in combination with FISH detection of claim 1, wherein said inputting the values of the respective predictors and the FISH detection values into the clinical predictive model, after obtaining the recurrence risk score for the target patient, further comprises:
predicting the risk of recurrence of the patient in the future 1 year, the future 2 years and the future 3 years respectively according to the clinical prediction model, and establishing a nomogram corresponding to the clinical prediction model;
combining the relapse risk score of the target patient with the nomogram, predicting the relapse risk of the target patient within 1 year, 2 years and 3 years of the future.
6. A bladder cancer postoperative recurrence risk prediction device in combination with FISH detection, comprising:
the screening module is used for screening a plurality of predictive factors from candidate clinical factors, and is specifically used for: performing correlation screening on candidate clinical factors in a training group by using a LASSO Cox regression algorithm, and taking clinical factors with regression coefficients not being 0 as prediction factors; the training group is obtained by grouping data of a clinical pathology database and is used for training a clinical prediction model;
the model construction module is used for constructing a clinical prediction model according to the plurality of predictors and the FISH detection result, and is specifically used for: in Cox regression, performing shrinkage punishment on the plurality of predictors and the FISH detection result by using a Lasso regression algorithm according to a preset norm, and adjusting regression coefficients corresponding to the plurality of predictors and the FISH detection result to obtain a calculation formula of recurrence risk scores; enabling the C index score of the recurrence risk score calculation formula and the consistency of the calibration curve to reach an expected target; under different cut-off points, kaplan-Meier survival analysis and log rank test are carried out, and the cut-off point corresponding to the highest χ2 value is selected as the optimal cut-off point of recurrence risk score;
the factor value taking module is used for obtaining the value of each prediction factor according to the clinical data of the target patient;
the FISH value module is used for confirming a FISH detection value according to the urine sample of the target patient;
the scoring module is used for inputting the values of the predictive factors and the FISH detection values into the clinical predictive model to obtain the recurrence risk score of the target patient;
and the prediction module is used for predicting the postoperative recurrence risk of the target patient according to the recurrence risk score to obtain the risk stratification of the target patient.
7. A computer readable storage medium, characterized in that it stores a computer program which, when executed by a processor, implements the method for predicting risk of recurrence after bladder cancer surgery in combination with FISH detection as claimed in any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310032705.0A CN116013528B (en) | 2023-01-10 | 2023-01-10 | Bladder cancer postoperative recurrence risk prediction method, device and medium combining with FISH detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310032705.0A CN116013528B (en) | 2023-01-10 | 2023-01-10 | Bladder cancer postoperative recurrence risk prediction method, device and medium combining with FISH detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116013528A CN116013528A (en) | 2023-04-25 |
| CN116013528B true CN116013528B (en) | 2023-11-24 |
Family
ID=86024641
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310032705.0A Active CN116013528B (en) | 2023-01-10 | 2023-01-10 | Bladder cancer postoperative recurrence risk prediction method, device and medium combining with FISH detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116013528B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111640509A (en) * | 2020-06-02 | 2020-09-08 | 山东大学齐鲁医院 | Cervical cancer postoperative recurrence risk prediction method and system |
| CN112725454A (en) * | 2021-02-03 | 2021-04-30 | 山东第一医科大学附属省立医院(山东省立医院) | Bladder cancer patient overall survival rate prognosis model |
| CN114045338A (en) * | 2021-11-01 | 2022-02-15 | 中日友好医院(中日友好临床医学研究所) | Application of OLC1 gene expression level in bladder cancer prognosis evaluation |
| CN114807377A (en) * | 2022-06-29 | 2022-07-29 | 南京世和基因生物技术股份有限公司 | Application of bladder cancer prognosis survival time marker, evaluation device and computer readable medium |
| CN114863999A (en) * | 2022-04-12 | 2022-08-05 | 中国人民解放军海军军医大学第一附属医院 | Tumor prognosis prediction model construction method based on angiogenesis related genes |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107548498A (en) * | 2015-01-20 | 2018-01-05 | 南托米克斯有限责任公司 | System and method for the chemotherapy in the high-level carcinoma of urinary bladder of response prediction |
| CN110621788A (en) * | 2017-05-18 | 2019-12-27 | 基美健有限公司 | DNA methylation and mutation analysis methods for bladder cancer monitoring |
| CA3090426A1 (en) * | 2018-04-14 | 2019-10-17 | Natera, Inc. | Methods for cancer detection and monitoring by means of personalized detection of circulating tumor dna |
-
2023
- 2023-01-10 CN CN202310032705.0A patent/CN116013528B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111640509A (en) * | 2020-06-02 | 2020-09-08 | 山东大学齐鲁医院 | Cervical cancer postoperative recurrence risk prediction method and system |
| CN112725454A (en) * | 2021-02-03 | 2021-04-30 | 山东第一医科大学附属省立医院(山东省立医院) | Bladder cancer patient overall survival rate prognosis model |
| CN114045338A (en) * | 2021-11-01 | 2022-02-15 | 中日友好医院(中日友好临床医学研究所) | Application of OLC1 gene expression level in bladder cancer prognosis evaluation |
| CN114863999A (en) * | 2022-04-12 | 2022-08-05 | 中国人民解放军海军军医大学第一附属医院 | Tumor prognosis prediction model construction method based on angiogenesis related genes |
| CN114807377A (en) * | 2022-06-29 | 2022-07-29 | 南京世和基因生物技术股份有限公司 | Application of bladder cancer prognosis survival time marker, evaluation device and computer readable medium |
Non-Patent Citations (5)
| Title |
|---|
| FISH技术在监测膀胱尿路上皮癌术后复发的临床价值.《当代医学》.2019,第11-13页. * |
| FISH技术在监测膀胱尿路上皮癌术后复发的临床价值;贾志红;胡招兵;王仁杰;吴颖虹;;当代医学(36);全文 * |
| 卢善明 ; 朱文标 ; 谢寿城 ; .组织切片FISH技术在预测非肌层浸润性膀胱癌复发和进展的作用.实用医学杂志.2016,(09),全文. * |
| 组织切片FISH技术在预测非肌层浸润性膀胱癌复发和进展的作用;卢善明;朱文标;谢寿城;;实用医学杂志(09);全文 * |
| 非肌层浸润性膀胱尿路上皮癌电切术后影响预后因素分析及预测复发模型的建立;皮江川;《万方》;正文第5-27页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116013528A (en) | 2023-04-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR101672531B1 (en) | Genetic markers for prognosing or predicting early stage breast cancer and uses thereof | |
| CN113366577A (en) | Enhanced detection of target DNA by fragment size analysis | |
| CN111833965A (en) | Urinary sediment genomic DNA classification method, device and application | |
| CN111640518A (en) | Cervical cancer postoperative survival prediction method, system, equipment and medium | |
| CN110760585B (en) | Prostate cancer biomarker and application thereof | |
| Barr Fritcher et al. | FISH ing for pancreatobiliary tract malignancy in endoscopic brushings enhances the sensitivity of routine cytology | |
| CN115410713A (en) | Hepatocellular carcinoma prognosis risk prediction model construction based on immune-related gene | |
| CN114613502A (en) | Nasopharynx cancer patient survival prediction model, construction method, device and storage medium | |
| EP2682477A1 (en) | miR-181a and miR652 as oncologic biomarker of breast cancer | |
| CN116013528B (en) | Bladder cancer postoperative recurrence risk prediction method, device and medium combining with FISH detection | |
| Racz et al. | The accuracy of three predictive models in the evaluation of recurrence rates for gastrointestinal stromal tumors | |
| US20210215700A1 (en) | Personalized treatment of pancreatic cancer | |
| CN113234823B (en) | Pancreatic cancer prognosis risk assessment model and application thereof | |
| Zhang et al. | A novel approach for the non-invasive diagnosis of pulmonary nodules using low-depth whole-genome sequencing of cell-free DNA | |
| CN116469552A (en) | Method and system for breast cancer polygene genetic risk assessment | |
| Wada et al. | Circulating miRNA signature predicts response to preoperative chemoradiotherapy in locally advanced rectal cancer | |
| CN110760584B (en) | Prostate cancer disease progression biomarker and application thereof | |
| WO2014052930A2 (en) | Biomarkers for prostate cancer prognosis | |
| WO2017185165A1 (en) | Gene signature for prostate cancer prognosis | |
| WO2021087508A1 (en) | Methods relating to sepsis associated acute kidney injury | |
| CN114507717A (en) | Method for predicting bile duct cancer recurrence by combining multiple mRNAs and application thereof | |
| Dehal et al. | Accuracy of nodal staging is influenced by sidedness in colon cancer | |
| LU502513B1 (en) | Breast cancer prognosis evaluation method and system based on autophagy-related incrna model | |
| CN116656829B (en) | Gene marker combination, kit and system for predicting bad prognosis of gastric cancer | |
| CN117789976A (en) | Application of detecting chromosome segment information in extrahepatic transfer prediction of primary liver cancer patient |
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 |