CN113658698A - Cervical adenocarcinoma prognosis method - Google Patents
Cervical adenocarcinoma prognosis method Download PDFInfo
- Publication number
- CN113658698A CN113658698A CN202110897414.9A CN202110897414A CN113658698A CN 113658698 A CN113658698 A CN 113658698A CN 202110897414 A CN202110897414 A CN 202110897414A CN 113658698 A CN113658698 A CN 113658698A
- Authority
- CN
- China
- Prior art keywords
- cervical adenocarcinoma
- prognosis
- model
- clinical pathological
- tumor
- 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
Images
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Data Mining & Analysis (AREA)
- Biomedical Technology (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The invention discloses a cervical adenocarcinoma prognosis method, which comprises the following steps: acquiring clinical pathological parameters, establishing a corresponding array structure in a storage medium according to the clinical pathological parameters, and storing the clinical pathological parameters into corresponding storage spaces in the array structure, wherein the clinical pathological parameters comprise histological grading, primary tumor stage, lymph node stage, distant metastasis stage, whether a primary focus is operated or not and the maximum diameter of a primary tumor; a space structure for storing a cervical adenocarcinoma prognosis model is further arranged in the storage medium, and the established cervical adenocarcinoma prognosis model is stored in the space structure; reading each clinical pathological parameter through a processor, inputting each clinical pathological parameter into the cervical adenocarcinoma prognosis model, and displaying data information in a dynamic nomogram form; and predicting according to the data information. The invention displays more intuitive and rational data by using the dynamic nomogram, thereby improving the accuracy and efficiency of decision and prognosis of doctors.
Description
Technical Field
The invention relates to the technical field of medicine, in particular to a cervical adenocarcinoma prognosis method.
Background
Cervical Adenocarcinoma (UCA) is an important pathological type of cervical adenocarcinoma, accounting for about 10% -25%, and its absolute and relative incidence rates are on the rise in recent 20 years, especially in the population of 20-39 years. Because most of cervical adenocarcinoma is endogenous, most of the lesions are located in the cervical canal, and early screening is difficult; the adenocarcinoma has multiple histological types and obvious tumor heterogeneity; compared with squamous carcinoma, adenocarcinoma has higher lymph node metastasis, ovarian metastasis and distant metastasis rates and poorer prognosis, and the early diagnosis, effective treatment and prognosis evaluation of cervical adenocarcinoma all become the predicaments faced by clinicians. At present, the treatment principle and prognosis judgment of cervical adenocarcinoma mainly refer to the standard of cervical squamous carcinoma according to the International Federation of Gynecology and Obstetrics (FIGO) stage and the National Comprehensive Cancer Network (NCCN) clinical practice guideline: the early stage is mainly comprehensive treatment of operation, and the later stage is recommended to adopt radiotherapy and chemotherapy. Researchers find that the accuracy rate of the method for predicting OS of IB-IIA early-stage cervical adenocarcinoma patients in 5 years after surgery by using FIGO only in stages is only 0.54. Moreover, multiple studies prove that the biological behavior, the sensitivity to chemotherapy and radiotherapy and the prognosis of cervical adenocarcinoma are different from those of squamous carcinoma. Silva and the like take the biological behavior of tumors as a focus of attention, classify the tumors according to the growth mode of tumor cells under a microscope and bring the tumors into LVSI, propose that cervical adenocarcinoma is judged by Silva typing for prognosis, an infiltration mode is used for replacing the infiltration depth, and propose that different treatment modes are determined by the infiltration mode of the cervical adenocarcinoma. However, the researchers suggested that Silva typing is only suitable for patients with HPV positive cervical adenocarcinoma prognosis for prognosis of cervical adenocarcinoma. Therefore, analyzing the independent risk factors of cervical adenocarcinoma prognosis and constructing a prediction model by using the factors have important significance in realizing more accurate individual assessment of the prognosis of cervical adenocarcinoma patients and guiding clinical treatment, follow-up and prediction of disease progress.
At present, for cervical adenocarcinoma, a corresponding prediction model is lacked, and the existing prediction model is mostly displayed in a static nomogram form and cannot provide more intuitive and rational information for decision and prognosis of doctors.
Disclosure of Invention
Aiming at the problems, the invention provides a cervical adenocarcinoma prognosis method, which displays more intuitive and rational information on a prediction model in a dynamic nomogram form, thereby improving the accuracy and efficiency of decision and prognosis of doctors.
The technical scheme of the invention is as follows: a method of prognosis of cervical adenocarcinoma, comprising the steps of: acquiring clinical pathological parameters of a patient, establishing a corresponding array structure in a storage medium according to the number of the clinical pathological parameters, wherein the clinical pathological parameters comprise histological grading, primary tumor stage, lymph node stage, distant metastasis stage, whether a primary focus is operated or not and the maximum diameter of a primary tumor, and storing each clinical pathological parameter into a corresponding storage space in the array structure; a space structure for storing a cervical adenocarcinoma prognosis model is further arranged in the storage medium, and the established cervical adenocarcinoma prognosis model is stored in the space structure; reading each clinical pathological parameter in the array structure through a processor, inputting each clinical pathological parameter into the established cervical adenocarcinoma prognosis model, and displaying data information in a dynamic nomogram form; and predicting according to the data information.
The working principle of the invention is as follows: after obtaining the cervical adenocarcinoma prognosis model, storing clinical pathological parameters including histological grading, primary tumor stage, lymph node stage, distant metastasis stage, whether the primary focus is operated or not and the maximum diameter of the primary tumor into a storage space corresponding to an array structure, reading clinical pathological parameter data through a processor and inputting the clinical pathological parameter data into the established cervical adenocarcinoma prognosis model to obtain information displayed by a dynamic nomogram.
Compared with the prior art, the invention obtains the information displayed by the dynamic nomogram by establishing the cervical adenocarcinoma prognosis model, storing the clinical pathological parameters of the patient in the storage space corresponding to the array structure, reading the clinical pathological parameter data by the processor and inputting the clinical pathological parameter data into the established cervical adenocarcinoma prognosis model, and can directly obtain the vital data and trend of the patient, such as survival probability, tumor specific survival probability and the like, required by a doctor compared with the existing static nomogram without carrying out scale measurement for numerical calculation, thereby improving the accuracy and efficiency of the decision and prognosis of the doctor.
In a further aspect, the cervical adenocarcinoma prognosis method further includes inputting the predicted time point into the cervical adenocarcinoma prognosis model.
By inputting the predicted time point into the cervical adenocarcinoma prognosis model, the tumor-specific survival probability of the patient at the time point in the future, the 95% confidence interval thereof, and the like can be obtained.
In a further aspect, the dynamic nomogram comprises a survival graph, the survival graph being a time-patient survival probability graph.
The survival curve chart dynamically shows the relationship between the survival probability of the patient and the time, so that a doctor can more intuitively acquire the trend of the survival probability of the patient and provide basis for prognosis and decision making.
In a further aspect, the dynamic nomogram comprises a survival probability map having tumor-specific survival probability data and confidence intervals therefor.
The survival probability chart visually shows the tumor specific survival probability of the patient at a certain time point, is simple and efficient, and does not need to carry out complex scale calculation.
In a further aspect, the dynamic nomogram comprises a data list comprising clinical pathology parameters of the patient, survival probability of the patient, tumor-specific survival probability and confidence interval data thereof at the predicted time point.
Through the data list, the data such as clinical pathological parameters, the survival probability of patients, the tumor specific survival probability and the confidence interval thereof at a certain time point in the future can be intuitively acquired.
In a further technical scheme, the cervical adenocarcinoma prognosis model is established by a COX proportional risk model. In addition, the COX proportional hazards model includes: regression coefficients, the positive and negative of which indicate protective and adverse factors, respectively, for the patient's prognosis; an index coefficient, the magnitude of which reflects the degree of contribution of the corresponding variable to tumor-specific death; standard error of the regression coefficient; a statistical significance value for assessing the statistical significance of the contribution of the respective variable to tumor-specific survival; upper and lower limits of 95% confidence intervals for the index coefficients; c statistic used for characterizing the discrimination of the cervical adenocarcinoma prognosis model; a standard deviation of the C statistic; a likelihood ratio test, a Wald test and a time series test for assessing the statistical significance of the cervical adenocarcinoma prognostic model.
The cervical adenocarcinoma prognosis model is constructed by the COX proportional risk model, so that the influence of clinical pathological parameters on prognosis, the influence and the evaluation of statistical significance can be determined, and the method is more scientific.
In a further technical solution, the dynamic nomogram includes a model synopsis data list, the model synopsis data list uses the clinical pathology parameter as a variable, and uses the regression coefficient, the index coefficient, the standard error of the regression coefficient, the statistically significant value, the C statistic, the standard deviation of the C statistic, and the upper and lower limits of the 95% confidence interval of the index coefficient as function values, and further includes statistically significant evaluation values of the likelihood ratio test, the wald test, and the time series test.
By displaying the synopsis data list, doctors can acquire the influence of corresponding variables on the patient prognosis, the influence and the like, and the doctors can give more rational prognosis and decision on the variables with larger influence.
The invention has the beneficial effects that:
1. compared with the prior art, the invention obtains the information displayed by the dynamic nomogram by establishing the cervical adenocarcinoma prognosis model, storing the clinical pathological parameters of the patient into the storage space corresponding to the array structure, reading the clinical pathological parameter data by the processor and inputting the clinical pathological parameter data into the established cervical adenocarcinoma prognosis model, and can directly obtain the vital data and trend of the survival probability, tumor specific survival probability and the like of the patient required by a doctor without carrying out scale measurement and numerical calculation compared with the existing static nomogram, thereby improving the accuracy and efficiency of the decision and prognosis of the doctor;
2. inputting the predicted time point into a cervical adenocarcinoma prognosis model, the tumor specific survival probability, 95% confidence interval and the like of the patient at the future time point can be obtained;
3. the survival curve chart dynamically shows the relationship between the survival probability and the time of the patient, so that a doctor can more intuitively acquire the survival probability and the trend of the patient and provide a basis for prognosis and decision making;
4. the survival probability chart visually shows the tumor specific survival probability of the patient at a certain time point, is simple and efficient, and does not need to perform complex scale calculation;
5. through the data list, data such as clinical pathological parameters, survival probability of patients, tumor specific survival probability and confidence interval thereof at a certain time point in the future can be intuitively acquired;
6. the cervical adenocarcinoma prognosis model is constructed through the COX proportional risk model, so that the influence of clinical pathological parameters on prognosis, the influence and the evaluation of statistical significance can be determined, and the method is more scientific;
7. by displaying the synopsis data list, doctors can acquire the influence of corresponding variables on the patient prognosis, the influence and the like, and the doctors can give more rational prognosis and decision on the variables with larger influence.
Drawings
FIG. 1 is a flowchart of a method for prognosis of cervical adenocarcinoma according to an embodiment of the present invention;
FIG. 2 is a survival graph of the cervical adenocarcinoma prognosis model according to the embodiment of the present invention;
fig. 3 is a survival probability map of the cervical adenocarcinoma prognosis model in the example of the present invention;
fig. 4 is a data list of the cervical adenocarcinoma prognosis model according to the embodiment of the present invention;
fig. 5 is a table of general data of the cervical adenocarcinoma prognosis model according to the embodiment of the present invention.
Detailed Description
The embodiments of the present invention will be further described with reference to the accompanying drawings.
Example (b):
as shown in fig. 1, a cervical adenocarcinoma prognosis method comprises the following steps: acquiring clinical pathological parameters of a patient, establishing a corresponding array structure in a storage medium according to the number of the clinical pathological parameters, wherein the clinical pathological parameters comprise histological grading, primary tumor stage, lymph node stage, distant metastasis stage, whether a primary focus is operated or not and the maximum diameter of a primary tumor, and storing each clinical pathological parameter into a corresponding storage space in the array structure.
A spatial structure for storing the cervical adenocarcinoma prognosis model is also arranged in the storage medium, and the established cervical adenocarcinoma prognosis model is stored in the spatial structure.
Reading each clinical pathological parameter in the array structure through a processor, inputting each clinical pathological parameter into the established cervical adenocarcinoma prognosis model, displaying data information in a dynamic nomogram form, and then predicting according to the data information.
As shown in fig. 2-5, time _ depth is the predicted time point (month), and grade represents the histological grade; stage _ T is the T stage (i.e., primary tumor stage) of the TNM stage, stage _ N is the N stage (i.e., lymph node stage) of the TNM stage, and stage _ M is the M stage (i.e., distant metastasis stage) of the TNM stage; surg _ prim is whether the primary lesion is operated or not, and tumor _ size is the maximum diameter of the primary tumor; a Prediction button; lower bound is the lower limit of the 95% confidence interval and upper bound is the upper limit of the 95% confidence interval.
For example, a cervical adenocarcinoma prognostic model can be established using SEER data and validated internally and ex-peri-chronologically. Constructing a predictive model of the probability of tumor-specific survival (CSS) for 3 years and 5 years by using cervical adenocarcinoma patients (n-5655) diagnosed from 1988 to 2010 by using a SEER database, carrying out internal verification by adopting a Bootstrap resampling method, and carrying out time interval external verification by using cervical adenocarcinoma patients (n-3336) diagnosed from 2011 to 2016 to conclude that the tumor histological grading, the TNM stage, the tumor size and the surgical excision of primary tumor lesions are independent risk factors influencing UCA 3-year and 5-year CSS; the C statistics after internal verification and time-interval external verification are respectively 0.89 (95% CI:0.88-0.91) and 0.88 (95% CI:0.83-0.94), which are both greater than 0.75; and the Brier score of the model is 0.10 (95% CI:0.10-0.11) and 0.10 (95% CI:0.00-0.38), both less than 0.25; the calibration slope of the calibration graph is 1.09 and is close to 1.0, and the predicted value and the actual observed value of the CSS in 3 years and 5 years show good consistency. The results show that the model has high Discrimination (Discrimination) and Calibration (Calibration) and can accurately predict the CSS of the cervical adenocarcinoma for 3 years and 5 years. The model is constructed and internally verified based on the SEER database in America, and has large sample amount and strong statistical efficiency.
The working principle of the invention is as follows: as shown in fig. 1, after obtaining the cervical adenocarcinoma prognosis model, storing clinical pathological parameters including histological grading, primary tumor stage, lymph node stage, distant metastasis stage, whether the primary lesion is operated or not and the maximum diameter of the primary tumor into a storage space corresponding to an array structure, and reading clinical pathological parameter data through a processor and inputting the clinical pathological parameter data into the established cervical adenocarcinoma prognosis model to obtain information displayed by a dynamic nomogram.
Compared with the prior art, as shown in fig. 1, the invention obtains the information displayed by the dynamic nomogram by establishing the cervical adenocarcinoma prognosis model, storing the clinical pathological parameters of the patient in the storage space corresponding to the array structure, reading the clinical pathological parameter data by the processor and inputting the clinical pathological parameter data into the established cervical adenocarcinoma prognosis model, and can directly obtain the key data and the trend of the survival probability, the tumor specific survival probability and the like of the patient, which are required by a doctor, without scale measurement to carry out numerical calculation compared with the existing static nomogram, thereby improving the accuracy and the efficiency of the decision and the prognosis of the doctor.
In further embodiments, as shown in fig. 2-5, the cervical adenocarcinoma prognosis method further includes inputting a predicted time point (e.g., 120 months in the figure) into the cervical adenocarcinoma prognosis model. By inputting the predicted time point into the cervical adenocarcinoma prognosis model, the tumor-specific survival probability of the patient at the time point in the future, the 95% confidence interval thereof, and the like can be obtained.
In a further embodiment, as shown in fig. 2, the dynamic nomogram comprises a Survival Plot (i.e., survivval Plot) that is a Plot of time versus probability of Survival for the patient. The survival curve chart dynamically shows the relationship between the survival probability (i.e., the estimated survival probability) and the time (follow-up time) of the patient, so that a doctor can more intuitively acquire the trend of the survival probability of the patient, and basis is provided for prognosis and decision making.
In a further embodiment, as shown in fig. 3, the dynamic nomogram comprises a probability of Survival map (i.e., Predicted survivval) with tumor-specific probability of Survival data and its confidence interval. The survival probability chart visually shows the tumor specific survival probability at a certain time point, is simple and efficient, and does not need to carry out complex scale calculation. For example, the confidence interval is 95%. Tumor specific survival probability data and its 95% confidence interval, i.e., 95% confidence interval for survivability.
In a further embodiment, as shown in fig. 4, the dynamic nomogram comprises a data list (i.e., Numerical Summary) comprising the patient's clinicopathological parameters, the patient's probability of survival, the tumor-specific probability of survival, and their confidence interval data at the predicted time point. Through the data list, the data such as clinical pathological parameters, the survival probability of patients, the tumor specific survival probability and the confidence interval thereof at a certain time point in the future can be intuitively acquired.
In a further embodiment, as shown in fig. 5, the cervical adenocarcinoma prognostic model is established by a COX proportional hazards model. In addition, the COX proportional hazards model includes: regression coefficients (i.e., coef), the positive and negative of which indicate protective and adverse factors, respectively, for the patient's prognosis; an index coefficient (i.e., exp (coef)), the magnitude of which reflects the degree of contribution of the corresponding variable to tumor-specific death; standard error of the regression coefficient (i.e., se (coef)); a statistical significance (i.e. a column labeled z) for assessing the statistical significance of the corresponding variable for tumor-specific survival; upper and lower limits of 95% confidence intervals for the index coefficients; a C statistic (i.e., Concordance) for characterizing a degree of discrimination of the cervical adenocarcinoma prognostic model; the standard deviation (i.e., se) of the C statistic; likelihood ratio tests (i.e., likelihood test), Wald test (i.e., Wald test), and time series tests (i.e., logrank test) for assessing the statistical significance of the cervical adenocarcinoma prognosis model. The cervical adenocarcinoma prognosis model is constructed by the COX proportional risk model, so that the influence of clinical pathological parameters on prognosis, the influence and the evaluation of statistical significance can be determined, and the method is more scientific.
In a further embodiment, as shown in fig. 5, the dynamic nomogram includes a model synopsis data list having the clinical pathology parameter as a variable, and function values of the regression coefficient, the index coefficient, the standard error of the regression coefficient, the statistically significant value, the C statistic, the standard difference of the C statistic, and the upper and lower limits of the 95% confidence interval of the index coefficient, and also includes statistically significant evaluation values of the likelihood ratio test, the wald test, and the time series test. By displaying the synopsis data list, doctors can acquire the influence of corresponding variables on the patient prognosis, the influence and the like, and the doctors can give more rational prognosis and decision on the variables with larger influence.
The above-mentioned embodiments only express the specific embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention.
Claims (8)
1. A method of prognosis of cervical adenocarcinoma, comprising the steps of:
acquiring clinical pathological parameters of a patient, establishing a corresponding array structure in a storage medium according to the number of the clinical pathological parameters, wherein the clinical pathological parameters comprise histological grading, primary tumor stage, lymph node stage, distant metastasis stage, whether a primary focus is operated or not and the maximum diameter of a primary tumor, and storing each clinical pathological parameter into a corresponding storage space in the array structure;
a space structure for storing a cervical adenocarcinoma prognosis model is further arranged in the storage medium, and the established cervical adenocarcinoma prognosis model is stored in the space structure;
reading each clinical pathological parameter in the array structure through a processor, inputting each clinical pathological parameter into the established cervical adenocarcinoma prognosis model, and displaying data information in a dynamic nomogram form;
and predicting according to the data information.
2. The method of claim 1, further comprising inputting the predicted time point into the cervical adenocarcinoma prognosis model.
3. The method of claim 1, wherein the dynamic nomogram comprises a survival graph, wherein the survival graph is a time-to-patient survival probability graph.
4. The method of claim 1, wherein the dynamic nomogram comprises a survival probability map having tumor-specific survival probability data and confidence intervals thereof.
5. The cervical adenocarcinoma prognosis method according to claim 1, wherein the dynamic nomogram comprises a data list comprising the clinicopathological parameter of the patient, the survival probability of the patient, the tumor-specific survival probability and the confidence interval data thereof at the predicted time point.
6. The method for the prognosis of cervical adenocarcinoma according to claim 1, wherein the cervical adenocarcinoma prognosis model is established by a COX proportional hazards model.
7. The method of claim 6, wherein the COX proportional risk model comprises:
regression coefficients, the positive and negative of which indicate protective and adverse factors, respectively, for the patient's prognosis;
an index coefficient, the magnitude of which reflects the degree of contribution of the corresponding variable to tumor-specific death;
standard error of the regression coefficient;
a statistical significance value for assessing the statistical significance of the degree of contribution of the respective variable to tumor-specific survival;
upper and lower limits of 95% confidence intervals for the index coefficients;
c statistic used for characterizing the discrimination of the cervical adenocarcinoma prognosis model;
a standard deviation of the C statistic;
a likelihood ratio test, a Wald test and a time series test for assessing the statistical significance of the cervical adenocarcinoma prognostic model.
8. The cervical adenocarcinoma prognosis method according to claim 7, wherein said dynamic nomogram comprises a model synopsis data list having said clinical pathology parameter as a variable, said regression coefficient, an index coefficient, a standard deviation of said regression coefficient, a statistically significant value, a C statistic, a standard deviation of said C statistic, and upper and lower limits of 95% confidence intervals of said index coefficient as function values, and statistically significant evaluation values of said likelihood ratio test, Wald test and time series test.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110897414.9A CN113658698A (en) | 2021-08-05 | 2021-08-05 | Cervical adenocarcinoma prognosis method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110897414.9A CN113658698A (en) | 2021-08-05 | 2021-08-05 | Cervical adenocarcinoma prognosis method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113658698A true CN113658698A (en) | 2021-11-16 |
Family
ID=78478522
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110897414.9A Pending CN113658698A (en) | 2021-08-05 | 2021-08-05 | Cervical adenocarcinoma prognosis method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113658698A (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111640518A (en) * | 2020-06-02 | 2020-09-08 | 山东大学齐鲁医院 | Cervical cancer postoperative survival prediction method, system, equipment and medium |
| CN112908467A (en) * | 2021-01-19 | 2021-06-04 | 武汉大学 | Multivariable dynamic nomogram prediction model and application thereof |
-
2021
- 2021-08-05 CN CN202110897414.9A patent/CN113658698A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111640518A (en) * | 2020-06-02 | 2020-09-08 | 山东大学齐鲁医院 | Cervical cancer postoperative survival prediction method, system, equipment and medium |
| CN112908467A (en) * | 2021-01-19 | 2021-06-04 | 武汉大学 | Multivariable dynamic nomogram prediction model and application thereof |
Non-Patent Citations (2)
| Title |
|---|
| 唐知己: "颅脑损伤患者行I期去骨瓣减压术不良预后的早期预测模型的构建及验证", 《中国博士学位论文全文数据库医药卫生科技辑》, no. 6, pages 066 - 28 * |
| 欧燕兰 等: "宫颈癌患者预后预测列线图的建立", 《中华肿瘤防治杂志》, vol. 22, no. 16, pages 1303 - 1307 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Sommariva et al. | Prognostic value of the cell cycle progression score in patients with prostate cancer: a systematic review and meta-analysis | |
| Huang et al. | Gleason score 3+ 4= 7 prostate cancer with minimal quantity of gleason pattern 4 on needle biopsy is associated with low-risk tumor in radical prostatectomy specimen | |
| Fletcher et al. | Contemporary national trends in prostate cancer risk profile at diagnosis | |
| Tosoian et al. | Active surveillance of prostate cancer: use, outcomes, imaging, and diagnostic tools | |
| Bobdey et al. | A nomogram based prognostic score that is superior to conventional TNM staging in predicting outcome of surgically treated T4 buccal mucosa cancer: time to think beyond TNM | |
| Cao et al. | Incidence and survival trends for gastric neuroendocrine neoplasms: an analysis of 3523 patients in the SEER database | |
| Li et al. | Machine learning–based computational models derived from large-scale radiographic-radiomic images can help predict adverse histopathological status of gastric cancer | |
| Canfield et al. | A guide for clinicians in the evaluation of emerging molecular diagnostics for newly diagnosed prostate cancer | |
| Bangma et al. | Defining and predicting indolent and low risk prostate cancer | |
| Jalali et al. | A risk calculator to inform the need for a prostate biopsy: a rapid access clinic cohort | |
| Chao et al. | Re-excision or “wait and watch”—a prediction model in breast phyllodes tumors after surgery | |
| Finne et al. | The Finnish trial of prostate cancer screening: where are we now? | |
| Machens et al. | Prediction of mediastinal lymph node metastasis in papillary thyroid cancer | |
| Inoue et al. | Combining longitudinal studies of PSA | |
| Wei et al. | Predicting the recurrence-free survival of phyllodes tumor of the breast: a nomogram based on clinicopathology features, treatment, and surgical margin | |
| Segnan et al. | Estimate of false-positive breast cancer diagnoses from accuracy studies: a systematic review | |
| CN113658698A (en) | Cervical adenocarcinoma prognosis method | |
| Wang et al. | Integrating DOI in T classification improves the predictive performance of laryngeal cancer staging | |
| Zhang et al. | Development of a nomogram for preoperative prediction of lymph node metastasis in non-small cell lung cancer: a SEER-based study | |
| Zhang et al. | A retrospective analysis of the diagnostic accuracy and technical quality of frozen sections in detecting hepatobiliary lesions | |
| Hu et al. | A preoperative nomogram predicting the pseudocapsule status in localized renal cell carcinoma | |
| Salcedo-Hernández et al. | The usefulness of intraoperative consultation for the diagnosis of borderline ovarian tumors | |
| Moltajaei et al. | Clinicopathological and prognostic value of Ki-67 expression in oral malignant melanoma: A systematic review and meta-analysis | |
| Chang et al. | Age and cystic size are associated with clinical impact of endoscopic ultrasonography-guided fine-needle aspiration on the management of pancreatic cystic neoplasms | |
| Wu et al. | Prediction model of adnexal masses with complex ultrasound morphology |
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 |