CN117976212A - Method, system, equipment and medium for acquiring osteosarcoma prognosis risk factors - Google Patents
Method, system, equipment and medium for acquiring osteosarcoma prognosis risk factors Download PDFInfo
- Publication number
- CN117976212A CN117976212A CN202410143542.8A CN202410143542A CN117976212A CN 117976212 A CN117976212 A CN 117976212A CN 202410143542 A CN202410143542 A CN 202410143542A CN 117976212 A CN117976212 A CN 117976212A
- Authority
- CN
- China
- Prior art keywords
- osteosarcoma
- adolescent
- factors
- risk factors
- survival
- 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
- 201000008968 osteosarcoma Diseases 0.000 title claims abstract description 107
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000004393 prognosis Methods 0.000 title claims abstract description 39
- 230000004083 survival effect Effects 0.000 claims abstract description 51
- 206010028980 Neoplasm Diseases 0.000 claims abstract description 46
- 208000009458 Carcinoma in Situ Diseases 0.000 claims abstract description 23
- 201000004933 in situ carcinoma Diseases 0.000 claims abstract description 23
- 238000011156 evaluation Methods 0.000 claims abstract description 6
- 238000004458 analytical method Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 15
- 238000007619 statistical method Methods 0.000 claims description 14
- 238000001356 surgical procedure Methods 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 14
- 238000010200 validation analysis Methods 0.000 claims description 13
- 230000007774 longterm Effects 0.000 claims description 12
- 206010027476 Metastases Diseases 0.000 claims description 10
- 230000009401 metastasis Effects 0.000 claims description 10
- 238000002512 chemotherapy Methods 0.000 claims description 7
- 238000001959 radiotherapy Methods 0.000 claims description 7
- 238000012502 risk assessment Methods 0.000 claims description 7
- 210000000988 bone and bone Anatomy 0.000 claims description 6
- 210000003557 bones of lower extremity Anatomy 0.000 claims description 6
- 238000012314 multivariate regression analysis Methods 0.000 claims description 6
- 238000002266 amputation Methods 0.000 claims description 5
- 238000007405 data analysis Methods 0.000 claims description 4
- 230000002596 correlated effect Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 3
- 201000010099 disease Diseases 0.000 abstract description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 abstract description 2
- 238000011160 research Methods 0.000 abstract description 2
- 238000007418 data mining Methods 0.000 abstract 1
- 210000003414 extremity Anatomy 0.000 description 5
- 238000011282 treatment Methods 0.000 description 4
- 238000002591 computed tomography Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 201000011510 cancer Diseases 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 238000011065 in-situ storage Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 206010005949 Bone cancer Diseases 0.000 description 1
- 101001121408 Homo sapiens L-amino-acid oxidase Proteins 0.000 description 1
- 102100026388 L-amino-acid oxidase Human genes 0.000 description 1
- 101100012902 Saccharomyces cerevisiae (strain ATCC 204508 / S288c) FIG2 gene Proteins 0.000 description 1
- 238000009098 adjuvant therapy Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 230000000875 corresponding effect Effects 0.000 description 1
- 238000002405 diagnostic procedure Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 230000009554 growth spurt Effects 0.000 description 1
- 210000003127 knee Anatomy 0.000 description 1
- 238000002595 magnetic resonance imaging Methods 0.000 description 1
- 230000008506 pathogenesis Effects 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 238000012106 screening analysis Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000011272 standard treatment Methods 0.000 description 1
- 210000004881 tumor cell Anatomy 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/30—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
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Measuring Or Testing Involving Enzymes Or Micro-Organisms (AREA)
Abstract
本发明为一种骨肉瘤预后风险因素的获取方法、系统、设备、介质，涉及生物技术领域，创建的一个公共数据库和研究资源的数据库运用数据挖掘技术，从青少年群体骨肉瘤患者的临床特征中找到以下预示该疾病临床生存率的智能化风险因素：性别、手术方式、原位癌发病位置、seer肿瘤分期、肿瘤数量。根据风险因素的预测价值建立青少年骨肉瘤预后生存的预测模型。有助于针对性、精确化评估青少年骨肉瘤患者的预后评估，且操作简单、结果直观，将大量临床数据整合成预测模型，方便评估青少年骨肉瘤患者的预后生存。
The present invention is a method, system, device, and medium for obtaining prognostic risk factors for osteosarcoma, which relates to the field of biotechnology. A public database and a database of research resources are created, and data mining technology is used to find the following intelligent risk factors that predict the clinical survival rate of the disease from the clinical characteristics of osteosarcoma patients in the adolescent group: gender, surgical method, location of carcinoma in situ, seer tumor stage, and number of tumors. A prediction model for the prognosis and survival of adolescent osteosarcoma is established based on the predictive value of risk factors. It is helpful to conduct targeted and accurate prognosis evaluation of adolescent osteosarcoma patients, and the operation is simple and the results are intuitive. A large amount of clinical data is integrated into a prediction model, which is convenient for evaluating the prognosis and survival of adolescent osteosarcoma patients.
Description
技术领域Technical Field
本发明涉及生物医学技术领域，尤其涉及一种骨肉瘤预后风险因素的获取方法、系统、设备、介质。The present invention relates to the field of biomedical technology, and in particular to a method, system, device and medium for acquiring prognostic risk factors of osteosarcoma.
背景技术Background technique
骨肉瘤(Osteosarcoma)是一种主要影响儿童和青少年的恶性骨肿瘤。尽管如此，它在整体癌症中仍然相对罕见。全球范围内，骨肉瘤的年发病率大约在4.4例/百万儿童和青少年中。骨肉瘤主要影响年龄在10至20岁的青少年，尤其是在他们的生长高峰期间。这种肿瘤在儿童中较少见，而在成年人中更为罕见。它通常发生在快速生长的骨骼区域，如膝盖附近的长骨。骨肉瘤的发病机制复杂，涉及多种遗传和环境因素。青少年骨肉瘤的预后取决于多种因素，包括肿瘤的大小、位置、是否已经转移，以及患者接受的治疗方式等。Osteosarcoma is a malignant bone tumor that mainly affects children and adolescents. Despite this, it is still relatively rare among cancers overall. Globally, the annual incidence of osteosarcoma is approximately 4.4 cases per million children and adolescents. Osteosarcoma mainly affects adolescents between the ages of 10 and 20, especially during their growth spurt. This tumor is less common in children and even rarer in adults. It usually occurs in areas of rapidly growing bones, such as the long bones near the knee. The pathogenesis of osteosarcoma is complex and involves multiple genetic and environmental factors. The prognosis for osteosarcoma in adolescents depends on many factors, including the size of the tumor, its location, whether it has metastasized, and the type of treatment the patient receives.
骨肉瘤的诊断通常需要结合病史、体检和一系列检查，包括X光、磁共振成像(MRI)、计算机断层扫描(CT)和生物镜检查。生物镜检查，即从疑似区域取样并在显微镜下检查，是确诊骨肉瘤的关键步骤。而在治疗上，手术是治疗骨肉瘤的主要方法之一。手术的目标是完全切除肿瘤并保留尽可能多的功能。在过去，这通常意味着截肢，但随着技术的进步，越来越多的患者可以接受肢体保育手术。化疗在骨肉瘤的治疗中扮演着关键角色。它通常在手术前后进行，旨在缩小肿瘤、杀死肿瘤细胞，以及消灭可能已经扩散到身体其他部分的癌细胞。放疗在骨肉瘤的标准治疗中不是主要手段，但在某些情况下，它可以作为辅助治疗手段。尽管诊断手段和治疗方法不断进步，但晚期的骨肉瘤预后仍然较差，且没有青少年骨肉瘤的针对性预后预测工具。The diagnosis of osteosarcoma usually requires a combination of medical history, physical examination, and a series of tests, including X-rays, magnetic resonance imaging (MRI), computed tomography (CT), and bioscopy. Bioscopy, which involves taking a sample from the suspected area and examining it under a microscope, is a key step in confirming the diagnosis of osteosarcoma. In terms of treatment, surgery is one of the main methods for treating osteosarcoma. The goal of surgery is to completely remove the tumor and preserve as much function as possible. In the past, this often meant amputation, but with advances in technology, more and more patients can undergo limb-preserving surgery. Chemotherapy plays a key role in the treatment of osteosarcoma. It is usually given before and after surgery and is designed to shrink the tumor, kill tumor cells, and eliminate cancer cells that may have spread to other parts of the body. Radiotherapy is not a mainstay in the standard treatment of osteosarcoma, but in some cases, it can be used as an adjuvant therapy. Despite advances in diagnostic methods and treatments, the prognosis of advanced osteosarcoma remains poor, and there are no targeted prognostic prediction tools for adolescent osteosarcoma.
以往没有针对青少年骨肉患者的预后的数据进行整理，无法从现有的大量数据中构建关于青少年骨肉瘤预后预测模型的建立，因为该病种较为罕见，其个性化的预测模型以及对应的工具没有做到落实，而青少年时期是骨肉瘤好发的一个高峰时期，以往有骨肉瘤患者总体的预测模型或是四肢骨肉瘤的预测工具，但是限于青少年使用的骨肉瘤预后预测工具，却没有出现。于是，在青少年群体中找到与其预后生存显著相关的因素，并从这些因素入手，解决目前临床针对青少年骨肉瘤预测工具的欠缺问题，优化预测精准度。In the past, there was no data on the prognosis of adolescent osteosarcoma patients, and it was impossible to build a prognosis prediction model for adolescent osteosarcoma from the existing large amount of data. Because the disease is relatively rare, its personalized prediction model and corresponding tools have not been implemented. Adolescence is a peak period for the occurrence of osteosarcoma. In the past, there were overall prediction models for osteosarcoma patients or prediction tools for limb osteosarcoma, but there were no osteosarcoma prognosis prediction tools limited to adolescents. Therefore, we found factors that are significantly related to their prognosis and survival in the adolescent group, and started from these factors to solve the current lack of clinical prediction tools for adolescent osteosarcoma and optimize the prediction accuracy.
发明内容Summary of the invention
为了克服上述现有技术没有青少年骨肉患者的预后生存预测工具的缺点，本发明的主要目的在于提供一种关于青少年骨肉瘤预后生存的临床预测模型及其构建方法。In order to overcome the disadvantage of the prior art that there is no prognosis and survival prediction tool for adolescent osteosarcoma patients, the main purpose of the present invention is to provide a clinical prediction model for the prognosis and survival of adolescent osteosarcoma and a construction method thereof.
为达到上述目的，本发明采用以下技术方案，一种骨肉瘤预后风险因素的获取方法，包括以下步骤：To achieve the above object, the present invention adopts the following technical scheme, a method for obtaining prognostic risk factors for osteosarcoma, comprising the following steps:
获取青少年骨肉瘤患者预后的临床数据，通过相关因素统计学分析，获取青少年骨肉瘤患者长期生存情况的相关因素；To obtain clinical data on the prognosis of adolescent osteosarcoma patients and obtain the relevant factors for the long-term survival of adolescent osteosarcoma patients through statistical analysis of relevant factors;
将临床数据划分为训练组与验证组，对训练组的青少年骨肉瘤患者长期生存情况相关的因素进行多因素回归分析，确认对青少年骨肉瘤患者预后存在影响的风险因素。The clinical data were divided into a training group and a validation group. Multivariate regression analysis was performed on factors related to the long-term survival of adolescent osteosarcoma patients in the training group to identify risk factors that affect the prognosis of adolescent osteosarcoma patients.
所述通过相关因素统计学分析中，通过单因素Cox分析中，筛选出显著影响青少年骨肉瘤生存的风险评价指标；The risk evaluation indexes that significantly affect the survival of adolescent osteosarcoma were screened out through statistical analysis of related factors and univariate Cox analysis;
将单因素cox分析筛选出的与青少年骨肉瘤生存的显著相关的风险评价指标加入多因素cox模型，采用多因素cox分析，通过风险比将各因素划分为危险因素、中间因素和无关因素，将危险因素设为青少年骨肉瘤生存情况相关的因素，通过病例数据的统计分析及模型拟合，确定影响青少年骨肉瘤生存的危险因素。The risk assessment indicators that were significantly correlated with the survival of adolescent osteosarcoma screened out by univariate cox analysis were added to the multivariate cox model. Multivariate cox analysis was used to divide each factor into risk factors, intermediate factors and irrelevant factors through hazard ratio. Risk factors were set as factors related to the survival of adolescent osteosarcoma. Through statistical analysis of case data and model fitting, the risk factors affecting the survival of adolescent osteosarcoma were determined.
所述风险评价指标包括性别、手术方式、是否化疗、是否放疗、原位癌发病位置seer分期、Grade分级、肿瘤数量、肿瘤大小。The risk assessment indicators include gender, surgical method, whether chemotherapy is used, whether radiotherapy is used, the location of carcinoma in situ, seer stage, Grade, number of tumors, and tumor size.
所述危险因素包括性别、手术方式、原位癌位置、seer肿瘤分期、肿瘤数量。The risk factors include gender, surgical method, location of carcinoma in situ, seer tumor stage, and number of tumors.
所述采用多因素cox分析，得到的五个独立危险因素的OR：性别、手术方式、保肢手术、原位癌位置、seer肿瘤分期、肿瘤数量。The multivariate cox analysis was used to obtain the ORs of five independent risk factors: gender, surgical method, limb-salvage surgery, location of carcinoma in situ, seer tumor stage, and number of tumors.
所述对构建青少年骨肉瘤患者预后预测模型进行采样矫正，并根据验证组的临床数据对青少年骨肉瘤患者预后预测模型进行验证，The prognosis prediction model for adolescent osteosarcoma patients is constructed by sampling and correction, and the prognosis prediction model for adolescent osteosarcoma patients is verified based on the clinical data of the validation group.
采用Lasso回归从危险因素中筛选预测因子，是以性别作为第一预测因子，手术方式作为第二预测因子、原位癌位置作为第三预测因子、seer分期作为第四预测因子和肿瘤数量作为第五预测因子。Lasso regression was used to screen predictive factors from risk factors, with gender as the first predictor, surgical method as the second predictor, carcinoma in situ location as the third predictor, seer stage as the fourth predictor, and tumor number as the fifth predictor.
所述第一预测因子的性别女或男分别对应第一因子分值0分或21分；所述第二预测因子的手术方式截肢、不手术、保肢分别对应第二因子分值20分或77分或0分；所述第三预测因子原位癌位置中轴骨和四肢骨分别对应第三因子分值30或0分；所述第四预测因子seer分期远处转移、不发生转移、近处扩散分别对应第四因子分值100或0分或39分；所述第五预测因子的肿瘤数量等于1个、大于1个分别对应第五因子分值0分或27分；根据以上测试因子的分值分别计算骨肉瘤青少年患者群体1年、3年、5年的生存概率，并绘制其Nomogram图，计算公式为：The gender of the first predictor, female or male, corresponds to a first factor score of 0 or 21 points, respectively; the surgical method of the second predictor, amputation, no surgery, and limb salvage, corresponds to a second factor score of 20 or 77 or 0 points, respectively; the third predictor, the location of the carcinoma in situ, the axial bones and the limb bones, corresponds to a third factor score of 30 or 0 points, respectively; the fourth predictor, seer stage, distant metastasis, no metastasis, and near spread, corresponds to a fourth factor score of 100 or 0 or 39 points, respectively; the fifth predictor, the number of tumors equal to 1 and greater than 1, corresponds to a fifth factor score of 0 or 27 points, respectively; according to the scores of the above test factors, the 1-year, 3-year, and 5-year survival probabilities of the adolescent patient group with osteosarcoma are calculated, and their Nomograms are drawn, and the calculation formula is:
1年的预测生存概率＝0*points^3+-2e-05*points^2+0.00255*points+0.82566；1-year predicted survival probability = 0*points^3+-2e-05*points^2+0.00255*points+0.82566;
3年的预测生存概率＝0*points^3+-4e-05*points^2+0.00075*points+0.8944；3-year predicted survival probability = 0*points^3+-4e-05*points^2+0.00075*points+0.8944;
5年的预测生存概率＝0*points^3+-3e-05*points^2+-9e-04*points+0.8922。The predicted survival probability in 5 years = 0*points^3+-3e-05*points^2+-9e-04*points+0.8922.
一种骨肉瘤预后风险因素的获取系统，包括：A system for obtaining prognostic risk factors for osteosarcoma, comprising:
数据处理模块，获取青少年骨肉瘤患者预后的临床数据，通过相关因素统计学分析，获取青少年骨肉瘤患者长期生存情况的相关因素；The data processing module obtains clinical data on the prognosis of adolescent osteosarcoma patients and obtains the relevant factors for the long-term survival of adolescent osteosarcoma patients through statistical analysis of relevant factors;
数据分析模块，将临床数据划分为训练组与验证组，对训练组的青少年骨肉瘤患者长期生存情况相关的因素进行多因素回归分析，确认对青少年骨肉瘤患者预后存在影响的风险因素；The data analysis module divides the clinical data into a training group and a validation group, conducts a multivariate regression analysis on the factors related to the long-term survival of adolescent osteosarcoma patients in the training group, and identifies the risk factors that affect the prognosis of adolescent osteosarcoma patients;
一种计算机设备，包括：A computer device comprising:
至少一个存储器；at least one memory;
至少一个处理器；at least one processor;
至少一个计算机程序；at least one computer program;
所述至少一个计算机程序被存储在所述至少一个存储器中，所述至少一个处理器执行所述至少一个计算机程序以实现：如一种骨肉瘤预后预测模型的建立系统。The at least one computer program is stored in the at least one memory, and the at least one processor executes the at least one computer program to implement: for example, a system for establishing a prognosis prediction model for osteosarcoma.
一种计算机可读介质，所述计算机可读介质存储有计算机程序，所述计算机程序用于使计算机执行：如一种骨肉瘤预后风险因素的获取方法。A computer-readable medium stores a computer program, wherein the computer program is used to enable a computer to execute: for example, a method for obtaining prognostic risk factors for osteosarcoma.
与现有技术相比较，本发明的有益效果为：Compared with the prior art, the beneficial effects of the present invention are:
本发明提供一种对于患者临床数据整理，建立了对于青少年骨肉瘤预后预测模型的方法，可以根据预测模型及其Nomogram图为临床医生评估骨肉瘤青少年患者提供了一种更为简单有效的方式，本发明模型需要的参数都可以通过简单的查体和急诊CT快速获取，用于骨肉瘤青少年患者预后预测有较好的敏感性和特异性。本发明可以在青少年患者因骨肉瘤入院后，完善基础检查的条件下即可快速进行评估，方法简便经济。The present invention provides a method for collating clinical data of patients and establishing a prognosis prediction model for adolescent osteosarcoma. The prediction model and its Nomogram diagram provide a simpler and more effective way for clinicians to evaluate adolescent patients with osteosarcoma. The parameters required by the model of the present invention can be quickly obtained through simple physical examination and emergency CT, and it has good sensitivity and specificity for the prognosis prediction of adolescent patients with osteosarcoma. The present invention can quickly evaluate adolescent patients after they are admitted to the hospital for osteosarcoma under the condition of completing basic examinations. The method is simple and economical.
附图说明BRIEF DESCRIPTION OF THE DRAWINGS
图1是青少年骨肉瘤患者临床数据资料通过多因素cox筛选分析得到危险因素结果的森林图，其中显示了危险因素的OR值和95％CI；FIG1 is a forest diagram of the risk factor results obtained through multivariate cox screening analysis of clinical data of adolescent osteosarcoma patients, which shows the OR value and 95% CI of the risk factors;
图2是本发明青少年骨肉瘤患者临床预测模型Nomogram图；FIG2 is a Nomogram of the clinical prediction model for adolescent osteosarcoma patients according to the present invention;
图3是本发明的流程结构示意图。FIG. 3 is a schematic diagram of the process structure of the present invention.
具体实施方式Detailed ways
下面结合附图和实施方式对本发明作进一步说明。The present invention will be further described below in conjunction with the accompanying drawings and implementation modes.
实施例1：Embodiment 1:
参阅图1-3，一种骨肉瘤预后风险因素的获取方法、系统、设备、介质，包括以下步骤：Referring to Figures 1-3, a method, system, device, and medium for obtaining prognostic risk factors for osteosarcoma include the following steps:
获取青少年骨肉瘤患者预后的临床数据，通过相关因素统计学分析，获取青少年骨肉瘤患者长期生存情况的相关因素；To obtain clinical data on the prognosis of adolescent osteosarcoma patients and obtain the relevant factors for the long-term survival of adolescent osteosarcoma patients through statistical analysis of relevant factors;
将临床数据划分为训练组与验证组，对训练组的青少年骨肉瘤患者长期生存情况相关的因素进行多因素回归分析，确认对青少年骨肉瘤患者预后存在影响的风险因素；The clinical data were divided into a training group and a validation group. Multivariate regression analysis was performed on the factors related to the long-term survival of adolescent osteosarcoma patients in the training group to identify the risk factors that affect the prognosis of adolescent osteosarcoma patients.
在本实施例中，将确认的风险因素按比例转换为分数后作为预测因子，构建青少年骨肉瘤患者预后预测模型，并根据验证组的临床数据对青少年骨肉瘤患者预后预测模型进行验证。其中，对构建青少年骨肉瘤患者预后预测模型进行采样矫正，并根据验证组的临床数据对青少年骨肉瘤患者预后预测模型进行验证。In this embodiment, the confirmed risk factors are converted into scores in proportion as predictive factors to construct a prognosis prediction model for adolescent osteosarcoma patients, and the prognosis prediction model for adolescent osteosarcoma patients is verified based on the clinical data of the validation group. Among them, sampling correction is performed on the construction of the prognosis prediction model for adolescent osteosarcoma patients, and the prognosis prediction model for adolescent osteosarcoma patients is verified based on the clinical data of the validation group.
更为具体的是通过相关因素统计学分析中，通过单因素Cox分析中，筛选出显著影响青少年骨肉瘤生存的风险评价指标；More specifically, through statistical analysis of related factors and univariate Cox analysis, we screened out risk assessment indicators that significantly affect the survival of adolescent osteosarcoma;
将单因素cox分析筛选出的与青少年骨肉瘤生存的显著相关的风险评价指标加入多因素cox模型，采用多因素cox分析，通过风险比将各因素划分为危险因素、中间因素和无关因素，将危险因素设为青少年骨肉瘤生存情况相关的因素，通过病例数据的统计分析及模型拟合，确定影响青少年骨肉瘤生存的危险因素。The risk assessment indicators that were significantly correlated with the survival of adolescent osteosarcoma screened out by univariate cox analysis were added to the multivariate cox model. Multivariate cox analysis was used to divide each factor into risk factors, intermediate factors and irrelevant factors through hazard ratio. Risk factors were set as factors related to the survival of adolescent osteosarcoma. Through statistical analysis of case data and model fitting, the risk factors affecting the survival of adolescent osteosarcoma were determined.
风险评价指标包括性别、手术方式、是否化疗、是否放疗、原位癌发病位置seer分期、Grade分级、肿瘤数量、肿瘤大小。Risk assessment indicators include gender, surgical method, chemotherapy, radiotherapy, location of carcinoma in situ, Seer stage, Grade, number of tumors, and tumor size.
其中的危险因素包括性别、手术方式、原位癌位置、seer肿瘤分期、肿瘤数量。The risk factors include gender, surgical method, location of carcinoma in situ, seer tumor stage, and number of tumors.
采用多因素cox分析，得到的五个独立危险因素的OR：性别(男性危险比HR1.38495％CI 1.086-1.764)、手术方式(不手术危险比HR 2.384，95％CI 1.61-3.692；保肢手术危险比HR 0.733，95％CI 0.577-0.965)、原位癌位置(四肢骨危险比HR 0.629，95％CI0.433-0.915)、seer肿瘤分期(原位危险比HR 0.208，95％CI 0.148-0.293；近处转移危险比HR 0.386，95％CI 0.297-0.500)、肿瘤数量(肿瘤数量＝1危险比HR 0.655，95％CI0.433-0.967)。Multivariate Cox analysis was used to obtain the ORs of five independent risk factors: sex (hazard ratio HR for males 1.384, 95% CI 1.086-1.764), surgical method (hazard ratio HR for no surgery 2.384, 95% CI 1.61-3.692; hazard ratio HR for limb-sparing surgery 0.733, 95% CI 0.577-0.965), location of carcinoma in situ (hazard ratio HR for limb bones 0.629, 95% CI 0.433-0.915), seer tumor stage (hazard ratio HR for in situ 0.208, 95% CI 0.148-0.293; hazard ratio HR for nearby metastasis 0.386, 95% CI 0.297-0.500), and number of tumors (hazard ratio HR for tumor number = 1 0.655, 95% CI 0.433-0.967).
采用Lasso回归从危险因素中筛选预测因子，是以性别作为第一预测因子，手术方式作为第二预测因子、原位癌位置作为第三预测因子、seer分期作为第四预测因子和肿瘤数量作为第五预测因子。Lasso regression was used to screen predictive factors from risk factors, with gender as the first predictor, surgical method as the second predictor, carcinoma in situ location as the third predictor, seer stage as the fourth predictor, and tumor number as the fifth predictor.
所述第一预测因子的性别女或男分别对应第一因子分值0分或21分；所述第二预测因子的手术方式截肢、不手术、保肢分别对应第二因子分值20分或77分或0分；所述第三预测因子原位癌位置中轴骨和四肢骨分别对应第三因子分值30或0分；所述第四预测因子seer分期远处转移、不发生转移、近处扩散分别对应第四因子分值100或0分或39分；所述第五预测因子的肿瘤数量等于1个、大于1个分别对应第五因子分值0分或27分；根据以上测试因子的分值分别计算骨肉瘤青少年患者群体1年、3年、5年的生存概率，并绘制其Nomogram图，计算公式为：The gender of the first predictor, female or male, corresponds to a first factor score of 0 or 21 points, respectively; the surgical method of the second predictor, amputation, no surgery, and limb salvage, corresponds to a second factor score of 20 or 77 or 0 points, respectively; the third predictor, the location of carcinoma in situ, axial bones and limb bones, corresponds to a third factor score of 30 or 0 points, respectively; the fourth predictor, seer stage, distant metastasis, no metastasis, and near spread, corresponds to a fourth factor score of 100 or 0 or 39 points, respectively; the fifth predictor, the number of tumors equal to 1 and greater than 1, corresponds to a fifth factor score of 0 or 27 points, respectively; according to the scores of the above test factors, the 1-year, 3-year, and 5-year survival probabilities of the adolescent patient group with osteosarcoma are calculated, and their Nomograms are drawn, and the calculation formula is:
1年的预测生存概率＝0*points^3+-2e-05*points^2+0.00255*points+0.82566；1-year predicted survival probability = 0*points^3+-2e-05*points^2+0.00255*points+0.82566;
3年的预测生存概率＝0*points^3+-4e-05*points^2+0.00075*points+0.8944；3-year predicted survival probability = 0*points^3+-4e-05*points^2+0.00075*points+0.8944;
5年的预测生存概率＝0*points^3+-3e-05*points^2+-9e-04*points+0.8922。The predicted survival probability in 5 years = 0*points^3+-3e-05*points^2+-9e-04*points+0.8922.
一种骨肉瘤预后风险因素的获取系统，包括：A system for obtaining prognostic risk factors for osteosarcoma, comprising:
数据处理模块，获取青少年骨肉瘤患者预后的临床数据，通过相关因素统计学分析，获取青少年骨肉瘤患者长期生存情况的相关因素；The data processing module obtains clinical data on the prognosis of adolescent osteosarcoma patients and obtains the relevant factors for the long-term survival of adolescent osteosarcoma patients through statistical analysis of relevant factors;
数据分析模块，将临床数据划分为训练组与验证组，对训练组的青少年骨肉瘤患者长期生存情况相关的因素进行多因素回归分析，确认对青少年骨肉瘤患者预后存在影响的风险因素；The data analysis module divides the clinical data into a training group and a validation group, conducts a multivariate regression analysis on the factors related to the long-term survival of adolescent osteosarcoma patients in the training group, and identifies the risk factors that affect the prognosis of adolescent osteosarcoma patients;
当用于实际临床数据分析的时候，还可以有模型建立模块，将确认的风险因素按比例转换为分数后作为预测因子，构建青少年骨肉瘤患者预后预测模型，并根据验证组的临床数据对青少年骨肉瘤患者预后预测模型进行验证。When used for actual clinical data analysis, there can also be a model building module to convert the confirmed risk factors into scores in proportion as predictive factors, build a prognosis prediction model for adolescent osteosarcoma patients, and verify the prognosis prediction model for adolescent osteosarcoma patients based on the clinical data of the validation group.
一种计算机设备，包括：A computer device comprising:
至少一个存储器；at least one memory;
至少一个处理器；at least one processor;
至少一个计算机程序；at least one computer program;
所述至少一个计算机程序被存储在所述至少一个存储器中，所述至少一个处理器执行所述至少一个计算机程序以实现：如一种骨肉瘤预后预测模型的建立系统。The at least one computer program is stored in the at least one memory, and the at least one processor executes the at least one computer program to implement: for example, a system for establishing a prognosis prediction model for osteosarcoma.
一种计算机可读介质，A computer readable medium,
所述计算机可读介质存储有计算机程序，所述计算机程序用于使计算机执行：The computer readable medium stores a computer program, and the computer program is used to cause a computer to execute:
如一种骨肉瘤预后风险因素的获取方法。Such as a method for obtaining prognostic risk factors for osteosarcoma.
实施例2Example 2
参阅图1-3，在实施例1的基础上，在该模型构建的研究中使用和分析的数据可在美国国家癌症研究所的监测、流行病学和最终结果(SEER)数据库(http://seer.cancer.gov)中免费下载获得。无需通过伦理委员会批准，无利益风险冲突。Referring to Figures 1-3, based on Example 1, the data used and analyzed in the study of model construction can be downloaded free of charge from the Surveillance, Epidemiology, and End Results (SEER) database of the National Cancer Institute of the United States (http://seer.cancer.gov). No ethics committee approval is required, and there is no conflict of interest risk.
收集青少年骨肉瘤患者，通过过滤临床信息数据不明的患者，最终纳入1116例。纳入的所研究的自变量数据有：患者的性别、种族、手术方式、是否化疗、是否放疗、原位癌发病位置、seer分期、Grade分级、肿瘤数量、肿瘤大小。并且收集患者生存状态信息和生存时间信息。根据7:3的比例将1116名患者划分为训练组和验证组。训练组用于构建模型，验证组用于验证。Adolescent osteosarcoma patients were collected, and 1116 cases were finally included by filtering patients with unclear clinical information data. The independent variable data included in the study were: patient's gender, race, surgical method, chemotherapy, radiotherapy, location of carcinoma in situ, seer stage, grade, number of tumors, and tumor size. The patient's survival status and survival time information were also collected. The 1116 patients were divided into a training group and a validation group according to a ratio of 7:3. The training group was used to build the model, and the validation group was used for validation.
在seer数据库中下载2004-2015年青少年骨肉瘤人群的临床数据，收集构建模型基础的研究群体的基本资料，其中包括性别、种族、手术方式、是否化疗、是否放疗、原位癌发病位置、seer分期、Grade分级、肿瘤数量、肿瘤大小。Clinical data of adolescent osteosarcoma from 2004 to 2015 were downloaded from the SEER database, and basic information of the research population on which the model was based was collected, including gender, race, surgical method, chemotherapy, radiotherapy, location of carcinoma in situ, SEER stage, Grade, number of tumors, and tumor size.
对上述收集的资料首先进行数据过滤，筛掉数据信息不明确或缺失的患者，随后对完成上述步骤后的数据，进行单因素cox统计学分析，筛选出显著影响青少年四肢骨肉瘤生存的风险评价指标，所述的评价指标包括性别、手术方式、是否化疗、是否放疗、原位癌发病位置seer分期、Grade分级、肿瘤数量、肿瘤大小。The collected data were first filtered to screen out patients with unclear or missing data information. Then, the data after completing the above steps were subjected to univariate cox statistical analysis to screen out risk evaluation indicators that significantly affect the survival of adolescent limb osteosarcoma. The evaluation indicators included gender, surgical method, chemotherapy, radiotherapy, location of carcinoma in situ, seer stage, Grade, number of tumors, and tumor size.
将单因素cox分析筛选出的与青少年骨肉瘤生存的显著相关的风险评价指标加入多因素cox模型，采用多因素cox分析，通过病例数据的统计分析及模型拟合，确定影响青少年骨肉瘤生存的危险因素。所述的危险因素标志物包括性别、手术方式、原位癌位置、seer肿瘤分期、肿瘤数量，根据标志物的预测价值建立青少年骨肉瘤预后生存的预测模型。The risk evaluation indexes significantly associated with the survival of adolescent osteosarcoma screened out by univariate cox analysis were added to the multivariate cox model, and the multivariate cox analysis was used to determine the risk factors affecting the survival of adolescent osteosarcoma through statistical analysis of case data and model fitting. The risk factor markers include gender, surgical method, location of carcinoma in situ, SEER tumor stage, and number of tumors. A prediction model for the prognosis and survival of adolescent osteosarcoma was established based on the predictive value of the markers.
根据标志物的预测价值建立青少年骨肉瘤预后生存的预测模型，是以性别作为第一预测因子，手术方式作为第二预测因子、原位癌位置作为第三预测因子、seer分期作为第四预测因子，肿瘤数量作为第五预测因子。根据以上预测因子的总分值判断骨肉瘤青少年患者群体1年、3年、5年的生存概率。并且由图1提示，基于多因素cox分析得到的五个独立危险因素的OR：性别(男性危险比HR 1.38495％CI 1.086-1.764)、手术方式(不手术危险比HR2.384，95％CI 1.61-3.692；保肢手术危险比HR 0.733，95％CI 0.577-0.965)、原位癌位置(四肢骨危险比HR 0.629，95％CI0.433-0.915)、seer肿瘤分期(原位危险比HR 0.208，95％CI 0.148-0.293；近处转移危险比HR 0.386，95％CI 0.297-0.500)、肿瘤数量(肿瘤数量＝1危险比HR 0.655，95％CI 0.433-0.967)。所述的根据以上预测因子的总分值判断青少年骨肉瘤患者在1年、3年、5年的生存概率。具体分析为：性别女或男分别对应第一因子分值0分或21分；手术方式截肢、不手术、保肢分别对应第二因子分值20分或77分或0分；原位癌位置中轴骨和四肢骨分别对应第三因子分值30或0分；seer分期远处转移、不发生转移、近处扩散分别对应第四因子分值100或0分或39分；肿瘤数量等于1个、大于1个分别对应第五因子分值0分或27分。以上标志物的不同水平与组合得到的预测因子总分0～260分别垂直向下对应图2中1年、3年、5年的生存概率。根据公式来计算，本发明所述预测模型中五个因子的总得分与1年、3年、5年关系的方程分别为1年的预测生存概率＝0*points^3+-2e-05*points^2+According to the predictive value of the markers, a prediction model for the prognosis and survival of adolescent osteosarcoma was established, with gender as the first predictor, surgical method as the second predictor, carcinoma in situ location as the third predictor, seer stage as the fourth predictor, and tumor number as the fifth predictor. The total score of the above predictive factors was used to determine the 1-year, 3-year, and 5-year survival probabilities of adolescent osteosarcoma patients. As shown in Figure 1, the ORs of five independent risk factors obtained based on multivariate cox analysis were: sex (hazard ratio HR for males 1.384, 95% CI 1.086-1.764), surgical method (hazard ratio HR for non-surgery 2.384, 95% CI 1.61-3.692; hazard ratio HR for limb-sparing surgery 0.733, 95% CI 0.577-0.965), location of carcinoma in situ (hazard ratio HR for limb bones 0.629, 95% CI 0.433-0.915), seer tumor stage (hazard ratio HR for in situ 0.208, 95% CI 0.148-0.293; hazard ratio HR for nearby metastasis 0.386, 95% CI 0.297-0.500), and number of tumors (hazard ratio HR for tumor number = 1 0.655, 95% CI 0.433-0.967). The total score of the above prediction factors is used to judge the 1-year, 3-year, and 5-year survival probabilities of adolescent osteosarcoma patients. The specific analysis is as follows: gender female or male corresponds to a first factor score of 0 or 21 points respectively; surgical method amputation, no surgery, and limb preservation correspond to a second factor score of 20 or 77 or 0 points respectively; the location of the carcinoma in situ in the axial bones and limb bones corresponds to a third factor score of 30 or 0 points respectively; SEER stage distant metastasis, no metastasis, and near spread correspond to a fourth factor score of 100 or 0 or 39 points respectively; the number of tumors equal to 1 and greater than 1 correspond to a fifth factor score of 0 or 27 points respectively. The total scores of the prediction factors of 0 to 260 obtained by different levels and combinations of the above markers correspond vertically downward to the 1-year, 3-year, and 5-year survival probabilities in Figure 2 respectively. According to the formula, the equations for the relationship between the total scores of the five factors in the prediction model of the present invention and 1 year, 3 years, and 5 years are respectively: 1-year predicted survival probability = 0*points^3+-2e-05*points^2+
0.00255*points+0.82566；3年的预测生存概率＝0*points^3+-4e-05*points^2+0.00075*points+0.8944；5年的预测生存概率＝0*points^3+-3e-05*points^2+-9e-04*points+0.8922。0.00255*points+0.82566; 3-year predicted survival probability = 0*points^3+-4e-05*points^2+0.00075*points+0.8944; 5-year predicted survival probability = 0*points^3+-3e-05*points^2+-9e-04*points+0.8922.
需要说明的是，在本发明中，诸如第一和第二等之类的关系术语仅仅用来将一个实体或者操作与另一个实体或操作区分开来，而不一定要求或者暗示这些实体或操作之间存在任何这种实际的关系或者顺序。而且，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者还包括为这种过程、方法、物品或者设备所固有的要素。It should be noted that, in the present invention, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.
以上实施例仅仅是对本发明的举例说明，并不构成对本发明的保护范围的限制，凡是与本发明相同或相似的设计均属于本发明的保护范围之内。The above embodiments are merely examples of the present invention and do not limit the protection scope of the present invention. All designs that are the same or similar to the present invention fall within the protection scope of the present invention.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410143542.8A CN117976212A (en) | 2024-02-01 | 2024-02-01 | Method, system, equipment and medium for acquiring osteosarcoma prognosis risk factors |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410143542.8A CN117976212A (en) | 2024-02-01 | 2024-02-01 | Method, system, equipment and medium for acquiring osteosarcoma prognosis risk factors |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117976212A true CN117976212A (en) | 2024-05-03 |
Family
ID=90851141
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410143542.8A Pending CN117976212A (en) | 2024-02-01 | 2024-02-01 | Method, system, equipment and medium for acquiring osteosarcoma prognosis risk factors |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117976212A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118280584A (en) * | 2024-06-04 | 2024-07-02 | 中国人民解放军空军特色医学中心 | Construction method of model for predicting survival time of small cell carcinoma of prostate |
-
2024
- 2024-02-01 CN CN202410143542.8A patent/CN117976212A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118280584A (en) * | 2024-06-04 | 2024-07-02 | 中国人民解放军空军特色医学中心 | Construction method of model for predicting survival time of small cell carcinoma of prostate |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110991536B (en) | Training method for early warning model of primary liver cancer | |
| KR102510221B1 (en) | A method of bone fracture prediction and an apparatus thereof | |
| WO2019102829A1 (en) | Image analysis method, image analysis device, image analysis system, image analysis program, and storage medium | |
| CN111739641A (en) | Gastric cancer risk prediction method and system, computer equipment and readable storage medium | |
| EP3878353A1 (en) | Cad device and method for assisting an estimation of lung disease from medical images | |
| CN118762849B (en) | Urinary surgery diagnosis and treatment data intelligent processing method and system | |
| CN117976212A (en) | Method, system, equipment and medium for acquiring osteosarcoma prognosis risk factors | |
| Huang et al. | Perihematomal edema-based CT-radiomics model to predict functional outcome in patients with intracerebral hemorrhage | |
| CN115067978B (en) | Method and system for assessing curative effect of osteosarcoma | |
| JPWO2018207925A1 (en) | Biomarker detection method, disease determination method, biomarker detection device, and biomarker detection program | |
| Chrzan et al. | The role of artificial intelligence technology analysis of high-resolution computed tomography images in predicting the severity of COVID-19 pneumonia. Pol | |
| CN111265234A (en) | Method and system for judging properties of lung mediastinal lymph nodes | |
| US8935099B2 (en) | Method and system for identifying, assessing, and managing cancer growth rates and potential metastasis | |
| CN111430030A (en) | Methods and systems for the application of biomarkers in the evaluation of ovarian cancer | |
| US20170140123A1 (en) | Method for prognosing a risk of occurrence of a disease | |
| Zhao et al. | Evaluation of risk assessment tools for breast cancer screening in Chinese population | |
| CN118588314B (en) | Tumor marker data intelligent processing system | |
| CN111351942B (en) | Lung cancer tumor marker screening system and lung cancer risk analysis system | |
| KR101439981B1 (en) | Apparatus for diagnosis breast cancer | |
| CN116993689A (en) | Method, system, electronic equipment and storage medium for predicting pancreatic cancer mesothelin expression level | |
| Eames | Computed Tomography in Medicolegal Death Investigation: A Critical Review | |
| Sankar | Ultra-Low Latency Hybrid Feature Learning for Accurate Multiple Sclerosis Detection Using Multi-Scale Extraction and Adaptive Attention | |
| CN118983079A (en) | Method for constructing lung cancer screening model based on UVP-TOF-MS | |
| Zhang | Coronary heart disease evaluation using PCAT radiomics model based on coronary CT angiography and pericoronary adipose tissue | |
| Byrne | Body Composition and Biomarkers to Explore Disparities in Sarcopenia and Inflammation of Lung Cancer |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |