Esophageal fistula risk prediction systems, methods, electronic devices, and media
Patent Information
- Application Number
- CN202510530801.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-25
- Publication Date
- 2026-10-27
AI Technical Summary
[0004]本申请的目的在于提供一种食管瘘风险预测系统、方法、电子设备及介质，用于解决现有技术中缺少量化预测食管瘘风险模型的问题
[0004]本申请的目的在于提供一种食管瘘风险预测系统、方法、电子设备及介质，用于解决现有技术中缺少量化预测食管瘘风险模型的问题。
Smart Images
Figure CN122991569A_ABST
Abstract
Description
Technical Field
[0001] This application belongs to the field of medical artificial intelligence technology, and relates to an esophageal fistula risk prediction system, and in particular to an esophageal fistula risk prediction system, method, electronic device and medium. Background Technology
[0002] Esophageal submucosal tumors (SMTs) are lesions originating from the muscularis mucosa, submucosa, or muscularis propria of the esophagus. Traditionally, "giant SMTs" with a diameter ≥30 mm require thoracic surgery for resection due to significant symptoms and a high potential risk of malignancy. While smaller SMTs are often benign, endoscopic resection still presents technical challenges. In recent years, breakthroughs such as endoscopic submucosal dissection, transmucosal tunneling tumor resection, and full-thickness resection have greatly expanded the indications for endoscopic treatment, enabling the minimally invasive resection of more complex SMTs. However, the risks of postoperative complications such as perforation, bleeding, mediastinal emphysema, and esophageal fistula should not be ignored. Esophageal fistula, in particular, has become a focus of clinical attention due to its potential for severe infection and even death.
[0003] Despite significant advancements in endoscopic technology, core limitations remain: current clinical practice relies on empirical judgment, making it difficult to quantify and assess individualized patient risks, and there is a lack of accurate predictive models for the risk of esophageal fistula. Summary of the Invention
[0004] The purpose of this application is to provide an esophageal fistula risk prediction system, method, electronic device and medium to solve the problem of the lack of quantitative prediction models for esophageal fistula risk in the prior art.
[0005] In a first aspect, this application provides an esophageal fistula risk prediction system. The esophageal fistula risk prediction system includes: a data acquisition module for acquiring medical data on esophageal fistulas; a data filtering module for analyzing and filtering the medical data on esophageal fistulas using statistical analysis to obtain influencing factors of esophageal fistulas; a data processing module for performing regression analysis on the influencing factors of esophageal fistulas using a regression analysis model to obtain independent risk factors; and a model prediction module for constructing an esophageal fistula risk prediction model based on the analysis results of each independent risk factor, and using the esophageal fistula risk prediction model to obtain the esophageal fistula risk probability of the medical data to be predicted.
[0006] This application utilizes statistical data analysis to classify and screen medical data on esophageal fistulas, identifying influencing factors. Regression analysis is then performed on these influencing factors to identify independent risk factors. Based on the analysis results of these independent risk factors, an esophageal fistula risk prediction model is constructed. Finally, this model is used to obtain the probability of esophageal fistula risk for the tested data. This esophageal fistula risk prediction system can quantitatively predict the risk of esophageal fistula occurrence, enabling risk stratification management and precise prevention, thereby improving the safety and accessibility of esophageal fistula risk prediction.
[0007] In one implementation of the first aspect, the analysis and screening of the esophageal fistula medical data using statistical data analysis includes: using statistical analysis methods to distinguish the esophageal fistula medical data to obtain continuous variables and categorical variables; using a one-way chi-square test to screen the categorical variables and using a t-test to screen the continuous variables to obtain the influencing factors of the esophageal fistula.
[0008] In one implementation of the first aspect, the independent risk factors for the esophageal fistula include: perforator vessel damage, muscle layer injury, growth pattern, and surgical time.
[0009] In one implementation of the first aspect, using a regression analysis model to perform regression analysis on the influencing factors of the esophageal fistula to obtain independent risk factors includes: using a regression model to perform regression analysis on the influencing factors of the esophageal fistula to obtain regression coefficients; and screening the influencing factors of the esophageal fistula based on the regression coefficients to obtain the independent risk factors.
[0010] In one implementation of the first aspect, constructing an esophageal fistula risk prediction model based on the analysis results of each independent risk factor includes: performing parameter matching on each independent risk factor to obtain the analysis results of the independent risk factors; and training an initial esophageal fistula risk prediction model using the analysis results of the independent risk factors to obtain the esophageal fistula risk prediction model.
[0011] In one implementation of the first aspect, the esophageal fistula risk prediction system includes: adjusting the initial esophageal fistula risk prediction model using a 10x cross-validation method to obtain the esophageal fistula risk prediction model.
[0012] In one implementation of the first aspect, obtaining the esophageal fistula probability of the medical data to be predicted using the esophageal fistula risk prediction model includes: matching parameters of the independent risk factors of the medical data to be predicted to obtain variable parameters of the medical data to be predicted; processing the esophageal fistula risk probability of the esophageal fistula risk prediction model and the variable parameters of the medical data to be predicted to obtain a prediction score; and judging the prediction score using a preset threshold. If the prediction score is less than the preset threshold, the predicted esophageal fistula probability is low; otherwise, the predicted esophageal fistula probability is high.
[0013] Secondly, this application provides a method for predicting the risk of esophageal fistula. The method includes: acquiring medical data on esophageal fistula; analyzing and screening the medical data using statistical analysis to obtain influencing factors of esophageal fistula; performing regression analysis on the influencing factors of esophageal fistula using a regression analysis model to obtain independent risk factors; constructing an esophageal fistula risk prediction model based on the analysis results of each independent risk factor; and using the esophageal fistula risk prediction model to obtain the probability of esophageal fistula in the medical data to be predicted.
[0014] Thirdly, this application provides an electronic device. The electronic device includes: a memory for storing a computer program; and a processor for executing the computer program stored in the memory to cause the electronic device to perform the esophageal fistula risk prediction method as described in the second aspect.
[0015] Fourthly, this application provides a computer-readable storage medium. The computer-readable storage medium stores a computer program that, when executed by a processor, implements the esophageal fistula risk prediction method described in the second aspect. Attached Figure Description
[0016] Figure 1A This diagram illustrates an application scenario of the esophageal fistula risk prediction method described in this application.
[0017] Figure 1B This diagram illustrates the structure of the mid-cloud interaction scenario in these implementation methods.
[0018] Figure 2 The diagram shown is a flowchart illustrating the esophageal fistula risk prediction method described in the embodiments of this application.
[0019] Figure 3 The diagram shown is a flowchart illustrating the esophageal fistula risk prediction method described in the embodiments of this application.
[0020] Figure 4 The diagram shown is a flowchart illustrating the esophageal fistula risk prediction method described in the embodiments of this application.
[0021] Figure 5 The graph shown is the ROC curve of the esophageal fistula risk prediction model described in the embodiments of this application.
[0022] Figure 6 The diagram shown is a structural schematic of the esophageal fistula risk prediction system described in an embodiment of this application.
[0023] Figure 7 The diagram shown is a structural schematic of the electronic device described in an embodiment of this application.
[0024] Component designation explanation
[0025] 1. Esophageal fistula risk prediction device
[0026] 11. Testing equipment
[0027] 12 Local Processors
[0028] 13 Display Terminals
[0029] 2-Terminal-Cloud Interactive System
[0030] 20 terminals
[0031] 21 Cloud Servers
[0032] 100 Esophageal Fistula Risk Prediction System
[0033] 110 Data Acquisition Module
[0034] 120 Data Filtering Module
[0035] 130 Data Processing Module
[0036] 140 Model Prediction Module
[0037] 700 electronic devices
[0038] 710 Memory
[0039] 720 processor
[0040] 730 monitor
[0041] Steps S11 to S14
[0042] Steps S121~S123
[0043] Steps S141~S143 Detailed Implementation
[0044] The following specific examples illustrate the implementation of this application. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be noted that, unless otherwise specified, the following embodiments and features in the embodiments can be combined with each other.
[0045] It should be noted that in the embodiments of this application, the words "optionally" or "for example" indicate examples, illustrations, or descriptions. Any embodiment or design scheme described as "optionally" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of the words "optionally" or "for example" is intended to present the relevant concepts in a specific manner.
[0046] In this application embodiment, "at least one" refers to one or more, and "more than one" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.
[0047] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of this application. Therefore, the drawings only show the components related to this application and are not drawn according to the number, shape and size of the components in actual implementation. In actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.
[0048] In recent years, there have been increasing reports of successful endoscopic esophageal tumor resection (SMTs), which has boosted clinical confidence in this technique. Common complications of endoscopic esophageal resection include perforation, bleeding, mediastinal emphysema, and postoperative stricture. Although the incidence is low, the formation of esophageal fistula after endoscopic resection remains a serious risk, highlighting the importance of identifying risk factors and implementing preventive strategies. Studies have identified several key risk factors leading to fistula formation after endoscopic surgery, including irregular tumor shape, deep location, long operation time, intraoperative pneumatic insufflation, mechanical damage to the mucosa during surgery, and thermal damage caused by excessive electrocoagulation. Therefore, there is an urgent need to classify the risk of esophageal fistula after esophageal SMTs and to assist in individualized risk prediction to facilitate early prevention and intervention.
[0049] To address at least the aforementioned problems, this application provides an esophageal fistula risk prediction system. The esophageal fistula risk prediction system includes: a data acquisition module for acquiring medical data on esophageal fistulas; a data filtering module for analyzing and filtering the medical data on esophageal fistulas using statistical analysis to obtain influencing factors of esophageal fistulas; a data processing module for performing regression analysis on the influencing factors of esophageal fistulas using a regression analysis model to obtain independent risk factors; and a model prediction module for constructing an esophageal fistula risk prediction model based on the analysis results of each independent risk factor, and using the esophageal fistula risk prediction model to obtain the esophageal fistula risk probability of the medical data to be predicted.
[0050] In this embodiment, statistical data analysis is used to classify and screen medical data on esophageal fistulas to obtain influencing factors. Regression analysis is then performed on these influencing factors to identify independent risk factors. Based on the analysis results of these independent risk factors, an esophageal fistula risk prediction model is constructed. Finally, this model is used to obtain the probability of esophageal fistula risk for the tested data. This esophageal fistula risk prediction system can quantitatively predict the risk of esophageal fistula occurrence, enabling risk stratification management and precise prevention, thereby improving the safety and accessibility of esophageal fistula risk prediction.
[0051] Figure 1A This diagram illustrates an application scenario of the esophageal fistula risk prediction method described in this application. The esophageal fistula risk prediction device 1 can be used to implement the esophageal fistula risk prediction method provided in the embodiments of this application, but the application scenarios of the esophageal fistula risk prediction method provided in the embodiments of this application are not limited to this. Figure 1A The esophageal fistula risk prediction device 1 shown is as follows. Figure 1A As shown, the esophageal fistula risk prediction device 1 includes a detection device 11, a local processor 12, and a display terminal 13. The esophageal fistula risk prediction method provided in this application embodiment can be applied to the local processor 12.
[0052] in, Figure 1AThe local processor 12 can be a single local processor, a cluster of multiple local processors, or a cloud computing center, etc., and is not specifically limited here. Although Figure 1A Only one detection device 11, one local processor 12, and one display terminal 13 are shown, but it should be understood that... Figure 1A The examples in this paper are only for understanding this solution. The specific number of local processors 12 and display terminals 13 should be flexibly determined based on the actual situation.
[0053] In some other implementations, the esophageal fistula risk prediction device 1 may not include a display terminal 13, but only a local processor 12 with display function and a detection device 11. The esophageal fistula risk prediction method provided in this application embodiment can be applied to the local processor 12. The local processor 12 with display function may include tablet computers, PDAs, mobile phones, personal computers, and voice interaction devices, etc., and is not limited here.
[0054] In some other implementations, the esophageal fistula risk prediction method described in this application can be applied to end-to-cloud interaction scenarios. Figure 1B This diagram illustrates the structure of the endpoint-cloud interaction scenario in these implementation methods. For example... Figure 1B As shown, the terminal-cloud interaction system 2 includes a terminal 20 and a cloud server 21. The terminal 20 and the cloud server 21 can communicate with each other, and the communication method is not limited to wired or wireless.
[0055] The terminal 20 can be mobile or fixed. For example, it can be a wireless terminal or a wired terminal. A wireless terminal can refer to a device with wireless transceiver capabilities, which can be deployed indoors, outdoors, and in industrial workshops. The terminal 20 can be a medical testing instrument, a mobile phone, a tablet computer, a laptop computer, etc., and is not limited thereto. The cloud server 21 can include one or more servers, or one or more processing nodes, or one or more virtual machines running on the server. The cloud server 21 can also be referred to as a server cluster, a management platform, a data processing center, etc., and is not limited thereto in this embodiment.
[0056] The technical solutions in the embodiments of this application will be described in detail below with reference to the accompanying drawings.
[0057] The following embodiments of this application provide a method for predicting the risk of esophageal fistula, which, for example, can be achieved through... Figure 1A The local processor 12 shown Figure 1B The cloud server 21 shown is used to implement this. Figure 2 The diagram shown is a flowchart illustrating the esophageal fistula risk prediction method described in an embodiment of this application. Figure 2As shown, the esophageal fistula risk prediction method includes steps S11 to S14.
[0058] Step S11: Obtain medical data on esophageal fistula.
[0059] Step S12: Analyze and screen the medical data on esophageal fistula using statistical data analysis to obtain the influencing factors of esophageal fistula.
[0060] Step S13: Use a regression analysis model to perform regression analysis on the influencing factors of the esophageal fistula to obtain independent risk factors.
[0061] Step S14: Construct an esophageal fistula risk prediction model based on the analysis results of each independent risk factor, and use the esophageal fistula risk prediction model to obtain the probability of esophageal fistula in the medical data to be predicted. Specifically, the esophageal fistula risk prediction model is a scoring model that can quantify the risk of esophageal fistula occurrence and achieve tiered management.
[0062] In some possible implementations, medical data on esophageal fistulas are obtained through clinical data collection. Sources of clinical data collection include electronic medical record systems, endoscopic imaging databases, and / or postoperative follow-up records. Esophageal fistula medical data includes patient gender, age, history of previous endoscopic treatment of the esophagus, comorbidities, maximum diameter of the lesion, location, depth, histological assessment, growth pattern, morphology, surface mucosal condition, endoscopic surgical method, mucosal damage, submucosal fibrosis, presence and damage of perforating vessels, muscle layer damage, suture method, en bloc resection rate, operation time, esophageal fistula, postoperative bleeding, postoperative infection, esophageal stricture, length of hospital stay, and recurrence rate. Table 1 shows the differences between the esophageal fistula group and the non-esophageal fistula group.
[0063] Table 1: Comparison Table of Medical Data for Esophageal Fistula
[0064]
[0065]
[0066] Univariate analysis was used in statistical data analysis to test categorical and continuous variables of esophageal fistula medical data to screen for influencing factors. A multivariate logistic regression model was used to perform regression analysis on the influencing factors of esophageal fistula, and a backward stepwise regression method was used to eliminate collinear variables, ultimately obtaining independent risk factors for esophageal fistula. Based on the analysis results of each independent risk factor, corresponding parameter values were matched. These parameter values and an esophageal fistula risk prediction model were used to predict the probability of esophageal fistula in the medical data to be predicted. The probability obtained from the esophageal fistula risk prediction model is Logit(P), and the formula for calculating the probability of esophageal fistula is:
[0067]
[0068] In this embodiment, statistical data analysis is used to classify and screen medical data on esophageal fistulas to obtain influencing factors. Regression analysis is then performed on these influencing factors to identify independent risk factors. Based on the analysis results of these independent risk factors, an esophageal fistula risk prediction model is constructed. Finally, this model is used to obtain the probability of esophageal fistula risk for the tested data. This method can quantify and predict the risk of esophageal fistula occurrence, enabling risk stratification management and precise prevention, thereby improving the safety and accessibility of esophageal fistula risk prediction.
[0069] Figure 3 The diagram shown is a flowchart illustrating the esophageal fistula risk prediction method described in an embodiment of this application. Figure 3 As shown, step S12 includes steps S121 to S123.
[0070] Step S121: Use statistical analysis methods to distinguish the esophageal fistula medical data and obtain continuous variables and categorical variables.
[0071] Step S122: Use a one-way chi-square test to screen the categorical variables and obtain the influencing factors of the esophageal fistula.
[0072] Step S123: Use the t-test to screen the continuous variables and obtain the influencing factors of the esophageal fistula. The univariate chi-square test and t-test are two methods for statistical hypothesis testing used to analyze the influence of a single factor (i.e., one independent variable) on a variable, and are applicable to different data types. The t-test handles the relationship between a continuous dependent variable and a binary independent variable, while the chi-square test handles the association or distributional differences between categorical variables.
[0073] In some possible implementations, univariate analysis in statistical data analysis is used to analyze and process the medical data on esophageal fistula. Specifically, the statistical analysis uses SPSS 26.0 and R4.0.2 software, where continuous variables of the esophageal fistula medical data are expressed as mean ± standard deviation, and categorical variables are expressed as number of cases (percentage), distinguishing between continuous and categorical variables. A univariate chi-square test is used to screen categorical variables, and a t-test is used to screen continuous variables to identify the influencing factors of esophageal fistula.
[0074] In one embodiment of this application, the independent risk factors for the esophageal fistula include: perforator vessel damage, muscle layer injury, growth pattern, and operation time.
[0075] In one embodiment of this application, using a regression analysis model to perform regression analysis on the influencing factors of the esophageal fistula to obtain independent risk factors includes: using a regression model to perform regression analysis on the influencing factors of the esophageal fistula to obtain regression coefficients; and screening the influencing factors of the esophageal fistula based on the regression coefficients to obtain the independent risk factors.
[0076] In some possible implementations, regression analysis models are used to perform regression analysis on the influencing factors of the esophageal fistula, obtaining the regression coefficients of each influencing factor. The regression coefficients of the logistic regression model are converted into odds ratios (OR values). A screening criterion combining a preset significance level (P-value) and OR values is used to screen the influencing factors of the esophageal fistula, identifying those meeting a preset threshold as independent risk factors. For example, an OR value less than 1 and a significance level (P < 0.05) can be used as the screening criterion to identify independent risk factors.
[0077] In one embodiment of this application, constructing an esophageal fistula risk prediction model based on the analysis results of each independent risk factor includes: performing parameter matching on each independent risk factor to obtain the analysis results of the independent risk factors; and training an initial esophageal fistula risk prediction model using the analysis results of the independent risk factors to obtain the esophageal fistula risk prediction model.
[0078] In some possible implementations, each independent risk factor is matched with a parameter value to obtain the analysis results of the independent risk factors. A simplified esophageal fistula risk prediction model is then established using the analysis results of the independent risk factors.
[0079] In one embodiment of this application, the esophageal fistula risk prediction method includes: adjusting the initial esophageal fistula risk prediction model using a 10x cross-validation method to obtain the esophageal fistula risk prediction model.
[0080] One possible implementation involves a cycle of model training and validation. In each round, nine data subsets are selected for training, and one subset is used for testing. The model parameters are then adjusted based on the average regression coefficients obtained from ten rounds of validation. This improves the model's generalization ability, avoids over-reliance on a single dataset, and reduces the risk of missed or misdiagnosed cases.
[0081] Figure 4 The diagram shown is a flowchart illustrating the esophageal fistula risk prediction method described in an embodiment of this application. Figure 4 As shown, step S14 includes steps S141 to S143.
[0082] Step S141: Perform parameter matching on the independent risk factors of the medical data to be predicted for esophageal fistula to obtain the variable parameters of the medical data to be predicted for esophageal fistula.
[0083] Step S142: Process the esophageal fistula risk probability of the esophageal fistula risk prediction model and the variable parameters of the medical data of the esophageal fistula to be predicted to obtain a prediction score.
[0084] Step S143: Use a preset threshold to judge the predicted score. If it is less than the preset threshold, the predicted probability of esophageal fistula is low; otherwise, the predicted probability of esophageal fistula is high.
[0085] In some possible implementations, a β value is assigned to each independent risk factor, and the integer value of the β value is used as a weighting coefficient for the variable in the model. The model coefficients β values for the Logistic Regression model are shown in Table 2. As shown in Table 2, significant variables with p-values < 0.05 are retained, while insignificant factors are removed. The β value is added to the OR value and rounded to the nearest integer to obtain the predicted score. The scores of all significant variables are added together to obtain the total score. A total score less than 3 points indicates a low predicted probability of esophageal fistula, while a total score greater than or equal to 3 points indicates a high predicted probability of esophageal fistula.
[0086] Table 2: Basis for calculating coefficients and prediction scores of the Logistic regression model.
[0087]
[0088] In this embodiment of the application, independent risk factors for esophageal fistula after endoscopic resection of esophageal SMTs were screened for the first time. The coefficients of each factor were assigned using the Logistic regression formula to establish a risk prediction model for esophageal fistula. Figure 5 The image shown is an ROC curve of the esophageal fistula risk prediction model described in the embodiments of this application. Figure 5 As shown, the area under the ROC curve of the esophageal fistula risk prediction model is 0.932, demonstrating its good predictive ability, and this was validated using external data. This esophageal fistula risk prediction model can more intuitively and quantitatively assess the risk of esophageal fistula after endoscopic esophageal MTs resection, enabling stratified management and individualized assessment for patients, and providing auxiliary theoretical basis for endoscopists to predict the occurrence of esophageal fistula after endoscopic esophageal MTs resection.
[0089] Figure 6 The diagram shown is a structural schematic of the esophageal fistula risk prediction system described in an embodiment of this application. Figure 6 As shown, the esophageal fistula risk prediction system 100 includes a data acquisition module 110, a data filtering module 120, a data processing module 130, and a model prediction module 140.
[0090] The data acquisition module 110 is used to acquire medical data about esophageal fistulas.
[0091] The data filtering module 120 is used to analyze and filter the medical data of esophageal fistula using data statistical analysis to obtain the influencing factors of esophageal fistula.
[0092] The data processing module 130 is used to perform regression analysis on the influencing factors of the esophageal fistula using a regression analysis model to obtain independent risk factors.
[0093] The model prediction module 140 is used to construct an esophageal fistula risk prediction model based on the analysis results of each of the independent risk factors, and to obtain the esophageal fistula risk probability of the medical data to be predicted using the esophageal fistula risk prediction model.
[0094] In some possible implementations, the data acquisition module 110 is used to collect medical data on esophageal fistula using clinical data collection. Sources of clinical data collection include electronic medical record systems, endoscopic image databases, and / or postoperative follow-up records. Esophageal fistula medical data includes patient gender, age, history of previous endoscopic treatment of the esophagus, comorbidities, maximum diameter of the lesion, location, depth, histological assessment, growth pattern, morphology, surface mucosal condition, endoscopic surgical method, mucosal injury, submucosal fibrosis, presence and damage of perforating vessels, muscle layer injury, suture method, en bloc resection rate, operation time, esophageal fistula, postoperative bleeding, postoperative infection, esophageal stricture, length of hospital stay, and recurrence rate. The data screening module 120 is used to perform univariate analysis in data statistical analysis to test categorical and continuous variables of the esophageal fistula medical data to screen for influencing factors of esophageal fistula. The data processing module 130 is used to perform regression analysis on the influencing factors of esophageal fistula using a multivariate logistic regression model, employing a backward stepwise regression method to eliminate collinear variables, and finally obtaining independent risk factors for esophageal fistula. Based on the analysis results of each independent risk factor, the corresponding parameter values are matched. The model prediction module 140 is used to perform predictive analysis on the medical data of the esophageal fistula to be predicted using the parameter values and the esophageal fistula risk prediction model, and obtain the probability of esophageal fistula in the medical data of the esophageal fistula to be predicted.
[0095] In this embodiment, statistical data analysis is used to classify and screen medical data on esophageal fistulas to obtain influencing factors. Regression analysis is then performed on these influencing factors to identify independent risk factors. Based on the analysis results of these independent risk factors, an esophageal fistula risk prediction model is constructed. Finally, this model is used to obtain the probability of esophageal fistula risk for the tested data. This method can quantify and predict the risk of esophageal fistula occurrence, enabling risk stratification management and precise prevention, thereby improving the safety and accessibility of esophageal fistula risk prediction.
[0096] In the embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, or methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of modules / units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or units may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection of apparatuses or modules or units may be electrical, mechanical, or other forms.
[0097] The modules / units described as separate components may or may not be physically separate. The components shown as modules / units may or may not be physical modules; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules / units can be selected to achieve the objectives of the embodiments of this application, depending on actual needs. For example, the functional modules / units in the various embodiments of this application may be integrated into one processing module, or each module / unit may exist physically separately, or two or more modules / units may be integrated into one module / unit.
[0098] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.
[0099] This application also provides an electronic device. Figure 7 The diagram shown is a structural schematic of the electronic device 700 described in an embodiment of this application. Figure 7 As shown, in this embodiment, the electronic device 700 includes a memory 710 and a processor 720.
[0100] The memory 710 is used to store computer programs; preferably, the memory 710 includes various media that can store program code, such as ROM, RAM, magnetic disk, USB flash drive, memory card or optical disk.
[0101] Specifically, memory 710 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) and / or cache memory. Electronic device 700 may further include other removable / non-removable, volatile / non-volatile computer system storage media. Memory 710 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of this application. It is understood that memory 710 may be volatile memory or non-volatile memory, or both. Non-volatile memory may be read-only memory (ROM) or programmable read-only memory (PROM), which serves as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (SRAM) and synchronous static random access memory (SSRAM). The memories described in the embodiments of this invention are intended to include, but are not limited to, these and any other suitable categories of memories.
[0102] The processor 720 is connected to the memory 710 and is used to execute the computer program stored in the memory 710 so that the electronic device 700 performs the esophageal fistula risk prediction method described in any embodiment of this application.
[0103] Optionally, the processor 720 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.
[0104] Optionally, the electronic device 700 in this embodiment may further include a display 730. The display 730 is communicatively connected to the memory 710 and the processor 720, and is used to display the relevant graphical user interface (GUI) of the esophageal fistula risk prediction method described in this application embodiment.
[0105] This application also provides a computer-readable storage medium having a computer program stored thereon. When executed by a processor, the program implements the esophageal fistula risk prediction method described in any embodiment of this application.
[0106] As used in this specification, the terms "component," "module," "system," etc., are used to refer to computer-related entities, hardware, firmware, combinations of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, a process running on a processor, a processor, an object, an executable file, an execution thread, a program, and / or a computer. As illustrated, applications running on computing devices and computing devices can both be components. One or more components may reside in a process and / or an execution thread, and components may be located on a single computer and / or distributed among two or more computers. Furthermore, these components can be executed from various computer-readable media on which various data structures are stored. Components can communicate, for example, via local and / or remote processes based on signals having one or more data packets (e.g., data from two components interacting with another component between a local system, a distributed system, and / or a network, such as the Internet interacting with other systems via signals).
[0107] The descriptions of the processes or structures corresponding to the above figures each have their own emphasis. For parts of a process or structure that are not described in detail, please refer to the relevant descriptions of other processes or structures.
[0108] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in this application should still be covered by the claims of this application.
Claims
1. An esophageal fistula risk prediction system, characterized in that, include: The data acquisition module is used to acquire medical data about esophageal fistulas. The data filtering module is used to analyze and filter the medical data on esophageal fistula using statistical data analysis to obtain the influencing factors of esophageal fistula. The data processing module is used to perform regression analysis on the influencing factors of the esophageal fistula using a regression analysis model to obtain independent risk factors. The model prediction module is used to construct an esophageal fistula risk prediction model based on the analysis results of each independent risk factor, and to obtain the esophageal fistula risk probability of the medical data to be predicted using the esophageal fistula risk prediction model.
2. The esophageal fistula risk prediction system according to claim 1, characterized in that, The analysis and screening of the esophageal fistula medical data using statistical data analysis includes: Statistical analysis methods were used to differentiate the esophageal fistula medical data, obtaining continuous and categorical variables; The categorical variables were screened using a one-way chi-square test, and the continuous variables were screened using a t-test to obtain the influencing factors of the esophageal fistula.
3. The esophageal fistula risk prediction system according to claim 1, characterized in that, Independent risk factors for esophageal fistula include: perforator vessel damage, muscle layer injury, growth pattern, and surgical time.
4. The esophageal fistula risk prediction system according to claim 1, characterized in that, Regression analysis was performed using a regression model to identify the influencing factors of the esophageal fistula, including: Regression analysis was performed on the influencing factors of the esophageal fistula using a regression model to obtain regression coefficients; The influencing factors of the esophageal fistula are screened based on the regression coefficients to obtain the independent risk factors.
5. The esophageal fistula risk prediction system according to claim 1, characterized in that, Based on the analysis results of each of the independent risk factors, an esophageal fistula risk prediction model was constructed, including: Parameter matching is performed on each of the independent risk factors to obtain the analysis results of the independent risk factors; The initial esophageal fistula risk prediction model was trained using the analysis results of the independent risk factors to obtain the esophageal fistula risk prediction model.
6. The esophageal fistula risk prediction system according to claim 5, characterized in that, include: The initial esophageal fistula risk prediction model was adjusted using a 10-fold cross-validation method to obtain the esophageal fistula risk prediction model.
7. The esophageal fistula risk prediction system according to claim 1, characterized in that, The esophageal fistula probability obtained using the aforementioned esophageal fistula risk prediction model includes: The independent risk factors of the medical data to be predicted for esophageal fistula are matched with parameters to obtain the variable parameters of the medical data to be predicted for esophageal fistula. The prediction score is obtained by processing the esophageal fistula risk probability of the esophageal fistula risk prediction model and the variable parameters of the medical data of the esophageal fistula to be predicted. The predicted score is judged using a preset threshold. If the score is less than the preset threshold, the probability of esophageal fistula is low; otherwise, the probability of esophageal fistula is high.
8. A method for predicting the risk of esophageal fistula, characterized in that, include: Acquire medical data on esophageal fistulas; The medical data on esophageal fistula were analyzed and screened using statistical data analysis to identify the influencing factors of esophageal fistula. Regression analysis was used to analyze the influencing factors of the esophageal fistula to obtain independent risk factors; An esophageal fistula risk prediction model is constructed based on the analysis results of each independent risk factor, and the probability of esophageal fistula in the medical data to be predicted is obtained using the esophageal fistula risk prediction model.
9. An electronic device, characterized in that, The electronic device includes: Memory, used to store computer programs; A processor for executing a computer program stored in the memory to cause the electronic device to perform the esophageal fistula risk prediction method as described in claim 8.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the esophageal fistula risk prediction method as described in claim 8.