R language construction-based stroke patient dysphagia risk prediction and personalized intervention recommendation system

Abstract

The invention belongs to the technical field of assessment of dysphagia of stroke patients, and provides a stroke patient dysphagia risk prediction and personalized intervention recommendation system based on R language construction, which comprises a data processing module, a prediction model module, an intervention recommendation module and an output module, the data processing module receives and processes an input predictive factor value, the predictive model module constructed based on a large amount of case data is used for calculating a dysphagia risk score, then the intervention recommendation module intelligently recommends personalized intervention measures, and the personalized intervention measures are displayed to a user in a visual form through the output module; according to the system, accurate prediction and personalized intervention recommendation of the dysphagia risk of the stroke patient are realized, the prediction accuracy and reliability are improved, meanwhile, the pertinence and effectiveness of intervention measures are enhanced, and the life quality and rehabilitation effect of the patient are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of dysphagia assessment for stroke patients, and specifically is a dysphagia risk prediction and personalized intervention recommendation system for stroke patients based on R language. Background Art

[0002] Stroke, as a common cerebrovascular disease, has a high incidence and disability rate. Dysphagia is one of the common complications of stroke patients, which seriously affects the quality of life and rehabilitation process of patients. At present, the clinical evaluation of dysphagia in stroke patients mainly relies on the experience of doctors and traditional assessment tools. This method is not only time-consuming and labor-intensive, but also the accuracy and objectivity of the assessment results are difficult to guarantee. In addition, intervention measures for dysphagia also lack personalization and precision, resulting in poor treatment effects.

[0003] In the existing technology, although some methods based on data analysis and machine learning are used for disease risk assessment and intervention recommendations, these methods often target the common characteristics of the general population or specific diseases and fail to fully consider the complexity and diversity of swallowing disorders in stroke patients.

[0004] To this end, those skilled in the art have proposed a risk prediction and personalized intervention recommendation system for dysphagia in stroke patients based on R language to solve the problems raised by the background technology. Summary of the invention

[0005] In order to solve the above technical problems, the present invention provides a risk prediction and personalized intervention recommendation system for dysphagia in stroke patients based on R language, so as to solve the problems that the existing technology often targets the general characteristics of the general population or specific diseases, and fails to fully consider the complexity and diversity of dysphagia in stroke patients.

[0006] A risk prediction and personalized intervention recommendation system for dysphagia in stroke patients based on R language, including:

[0007] A data processing module, used for receiving and processing inputted stroke patient-related prediction factor values;

[0008] The prediction model module was built using R language based on multiple stroke case data and was used to calculate the dysphagia risk score according to the input predictor values;

[0009] The intervention recommendation module intelligently recommends personalized dysphagia intervention measures based on the calculated risk score;

[0010] The output module is used to present the risk scores and recommended interventions to the user in visual or textual form.

[0011] Preferably, the predictive factors include, but are not limited to, the patient's age, gender, stroke type, lesion location, and degree of neurological deficit.

[0012] Preferably, a standardization algorithm is introduced to standardize the prediction factors to eliminate the dimensional differences between different features and improve the accuracy and stability of the model.

[0013] Preferably, in the prediction model module, a logistic regression model is also constructed to calculate the probability of dysphagia in the patient;

[0014] At the same time, support vector machine (SVM) is introduced to process more complex data patterns and improve the accuracy of prediction.

[0015] Preferably, in the prediction model module, for the prediction of long-term dysphagia risk in stroke patients, a survival analysis algorithm is introduced to evaluate the dysphagia risk of patients in different time periods.

[0016] Preferably, the intervention recommendation module further introduces a collaborative filtering algorithm for recommending content based on the user's historical behavior and the behavior of other users.

[0017] Preferably, the system also includes a user feedback module for collecting user feedback on the implementation effects of recommended intervention measures to optimize the prediction model and intervention recommendation strategy.

[0018] A method for predicting the risk of dysphagia and recommending personalized intervention for stroke patients based on R language, using the above-mentioned method for predicting the risk of dysphagia and recommending personalized intervention for stroke patients based on R language, comprising:

[0019] S1. Receive and process inputted stroke patient-related prediction factor values ​​through a data processing module, where the prediction factors include but are not limited to the patient's age, gender, stroke type, lesion location, degree of neurological deficit, etc.;

[0020] S2. Using the R language based on more than 6,000 stroke case data, the prediction model module was constructed to calculate the dysphagia risk score according to the input predictor value. The prediction model module constructed a logistic regression model and a support vector machine (SVM) to improve the accuracy of the prediction. The logistic regression model was used to calculate the probability of dysphagia in patients, and the support vector machine was used to process more complex data patterns.

[0021] S3. Based on the calculated risk score, the intervention recommendation module intelligently recommends personalized dysphagia intervention measures; the intervention recommendation module further introduces a collaborative filtering algorithm to recommend content based on the user's historical behavior and the behavior of other users;

[0022] S4, presenting the risk score and recommended intervention measures to the user in a visual or textual form through an output module;

[0023] S5. Collect user feedback on the implementation effects of recommended intervention measures through the user feedback module to optimize the prediction model and intervention recommendation strategy.

[0024] A processor is configured to execute the above-mentioned dysphagia risk prediction and personalized intervention recommendation system for stroke patients based on the R language.

[0025] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the above-mentioned dysphagia risk prediction and personalized intervention recommendation system for stroke patients based on R language.

[0026] Compared with the prior art, the present invention has the following beneficial effects:

[0027] 1. The present invention realizes accurate prediction of the risk of dysphagia in stroke patients by constructing a risk prediction model for dysphagia in stroke patients based on R language; the model is constructed based on more than 6,000 stroke case data, and fully considers multiple predictive factors such as the patient's age, gender, stroke type, lesion location, degree of neurological impairment, etc., thereby improving the accuracy and reliability of the prediction.

[0028] 2. The present invention introduces a personalized intervention recommendation module to intelligently recommend personalized dysphagia intervention measures based on the prediction results; this module not only takes into account the patient's specific situation, but also introduces a collaborative filtering algorithm to recommend content based on the user's historical behavior and the behavior of other users, further improving the pertinence and effectiveness of the intervention measures.

[0029] 3. The invention displays risk scores and recommended intervention measures in visual or textual form, so that doctors and patients can intuitively understand the evaluation results and intervention suggestions, thereby improving the efficiency and effectiveness of communication; at the same time, the invention also collects user feedback on the implementation effect of recommended intervention measures through a user feedback module to optimize the prediction model and intervention recommendation strategy, thereby achieving continuous improvement and optimization of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 This is a framework diagram of the dysphagia risk prediction and personalized intervention recommendation system for stroke patients built based on R language of the present invention. DETAILED DESCRIPTION

[0031] The following embodiments of the present invention are described in further detail in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0032] Embodiment: The present invention provides a risk prediction and personalized intervention recommendation system for dysphagia in stroke patients based on R language, such as Figure 1 As shown, it includes a data processing module, a prediction model module, an intervention recommendation module and an output module, and the data processing module, the prediction model module, the intervention recommendation module and the output module are electrically connected in sequence:

[0033] A data processing module, used for receiving and processing inputted stroke patient-related prediction factor values;

[0034] The prediction model module, built using R language based on data from more than 6,000 stroke cases, is used to calculate the risk score for dysphagia based on the input predictor values;

[0035] The intervention recommendation module intelligently recommends personalized dysphagia intervention measures based on the calculated risk score;

[0036] The output module is used to present the risk scores and recommended interventions to the user in visual or textual form.

[0037] As can be seen from the above, the input prediction factor values ​​are received and processed by the data processing module, and the dysphagia risk score is calculated using the prediction model module built based on a large amount of case data. The intervention recommendation module then intelligently recommends personalized intervention measures and presents them to the user in an intuitive form through the output module. The system realizes accurate prediction of the dysphagia risk of stroke patients and personalized intervention recommendations, improves the accuracy and reliability of the prediction, and at the same time enhances the pertinence and effectiveness of the intervention measures, which helps to improve the quality of life and rehabilitation effects of patients.

[0038] Furthermore, predictive factors include, but are not limited to, the patient's age, gender, stroke type, lesion location, degree of neurological deficit, etc.

[0039] Furthermore, a standardization algorithm is introduced to standardize the prediction factors to eliminate the dimensional differences between different features and improve the accuracy and stability of the model; the formula of the standardization algorithm is as follows:

[0040]

[0041] Among them, Z represents the standardized eigenvalue, X represents the original eigenvalue, μ represents the mean of the feature, σ Represents the standard deviation of the feature.

[0042] From the above, it can be seen that by eliminating the dimensional differences between different features, the accuracy and stability of the model are significantly improved; it ensures that the model can maintain consistent performance when dealing with diverse predictors, thereby improving the overall effectiveness and reliability of the risk prediction and personalized intervention recommendation system for dysphagia in stroke patients.

[0043] Furthermore, in the prediction model module, a logistic regression model is constructed to calculate the probability of dysphagia in patients; the formula of the logistic regression model is as follows:

[0044]

[0045] Among them, P(Y=1X) represents the probability of swallowing disorder in patients, X1,X 2,..., X n represents the predictor, β0, β 1,..., β n represents the regression coefficient;

[0046] At the same time, support vector machine (SVM) is introduced to process more complex data patterns and improve the accuracy of prediction. The formula of support vector machine is as follows:

[0047]

[0048] Among them, α i is the Lagrange multiplier, y i is the sample label, K(x i ,x) is the kernel function and b is the bias term.

[0049] As can be seen from the above, the present invention constructs a logistic regression model and introduces a support vector machine (SVM) in the prediction model module, and this combination significantly improves the accuracy of the prediction; the logistic regression model can accurately calculate the probability of dysphagia in patients based on predictive factors and regression coefficients, while the support vector machine is good at processing more complex data patterns, further enhancing the prediction ability of the model; the two complement each other and jointly improve the prediction accuracy of the dysphagia risk prediction and personalized intervention recommendation system for stroke patients, providing more reliable support for clinical decision-making.

[0050] Furthermore, in the prediction model module, for the long-term risk prediction of dysphagia in stroke patients, a survival analysis algorithm is introduced to evaluate the risk of dysphagia in patients at different time points. The formula of the survival analysis algorithm is as follows:

[0051] h(tx)=h0(t)exp(β1x1+β2x2+...+β n x n );

[0052] Where h(tx) is the patient’s risk function at time t, h0(t) is the baseline risk function, and β i is the regression coefficient, x i is a predictor.

[0053] From the above, it can be seen that the present invention introduces a survival analysis algorithm in the prediction model module to evaluate the long-term dysphagia risk of stroke patients at different time points, so that the system can have a more comprehensive understanding of the development trend of the patient's dysphagia, thereby providing a scientific basis for the formulation of long-term intervention strategies; the introduction of the survival analysis algorithm not only improves the accuracy of long-term risk prediction, but also helps doctors to adjust treatment plans in a timely manner, optimize the patient's rehabilitation process, and reduce the potential risks and complications caused by dysphagia.

[0054] Furthermore, the intervention recommendation module further introduces a collaborative filtering algorithm to recommend content based on the user's historical behavior and the behavior of other users. The formula of the collaborative filtering algorithm is as follows:

[0055]

[0056] Among them, S(u,i) is the predicted score of user u for item i, N(u) is the neighbor set of user u, sim(u,v) is the similarity between users u and v, r vi is the actual rating of user v on item i.

[0057] From the above, it can be seen that the present invention further introduces a collaborative filtering algorithm in the intervention recommendation module, which significantly improves the accuracy of personalized intervention recommendations and user experience; by comprehensively considering the user's historical behavior and the behavior of other users, the collaborative filtering algorithm can intelligently recommend swallowing disorder intervention measures that are more in line with their needs and preferences to the user; this recommendation method based on user behavior data not only enhances the personalization of the recommendation, but also helps to improve the user's acceptance of the recommended content and the implementation effect, thereby further promoting the rehabilitation process of stroke patients.

[0058] Furthermore, the system also includes a user feedback module for collecting user feedback on the implementation effects of recommended intervention measures to optimize the prediction model and intervention recommendation strategy.

[0059] From the above, we can see that by continuously obtaining actual feedback from users, the system can timely adjust and improve the prediction algorithm and recommendation logic, thereby ensuring that the recommended intervention measures are closer to the actual needs of patients; this continuous optimization mechanism based on user feedback not only improves the practicality and effectiveness of the system, but also helps to promote the continuous advancement of risk assessment and intervention technology for dysphagia in stroke patients.

[0060] Working principle: The data processing module receives and processes the relevant predictive factor values ​​of stroke patients, and then uses the prediction model module built based on a large amount of case data, including logistic regression model and support vector machine, to calculate the patient's dysphagia risk score; based on the calculated risk score, the intervention recommendation module will intelligently recommend personalized dysphagia intervention measures, which are further combined with collaborative filtering algorithms to improve the accuracy of recommendations; finally, the output module presents the risk score and recommended intervention measures to the user in a visual or textual form; at the same time, the user feedback module collects user feedback on the implementation effect of the recommended intervention measures in order to continuously optimize the prediction model and intervention recommendation strategy.

[0061] Furthermore, the effects of a dysphagia risk prediction and personalized intervention recommendation system for stroke patients based on R language in the embodiment are compared with the disease risk assessment and intervention recommendation system (comparative ratio) in the current prior art, and the following table is obtained:

[0062]

[0063]

[0064] As can be seen from the above table, the R language-based dysphagia risk prediction and personalized intervention recommendation system for stroke patients in this embodiment is comparable to many aspects of the disease risk assessment and intervention recommendation systems in the current prior art, highlighting the advantages and innovations of the present invention.

[0065] A method for predicting the risk of dysphagia and recommending personalized intervention for stroke patients based on R language, using the above-mentioned method for predicting the risk of dysphagia and recommending personalized intervention for stroke patients based on R language, comprising:

[0066] S1. Receive and process inputted stroke patient-related prediction factor values ​​through a data processing module, where the prediction factors include but are not limited to the patient's age, gender, stroke type, lesion location, degree of neurological deficit, etc.;

[0067] S2. Using the R language based on more than 6,000 stroke case data, the prediction model module was constructed to calculate the dysphagia risk score according to the input predictor value. The prediction model module constructed a logistic regression model and a support vector machine (SVM) to improve the accuracy of the prediction. The logistic regression model was used to calculate the probability of dysphagia in patients, and the support vector machine was used to process more complex data patterns.

[0068] S3. Based on the calculated risk score, the intervention recommendation module intelligently recommends personalized dysphagia intervention measures; the intervention recommendation module further introduces a collaborative filtering algorithm to recommend content based on the user's historical behavior and the behavior of other users;

[0069] S4, presenting the risk score and recommended intervention measures to the user in a visual or textual form through an output module;

[0070] S5. Collect user feedback on the implementation effects of recommended intervention measures through the user feedback module to optimize the prediction model and intervention recommendation strategy.

[0071] The present application embodiment provides an electronic device, which is applicable to the above-mentioned stroke patient dysphagia risk prediction and personalized intervention recommendation system based on R language, including:

[0072] Memory, used to protect computer programs and data;

[0073] Processor, used to run system programs.

[0074] An embodiment of the present application provides a computer storage medium, which is applicable to the above-mentioned swallowing disorder risk prediction and personalized intervention recommendation system for stroke patients built based on R language, and performs hierarchical confidentiality management on the above-mentioned system and data in accordance with confidentiality management requirements.

[0075] Those skilled in the art will appreciate that the embodiments of the present application may be provided as a system or a computer program product. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0076] The present application is described with reference to the flowcharts and / or block diagrams of the devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0077] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0078] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0079] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0080] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0081] Computer readable media include permanent and non-permanent, removable and non-removable media, and can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include transitory media such as modulated data signals and carrier waves.

[0082] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, commodity 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, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, commodity or device including the elements.

[0083] The embodiments of the present invention are provided for the purpose of illustration and description. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations of the present invention. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A risk prediction and personalized intervention recommendation system for dysphagia in stroke patients based on R language, characterized by: include: A data processing module, used for receiving and processing inputted stroke patient-related prediction factor values; The prediction model module was built using R language based on multiple stroke case data and was used to calculate the dysphagia risk score according to the input predictor values; The intervention recommendation module intelligently recommends personalized dysphagia intervention measures based on the calculated risk score; The output module is used to present the risk scores and recommended interventions to the user in visual or textual form.

2. The risk prediction and personalized intervention recommendation system for dysphagia in stroke patients based on R language as claimed in claim 1, characterized in that: The predictive factors include, but are not limited to, the patient's age, gender, stroke type, lesion location, and degree of neurological deficit.

3. A stroke patient dysphagia risk prediction and personalized intervention recommendation system based on R language as claimed in claim 2, characterized in that: A standardization algorithm is introduced to standardize the predictors.

4. The risk prediction and personalized intervention recommendation system for dysphagia in stroke patients based on R language as claimed in claim 1, characterized in that: In the prediction model module, a logistic regression model was also constructed to calculate the probability of patients developing dysphagia; At the same time, support vector machines are introduced to handle more complex data patterns.

5. The risk prediction and personalized intervention recommendation system for dysphagia in stroke patients based on R language as claimed in claim 1, characterized in that: In the prediction model module, for the long-term risk prediction of dysphagia in stroke patients, a survival analysis algorithm was introduced to evaluate the risk of dysphagia in patients at different time points.

6. The risk prediction and personalized intervention recommendation system for dysphagia in stroke patients based on R language as claimed in claim 1, characterized in that: The intervention recommendation module further introduces a collaborative filtering algorithm for recommending content based on the user's historical behavior and the behavior of other users.

7. The risk prediction and personalized intervention recommendation system for dysphagia in stroke patients based on R language as claimed in claim 1, characterized in that: The system also includes a user feedback module for collecting user feedback on the implementation effects of recommended interventions to optimize the prediction model and intervention recommendation strategy.

8. A method for predicting the risk of dysphagia and recommending personalized intervention for stroke patients based on R language, characterized by: A stroke patient dysphagia risk prediction and personalized intervention recommendation system based on R language as described in any one of claims 1 to 7, comprising: S1. Receive and process inputted stroke patient-related prediction factor values ​​through a data processing module, wherein the prediction factors include but are not limited to the patient's age, gender, stroke type, lesion location, and degree of neurological impairment; S2. Using a prediction model module constructed in R language based on more than 6,000 stroke case data, the risk score of dysphagia is calculated according to the input prediction factor value; a logistic regression model and a support vector machine are constructed in the prediction model module; the logistic regression model is used to calculate the probability of dysphagia in patients, and the support vector machine is used to process more complex data patterns; S3. Based on the calculated risk score, an intervention recommendation module intelligently recommends personalized dysphagia intervention measures; the intervention recommendation module further introduces a collaborative filtering algorithm to recommend content based on the user's historical behavior and the behavior of other users; S4, presenting the risk score and recommended intervention measures to the user in a visual or textual form through an output module; S5. Collect user feedback on the implementation effects of recommended intervention measures through the user feedback module to optimize the prediction model and intervention recommendation strategy.

9. A processor, characterized in that: The system is configured to execute a dysphagia risk prediction and personalized intervention recommendation system for stroke patients based on R language according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the system for predicting the risk of dysphagia in stroke patients and recommending personalized intervention based on R language as described in any one of claims 1 to 7 is implemented.

Images