Colorectal tumor patient state real-time monitoring method and system

Abstract

The invention discloses a real-time monitoring method and system for the state of a colorectal tumor patient, and relates to the technical field of colorectal tumor monitoring, and the method comprises the steps: collecting the health original data of the patient, carrying out the preprocessing, and generating a patient health monitoring data set; performing data analysis and risk assessment operation on the patient health monitoring data set to obtain a physiological risk assessment result; according to the personalized intervention measures, through treatment effect monitoring and feedback adjustment operation, an optimized treatment scheme is obtained; and performing treatment effect monitoring and patient feedback analysis operation on the optimized treatment scheme to generate a health report. According to the invention, through accurate data acquisition and preprocessing, deep analysis and generation of personalized intervention measures, the accuracy and personalization of a treatment scheme are effectively improved.

Description

Technical Field

[0001] This invention relates to the field of colorectal tumor monitoring technology, and in particular to a method and system for real-time monitoring of the condition of colorectal tumor patients. Background Technology

[0002] In recent years, the early diagnosis and treatment of colorectal cancer has become a crucial research area in global public health. With the rapid development of medical imaging technology and molecular biology, clinicians can now comprehensively assess patients' physiological, imaging, and tumor marker data in real time, enabling early screening, accurate diagnosis, and personalized treatment plans. These technological advancements have significantly improved the survival rate and quality of life for colorectal cancer patients.

[0003] While existing technologies have made some progress in data acquisition, processing, and evaluation, some limitations remain. Current technologies often rely on traditional data analysis methods, which suffer from problems such as data noise interference, insufficient imputation of missing values, and inadequate handling of outliers. This results in inaccurate health monitoring datasets, affecting the precision of subsequent risk assessment and treatment optimization. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a method for real-time monitoring of the condition of colorectal cancer patients, which solves the shortcomings of existing technologies in terms of data processing accuracy and personalized treatment plan optimization.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: In a first aspect, the present invention provides a method for real-time monitoring of the condition of patients with colorectal cancer, comprising, Collect raw patient health data, perform preprocessing, and generate a patient health monitoring dataset; Perform data analysis and risk assessment on the patient health monitoring dataset to obtain physiological risk assessment results; The physiological risk assessment results and the patient's comprehensive characteristic data are input into the comprehensive assessment model to perform in-depth analysis and treatment plan optimization, and generate personalized intervention measures. Based on personalized interventions, the operation is adjusted through treatment effect monitoring and feedback to obtain an optimized treatment plan; The system monitors the treatment effectiveness of optimized treatment plans and analyzes patient feedback to generate health reports.

[0007] As a preferred embodiment of the real-time monitoring method for the status of colorectal cancer patients according to the present invention, the specific steps for collecting raw patient health data, preprocessing it, and generating a patient health monitoring dataset are as follows. Raw patient health data is collected, denoised, and cleaned to generate a dataset. Then, standardization is performed to obtain a standardized patient health dataset. Perform missing value imputation on the standardized patient health dataset to obtain the complete health dataset, and perform outlier correction to generate an optimized health monitoring dataset; A comprehensive analysis and evaluation are performed on the optimized health monitoring dataset to generate a patient health monitoring dataset.

[0008] In a preferred embodiment of the real-time monitoring method for the status of colorectal cancer patients described in this invention, the steps for performing data analysis and risk assessment on the patient health monitoring dataset to obtain physiological risk assessment results are as follows: Multidimensional feature extraction is performed on the patient health monitoring dataset, and combined with time series analysis, the dynamic trends in the patient health monitoring dataset are captured to obtain the patient health trend dataset. Based on the patient health trend dataset, intelligent dimensionality reduction is used for feature selection and data compression to identify abnormal fluctuations and potential risks in health data, resulting in an abnormal risk indicator dataset. By integrating patient health trend datasets and abnormal risk indicator datasets, and through multi-dimensional analysis and intelligent weighting mechanisms, the assessment weights are adjusted in real time to accurately assess patient health risks and generate physiological risk assessment results.

[0009] As a preferred embodiment of the real-time monitoring method for the status of colorectal cancer patients according to the present invention, the specific steps for generating personalized intervention measures are as follows: The physiological risk assessment results and the patient's comprehensive characteristic data are input into the comprehensive assessment model to perform in-depth analysis and treatment plan optimization, and generate a health risk prediction report. The health risk prediction report and physiological risk assessment indicators are integrated and standardized to generate a comprehensive input dataset; Based on the comprehensive input dataset, priority scores are output through deep neural network analysis. Personalized intervention decisions are made based on priority scores to generate personalized intervention measures.

[0010] As a preferred embodiment of the real-time monitoring method for the status of colorectal tumor patients according to the present invention, the specific steps for obtaining the optimized treatment plan are as follows: Collect patient physiological data, and perform noise reduction, standardization, and outlier detection to generate a cleaned treatment effect dataset; The cleaned treatment effect dataset is input into a deep neural network model, and preliminary treatment effect evaluation results are generated through feature extraction and pattern recognition. Based on the preliminary treatment effect assessment results, a reinforcement learning mechanism is used to dynamically optimize the treatment plan and generate a preliminary optimized treatment plan. By using the cleaned treatment effect dataset and the preliminary optimized treatment plan, combined with treatment feedback data, the differences in the effects on physiological indicators, symptom improvement and side effects are evaluated. Based on the evaluation results, the preliminary optimized treatment plan is adjusted and the adjusted treatment plan is generated. The effects of the adjusted treatment plan are simulated and predicted to generate an optimized treatment plan.

[0011] In a preferred embodiment of the real-time monitoring method for the status of colorectal cancer patients according to the present invention, the specific steps for generating a health report are as follows: Collect treatment feedback data from the implementation of optimized treatment plans and generate a treatment feedback dataset; Data analysis and comparison are performed on the treatment feedback dataset to generate evaluation results of differences in treatment effectiveness; Based on the evaluation results of differences in treatment effects, the effectiveness of optimizing treatment plans is analyzed, and combined with real-time monitored patient feedback data, treatment parameters are automatically adjusted to generate customized adjustment plans. The customized adjustment plan is applied to the treatment procedure, the treatment effect is continuously monitored and the patient feedback is analyzed to generate health reports.

[0012] As a preferred embodiment of the real-time monitoring method for the status of colorectal cancer patients according to the present invention, the specific steps for generating the patient health monitoring dataset are as follows: For the optimized health monitoring dataset, feature extraction and multidimensional data fusion are performed to generate a comprehensive health status monitoring dataset by combining different dimensions of health status. Based on the comprehensive health status monitoring dataset, similarity analysis and multidimensional data fusion are used to obtain the health status difference assessment value; The assessment values ​​of differences in health status are comprehensively analyzed and integrated to generate a patient health monitoring dataset.

[0013] As a preferred embodiment of the real-time monitoring method for the status of colorectal cancer patients according to the present invention, the step of obtaining physiological risk assessment results based on a physiological feature dataset and a weighted risk assessment model is as follows: The physiological feature dataset is cleaned, features are extracted, and standardized to transform it into a numerical matrix. The numerical matrix is ​​input into the weighted risk assessment model for calculation and analysis to generate physiological risk assessment results.

[0014] As a preferred embodiment of the real-time monitoring method for the status of colorectal cancer patients according to the present invention, the specific steps for analyzing and comparing the treatment feedback dataset to generate a treatment effect difference evaluation result are as follows. The treatment feedback dataset is cleaned, invalid data and duplicate records are removed, features are extracted, and feature selection is performed to identify key variables. Comparative analysis and statistical processing of key variables were performed to calculate the differences before and after treatment and generate evaluation results of treatment effect differences.

[0015] Secondly, this invention provides a real-time monitoring system for the status of colorectal cancer patients, including, The data acquisition module is used to collect raw patient health data, perform preprocessing, and generate patient health monitoring datasets. The risk assessment module is used to perform data analysis and risk assessment operations on patient health monitoring datasets to obtain physiological risk assessment results. The treatment plan optimization module is used to input physiological risk assessment results and comprehensive patient characteristic data into the comprehensive assessment model, perform in-depth analysis and treatment plan optimization operations, and generate personalized intervention measures. The feedback adjustment module is used to obtain an optimized treatment plan based on personalized intervention measures through treatment effect monitoring and feedback adjustment operations; The report generation module is used to monitor the treatment effects of optimized treatment plans and analyze patient feedback to generate health reports.

[0016] The beneficial effects of this invention are as follows: It provides a method for real-time monitoring of the condition of colorectal cancer patients. Through precise data acquisition and preprocessing, in-depth analysis, and the generation of personalized intervention measures, it effectively improves the accuracy and personalization of treatment plans. Specifically, the noise reduction, standardization, and outlier correction steps ensure the accuracy of the data, providing a reliable basis for risk assessment and treatment optimization. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart for a method of real-time monitoring of the condition of colorectal cancer patients.

[0019] Figure 2 This is a schematic diagram of a real-time monitoring system for colorectal cancer patients.

[0020] Figure 3 A flowchart of the process for generating physiological risk assessment results.

[0021] Figure 4 A flowchart for the process of generating personalized interventions. Detailed Implementation

[0022] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0023] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0024] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0025] Reference Figures 1-4 As one embodiment of the present invention, this embodiment provides a method for real-time monitoring of the status of colorectal cancer patients, including the following steps: S1. Collect raw health data from patients, perform preprocessing, and generate a patient health monitoring dataset; S1.1 Collect raw patient health data, perform noise reduction processing to generate a cleaned dataset, and perform standardization processing to obtain a standardized patient health dataset; It should be noted that real-time monitoring of patients' physiological data, imaging data, and tumor marker data yields raw patient health data. Noise reduction methods, such as median filtering and wavelet denoising, are then used to remove noise and irrelevant information from the data, generating a cleaned dataset. The cleaned dataset undergoes standardization processing, including Z-score standardization for physiological data, grayscale standardization for imaging data, and interval scaling for tumor marker data, ensuring that all data conform to a uniform numerical range and units, resulting in a standardized patient health dataset.

[0026] S1.2 Perform missing value imputation on the standardized patient health dataset to obtain the complete health dataset, and perform outlier correction to generate an optimized health monitoring dataset; It should be noted that missing items in the standardized patient health dataset are identified. Mean imputation is used to fill in the missing data to ensure dataset integrity. When correcting outliers in the complete health dataset, outliers are identified through statistical methods, visualization checks, and distribution analysis. Median replacement, interpolation, and smoothing methods are used to correct outliers, and finally, validation is performed to ensure data quality. After these processes, an optimized health monitoring dataset is generated, ensuring high data quality standards.

[0027] S1.3 Perform comprehensive analysis and evaluation on the optimized health monitoring dataset to generate a patient health monitoring dataset.

[0028] It should be noted that feature extraction was performed on the optimized health monitoring dataset to identify important variables affecting patients' health status, such as physiological data, imaging data, and tumor marker data. Regression analysis was used to assess the interrelationships among these data and their impact on patient health. Combining these data, a comprehensive assessment of patient health status was conducted from multiple dimensions. For example, by analyzing the correlations between different data sources (physiological, imaging, and biomarker data), key factors influencing health were identified. The final complete patient health monitoring dataset provides a comprehensive assessment of health status.

[0029] S2. Perform data analysis and risk assessment on the patient health monitoring dataset to obtain physiological risk assessment results; S2.1. Perform multidimensional feature extraction on the patient health monitoring dataset and combine it with time series analysis to capture the dynamic trends in the patient health monitoring dataset and obtain the patient health trend dataset. It should be noted that multiple dimensions of features are extracted from the patient health monitoring dataset, including physiological parameters, imaging data, and biochemical biomarkers, with a focus on indicators closely related to health. Time-series analysis methods are used to identify the changing trends of each dimension of features over time, capturing dynamic fluctuation patterns of health indicators, such as periodic changes or sudden fluctuations. Based on the results of multidimensional feature extraction and time-series analysis, a patient health trend dataset is generated.

[0030] S2.2 Based on the patient health trend dataset, intelligent dimensionality reduction is used for feature selection and data compression to identify abnormal fluctuations and potential risks in health data, resulting in an abnormal risk indicator dataset.

[0031] It should be noted that intelligent dimensionality reduction is used to process the patient health trend dataset, selecting features closely related to changes in health status and removing redundant information, thereby compressing the data dimensionality. The dimensionality-reduced data is then used to identify abnormal fluctuations in the health data, which reveal potential health risks. Combined with dynamic trend information, these abnormal fluctuations are analyzed to generate an abnormal risk indicator dataset.

[0032] S2.3. By integrating the patient health trend dataset and the abnormal risk indicator dataset, and through multi-dimensional analysis and intelligent weighting mechanism, the assessment weights are adjusted in real time to accurately assess the patient's health risk and generate physiological risk assessment results.

[0033] It should be noted that the features from the patient health trend dataset and the abnormal risk indicator dataset are integrated to ensure comprehensive integration of relevant information from each dataset. Multi-dimensional analysis methods are used, combining the correlation and importance of each feature data, to identify key influencing factors in health status. An intelligent weighting mechanism is employed to adjust the evaluation weights of each feature, ensuring that important health indicators and risk factors are fully reflected in the comprehensive assessment process. Based on the adjusted evaluation weights, a precise health risk assessment is conducted, generating physiological risk assessment results.

[0034] S3. Input the physiological risk assessment results and the patient's comprehensive characteristic data into the comprehensive assessment model, perform in-depth analysis and treatment plan optimization operations, and generate personalized intervention measures; S3.1 Input the physiological risk assessment results and the patient's comprehensive characteristic data into the comprehensive assessment model, perform in-depth analysis and treatment plan optimization operations, and generate a health risk prediction report.

[0035] It should be noted that the results of the physiological risk assessment are combined with the patient's comprehensive characteristic data and provided as input data to the comprehensive assessment model. The comprehensive assessment model performs in-depth analysis of the input data to comprehensively assess the patient's health status and potential risks. During the analysis, the model optimizes the patient's treatment plan by adjusting the weights of various features and performing correlation analysis, ensuring that the most suitable treatment strategy is proposed based on the patient's specific health condition. Based on the results of the in-depth analysis and treatment plan optimization, a health risk prediction report is generated.

[0036] It should also be noted that the training process of the comprehensive evaluation model includes: preparing the training dataset, initializing the model parameters, performing forward propagation to calculate the output, calculating the error and adjusting the model parameters through backpropagation, and updating the parameters using an optimization algorithm. Through multiple iterative optimizations, the error is gradually reduced until the model accurately maps the relationship between the input features and the target output.

[0037] S3.2 Integrate and standardize the health risk prediction report and physiological risk assessment indicators to generate a comprehensive input dataset.

[0038] It should be noted that the health risk prediction report and physiological risk assessment indicators should be integrated to ensure that relevant information from both is fully combined. The integrated data should be standardized using appropriate methods (e.g., Z-score standardization) to ensure uniformity of measurement and avoid the impact of data scale differences on subsequent analysis. A comprehensive input dataset should then be generated.

[0039] S3.3 Based on the comprehensive input dataset, a priority score is output through deep neural network analysis; It should be noted that various features from the comprehensive input dataset (such as physiological data and risk assessment results) are used as input and processed by a deep neural network. The deep neural network continuously optimizes the weights through multi-layered feedforward and backpropagation processes, automatically extracting potential correlation patterns and complex relationships between features from the comprehensive health assessment dataset. Through repeated training and optimization, the deep neural network can identify the contribution of each feature to the overall health intervention. Based on the output of the deep neural network, the priority score of each feature in the health intervention is calculated. The priority score indicates the degree to which each feature should be given emphasis during the intervention process.

[0040] It should also be noted that the training process of a deep neural network (DNN) is optimized using the backpropagation algorithm. During training, forward propagation is used to calculate the output of each layer and the final prediction result. The prediction result is compared with the actual label to calculate the loss value. Using the backpropagation algorithm, the gradient of each neuron is calculated, and the weights and biases of the deep neural network are updated using gradient descent to minimize the loss. This process is repeated iteratively until the weights of the deep neural network converge, thus achieving effective learning and prediction of the data.

[0041] S3.4 Adjust the priority scores for personalized intervention decisions and generate personalized intervention measures.

[0042] It should be noted that, based on the priority scores output by the deep neural network, a comprehensive assessment of the patient's health status is conducted to identify the health characteristics and risk factors that have the greatest impact on the patient's health. This determines the priority of various personalized interventions (such as medication, dietary adjustments, and exercise programs), prioritizing those factors that have a greater impact on the patient's health. Based on the patient's specific health needs, medication, dietary adjustments, exercise programs, and psychological counseling are personalized. For example, based on the patient's physical condition, age, medical history, and other characteristics, medication dosages, treatment cycles, or lifestyle changes are tailored to their individual needs. Through this customized adjustment, more precise and efficient personalized interventions are generated.

[0043] S4. Based on personalized intervention measures, adjust the operation through treatment effect monitoring and feedback to obtain an optimized treatment plan; S4.1 Collect patient physiological data, and perform noise reduction, standardization, and outlier detection to generate a cleaned treatment effect dataset; It should be noted that patient physiological data is collected, which may include important physiological indicators such as heart rate, blood pressure, and body temperature. Denoising techniques are applied to process the data to remove potential noise and ensure data quality and accuracy. Commonly used denoising methods include median filtering or wavelet denoising. The processed data is then standardized to unify the data scale and ensure the comparability and consistency of various physiological indicators. Outlier detection is performed to identify extreme values ​​in the data, which may be due to measurement errors. Based on the results of denoising, standardization, and outlier detection, a cleaned treatment effect dataset is generated.

[0044] S4.2 Input the cleaned treatment effect dataset into the deep neural network model, and generate preliminary treatment effect evaluation results through feature extraction and pattern recognition.

[0045] It should be noted that the cleaned treatment effect dataset is used as input data to the deep neural network model. The deep neural network model extracts features from the input data through a multi-layered network structure, automatically identifying key patterns and potential relationships within the data. During feature extraction, the deep neural network model processes different treatment effect indicators, extracting the features with the highest diagnostic value. Through pattern recognition technology, the deep neural network model analyzes and identifies relevant patterns in the treatment effects, thereby generating preliminary treatment effect assessment results.

[0046] It should also be noted that the training steps for a deep neural network model include: preparing a training dataset, initializing network parameters, calculating the output using forward propagation, calculating the error and adjusting the parameters through backpropagation, and iteratively optimizing the network weights until the deep neural network model can accurately predict the target output.

[0047] S4.3 Based on the preliminary treatment effect evaluation results, a reinforcement learning mechanism is used to dynamically optimize the treatment plan and generate a preliminary optimized treatment plan.

[0048] It should be noted that, based on the preliminary treatment efficacy assessment results, the treatment plan is dynamically adjusted using a reinforcement learning mechanism. The reinforcement learning mechanism evaluates the rewards and penalties for each treatment decision based on the feedback from the current treatment plan's effectiveness, and adjusts the treatment strategy after each feedback. Through multiple iterations, the reinforcement learning mechanism gradually optimizes treatment decisions, adjusts treatment parameters, and makes the treatment plan more suitable for the patient's health needs, generating a preliminary optimized treatment plan.

[0049] S4.4. Using the cleaned treatment effect dataset and the preliminary optimized treatment plan, combined with treatment feedback data, evaluate the differences in the effects of physiological indicators, symptom improvement and side effects, adjust the preliminary optimized treatment plan based on the evaluation results, and generate the adjusted treatment plan.

[0050] It should be noted that the cleaned treatment effect dataset is combined with the preliminary optimized treatment plan, and treatment feedback data is incorporated to evaluate physiological indicators, symptom improvement, and side effects. By comparing data before and after treatment, changes in various physiological indicators, the degree of symptom improvement, and the frequency and intensity of side effects are analyzed to identify differences in treatment effectiveness. Based on the evaluation results, relevant parameters in the treatment plan are adjusted to optimize treatment effectiveness, reduce side effects, and generate a new treatment plan based on the adjusted plan.

[0051] S4.5 Perform effect simulation and predictive analysis on the adjusted treatment plan to generate an optimized treatment plan.

[0052] It should be noted that the adjusted treatment plan undergoes effect simulation, utilizing existing predictive analytics methods to virtually simulate the treatment process. Through simulation analysis, the effectiveness of the treatment plan under different conditions is predicted, including changes in physiological indicators, the likelihood of symptom improvement, and the incidence of side effects. The overall effectiveness of the treatment plan is evaluated based on the simulation results, identifying potential problems or areas for optimization. Based on the results of the effect simulation and predictive analysis, an optimized treatment plan is generated.

[0053] S5. Monitor the treatment effect and analyze patient feedback for the optimized treatment plan, and generate a health report.

[0054] S5.1 Collect all relevant feedback information from the patient's treatment process, including physiological reactions (such as changes in body temperature and blood sugar), imaging changes (such as changes in CT scans, X-rays, etc.), and changes in subjective symptoms (such as pain and fatigue). Organize and classify the collected feedback information to ensure that the reaction data, imaging changes, and subjective symptoms can effectively reflect the treatment effect and the patient's physiological and psychological reactions, and generate a treatment feedback dataset containing all feedback information.

[0055] S5.2 Analyze and compare the treatment feedback dataset to generate evaluation results of differences in treatment effectiveness; It should be noted that the data in the treatment feedback dataset should be organized to ensure comparability of feedback information under different treatment plans. Data analysis methods (such as statistical analysis and analysis of variance) should be used to compare the effects before and after treatment, evaluate the actual effectiveness of each treatment plan, and identify possible differences that may arise during the treatment process. For example, analyzing changes in the patient's physiological responses and imaging changes can clarify whether the treatment plan has achieved the expected results. Finally, the evaluation results of treatment effect differences are generated by comparing and analyzing various health indicators.

[0056] S5.3 Based on the evaluation results of differences in treatment effects, analyze the effectiveness of optimizing the treatment plan, and combine it with real-time monitored patient feedback data to automatically adjust treatment parameters and generate customized adjustment plans; It should be noted that, based on the evaluation results of treatment effect differences, the effectiveness of the optimized treatment plan is assessed, and it is analyzed whether the treatment has achieved the expected health improvement goals. By combining real-time monitored patient feedback data (such as blood pressure, heart rate, and imaging data), parameters of the treatment plan, such as drug dosage, treatment cycle, or intervention intensity, are dynamically adjusted to ensure maximum treatment effect. Similarity metric analysis is used to compare treatment responses from different patients, further optimizing the plan and ensuring that personalized treatment plans better meet the actual needs of patients. Customized adjustment plans are then generated.

[0057] It should also be noted that the effectiveness of the optimized treatment plan is determined through a comprehensive evaluation of pre- and post-treatment differences, the degree of achievement of treatment goals, patient feedback data, and similarity measurement analysis, in order to identify the treatment effect and guide adjustments.

[0058] S5.4 Apply customized adjustment plans to treatment procedures, continuously monitor treatment effects and analyze patient feedback to generate health reports.

[0059] It should be noted that customized adjustment plans are applied to actual treatment procedures, with continuous monitoring of patients' physiological data, imaging data, and subjective symptoms (such as pain and fatigue). Treatment effectiveness is periodically evaluated through statistical analysis of various indicators in the treatment effectiveness monitoring data and patient feedback, and compared with treatment goals to ensure consistency between the treatment process and the expected objectives. Continuous tracking and dynamic adjustments are made to ensure the accuracy and effectiveness of the treatment plan. A health report is ultimately generated by comparing the differences between the treatment effect and the expected goals.

[0060] This embodiment also provides a real-time monitoring system for the status of colorectal cancer patients, including: The data acquisition module is used to collect raw patient health data, perform preprocessing, and generate patient health monitoring datasets. The risk assessment module is used to perform data analysis and risk assessment operations on patient health monitoring datasets to obtain physiological risk assessment results. The treatment plan optimization module is used to input physiological risk assessment results and comprehensive patient characteristic data into the comprehensive assessment model, perform in-depth analysis and treatment plan optimization operations, and generate personalized intervention measures. The feedback adjustment module is used to obtain an optimized treatment plan based on personalized intervention measures through treatment effect monitoring and feedback adjustment operations; The report generation module is used to monitor the treatment effects of optimized treatment plans and analyze patient feedback to generate health reports.

[0061] This embodiment also provides a computer device applicable to the real-time monitoring method for the status of colorectal cancer patients, including: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to realize the real-time monitoring method for the status of colorectal cancer patients as proposed in the above embodiment.

[0062] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0063] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements the method for real-time monitoring of the status of colorectal cancer patients as proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0064] In summary, this invention provides a method for real-time monitoring of the condition of colorectal cancer patients. Through precise data acquisition and preprocessing, in-depth analysis, and the generation of personalized intervention measures, it effectively improves the accuracy and personalization of treatment plans. Specifically, denoising, standardization, and outlier correction steps ensure data accuracy, providing a reliable foundation for risk assessment and treatment optimization.

[0065] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for real-time monitoring of the status of a colorectal tumor patient, characterized in that: Comprising, Collecting patient health raw data, preprocessing, generating patient health monitoring data set; Performing data analysis and risk assessment operation on patient health monitoring data set, obtaining physiological risk assessment result; Inputting physiological risk assessment result and patient comprehensive feature data into comprehensive assessment model, performing deep analysis and treatment scheme optimization operation, generating individualized intervention measures; According to the individualized intervention measures, through the treatment effect monitoring and feedback adjustment operation, the optimized treatment scheme is obtained; Performing treatment effect monitoring and patient feedback analysis operation on the optimized treatment scheme, generating health report.

2. The method for real-time monitoring of the condition of colorectal cancer patients as described in claim 1, characterized in that: The collecting patient health raw data, preprocessing, generating patient health monitoring data set, specific steps are as follows, Collecting patient health raw data, denoising, generating cleaned data set, and performing standardization processing, obtaining standardized patient health data set; Performing missing value filling operation on the standardized patient health data set, obtaining complete health data set, and performing outlier correction, generating optimized health monitoring data set; Performing comprehensive analysis and evaluation on the optimized health monitoring data set, generating patient health monitoring data set.

3. The method of claim 2, wherein the method further comprises: determining the state of the patient based on the determined state of the patient and the determined state of the patient's colorectal tumor. The specific steps of the data analysis and risk assessment operation on the patient health monitoring data set are as follows, Extracting multi-dimensional features from patient health monitoring data set, and combining time series analysis to capture dynamic trend in patient health monitoring data set, obtaining patient health trend data set; Based on patient health trend data set, intelligent dimension reduction is used for feature selection and data compression, abnormal fluctuation and potential risk in health data are identified, and abnormal risk indication data set is obtained; Integrating patient health trend data set and abnormal risk indication data set, adjusting evaluation weight in real time through multi-dimensional analysis and intelligent weighting mechanism, accurately evaluating patient health risk, and generating physiological risk assessment result.

4. The method of claim 3, wherein the method further comprises: determining the state of the patient based on the determined state of the patient and the determined state of the patient's colorectal tumor. The specific steps of generating individualized intervention measures are as follows, Inputting physiological risk assessment result and patient comprehensive feature data into comprehensive assessment model, performing deep analysis and treatment scheme optimization operation, generating health risk prediction report; Integrating and standardizing health risk prediction report and physiological risk assessment index, generating comprehensive input data set; Based on the comprehensive input data set, the priority score is output through deep neural network analysis; Adjusting the priority score for individualized intervention decision, generating individualized intervention measures.

5. The method of claim 4, wherein the method further comprises: determining the state of the patient based on the determined state of the patient and the determined state of the patient's colorectal tumor. The specific steps of obtaining the optimized treatment scheme are as follows, Collecting patient physiological data, and performing denoising, standardization and outlier detection, generating cleaned treatment effect data set; Inputting the cleaned treatment effect data set into deep neural network model, generating preliminary treatment effect evaluation result through feature extraction and pattern recognition; Based on the preliminary treatment effect evaluation result, using reinforcement learning mechanism to dynamically optimize the treatment scheme, generating preliminary optimized treatment scheme; Through the cleaned treatment effect data set and the preliminary optimized treatment scheme, combining the treatment feedback data to evaluate the effect difference of physiological index, symptom improvement and side effect, and adjusting the preliminary optimized treatment scheme based on the evaluation result, and generating adjusted treatment scheme; The adjusted treatment plan is simulated and predicted to generate an optimized treatment plan.

6. The method of claim 5, wherein the method further comprises: determining the state of the patient based on the determined state of the patient and the determined state of the patient's colorectal tumor. The health report is generated, and the specific steps are as follows, Collect treatment feedback data of the optimized treatment plan to generate a treatment feedback dataset; Data analysis and comparison are performed on the treatment feedback dataset to generate a treatment effect difference evaluation result; According to the treatment effect difference evaluation result, the effectiveness of the optimized treatment plan is analyzed, and the treatment parameters are automatically adjusted combined with the real-time monitoring of patient feedback data to generate a customized adjustment plan; The customized adjustment plan is applied to the treatment operation, the treatment effect is continuously monitored, and the patient feedback is analyzed to generate a health report.

7. The method of claim 2, wherein the method further comprises: determining the presence of a colorectal tumor in the patient; and determining the presence of a colorectal tumor in the patient. The patient health monitoring dataset is generated, and the specific steps are as follows, According to the comprehensive health state monitoring dataset, the health state difference evaluation value is obtained through similarity analysis and multi-dimensional data fusion; The patient health monitoring dataset is generated by comprehensive analysis and data integration of the health state difference evaluation value. The physiological risk assessment result is obtained by calculating the physiological feature dataset based on the weighted risk assessment model, and the specific steps are as follows, 8. The method for real-time monitoring of the condition of colorectal cancer patients as described in claim 3, characterized in that: The physiological feature dataset is cleaned, the features are extracted, and the standardized processing is converted into a numerical matrix; The numerical matrix is input into the weighted risk assessment model for calculation and analysis to generate the physiological risk assessment result. The treatment feedback dataset is analyzed and compared to generate a treatment effect difference evaluation result, and the specific steps are as follows, 9. The method of claim 6, wherein the method further comprises: determining the presence of a colorectal tumor in the patient; and determining the presence of a colorectal tumor in the patient. The treatment feedback dataset is cleaned, invalid data and duplicate records are deleted, features are extracted, and key variables are selected and identified; The key variables are compared and statistically processed to calculate the difference before and after treatment and generate the treatment effect difference evaluation result. It includes, 10. A system for real-time monitoring of the status of a patient with colorectal cancer, based on the method for real-time monitoring of the status of a patient with colorectal cancer according to any one of claims 1 to 9, characterized in that: The data acquisition module is used to collect patient health raw data, pre-process, and generate a patient health monitoring dataset; The risk assessment module is used to perform data analysis and risk assessment operations on the patient health monitoring dataset to obtain a physiological risk assessment result; The scheme optimization module is used to input the physiological risk assessment result and patient comprehensive feature data into a comprehensive evaluation model to perform deep analysis and treatment plan optimization operations to generate individualized intervention measures; The feedback adjustment module is used to obtain an optimized treatment plan through treatment effect monitoring and feedback adjustment operations according to the individualized intervention measures; The report generation module is used to perform treatment effect monitoring and patient feedback analysis operations on the optimized treatment plan to generate a health report. ​

Images