Esophagus cancer patient nursing remote monitoring system and method capable of improving nursing level

Abstract

The invention relates to the technical field of data processing, and discloses an esophageal cancer patient nursing remote monitoring system and method capable of improving the nursing level, and the system comprises a data collection module, a personalized data transmission module, a remote monitoring center and a remote service module. The personalized data transmission module is used for predicting potential key data of a patient by using a collaborative recommendation algorithm, distributing corresponding personalized transmission parameters to the potential key data and non-potential key data in the monitoring data, and transmitting the monitoring data to the patient based on a 5G communication technology and the corresponding personalized transmission parameters; the potential key data and the non-potential key data are transmitted to a remote monitoring center; and the remote monitoring center is used for receiving the monitoring data and performing remote monitoring analysis on the nursing condition according to the monitoring data. According to the method, the doctor seeing burden of the patient can be relieved, medical staff can obtain key data in the first time, a more appropriate treatment scheme is formulated for the patient, and therefore the overall medical care level is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a remote monitoring system and method for the care of esophageal cancer patients capable of improving the care level. Background Art

[0002] In today's medical care field, patient care is particularly important for many diseases that require long-term monitoring, such as esophageal cancer. The treatment and recovery process of such diseases often requires medical staff to monitor the patient's vital signs and dietary status in real time in order to promptly detect and deal with possible complications. However, the traditional care model mostly relies on patients to go to hospitals or clinics for regular checkups in person. The limitations of this approach are obvious: it not only increases the physical and mental burden on patients, but also fails to achieve continuous and comprehensive real-time data monitoring and care intervention.

[0003] With the advancement of science and technology, especially the widespread application of 5G communication technology, remote medical monitoring systems are gradually becoming a reality. These monitoring systems based on 5G technology can transmit patients' health data to medical staff in real time through wireless networks, allowing medical staff to remotely monitor patients' health status in real time and provide professional nursing advice in a timely manner based on data changes. This innovative model has alleviated the pressure on patients to see a doctor to a certain extent and improved the convenience and efficiency of nursing work.

[0004] However, existing remote monitoring systems still face many challenges when processing massive amounts of monitoring data. Most systems lack effective data analysis and personalized transmission strategies, resulting in low data transmission efficiency and relatively high costs. On the one hand, a large amount of irrelevant data is mixed with key data, increasing the difficulty of data processing; on the other hand, due to the lack of judgment on data priority, key data cannot be transmitted in a timely manner, thus affecting the real-time and accuracy of remote monitoring.

[0005] In order to solve these problems, there is an urgent need for a remote medical monitoring system that can perform intelligent analysis on different data types and implement personalized transmission strategies. Therefore, the present invention proposes a remote monitoring system and method for the care of esophageal cancer patients that can improve the level of care. Summary of the invention

[0006] In view of the problems in the related art, the present invention proposes a remote monitoring system and method for the care of esophageal cancer patients that can improve the care level, so as to overcome the above-mentioned technical problems existing in the existing related art.

[0007] To this end, the specific technical solution adopted by the present invention is as follows: According to one aspect of the present invention, a remote monitoring system for esophageal cancer patient care that can improve the level of care is provided, including a data acquisition module, a personalized data transmission module, a remote monitoring center, and a remote service module; Wherein, the data acquisition module is used to monitor the patient's vital signs data and diet log in real time; The personalized data transmission module is used to predict the patient's potential key data using a collaborative recommendation algorithm, and to assign corresponding personalized transmission parameters to the potential key data and non-potential key data in the monitoring data, and to transmit the potential key data and non-potential key data to the remote monitoring center based on 5G communication technology and corresponding personalized transmission parameters; The remote monitoring center is used to receive monitoring data and perform remote monitoring and analysis on the nursing status based on the monitoring data; The remote service module is used to provide remote services to patients based on monitoring and analysis results; The personalized data transmission module includes a data characteristic analysis module, a potential key data prediction module, a personalized transmission parameter allocation module and a monitoring data transmission module; The data characteristic analysis module is used to analyze and identify the data type, data volume and data change rate of the monitoring data; The potential key data prediction module is used to predict and analyze the potential key data of the patient using a collaborative recommendation algorithm; The personalized transmission parameter allocation module is used to allocate corresponding personalized transmission parameters to potential key data and non-potential key data in the monitoring data using an optimization algorithm; The monitoring data transmission module is used to utilize 5G communication technology and corresponding personalized transmission parameters to transmit potential key data and non-potential key data to a remote monitoring center respectively.

[0008] Furthermore, the data acquisition module includes a vital sign data monitoring module and a diet status monitoring module; Wherein, the vital sign data monitoring module is used to collect vital sign data of esophageal cancer patients during the nursing process; The dietary status monitoring module is used to collect dietary data of esophageal cancer patients during the nursing process.

[0009] Furthermore, the potential key data prediction module includes a patient similarity analysis module, a patient network construction module and a potential key data recommendation module; Wherein, the patient similarity analysis module is used to analyze and calculate the similarities between different patients in the database; The patient network construction module is used to construct a patient network based on the similarity analysis results, and the patient network uses each patient as a node and establishes edges between similar patients; The potential key data recommendation module is used to find neighbors similar to the target patient in the patient network and recommend potential key data for the target patient based on the historical data of the neighbors.

[0010] Furthermore, the patient similarity analysis module includes: Obtain age, gender, esophageal cancer type, stage, treatment history, vital sign parameters, and dietary data of different patients in the database; The similarity measurement method was used to calculate the similarity of patients in terms of age, gender, esophageal cancer type, stage, treatment history, vital sign parameters and dietary data, and the comprehensive similarity between patients was calculated in combination with the preset weight factors.

[0011] Furthermore, the calculation formula of the comprehensive similarity is: In the formula, S ij Indicates patient i and patients j The comprehensive similarity score between represent the weights of age, sex, esophageal cancer type, stage, treatment history, vital sign parameters, and dietary data; Respectively, patients i and patients j Similarity scores were obtained for age, sex, esophageal cancer type, stage, treatment history, vital sign parameters, and dietary data.

[0012] Furthermore, when constructing a patient network according to the similarity analysis result, the patient network construction module includes: Treat each patient as a single node, create an empty graph or network, and determine a similarity score threshold; Traverse the similarity scores of all patient pairs. When the similarity score between each pair of patients exceeds the similarity score threshold, an edge is established between the nodes corresponding to the patients to obtain the patient network. A weight is assigned to each edge according to the similarity score, wherein the higher the similarity score, the greater the weight assigned to each edge.

[0013] Furthermore, the potential key data recommendation module searches for a neighbor similar to the target patient in the patient network and recommends potential key data for the target patient based on the historical data of the neighbor, including: Determine the target patient, traverse all nodes directly connected to the target patient in the constructed patient network, and obtain a set of similar patients; Obtain the real-time physical sign data and diet log of the target patient, and calculate the similarity between each patient in the similar patient set and the target patient in terms of physical sign data and diet log; Based on the similarity of physical sign data and diet logs, select patients with the most similar real-time conditions to the target patient from the set of similar patients; Obtain historical data of patients most similar to the real-time condition of the target patient from the database, and identify the importance of physical sign data and diet logs for treatment or care based on the historical data; According to the ranking results of importance, key data are recommended for target patients under real-time conditions, and the corresponding key data in the monitoring data are defined as potential key data, and the remaining data are defined as non-potential key data.

[0014] Furthermore, the personalized transmission parameter allocation module includes: The monitoring data is divided into potential key data and non-potential key data, and cleaned and formatted; Identify transmission parameters to be optimized and give higher priority to potentially critical data, including transmission frequency, compression ratio, and encryption level; Define optimization goals for potential key data and non-potential key data respectively, where the optimization goal for potential key data is to maximize transmission efficiency, and the optimization goal for non-potential key data is to minimize transmission cost; Establish objective functions for potential key data and non-potential key data respectively, and add weights or penalty items to the objective functions to ensure that the transmission efficiency of potential key data is given priority, wherein the objective function of potential key data focuses on transmission efficiency, while the objective function of non-potential key data focuses on cost savings; The optimization algorithm is used to simultaneously optimize the transmission parameters of potential key data and non-potential key data; based on the optimization results, the transmission parameters that maximize the transmission efficiency of potential key data while minimizing the data transmission cost of non-potential key data are selected as the optimal transmission parameters.

[0015] Furthermore, the remote service module includes a remote consultation module and a remote nursing plan adjustment module; Wherein, the remote consultation module is used for remote diagnosis and consultation between medical staff and patients; The remote nursing plan adjustment module is used to dynamically adjust the patient's nursing plan according to the remote monitoring analysis results.

[0016] According to another aspect of the present invention, a remote monitoring method for nursing care of esophageal cancer patients is provided, which can improve the nursing level, and comprises the following steps: S1. Real-time monitoring of the patient's vital signs and diet log to obtain test data; S2. Predicting the potential key data of patients using collaborative recommendation algorithms, and assigning corresponding personalized transmission parameters to the potential key data and non-potential key data in the monitoring data; S3, based on 5G communication technology and corresponding personalized transmission parameters, transmit potential key data and non-potential key data to the remote monitoring center respectively; S4. The remote monitoring center receives the monitoring data, performs remote monitoring and analysis on the nursing status based on the monitoring data, and provides remote services to the patients based on the monitoring and analysis results.

[0017] The beneficial effects of the present invention are: 1) The present invention can make full use of the high speed and low latency characteristics of 5G communication technology to provide patients with more accurate and efficient remote nursing services, which can not only reduce the burden of patients' medical treatment, but also enable medical staff to obtain key data in the first time and formulate more appropriate treatment plans for patients, thereby improving the overall level of medical care.

[0018] 2) The present invention can monitor the patient's vital signs data and dietary log in real time, and predict the patient's potential key data through a collaborative recommendation algorithm, so that corresponding personalized transmission parameters can be assigned to the potential key data and non-potential key data. This can not only ensure that the key data reaches the monitoring center quickly and improve the data transmission efficiency, but also reduce resource waste and data transmission costs by reasonably allocating transmission strategies for non-critical data, thereby significantly improving the remote care level of esophageal cancer patients and realizing efficient, economical and personalized medical care services.

[0019] 3) Through patient similarity analysis, patient network construction and potential key data recommendation modules, the present invention can provide patients with more accurate potential key data predictions based on historical data, thereby improving the pertinence and timeliness of nursing care. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 The invention is a structural block diagram of a remote monitoring system for nursing care of esophageal cancer patients capable of improving nursing care level according to an embodiment of the present invention.

[0022] In the figure: 1. Data acquisition module; 11. Vital sign data monitoring module; 12. Diet monitoring module; 2. Personalized data transmission module; 21. Data characteristic analysis module; 22. Potential key data prediction module; 23. Personalized transmission parameter allocation module; 24. Monitoring data transmission module; 3. Remote monitoring center; 4. Remote service module; 41. Remote consultation module; 42. Remote care plan adjustment module. DETAILED DESCRIPTION

[0023] To further illustrate each embodiment, the present invention provides drawings, which are part of the disclosure of the present invention and are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these contents, ordinary technicians in the field should be able to understand other possible implementations and advantages of the present invention. The components in the figures are not drawn to scale, and similar component symbols are generally used to represent similar components.

[0024] According to an embodiment of the present invention, a remote monitoring system and method for nursing care of esophageal cancer patients are provided, which can improve the nursing level.

[0025] The present invention is further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, the remote monitoring system for esophageal cancer patient care that can improve the nursing level according to an embodiment of the present invention includes a data acquisition module 1, a personalized data transmission module 2, a remote monitoring center 3 and a remote service module 4; Wherein, the data acquisition module 1 is used to monitor the patient's vital signs data and diet log in real time; Specifically, the data acquisition module 1 includes a physical sign data monitoring module 11 and a diet status monitoring module 12; Among them, the vital sign data monitoring module 11 is used to collect vital sign data (such as heart rate, blood pressure, blood oxygen saturation, etc.) during the nursing process of esophageal cancer patients; The dietary status monitoring module 12 is used to collect dietary data of esophageal cancer patients during the nursing process through manual or voice input by the patient to the user terminal, including the type, quantity, and eating time of food. These data are crucial for understanding the patient's dietary habits and nutritional intake.

[0026] The personalized data transmission module 2 is used to predict the patient's potential key data using a collaborative recommendation algorithm, and to assign corresponding personalized transmission parameters to the potential key data and non-potential key data in the monitoring data, and to transmit the potential key data and non-potential key data to the remote monitoring center based on 5G communication technology and corresponding personalized transmission parameters; The personalized data transmission module 2 includes a data characteristic analysis module 21, a potential key data prediction module 22, a personalized transmission parameter allocation module 23 and a monitoring data transmission module 24; The data characteristic analysis module 21 is used to analyze and identify the data type, data volume and data change rate of the monitoring data, and pre-process the data, including cleaning, deduplication and standardization, to prepare for subsequent algorithm processing; Specifically, analyzing and identifying the data type, data volume, and data change rate of monitoring data is a key step in understanding data characteristics and formulating subsequent processing strategies. The following are the specific steps for analyzing these data characteristics: 1) Data type identification: Data Sampling: Randomly draw or select a representative sample from the collected data for analysis.

[0027] Type detection: Use algorithms (including rule-based methods, statistical methods, machine learning-based methods) or manually inspect data samples to determine the type of data, such as numerical, categorical, time series, etc.

[0028] Rule-based approaches include regular expressions (i.e., using regular expressions to match specific data patterns, such as email addresses, dates, etc.) and predefined rule sets (i.e., identifying data types based on predefined rule sets, for example, if a number contains a decimal point, it may be identified as a floating point number).

[0029] Statistical methods include frequency analysis (i.e. counting the frequency of occurrence of each data value. Numerical data usually has a wider distribution, while categorical data will have a few concentrated values) and distribution testing (i.e. determining the type of data by testing whether it conforms to certain probability distributions).

[0030] Machine learning-based methods include naive Bayes classifier (using Bayes’ theorem to predict data types based on the probability distribution of features), decision trees (identifying data types by building decision trees, where each branch of the tree represents a decision on a data type), support vector machines (finding the best splitting plane in feature space to distinguish different data types), and deep learning (using deep neural networks to extract features and classify, such as convolutional neural networks or recurrent neural networks).

[0031] Data labeling: Add labels to identified data types for easier subsequent processing.

[0032] 2) Data volume analysis: Data statistics: the total amount of statistical data, the number of each data type, etc.

[0033] Data distribution: Analyze the distribution of data in different types to understand which types of data are more common or important.

[0034] 3) Data change rate analysis: Time series analysis: For time series data, analyze the trend and rate of change of data over time.

[0035] Rate of change calculation: Calculate the rate of change of data, such as the increase or decrease of data per unit time.

[0036] Anomaly detection: Identifying unusual points in data changes, such as sudden fluctuations or changes in trends.

[0037] 4) Summary of data characteristics: Characteristic report: Write a data characteristic analysis report to summarize the analysis results of data type, data volume and data change rate.

[0038] Visualization: Use tools such as charts or dashboards to intuitively display the analysis results of data characteristics.

[0039] Through these steps, we can fully understand the characteristics of the monitoring data and provide a basis for subsequent data processing and transmission strategies. For example, for data with a fast change rate, more frequent monitoring and faster transmission may be required; for data with large amounts of data, more efficient compression and transmission methods may be required. This information is crucial for designing personalized data transmission modules.

[0040] The potential key data prediction module 22 is used to predict and analyze the potential key data of the patient using a collaborative recommendation algorithm; Specifically, the potential key data prediction module 22 includes a patient similarity analysis module, a patient network construction module and a potential key data recommendation module; The patient similarity analysis module is used to analyze and calculate the similarities between different patients in the database; when analyzing and calculating the similarities between different patients in the database, the patient similarity analysis module includes: Obtain age, gender, esophageal cancer type, stage, treatment history, vital sign parameters, and dietary data of different patients in the database; The similarity measurement method was used to calculate the similarity of patients in terms of age, gender, esophageal cancer type, stage, treatment history, vital sign parameters and dietary data, and the comprehensive similarity between patients was calculated in combination with the preset weight factors.

[0041] The calculation formula of the comprehensive similarity is: In the formula, S ij Indicates patient iand patients j The comprehensive similarity score between represent the weights of age, sex, esophageal cancer type, stage, treatment history, vital sign parameters, and dietary data; Respectively, patients i and patients j Similarity scores were obtained for age, sex, esophageal cancer type, stage, treatment history, vital sign parameters, and dietary data.

[0042] Specifically, patients i and patients j Similarity score calculation methods for age, gender, esophageal cancer type, stage, treatment history, vital sign parameters, and diet data can be designed based on different data types and similarity metrics. The following are some common calculation methods: 1) Age similarity score: A simple difference can be used to represent similarity, for example, age similarity score = 1-|patient i Age-patient j Age | / Maximum age recorded in the database.

[0043] 2) Gender similarity score: For gender, you can directly assign a value. If the genders are the same, the gender similarity score = 1, otherwise the gender similarity score = 0.

[0044] 3) Esophageal cancer type similarity score: If the esophageal cancer types are the same, the esophageal cancer type similarity score = 1, otherwise the esophageal cancer type similarity score = 0.

[0045] 4) Stage similarity score: Stage similarity can be calculated based on the difference between stages, for example, stage similarity score = 1-|patient i Esophageal Cancer Stages - Patients j Esophageal cancer stages | / Highest stage recorded in the database.

[0046] 5) Treatment history similarity score: The similarity of treatment history can be calculated based on the similarity of treatment methods, which can be measured using the Jaccard similarity coefficient or the cosine similarity coefficient.

[0047] 6) Similarity score of vital sign parameters: For vital sign parameters such as heart rate, blood pressure, blood oxygen saturation, etc., the Euclidean distance or correlation coefficient can be used to calculate the similarity score.

[0048] 7) Diet data similarity score: The similarity of diet data can be calculated based on the similarity of food types and intake, and can be measured using the Jaccard similarity coefficient or the cosine similarity coefficient.

[0049] The patient network construction module is used to construct a patient network according to the similarity analysis results, and the patient network uses each patient as a node, and establishes edges between similar patients; when constructing the patient network according to the similarity analysis results, the patient network construction module includes: 1) Network initialization: Create Nodes: Create an empty graph or network treating each patient as a node.

[0050] Set threshold: Determine a similarity score threshold, and only when the similarity score between patients exceeds this threshold will an edge be established between them.

[0051] 2) Build the network: Iterate over similarity scores: Iterate over the similarity scores of all patient pairs.

[0052] Build edges: For each pair of patients, if their similarity score exceeds a threshold, build an edge between their corresponding nodes.

[0053] 3) Network optimization: Weight assignment: Assign a weight to each edge based on the similarity score. The higher the score, the greater the weight.

[0054] Network pruning: If necessary, edges with low weight or little impact on the network structure can be removed to simplify the network.

[0055] 4) Network verification: Connectivity check: Ensure that the network is connected, that is, any two nodes are connected by a series of edges.

[0056] Module detection: Identifying communities or modules in the network, which are groups of patients with similar characteristics.

[0057] 5) Network storage and management: Storing the network: The constructed patient network is stored in a database or graph database for easy query and analysis.

[0058] Update Mechanism: Establish a mechanism to regularly update the network to reflect the addition of new patient data or changes in the status of existing patients.

[0059] The potential key data recommendation module is used to find a neighbor similar to the target patient in the patient network, and recommend potential key data to the target patient based on the historical data of the neighbor; the potential key data recommendation module finds a neighbor similar to the target patient in the patient network, and recommends potential key data to the target patient based on the historical data of the neighbor, including: Determine the target patient, traverse all nodes directly connected to the target patient in the constructed patient network, and obtain a set of similar patients; Obtain the real-time physical sign data and diet log of the target patient, and calculate the similarity between each patient in the similar patient set and the target patient in terms of physical sign data and diet log; Based on the similarity of physical sign data and diet logs, select patients with the most similar real-time conditions to the target patient from the set of similar patients; Obtain historical data of patients most similar to the real-time condition of the target patient from the database, and identify the importance of physical sign data and diet logs for treatment or care based on the historical data; Specifically, obtaining historical data of patients with the most similar real-time conditions to the target patient from the database is a key step, because this will provide important reference information for recommending potential key data. The following is a specific implementation method for this step: 1) Historical data acquisition: First, the patients whose real-time condition is most similar to the target patient need to be identified. This is usually done through the previous similarity calculation step. Then, the historical data of these similar patients are extracted from the database. This data includes treatment records, nursing process, condition changes, vital signs history, diet logs, etc.

[0060] 2) Historical data analysis: Analyze historical data of similar patients to identify which physical sign data and dietary logs played an important role in the treatment or care process. The importance can be identified by the following methods: Statistical analysis: Use statistical methods (such as correlation analysis, analysis of variance, etc.) to determine which data are significantly associated with treatment outcomes or disease changes.

[0061] Machine learning: Use machine learning algorithms (such as decision trees, random forests, support vector machines, etc.) to identify which data features have greater predictive value for treatment outcomes.

[0062] Clinical Expert Knowledge: Data is manually reviewed using the experience and knowledge of clinical experts to determine which data are instructive in actual treatment or care.

[0063] 3) Identify key data: Based on the analysis results, identify the physical signs and diet logs that are important for treatment or care. These key data include those that can predict the progression of the disease, the effect of treatment, or the patient's prognosis.

[0064] 4) Importance ranking: Sort the identified key data and classify them according to their impact on treatment or care. Sorting can help medical staff prioritize the data that has the greatest impact on the current target patient's condition.

[0065] According to the ranking results of importance, key data are recommended for target patients under real-time conditions, and the corresponding key data in the monitoring data are defined as potential key data, and the remaining data are defined as non-potential key data.

[0066] Specifically, recommending key data for target patients in real-time conditions based on the importance ranking results, defining the corresponding key data in the monitoring data as potential key data, and defining the remaining data as non-potential key data is a key step to ensure the effective allocation of medical resources and the quality of patient care. The following is the implementation method of this step: 1) Importance ranking: Use the key data identified in the previous step to rank them according to their importance to treatment or care. You can use quantitative methods (such as statistical significance, predictive accuracy, etc.) or qualitative methods (such as clinical expert scoring) to determine the importance level of each data.

[0067] 2) Recommend key data: Based on the sorting results, recommend the most critical data for the target patient in real-time condition. These data should be those that have the greatest impact on the target patient’s current condition and future treatment.

[0068] 3) Define potential key data: Data points in the monitoring data that correspond to the recommended key data are defined as potential key data. These data need to be closely monitored and tracked because they have a significant impact on the treatment or care of patients.

[0069] 4) Definition of non-potentially critical data: The data other than the potentially critical data in the monitoring data are defined as non-potentially critical data. These data may have a certain importance to the overall care of the patient, but are not as urgent or critical as the potentially critical data.

[0070] 5) Implement monitoring and intervention: Implement more frequent or stricter monitoring of potential critical data to ensure that these data are within the normal range, and take timely intervention measures when abnormalities occur. For non-potential critical data, regular monitoring procedures can be followed, but regular review is still required to ensure the overall health of the patient.

[0071] 6) Dynamic adjustment: Regularly reassess the patient's condition and the importance ranking of key data to adapt to changes in the patient's condition. Based on the new assessment results, dynamically adjust the definition and monitoring strategy of potential key data and non-potential key data.

[0072] This approach allows medical professionals to focus on the data that is most important to the patient’s current condition, while not neglecting other data that may affect the patient’s long-term health. This approach helps improve care efficiency and ensures that patients receive the most appropriate care.

[0073] The personalized transmission parameter allocation module 23 is used to allocate corresponding personalized transmission parameters to potential key data and non-potential key data in the monitoring data using an optimization algorithm; Specifically, the personalized transmission parameter allocation module 23 includes: The monitoring data is divided into potential key data and non-potential key data, and cleaned and formatted; Identify transmission parameters to be optimized and give higher priority to potentially critical data, including transmission frequency, compression ratio, and encryption level; Define optimization goals for potential key data and non-potential key data respectively, where the optimization goal for potential key data is to maximize transmission efficiency, and the optimization goal for non-potential key data is to minimize transmission cost; Establish objective functions for potential critical data and non-potential critical data respectively, and add weights or penalty items to the objective functions to ensure that the transmission efficiency of potential critical data is given priority. The objective function of potential critical data focuses on transmission efficiency, that is, ensuring that these data can be transmitted quickly and reliably. The objective function includes minimizing the transmission time of data from source to destination, maximizing the success rate of data transmission, reducing the possibility of transmission failure, and ensuring that the integrity of data is not destroyed during transmission. The objective function of non-potential critical data focuses on cost saving, that is, minimizing the resources required to transmit these data without affecting the quality of care. The objective function includes minimizing the cost required for data transmission, including bandwidth, storage and energy consumption, maximizing the utilization of transmission resources, and avoiding resource waste. The optimization algorithm is used to simultaneously optimize the transmission parameters of potential key data and non-potential key data; based on the optimization results, the transmission parameters that maximize the transmission efficiency of potential key data while minimizing the data transmission cost of non-potential key data are selected as the optimal transmission parameters.

[0074] Specifically, in the process of optimizing medical data transmission parameters, it is crucial to use optimization algorithms to consider the transmission parameters of both potential critical data and non-potential critical data. The following is an analysis of this step: 1) Selection of optimization algorithm: Selecting a suitable optimization algorithm is the key. Common optimization algorithms include linear programming, integer programming, nonlinear programming, genetic algorithm, particle swarm optimization, simulated annealing, etc. For this problem, a multi-objective optimization algorithm such as Pareto optimization is needed because it can consider multiple conflicting objectives at the same time.

[0075] 2) Simultaneous optimization of transmission parameters: During the optimization process, the transmission parameters of potential key data and non-potential key data should be considered simultaneously. This means that the optimization algorithm needs to be able to handle two or more objective functions and find a set of parameters that can maximize the transmission efficiency of potential key data while minimizing the transmission cost of non-potential key data.

[0076] 3) Balance of optimization goals: If the goals of potential key data and non-potential key data conflict with each other (for example, improving transmission efficiency may increase costs), the optimization algorithm needs to find a balance between the two goals. This usually involves weighting, that is, determining the relative importance between the efficiency of potential key data transmission and the cost of non-potential key data transmission.

[0077] 4) Select the optimal parameters based on the optimization results: The optimization algorithm will provide a series of possible transmission parameter combinations, which have different performances in meeting different objectives. Based on the optimization results, a set of parameters needs to be selected that can maximize the transmission efficiency of potential key data while minimizing the transmission cost of non-potential key data.

[0078] 5) Criteria for selecting optimal transmission parameters: The criteria for selecting optimal transmission parameters should be based on actual clinical needs and resource constraints. Factors that need to be considered include but are not limited to: real-time data transmission, cost-effectiveness, system scalability and robustness.

[0079] 6) Implementation and evaluation: After the optimal delivery parameters are selected, they need to be implemented and evaluated in a real-world setting. The evaluation should include the impact on delivery efficiency, cost savings, and quality of patient care.

[0080] In this way, it is possible to ensure that medical data transmission is both efficient and economical while meeting the needs of clinical care. This approach helps to improve the operational efficiency of medical institutions, improve the quality of patient care, and potentially reduce overall medical costs.

[0081] The monitoring data transmission module 24 is used to utilize 5G communication technology and corresponding personalized transmission parameters to transmit potential key data and non-potential key data to a remote monitoring center respectively.

[0082] The remote monitoring center 3 is used to receive monitoring data and perform remote monitoring and analysis on the nursing status based on the monitoring data; Specifically, in the remote monitoring center, medical experts can receive data from patients in real time for monitoring and analysis. The center can also automatically generate alarms, and when abnormalities are detected, doctors can be notified immediately and provide necessary medical intervention.

[0083] The remote service module 4 is used to provide remote services to patients based on monitoring and analysis results; Specifically, the remote service module 4 includes a remote consultation module 41 and a remote nursing plan adjustment module 42; The remote consultation module 41 is used for remote diagnosis and consultation between medical staff and patients; The remote nursing plan adjustment module 42 is used to dynamically adjust the patient's nursing plan according to the remote monitoring analysis results.

[0084] According to another embodiment of the present invention, a remote monitoring method for nursing care of esophageal cancer patients that can improve the nursing level is provided. The remote monitoring method for nursing care of esophageal cancer patients that can improve the nursing level includes the following steps: S1. Real-time monitoring of the patient's vital signs and diet log to obtain test data; S2. Predicting the potential key data of patients using collaborative recommendation algorithms, and assigning corresponding personalized transmission parameters to the potential key data and non-potential key data in the monitoring data; S3, based on 5G communication technology and corresponding personalized transmission parameters, transmit potential key data and non-potential key data to the remote monitoring center respectively; S4. The remote monitoring center receives the monitoring data, performs remote monitoring and analysis on the nursing status based on the monitoring data, and provides remote services to the patients based on the monitoring and analysis results.

[0085] To sum up, with the help of the above-mentioned technical scheme of the present invention, the present invention can make full use of the high speed and low latency characteristics of 5G communication technology to provide patients with more accurate and efficient remote care services, which can not only reduce the patient's medical burden, but also allow medical staff to obtain key data in the first time and formulate more appropriate treatment plans for patients, thereby improving the overall medical care level.

[0086] In addition, the present invention can monitor the patient's vital signs data and dietary log in real time, and predict the patient's potential key data through a collaborative recommendation algorithm, so that corresponding personalized transmission parameters can be assigned to the potential key data and non-potential key data. This can not only ensure that the key data reaches the monitoring center quickly and improve the data transmission efficiency, but also reduce resource waste and reduce data transmission costs by reasonably allocating transmission strategies for non-critical data, thereby significantly improving the level of remote care for esophageal cancer patients and achieving efficient, economical and personalized medical care services.

[0087] In addition, the present invention can provide patients with more accurate potential key data predictions based on historical data through patient similarity analysis, patient network construction and potential key data recommendation modules, thereby improving the pertinence and timeliness of nursing care.

[0088] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A remote monitoring system for the care of esophageal cancer patients that can improve the level of care, characterized in that: The remote monitoring system for the care of esophageal cancer patients capable of improving the level of care comprises a data acquisition module (1), a personalized data transmission module (2), a remote monitoring center (3) and a remote service module (4); The data collection module (1) is used to monitor the patient's vital signs and diet log in real time; The personalized data transmission module (2) is used to predict the patient's potential key data using a collaborative recommendation algorithm, and to assign corresponding personalized transmission parameters to the potential key data and non-potential key data in the monitoring data, and to transmit the potential key data and non-potential key data to a remote monitoring center based on 5G communication technology and corresponding personalized transmission parameters; The remote monitoring center (3) is used to receive monitoring data and perform remote monitoring and analysis of the nursing status based on the monitoring data; The remote service module (4) is used to provide remote services to patients based on monitoring and analysis results; The personalized data transmission module (2) comprises a data characteristic analysis module (21), a potential key data prediction module (22), a personalized transmission parameter allocation module (23) and a monitoring data transmission module (24); The data characteristic analysis module (21) is used to analyze and identify the data type, data volume and data change rate of the monitoring data; The potential key data prediction module (22) is used to predict and analyze the potential key data of the patient using a collaborative recommendation algorithm; The personalized transmission parameter allocation module (23) is used to allocate corresponding personalized transmission parameters to potential key data and non-potential key data in the monitoring data using an optimization algorithm; The monitoring data transmission module (24) is used to utilize 5G communication technology and corresponding personalized transmission parameters to transmit potential key data and non-potential key data to a remote monitoring center respectively.

2. The remote monitoring system for esophageal cancer patient care that can improve the level of care according to claim 1 is characterized in that: The data collection module (1) comprises a physical sign data monitoring module (11) and a diet status monitoring module (12); The vital sign data monitoring module (11) is used to collect vital sign data of esophageal cancer patients during the nursing process; The dietary status monitoring module (12) is used to collect dietary data during the nursing process of esophageal cancer patients.

3. The remote monitoring system for esophageal cancer patient care that can improve the level of care according to claim 1 is characterized in that: The potential key data prediction module (22) includes a patient similarity analysis module, a patient network construction module and a potential key data recommendation module; Wherein, the patient similarity analysis module is used to analyze and calculate the similarities between different patients in the database; The patient network construction module is used to construct a patient network based on the similarity analysis results, and the patient network uses each patient as a node and establishes edges between similar patients; The potential key data recommendation module is used to find neighbors similar to the target patient in the patient network and recommend potential key data for the target patient based on the historical data of the neighbors.

4. The remote monitoring system for esophageal cancer patient care that can improve the level of care according to claim 3 is characterized in that: The patient similarity analysis module includes the following steps when analyzing and calculating the similarities between different patients in the database: Obtain age, gender, esophageal cancer type, stage, treatment history, vital sign parameters, and dietary data of different patients in the database; The similarity measurement method was used to calculate the similarity of patients in terms of age, gender, esophageal cancer type, stage, treatment history, vital sign parameters and dietary data, and the comprehensive similarity between patients was calculated in combination with the preset weight factors.

5. The remote monitoring system for esophageal cancer patient care that can improve the level of care according to claim 4 is characterized in that: The calculation formula of the comprehensive similarity is: In the formula, S ij Indicates patient i and patients j The comprehensive similarity score between represent the weights of age, sex, esophageal cancer type, stage, treatment history, vital sign parameters, and dietary data; Respectively, patients i and patients j Similarity scores were obtained for age, sex, esophageal cancer type, stage, treatment history, vital sign parameters, and dietary data.

6. The remote monitoring system for esophageal cancer patient care that can improve the level of care according to claim 3 is characterized in that: The patient network construction module comprises: Treat each patient as a single node, create an empty graph or network, and determine a similarity score threshold; Traverse the similarity scores of all patient pairs. When the similarity score between each pair of patients exceeds the similarity score threshold, an edge is established between the nodes corresponding to the patients to obtain the patient network. A weight is assigned to each edge according to the similarity score, wherein the higher the similarity score, the greater the weight assigned to each edge.

7. The remote monitoring system for esophageal cancer patient care that can improve the level of care according to claim 3 is characterized in that: The potential key data recommendation module searches for a neighbor similar to the target patient in the patient network and recommends potential key data for the target patient based on the historical data of the neighbor, including: Determine the target patient, traverse all nodes directly connected to the target patient in the constructed patient network, and obtain a set of similar patients; Obtain the real-time physical sign data and diet log of the target patient, and calculate the similarity between each patient in the similar patient set and the target patient in terms of physical sign data and diet log; Based on the similarity of physical sign data and diet logs, select patients with the most similar real-time conditions to the target patient from the set of similar patients; Obtain historical data of patients most similar to the real-time condition of the target patient from the database, and identify the importance of physical sign data and diet logs for treatment or care based on the historical data; According to the ranking results of importance, key data are recommended for target patients under real-time conditions, and the corresponding key data in the monitoring data are defined as potential key data, and the remaining data are defined as non-potential key data.

8. The remote monitoring system for esophageal cancer patient care that can improve the level of care according to claim 1 is characterized in that: The personalized transmission parameter allocation module (23) includes the following steps when allocating corresponding personalized transmission parameters to potential key data and non-potential key data in the monitoring data using an optimization algorithm: The monitoring data is divided into potential key data and non-potential key data, and cleaned and formatted; Identify transmission parameters to be optimized and give higher priority to potentially critical data, including transmission frequency, compression ratio, and encryption level; Define optimization goals for potential key data and non-potential key data respectively, where the optimization goal for potential key data is to maximize transmission efficiency, and the optimization goal for non-potential key data is to minimize transmission cost; Establish objective functions for potential key data and non-potential key data respectively, and add weights or penalty items to the objective functions to ensure that the transmission efficiency of potential key data is given priority, wherein the objective function of potential key data focuses on transmission efficiency, while the objective function of non-potential key data focuses on cost savings; The optimization algorithm is used to simultaneously optimize the transmission parameters of potential key data and non-potential key data; based on the optimization results, the transmission parameters that maximize the transmission efficiency of potential key data while minimizing the data transmission cost of non-potential key data are selected as the optimal transmission parameters.

9. The remote monitoring system for esophageal cancer patient care that can improve the level of care according to claim 1 is characterized in that: The remote service module (4) comprises a remote consultation module (41) and a remote nursing plan adjustment module (42); Wherein, the remote consultation module (41) is used for remote diagnosis and consultation between medical staff and patients; The remote nursing plan adjustment module (42) is used to dynamically adjust the patient's nursing plan according to the remote monitoring analysis results.

10. A remote monitoring method for the care of esophageal cancer patients capable of improving the nursing level, which is implemented by using the remote monitoring system for the care of esophageal cancer patients capable of improving the nursing level as claimed in any one of claims 1 to 9, characterized in that: The remote monitoring method for esophageal cancer patient care that can improve the level of care includes the following steps: S1. Real-time monitoring of the patient's vital signs and diet log to obtain test data; S2. Predicting the potential key data of patients using collaborative recommendation algorithms, and assigning corresponding personalized transmission parameters to the potential key data and non-potential key data in the monitoring data; S3, based on 5G communication technology and corresponding personalized transmission parameters, transmit potential key data and non-potential key data to the remote monitoring center respectively; S4. The remote monitoring center receives the monitoring data, performs remote monitoring and analysis on the nursing status based on the monitoring data, and provides remote services to the patients based on the monitoring and analysis results.

Images