Tumor remote monitoring system based on Internet of Things

Abstract

The invention discloses a tumor remote monitoring system based on the Internet of Things. The tumor remote monitoring system comprises a patient end device, a communication network and a medical care end platform. More complete patient condition information is provided for medical staff through multi-dimensional data, the data analysis and processing module of the medical end platform applies a machine learning algorithm and a deep learning model to establish a tumor patient condition prediction model, the development trend of the condition can be accurately predicted through deep analysis of the multi-dimensional data, and the accuracy of the tumor patient condition prediction is improved. Compared with traditional staged hospital examination, the dynamic change of the illness state can be captured in real time, the accuracy and timeliness of diagnosis and treatment are greatly improved, illness state worsening signs can be found in the early stage, and a treatment scheme can be adjusted in time.

Description

Technical Field

[0001] The present invention relates to the technical field of medical monitoring, and in particular to a tumor remote monitoring system based on the Internet of Things. Background Art

[0002] With the increasing incidence of cancer, the demand for long-term monitoring of cancer patients is growing. Traditional cancer monitoring mainly relies on patients to go to the hospital for regular examinations and diagnosis, which has many limitations. On the one hand, frequent trips to the hospital bring great inconvenience and financial burden to patients, especially for those with limited mobility or living in remote areas. On the other hand, hospital examinations are usually staged, making it difficult to capture the dynamic changes of the patient's condition in real time, which may lead to the inability to detect and treat the deterioration of the condition in a timely manner.

[0003] Although existing remote monitoring systems have achieved remote collection of some physiological parameters to a certain extent, their limitations are increasingly prominent in the field of cancer patient monitoring. Cancer patients' conditions are highly complex, and monitoring needs not only cover basic physiological indicators such as heart rate and blood pressure, but also special parameters such as tumor marker concentrations, pain levels, and sleep quality. However, existing systems are insufficient in both the breadth and depth of data collection, and their data analysis capabilities are difficult to meet clinical diagnosis and treatment needs, and their intelligence level is low. At the same time, the system lacks personalized customization functions and cannot formulate exclusive monitoring plans and early warning mechanisms based on the individual differences of each patient, making it difficult to effectively meet the diverse monitoring needs of cancer patients. Summary of the Invention

[0004] In view of the above problems existing in the existing remote monitoring system when in use, the present invention is proposed.

[0005] Therefore, the purpose of the present invention is to provide a tumor remote monitoring system based on the Internet of Things to solve the problems existing in existing tumor monitoring methods, realize comprehensive and real-time remote monitoring of tumor patients, improve monitoring efficiency and quality, and reduce patients' medical costs and burdens.

[0006] In order to achieve the above object, the present invention provides the following technical solutions:

[0007] IoT-based remote tumor monitoring system, including patient-side devices, communication networks, and medical-side platforms;

[0008] The patient-side device integrates a monitoring module, a data processing module, and a communication module. The monitoring module is used to collect physiological parameters and disease-related data of tumor patients. The data processing module performs noise reduction, normalization, and cache on the data collected by each sensor. The communication module uses 4G / 5G, Wi-Fi, and Bluetooth to realize data transmission.

[0009] The communication network uses virtual private network technology to ensure data transmission security and uses edge computing technology to perform preliminary data processing at network edge nodes;

[0010] The medical platform includes a data receiving and storage module, a data analysis and processing module, an early warning module and an interaction module. The data receiving and storage module receives and stores patient data. The data analysis and processing module uses machine learning algorithms and deep learning models to perform in-depth analysis of the data. The early warning module sets early warning thresholds based on the analysis results and issues multi-mode early warnings. The interaction module enables remote interaction between medical staff and patients and their families.

[0011] Preferably, the monitoring module includes a blood pressure sensor, a body temperature sensor, a blood oxygen saturation sensor, a tumor marker detection sensor for detecting tumor marker concentration, a pain sensor for monitoring pain level, a heart rate sensor for collecting basic vital signs, and a sleep monitoring sensor for monitoring sleep quality.

[0012] Preferably, the tumor marker detection sensor adopts microfluidic chip technology, the pain sensor monitors the pain level through pressure sensing and bioelectric signal analysis, and the sleep monitoring sensor combines an acceleration sensor and an electroencephalogram sensor to obtain sleep data.

[0013] Preferably, the data analysis and processing module of the medical platform establishes a prediction model for the condition of tumor patients, predicts the development trend of the disease by analyzing multi-dimensional data such as physiological parameters, tumor marker concentrations, and pain levels, and uses a clustering algorithm to classify patient data.

[0014] Preferably, the warning module generates warning signals of different levels according to the severity of the warning, including a red warning indicating that the condition is critical and a yellow warning indicating that the condition has a tendency to worsen.

[0015] Preferably, during the data transmission process of the communication network, 4G / 5G is used for remote communication between the patient-side device and the medical-side platform, Wi-Fi is suitable for data transmission in a network coverage environment, and Bluetooth is used for short-range data transmission between the patient-side device and other wearable devices or small medical instruments.

[0016] Preferably, the data receiving and storage module adopts a distributed database storage architecture to store a large amount of data such as the patient's historical monitoring data, diagnostic reports, etc.

[0017] Preferably, the data analysis and processing module constructs an individual feature vector space for the patient, and can dynamically adjust the weight parameters of the disease prediction model to achieve generation of personalized monitoring plans for different tumor types and treatment stages.

[0018] Preferably, the interaction module includes an intelligent intervention submodule, which can automatically generate a multimodal intervention plan including medication reminders, dietary recommendations and psychological counseling based on the patient's real-time data and historical response patterns, and push it to the patient-side device through the communication module.

[0019] Preferably, a method for implementing remote tumor monitoring based on an Internet of Things remote tumor monitoring system comprises the following steps:

[0020] S1. Patient-side devices use multiple sensors to collect physiological parameters and disease-related data of cancer patients in real time;

[0021] S2, the data processing module performs noise reduction and normalization on the collected data and performs local caching when communication is interrupted;

[0022] S3, the communication module transmits the processed data to the communication network via 4G / 5G, Wi-Fi or Bluetooth;

[0023] S4. The communication network encrypts data transmission through virtual private network technology and uses edge computing technology for data preprocessing;

[0024] S5. The medical platform receives data and stores it in a distributed database, using machine learning algorithms and deep learning models to analyze the data.

[0025] S6. Generate disease prediction reports and personalized monitoring recommendations based on analysis results, and trigger graded warnings when data is abnormal;

[0026] S7. Enable remote communication between medical staff and patients and their families through interactive modules, and push intelligent intervention plans.

[0027] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0028] The present invention integrates multiple types of sensors into patient-side devices to comprehensively collect physiological parameters and disease-related data of cancer patients. In addition to basic vital signs such as heart rate, blood pressure, and body temperature, it also covers special parameters such as tumor marker concentration, pain level, and sleep quality. Among them, the tumor marker detection sensor adopts microfluidic chip technology to achieve high-sensitivity detection of tumor markers; the pain sensor can accurately quantify the patient's pain level through pressure sensing and bioelectric signal analysis; the sleep monitoring sensor combines acceleration sensors and EEG sensors to obtain comprehensive sleep data; multi-dimensional data provides medical staff with more complete patient condition information. The data analysis and processing module of the medical platform uses machine learning algorithms and deep learning models to establish a cancer patient condition prediction model. Through in-depth analysis of multi-dimensional data, it can accurately predict the development trend of the disease. Compared with traditional staged hospital examinations, it can capture dynamic changes in the disease in real time, greatly improving the accuracy and timeliness of diagnosis and treatment, and helping to detect signs of disease deterioration early and adjust treatment plans in a timely manner.

[0029] The present invention uses the data analysis and processing module of the medical platform to construct the patient's individual feature vector space and dynamically adjust the weight parameters of the disease prediction model; according to different tumor types and treatment stages, a unique monitoring plan and early warning mechanism are formulated for each patient; the intelligent intervention submodule of the interactive module can automatically generate a multimodal intervention plan including medication reminders, dietary recommendations and psychological counseling based on the patient's real-time data and historical response patterns, and push it to the patient-side device; this personalized customization function fully takes into account the individual differences of patients, can effectively meet the diverse monitoring needs of cancer patients, and improve patients' treatment compliance and quality of life. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments described in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0031] Figure 1 This is a flow chart of the Internet of Things-based tumor remote monitoring system proposed by the present invention;

[0032] Figure 2 for Figure 1 Schematic diagram of the monitoring module flow chart;

[0033] Figure 3 This is a flowchart of the implementation method of tumor remote monitoring in the tumor remote monitoring system based on the Internet of Things. DETAILED DESCRIPTION

[0034] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings.

[0035] Example 1

[0036] IoT-based remote tumor monitoring system, including patient-side devices, communication networks, and medical-side platforms;

[0037] The patient-side device integrates a monitoring module, a data processing module, and a communication module. The monitoring module is used to collect physiological parameters and disease-related data of tumor patients. The data processing module performs noise reduction, normalization, and cache on the data collected by each sensor. The communication module uses 4G / 5G, Wi-Fi, and Bluetooth to realize data transmission.

[0038] The communication network uses virtual private network technology to ensure data transmission security and edge computing technology to perform preliminary data processing at the edge nodes of the network;

[0039] The medical platform includes a data receiving and storage module, a data analysis and processing module, an early warning module, and an interaction module. The data receiving and storage module receives and stores patient data. The data analysis and processing module uses machine learning algorithms and deep learning models to conduct in-depth analysis of the data. The early warning module sets early warning thresholds based on the analysis results and issues multi-mode early warnings. The interaction module enables remote interaction between medical staff and patients and their families.

[0040] The early warning module sets early warning thresholds based on the analysis results and generates early warning signals of different levels according to the severity of the warning. For example, a red warning indicates that the condition is critical, and a yellow warning indicates that the condition is deteriorating. Medical staff can receive early warning information in a timely manner, respond quickly, and take appropriate treatment measures. The interactive module enables remote interaction between medical staff and patients and their families, making it convenient for medical staff to understand the patient's physical condition and needs in real time and provide timely medical guidance and psychological support. Patients and their families can also consult medical staff at any time and obtain professional advice, which optimizes the medical service process and improves the quality and efficiency of medical services.

[0041] The monitoring module includes a blood pressure sensor, a body temperature sensor, a blood oxygen saturation sensor, a tumor marker detection sensor for detecting tumor marker concentrations, a pain sensor for monitoring pain levels, a heart rate sensor for collecting basic vital signs, and a sleep monitoring sensor for monitoring sleep quality.

[0042] Tumor marker detection sensors use microfluidic chip technology, pain sensors monitor pain levels through pressure sensing and bioelectric signal analysis, and sleep monitoring sensors combine acceleration sensors and EEG sensors to obtain sleep data.

[0043] The data analysis and processing module of the medical platform establishes a prediction model for the condition of cancer patients. It predicts the development trend of the disease by analyzing multi-dimensional data such as physiological parameters, tumor marker concentrations, and pain levels, and uses clustering algorithms to classify patient data.

[0044] The early warning module generates different levels of early warning signals according to the severity of the warning, including a red warning indicating that the condition is critical and a yellow warning indicating that the condition is deteriorating.

[0045] During data transmission on the communication network, 4G / 5G is used for remote communication between patient-side devices and medical platforms, Wi-Fi is suitable for data transmission in environments with network coverage, and Bluetooth is used for short-range data transmission between patient-side devices and other wearable devices or small medical instruments;

[0046] The communication network uses virtual private network technology to encrypt data transmission, ensure the security of patient data during transmission, and prevent data leakage and tampering; at the same time, edge computing technology is used to perform preliminary processing of data at the edge nodes of the network, reducing data transmission volume and delay, and improving data processing efficiency and system response speed.

[0047] The data receiving and storage module adopts a distributed database storage architecture to store a large amount of data such as patients' historical monitoring data, diagnostic reports, etc.; the data receiving and storage module of the medical platform adopts a distributed database storage architecture, which can stably store a large amount of data such as patients' historical monitoring data, diagnostic reports, etc., ensuring the integrity and reliability of the data, providing a solid data foundation for subsequent data analysis and diagnosis and treatment, and ensuring the stable operation of the entire system.

[0048] The data analysis and processing module constructs the patient's individual feature vector space, can dynamically adjust the weight parameters of the disease prediction model, and realize the generation of personalized monitoring plans for different tumor types and treatment stages.

[0049] The interactive module includes an intelligent intervention submodule, which can automatically generate a multimodal intervention plan including medication reminders, dietary recommendations, and psychological counseling based on the patient's real-time data and historical response patterns, and push it to the patient's terminal device through the communication module;

[0050] The intelligent interactive module automatically generates a multimodal intervention plan that includes medication reminders, dietary advice, and psychological counseling based on the patient's real-time data and historical response patterns, and pushes it to the patient's device. This personalized customization function fully takes into account the individual differences of patients, can effectively meet the diverse monitoring needs of cancer patients, and improve patients' treatment compliance and quality of life.

[0051] The method for implementing tumor remote monitoring in a tumor remote monitoring system based on the Internet of Things includes the following steps:

[0052] S1. Patient-side devices use multiple sensors to collect physiological parameters and disease-related data of cancer patients in real time;

[0053] S2, the data processing module performs noise reduction and normalization on the collected data and performs local caching when communication is interrupted;

[0054] S3, the communication module transmits the processed data to the communication network via 4G / 5G, Wi-Fi or Bluetooth;

[0055] S4. The communication network encrypts data transmission through virtual private network technology and uses edge computing technology for data preprocessing;

[0056] S5. The medical platform receives data and stores it in a distributed database, using machine learning algorithms and deep learning models to analyze the data.

[0057] S6. Generate disease prediction reports and personalized monitoring recommendations based on analysis results, and trigger graded warnings when data is abnormal;

[0058] S7. Enable remote communication between medical staff and patients and their families through interactive modules, and push intelligent intervention plans.

[0059] Example 2

[0060] Specific steps for implementing remote tumor monitoring

[0061] Data Collection (S1): The monitoring module of the patient-side device collects the physiological parameters and disease-related data of the cancer patient in real time through various sensors according to the preset collection frequency. For example, the blood pressure sensor collects blood pressure data every 15 minutes, and the tumor marker detection sensor regularly collects tumor marker concentration data according to the detection cycle set by the doctor.

[0062] Data processing (S2): After data collection, the data processing module immediately performs noise reduction processing on the data, using a filtering algorithm to remove noise interference in the data; performs normalization processing to convert the data into a unified format and range; at the same time, it monitors the communication status in real time. When a communication interruption is detected, the processed data is stored in the local cache and relevant information such as the data collection time is recorded.

[0063] Data transmission (S3): The communication module automatically selects the appropriate communication method based on the current network environment and transmits the processed data to the communication network. During the transmission process, the data is packaged and encapsulated, and necessary header information such as source address, destination address, data type, etc. is added to ensure that the data can be accurately transmitted to the medical platform.

[0064] Data transmission and preprocessing (S4): After the communication network receives the data, it first encrypts the data through virtual private network technology to ensure data transmission security; then it uses edge computing technology to perform preliminary data processing at the network edge node, such as data format conversion and data verification, to reduce data transmission volume and delay, and improve data transmission efficiency.

[0065] Data reception and storage (S5): The data reception and storage module of the medical platform receives data transmitted from the communication network and verifies the integrity and accuracy of the data. After the verification is passed, the data is stored in a distributed database according to patient identification, data type, collection time and other information to provide data support for subsequent data analysis and diagnosis and treatment.

[0066] Data analysis and early warning (S6): The data analysis and processing module reads data from the distributed database and uses machine learning algorithms and deep learning models to conduct in-depth analysis of the data; predicts the development trend of the disease through the disease prediction model and generates a disease prediction report; generates personalized monitoring recommendations based on the patient's individual characteristics and disease condition; at the same time, compares the analysis results with the early warning threshold. When the data is abnormal, it triggers the graded early warning mechanism and sends a warning signal of the corresponding level to medical staff.

[0067] Remote interaction and intervention (S7): Medical staff communicate remotely with patients and their families through the interactive module to understand the patients' physical conditions and needs; provide patients with professional medical guidance and advice based on disease prediction reports and personalized monitoring recommendations; the intelligent intervention submodule automatically generates multimodal intervention plans based on the patient's real-time data and historical response patterns, and pushes them to the patient's end device through the communication module to help patients better manage and treat themselves.

[0068] Example 3

[0069] 1. Patient-side device operation

[0070] Mr. Zhang, a lung cancer patient, wears a patient-side device integrated with multiple sensors. The blood pressure sensor, body temperature sensor, blood oxygen saturation sensor, heart rate sensor, etc. in the monitoring module collect his basic physiological parameters in real time according to the set sampling frequency (for example, the blood pressure sensor collects data every 15 minutes, and other vital sign sensors collect data every second). The tumor marker detection sensor uses microfluidic chip technology to automatically collect blood samples once a week to detect the concentrations of tumor markers such as carcinoembryonic antigen (CEA) and cytokeratin 19 fragment (CYFRA21-1). The pain sensor monitors Mr. Zhang's pain level in real time through pressure sensing and bioelectric signal analysis. When Mr. Zhang presses the sensor due to pain, the system records and analyzes the relevant signals. The sleep monitoring sensor combines an acceleration sensor and an EEG sensor to continuously obtain sleep data during Mr. Zhang's sleep, including the time of falling asleep, sleep duration, and deep and light sleep stages.

[0071] The collected data is transmitted to the data processing module, which first performs noise reduction on the data and uses the median filtering algorithm to remove the impulse noise in the blood pressure data; then it performs normalization processing to uniformly map the physiological parameters of different dimensions to the [0,1] interval; if a communication interruption occurs, the data processing module temporarily stores the data in the local cache and transmits it after the network is restored; the communication module selects the appropriate transmission method according to the actual network environment. When there is Wi-Fi network coverage at home, the processed data is transmitted to the communication network via Wi-Fi first; when Mr. Zhang goes out, it automatically switches to the 4G / 5G network for remote data transmission; if Mr. Zhang also wears other wearable devices such as smart bracelets, the communication module uses Bluetooth to realize short-range data transmission between the patient-end device and the smart bracelet to obtain more health data.

[0072] 2. Communication Network Transmission and Processing

[0073] After the communication network receives the data transmitted by the patient-side device, it uses virtual private network (VPN) technology to encrypt the data to ensure the security of the data during transmission and prevent the leakage of patient privacy. At the same time, edge computing technology is used to perform preliminary data processing at the network edge node close to the data source. For example, large amounts of sleep data are compressed to extract key feature information, reduce data transmission volume, and improve transmission efficiency. The processed encrypted data is transmitted to the medical platform via 4G / 5G network or Wi-Fi network.

[0074] 3. Medical Platform Workflow

[0075] (1) Data reception and storage

[0076] The data receiving and storage module of the medical platform receives data transmitted by the communication network and stores it in a distributed database; the database is indexed according to the patient ID and stores a large amount of data such as Mr. Zhang's historical monitoring data (including physiological parameters collected each time, tumor marker test results, pain records, sleep data, etc.), diagnostic reports and treatment plans, making it convenient for medical staff to query and analyze at any time.

[0077] (2) Data analysis and processing

[0078] The data analysis and processing module retrieves Mr. Zhang's data from the distributed database, and first uses a clustering algorithm to classify the data. It then compares and analyzes Mr. Zhang's disease data with the data of other lung cancer patients in the database to determine the stage and type of his disease. Then, it uses the principal component analysis (PCA) method to reduce the dimensionality of the multi-dimensional data, construct Mr. Zhang's individual feature vector space, and extract key features that have an important impact on disease prediction. Next, it uses time series analysis algorithms (such as long short-term memory networks (LSTMs)) to analyze these key features, explore the patterns and trends of data changes over time, and dynamically adjust the weight parameters of the disease prediction model. For example, during Mr. Zhang's chemotherapy, the model will automatically increase the weights of related features such as tumor marker concentrations and white blood cell counts to predict the development trend of the disease and generate personalized disease prediction reports and monitoring plans.

[0079] (3) Early warning module work

[0080] The early warning module sets the early warning threshold based on the results of the data analysis and processing module; when Mr. Zhang's tumor marker concentration exceeds the normal range and continues to rise, or physiological parameters such as heart rate and blood pressure fluctuate abnormally and reach the yellow early warning threshold, the early warning module issues a yellow early warning signal to remind medical staff that Mr. Zhang's condition is worsening; if Mr. Zhang's blood oxygen saturation suddenly drops sharply, falls below the life safety critical value, and reaches the red early warning threshold, the early warning module immediately issues a red early warning signal and notifies medical staff and Mr. Zhang's family through various methods such as text messages and APP push, so that timely treatment measures can be taken.

[0081] (IV) Interactive module application

[0082] The interactive module enables remote interaction between medical staff and Mr. Zhang and his family; when the early warning module sends out an early warning signal, the medical staff conducts a video call with Mr. Zhang through the interactive module to learn more about his physical condition and discomfort symptoms; at the same time, the intelligent intervention sub-module is based on the reinforcement learning algorithm and automatically generates a multimodal intervention plan including medication reminders (such as taking chemotherapy adjuvant drugs on time), dietary advice (such as consuming more protein-rich foods) and psychological counseling (pushing encouraging information and links to psychological counseling resources) according to Mr. Zhang's real-time data and historical response patterns, and pushes it to Mr. Zhang's patient-end device through the communication module; Mr. Zhang can use the patient-end device to provide feedback on his implementation of the intervention plan and his physical reaction, and the medical staff will further adjust the intervention plan based on the feedback information to achieve continuous health management of Mr. Zhang.

[0083] From the above examples, it can be seen that the IoT-based tumor remote monitoring system can achieve real-time, comprehensive, and personalized remote monitoring of tumor patients, improve the efficiency and quality of medical services, and provide strong protection for patients' health.

[0084] Among them, the new feature added in "patient-side device operation" is: the patient-side device records the placement of PICC, infusion port, chest and abdominal drainage tube and other pipelines and the last dressing change time through the time counter. One day before the maintenance cycle, the remaining maintenance time data is synchronously transmitted to the medical platform and the patient side through the communication module, triggering a two-way reminder.

[0085] The above-described embodiments merely represent several implementation methods of the embodiments of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention. It should be noted that a person skilled in the art may make various modifications and improvements without departing from the concept of the embodiments of the present application, and these modifications and improvements fall within the scope of protection of the embodiments of the present application.

Claims

1. The tumor remote monitoring system based on the Internet of Things is characterized by: Including patient-side devices, communication networks and medical-side platforms; The patient-side device integrates a monitoring module, a data processing module, and a communication module. The monitoring module is used to collect physiological parameters and disease-related data of tumor patients. The data processing module performs noise reduction, normalization, and cache on the data collected by each sensor. The communication module uses 4G / 5G, Wi-Fi, and Bluetooth to realize data transmission. The communication network uses virtual private network technology to ensure data transmission security and uses edge computing technology to perform preliminary data processing at network edge nodes; The medical platform includes a data receiving and storage module, a data analysis and processing module, an early warning module and an interaction module. The data receiving and storage module receives and stores patient data. The data analysis and processing module uses machine learning algorithms and deep learning models to perform in-depth analysis of the data. The early warning module sets early warning thresholds based on the analysis results and issues multi-mode early warnings. The interaction module enables remote interaction between medical staff and patients and their families.

2. The tumor remote monitoring system based on the Internet of Things according to claim 1, characterized in that: The monitoring module includes a blood pressure sensor, a body temperature sensor, a blood oxygen saturation sensor, a tumor marker detection sensor for detecting tumor marker concentration, a pain sensor for monitoring pain level, a heart rate sensor for collecting basic vital signs, and a sleep monitoring sensor for monitoring sleep quality.

3. The tumor remote monitoring system based on the Internet of Things according to claim 2, characterized in that: The tumor marker detection sensor adopts microfluidic chip technology, the pain sensor monitors the pain level through pressure sensing and bioelectric signal analysis, and the sleep monitoring sensor combines an acceleration sensor and an electroencephalogram sensor to obtain sleep data.

4. The tumor remote monitoring system based on the Internet of Things according to claim 1, characterized in that: The data analysis and processing module of the medical platform establishes a prediction model for the condition of tumor patients, predicts the development trend of the disease by analyzing multi-dimensional data such as physiological parameters, tumor marker concentrations, and pain levels, and uses a clustering algorithm to classify patient data.

5. The tumor remote monitoring system based on the Internet of Things according to claim 1, characterized in that: The warning module generates warning signals of different levels according to the severity of the warning, including a red warning indicating that the condition is critical and a yellow warning indicating that the condition is likely to worsen.

6. The tumor remote monitoring system based on the Internet of Things according to claim 1, characterized in that: During the data transmission process of the communication network, 4G / 5G is used for remote communication between the patient-side device and the medical-side platform, Wi-Fi is suitable for data transmission in a network coverage environment, and Bluetooth is used for short-range data transmission between the patient-side device and other wearable devices or small medical instruments.

7. The tumor remote monitoring system based on the Internet of Things according to claim 1, characterized in that: The data receiving and storage module adopts a distributed database storage architecture to store a large amount of data such as historical monitoring data, diagnosis reports, etc. of patients.

8. The tumor remote monitoring system based on the Internet of Things according to claim 1, characterized in that: The data analysis and processing module constructs the patient's individual feature vector space, can dynamically adjust the weight parameters of the disease prediction model, and realize the generation of personalized monitoring plans for different tumor types and treatment stages.

9. The tumor remote monitoring system based on the Internet of Things according to claim 1, characterized in that: The interaction module includes an intelligent intervention submodule, which can automatically generate a multimodal intervention plan including medication reminders, dietary recommendations and psychological counseling based on the patient's real-time data and historical response patterns, and push it to the patient's end device through the communication module.

10. The method for implementing remote tumor monitoring according to any one of claims 1 to 9, characterized in that: The following steps are involved: S1. Patient-side devices use multiple sensors to collect physiological parameters and disease-related data of cancer patients in real time; S2, the data processing module performs noise reduction and normalization on the collected data and performs local caching in the event of communication interruption; S3, the communication module transmits the processed data to the communication network via 4G / 5G, Wi-Fi or Bluetooth; S4. The communication network encrypts data transmission through virtual private network technology and uses edge computing technology for data preprocessing; S5. The medical platform receives data and stores it in a distributed database, using machine learning algorithms and deep learning models to analyze the data. S6. Generate disease prediction reports and personalized monitoring recommendations based on analysis results, and trigger graded warnings when data is abnormal; S7. Enable remote communication between medical staff and patients and their families through interactive modules, and push intelligent intervention plans.

Images