Intestinal monitoring and information management system for colorectal tumor patient

Abstract

The invention discloses an intestinal monitoring and information management system for a colorectal tumor patient, and relates to the field of real-time monitoring, data transmission, intelligent analysis and personalized health management of intestinal functions. The technical key points are as follows: the system comprises an intestinal monitoring module, a data acquisition and transmission module, a data analysis and decision module, an information management and display module and a remote monitoring module. The intestinal tract monitoring module collects key physiological data of the intestinal tract of a patient through a micro multi-mode sensor, wherein the key physiological data comprise pressure, peristalsis frequency, pH value and tumor marker concentration. The data acquisition and transmission module wirelessly transmits monitoring data to the cloud server, and the data analysis and decision module performs quantitative evaluation, abnormal early warning and future trend prediction on the health state of a patient based on health index calculation and a time sequence prediction algorithm. The information management and display module can generate a health trend chart and a personalized report, and visual reference information is provided for doctors and patients.

Description

Technical Field

[0001] The present invention relates to the technical field of intestinal monitoring, and in particular to an intestinal monitoring and information management system for patients with colorectal tumors. Background Art

[0002] Colorectal cancer is one of the most common malignant tumors in the world. Its morbidity and mortality have continued to rise in recent years, especially among the middle-aged and elderly population. With the advancement of diagnostic and treatment technologies, early detection and treatment of colorectal cancer have achieved remarkable results, but there are still many problems in the postoperative recovery, functional monitoring and long-term management of patients.

[0003] At present, the diagnosis of colorectal cancer mainly relies on endoscopy, imaging examination (such as CT and MRI), pathological biopsy and tumor marker detection. Although these methods play an important role in the discovery and diagnosis of tumors, they have significant deficiencies in functional evaluation and dynamic monitoring during treatment:

[0004] Endoscopy is the "gold standard" for the diagnosis of colorectal cancer, but it can only observe the anatomical changes of the tumor and cannot reflect the dynamic function of the patient's intestine, such as pressure changes, peristalsis frequency, and intestinal microenvironment (pH, inflammation, etc.). In addition, endoscopy is a one-time operation and cannot provide real-time, long-term data.

[0005] Postoperative patients often require repeated monitoring, but endoscopic examination is an invasive procedure and patients are reluctant to undergo it frequently, which increases the difficulty of diagnosis and treatment for doctors.

[0006] Tumor marker testing (such as CEA, CA19-9) is a common method for monitoring colorectal cancer recurrence, but these indicators can only provide an overall disease status and cannot accurately reflect local functional changes in the intestine. Marker levels often increase significantly in the late stages of the disease, so their sensitivity and predictive power are limited.

[0007] Abnormal intestinal function (such as decreased pressure and peristalsis) is a common problem in patients after colorectal cancer surgery, which has a great impact on postoperative recovery and quality of life. However, the current monitoring technology for intestinal function is relatively limited, especially in terms of dynamic, real-time and non-invasive monitoring.

[0008] Existing gastrointestinal motility monitoring devices mainly rely on catheter sensors, which require inserting a catheter or operating a complex testing device to obtain intestinal pressure and peristalsis data. For example, gastrointestinal pressure detection instruments (such as high-resolution esophageal pressure measurement) are usually limited to the evaluation of upper gastrointestinal function and are difficult to cover the colorectal area.

[0009] At the same time, most of these devices are suitable for short-term laboratory monitoring and cannot achieve long-term dynamic monitoring.

[0010] Changes in intestinal pH, temperature, and tumor microenvironment are of great significance to the progression of the disease and the recovery of patients, but there is currently a lack of convenient and continuous monitoring methods.

[0011] For example, pH monitoring usually requires invasive sampling to obtain intestinal contents, which is neither convenient nor able to reflect the dynamic changes in the intestinal microenvironment.

[0012] In current medical treatments, patients' physiological data mostly exist in isolated forms, lacking comprehensive processing and analysis mechanisms. This makes it difficult for doctors to fully understand the patient's overall health status, especially during postoperative recovery and treatment adjustments. Existing methods are difficult to support personalized treatment:

[0013] Currently, postoperative health monitoring of colorectal cancer patients is often scattered across different medical systems. For example, tumor marker test results, intestinal function test results, and patient lifestyle data (such as diet and exercise) cannot be effectively combined for analysis. This fragmented data situation limits doctors' comprehensive assessment of the patient's condition, especially when it is necessary to judge the disease trend and potential risks.

[0014] Most existing monitoring systems work passively, that is, they can only provide static reports after the patient's condition deteriorates, and cannot actively predict or warn of risks. For postoperative patients, the dynamic changes in health status are crucial. If personalized health advice based on real-time data cannot be provided, the best time for intervention may be missed.

[0015] Most existing medical monitoring devices are designed for short-term use and are not suitable for long-term dynamic monitoring. They also have the problem of causing great interference to patients' daily lives:

[0016] Many existing devices (such as catheter sensors) require invasive operations, and patients may feel obvious discomfort when using them, especially during the recovery period after colorectal cancer surgery. Such devices are prone to patient rejection and poor compliance.

[0017] At the same time, devices with poor portability cannot meet the monitoring needs of patients in their daily lives. For example, many gastrointestinal motility monitoring devices cannot achieve real-time data collection when patients are active.

[0018] Data security and privacy protection is a widely concerned issue. Existing medical devices usually ignore data encryption and privacy protection, which may lead to the risk of leaking sensitive patient information, further reducing patients' trust in the system.

[0019] Therefore, we urgently need to design an intestinal monitoring and information management system for colorectal cancer patients to solve the above problems. Summary of the invention

[0020] The purpose of the present invention is to provide a system for intestinal monitoring and information management of patients with colorectal tumors in view of the deficiencies of the prior art, so as to solve the problems raised in the background technology.

[0021] To achieve the above object, the present invention provides the following technical solutions:

[0022] A colorectal tumor patient intestinal monitoring and information management system, the system comprising:

[0023] Intestinal monitoring module: used to collect the patient's intestinal physiological data in real time, including: intestinal pressure P(t), in mmHg; intestinal temperature T(t), in °C; intestinal pH(t), dimensionless; intestinal peristalsis frequency f(t), in Hz; tumor marker concentration C biomarker (t), unit is ng / mL;

[0024] Data collection and transmission module: used to transmit the monitoring data to the cloud server via wireless communication, the wireless communication includes Bluetooth or Wi-Fi;

[0025] Data analysis and decision-making module: used to evaluate the patient's intestinal health status based on the following health index H(t) formula:

[0026]

[0027] Where: X i (t) represents the monitoring data of item i, including

[0028] P(t), T(t), pH(t), f(t), C b iomarker(t);X i0 is the normal reference value of the i-th monitoring data; σ i is the standard deviation of the i-th monitoring data; w i is the weight coefficient, indicating the influence of the i-th data on the health index; n is the total number of monitored data; the larger the value of the health index H(t), the higher the health risk;

[0029] Information management and display module: used to store, analyze and visualize health index and monitoring data;

[0030] Remote monitoring module: used to realize data interaction and health guidance between doctors and patients.

[0031] As a preferred technical solution of the present invention, the health index H(t) is obtained by setting a health threshold H th1 and H th2 The status is classified as follows:

[0032]

[0033] Where: H th1 is the health warning threshold; H th2 is the health abnormality threshold.

[0034] As a preferred technical solution of the present invention, the data analysis and decision-making module predicts the health index F(t+n) of the next n time steps based on the time series prediction algorithm, specifically:

[0035]

[0036] Where: F(t+n) is the health index predicted for the next n time steps; α k is the regression coefficient, obtained through model training; ΔH(tk) is the change in the historical health index.

[0037] As a preferred technical solution of the present invention, the time series prediction algorithm adopts a long short-term memory network or a gated recurrent unit, and optimizes the regression coefficient α through machine learning iteration. k , improve prediction accuracy.

[0038] As a preferred technical solution of the present invention, the intestinal monitoring module adopts a micro multi-mode sensor integration technology, and the sensor includes: a pressure sensor for collecting P(t); a temperature sensor for collecting T(t); a pH sensor for collecting pH(t); a biosensor for detecting C biomarker (t).

[0039] As a preferred technical solution of the present invention, the data acquisition and transmission module performs average processing on the data according to the time window Δt based on the time sequence grouping mechanism, and the specific calculation is:

[0040]

[0041] Where: X avg (t) is the average value within the time window Δt; X(t) is the monitoring data collected in real time.

[0042] As a preferred technical solution of the present invention, the remote monitoring module generates personalized health management suggestions G(t), specifically:

[0043] G(t)=β1·S(t)+β2·R(t)+β3·F(t+n);

[0044] Where: S(t) is the treatment plan input by the doctor; R(t) is the patient feedback data; F(t+n) is the predicted health index; β1, β2, β3 are the adjustment weight coefficients.

[0045] As a preferred technical solution of the present invention, the feedback management suggests dynamically adjusting the weights of β1, β2, and β3 through a machine learning model to optimize the health management effect.

[0046] As a preferred technical solution of the present invention, the system is configured to detect when the health index H(t) exceeds the abnormal threshold H th2 A health alarm is triggered when the following conditions are met:

[0047]

[0048] Where: γ is the threshold value of the rate of change of the health index; is the rate of change of the health index.

[0049] As a preferred technical solution of the present invention, the information management and display module is used to generate health trend graphs, parameter fluctuation graphs and predictive analysis reports, and supports real-time data viewing by doctors and patients.

[0050] Compared with the prior art, the present invention has the following beneficial effects:

[0051] This technical solution uses multi-mode sensors (such as pressure sensors, pH sensors and biosensors) to achieve real-time dynamic monitoring of key indicators such as intestinal pressure, peristalsis frequency, pH value, etc., which can fully reflect the intestinal function and microenvironment changes of colorectal cancer patients. This continuous non-invasive monitoring makes up for the shortcomings of traditional diagnostic methods (such as endoscopy and tumor marker detection) in dynamic monitoring, enabling doctors to detect potential problems earlier, such as intestinal motility disorders, postoperative dysfunction or chemotherapy-induced side effects, thereby significantly improving the accuracy of diagnosis and treatment. The system uses a health index model combined with a time series prediction algorithm to not only quantify the patient's current health status, but also predict future trends, and promptly remind doctors and patients through abnormal warning functions. This data-based intelligent analysis method solves the problems of data isolation and lack of correlation in traditional methods, and transforms the diagnosis and treatment process from "passive reaction" to "active management". At the same time, the generated personalized health management suggestions provide patients and doctors with a scientific treatment basis, which helps to optimize the treatment plan and improve the treatment effect. The monitoring device designed in this solution is small in size and light in weight, can be swallowed or worn, and can be easily used by patients in daily life without complex medical scenarios and invasive operations. The system supports remote data transmission and privacy encryption. Doctors can view the patient's real-time status and intervene through the online platform, which significantly improves the patient's compliance and comfort. This long-term dynamic monitoring method is particularly suitable for scenarios that require long-term attention, such as postoperative recovery and chemotherapy evaluation, and provides greater convenience and safety for patients' daily health management. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1This is a system block diagram of a colorectal tumor patient intestinal monitoring and information management system proposed by the present invention;

[0053] Figure 2 This is a specific structural diagram of the intestinal monitoring module of the intestinal monitoring and information management system for colorectal tumor patients proposed by the present invention. DETAILED DESCRIPTION

[0054] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0055] The following is combined with Figure 1 and Figure 2 , the specific implementation methods of the present invention are described in detail.

[0056] The present invention provides an intestinal monitoring and information management system for colorectal tumor patients, comprising an intestinal monitoring module, a data acquisition and transmission module, a data analysis and decision-making module, an information management and display module, and a remote monitoring module.

[0057] The specific structure and workflow of the system are as follows: The intestinal monitoring module is a wireless device with a built-in battery that can be swallowed into the intestine. The intestinal monitoring module includes a miniature multi-mode sensor for collecting physiological data in the patient's intestine, including: Intestinal pressure: The built-in MEMS piezoresistive pressure sensor monitors the pressure fluctuation P(t) in the intestine in mmHg, which is used to assess whether there is obstruction or abnormal pressure in the intestine. Intestinal temperature: The intestinal temperature T(t) is monitored by a miniature thermistor in °C to detect inflammation or infection.

[0058] Intestinal pH: The pH(t) of the intestinal environment is monitored by a micro pH sensor to evaluate changes in the intestinal microenvironment.

[0059] Intestinal motility frequency: The intestinal motility frequency f(t) is detected by a dynamic strain sensor in Hz and is used to evaluate the intestinal motility function.

[0060] Tumor marker concentration: through the biosensor Zenso r RDL1-800 series, detection of tumor marker concentration C biomarker (t), unit is ng / mL, used for early detection of colorectal tumors or monitoring of treatment effects.

[0061] Data acquisition and transmission module: The data collected by the sensor is transmitted to the mobile terminal device worn by the patient (such as a mobile phone or data receiver) via wireless communication (such as Bluetooth or Wi-Fi).

[0062] Data collection uses a time series grouping mechanism to group data according to the time window Δt and calculate the average value X within the window. avg (t):

[0063]

[0064] Where: X avg (t) is the average value within the time window Δt; X(t) is the monitoring data collected in real time;

[0065] Data analysis and decision-making module: After the data is transmitted to the cloud server, it is analyzed using the health index formula H(t):

[0066]

[0067] Where: X i (t) represents the monitoring data of item i, including

[0068] P(t), T(t), pH(t), f(t), C b iomarker(t);X i0 is the normal reference value of the i-th monitoring data; σ i is the standard deviation of the i-th monitoring data; w i is the weight coefficient, indicating the influence of the i-th data on the health index; n is the total number of monitored data; the larger the value of the health index H(t), the higher the health risk;

[0069] According to the health index H(t) and the preset health threshold H th1 and H th2 To classify the status:

[0070]

[0071] Where: H th1 is the health warning threshold; H th2 is the health abnormality threshold.

[0072] Use the time series prediction algorithm to predict the future health index F(t+n):

[0073]

[0074] Information management and display module: The prediction model optimizes the regression coefficient α through LSTM or GRU deep learning algorithm k , improve prediction accuracy.

[0075] The system displays health index, monitoring data and analysis results through data visualization, and generates health trend charts, parameter fluctuation charts, forecast analysis reports, etc. Patients and doctors can view data in real time through mobile applications (App).

[0076] Remote monitoring module: Doctors can view patients’ real-time health index and historical data, and generate personalized health management suggestions through feedback control equations:

[0077] G(t)=β1·S(t)+β2·R(t)+β3·F(t+n);

[0078] Where S(t) is the treatment plan input by the doctor, R(t) is the patient feedback data, and F(t+n) is the predicted value of the health index.

[0079] Example 1: Monitoring of intestinal recovery in patients after colorectal cancer surgery

[0080] Patient background: Male, 62 years old, 2 weeks after surgery, in the recovery period; Symptoms: occasional abdominal pain, weakened intestinal motility;

[0081] Objective: To monitor intestinal pressure, peristalsis frequency and other data in real time through the system to analyze postoperative recovery.

[0082] Data Collection: The physiological data collected by the built-in sensors are as follows (units are mmHg, Hz, dimensionless, ng / mL):

[0083]

[0084] Health index calculation process: normal reference value X i0 :

[0085] P0=10mmHg, f0=0.15Hz, pH0=7.0, C0=10.0ng / mL.

[0086] Standard deviation i :

[0087] σ P =3.0,σ f =0.05,σ pH =0.5,σ C =5.0.

[0088] Weight w i :

[0089] w P =0.3, w f =0.2, w pH =0.2, w C =0.3.

[0090] Health Index Formula:

[0091]

[0092] Take the data of the 6th hour as an example (pressure P(t) = 16.5, peristaltic frequency f(t) = 0.09, pH value pH(t) = 6.4, tumor marker concentration C biomarker (t) = 28.5):

[0093]

[0094] Status classification: Healthy Threshold: H th1 =4.0 (the dividing point between normal and warning); H th2 =7.0 (the dividing line between warning and abnormality).

[0095] Status result: The health index H(6) at the 6th hour = 6.10, which is in the "warning" state.

[0096] Time series forecasting: predict the health index F(12) for the next 6 hours:

[0097] F(12)=H(6)+α1·ΔH(6)+α2·ΔH(0),

[0098] Assume α1 = 0.6, α2 = 0.4, and ΔH(6) = H(6) - H(0) = 6.10 - 5.50 = 0.60,

[0099] ΔH(0)=H(0)-H base =5.50-4.0=1.50,

[0100] F(12)=6.10+0.6·0.60+0.4·1.50=6.10+0.36+0.60=7.06,

[0101] The predicted health index F(12)=7.06, entering the "abnormal" state, requiring intervention.

[0102] Personalized Recommendation Generation: Generate recommendations through feedback control equations:

[0103] G(t)=0.5·S(t)+0.3·R(t)+0.2·F(t+n);

[0104] The doctor inputs the treatment plan S(t)=2.0, the patient feedback R(t)=1.5, and the prediction index F(t+n)=7.06:

[0105] G(t)=0.5·2.0+0.3·1.5+0.2·7.06=1.0+0.45+1.41=2.86

[0106] System recommendations: Strengthen dietary control, increase the dose of intestinal motility drugs, and monitor every 6 hours.

[0107] Example 2: Diagnosis and monitoring of patients with intestinal motility disorders;

[0108] Patient background: Female, 45 years old, long-term constipation, suspected intestinal motility disorder; symptoms: weakened intestinal motility, difficult defecation, occasional abdominal distension;

[0109] Objective: This system can be used to collect data such as intestinal pressure and peristalsis frequency of patients, diagnose whether there is intestinal motility disorder, and develop a treatment plan for the patient.

[0110] Data collection: The patient swallows the microsensor capsule device of this system, and dynamically collects the following physiological data over 24 hours (units are mmHg, Hz, dimensionless, ng / mL):

[0111]

[0112] Health index calculation process: normal reference value X i0 :

[0113] P0=10mmHg,f0=0.15Hz, C0=10.0ng / mL,

[0114] Standard deviation i :σ P =3.0,σ f =0.05,σ pH =0.5,σ C =5.0.

[0115] Weight w i :

[0116] w P =0.3, w f =0.4, w pH =0.2, w C =0.1.

[0117] Health Index Formula:

[0118]

[0119] Take the data of the 12th hour as an example (pressure P(t) = 15.5, peristaltic frequency f(t) = 0.05, pH value pH(t) = 6.6, tumor marker concentration C biomarker (t) = 11.0):

[0120]

[0121] Health threshold: H th1 =2.0 (the dividing point between normal and warning); H th2 =4.0 (the dividing line between warning and abnormality).

[0122] Status result: The health index H(12) at the 12th hour is 2.744, which is in the "warning" state.

[0123] Time series forecasting: predict the health index F(18) for the next 6 hours:

[0124] F(18)=H(12)+α1·ΔH(12)+α2·ΔH(6),

[0125] Assume that α1=0.5, α2=0.5, and ΔH(12)=H(12)-H(6)=2.744-2.350=0.394, ΔH(6)=H(6)-H(0)=2.350-2.0=0.350,

[0126] F(18)=2.744+0.5·0.394+0.5·0.350=2.744+0.197+0.175=3.116,

[0127] The predicted health index F(18)=3.116, still in the "warning" state.

[0128] Personalized Recommendation Generation: Generate recommendations through feedback control equations:

[0129] G(t)=0.5·S(t)+0.3·R(t)+0.2·F(t+n)

[0130] The doctor inputs the treatment plan S(t)=2.0, the patient feedback R(t)=1.8, and the prediction index F(t+n)=3.116:

[0131] G(t)=0.5·2.0+0.3·1.8+0.2·3.116=1.0+0.54+0.623=2.163

[0132] System recommendation: It is recommended to increase the dose of intestinal motility drugs, and the patient is advised to consume more dietary fiber and retest within the next 12 hours.

[0133] Example 3: Monitoring of tumor markers in patients undergoing chemotherapy;

[0134] Patient background: Male, 55 years old, colorectal cancer patient, in the second cycle of chemotherapy; Symptoms: large fluctuations in the intestinal environment, suspected side effects caused by chemotherapy drugs;

[0135] Objective: To monitor tumor marker concentrations and intestinal pressure and pH changes, and to evaluate chemotherapy efficacy and side effects.

[0136]

[0137] Health index calculation: I will omit the detailed calculation process. The patient's health index decreases over time:

[0138] H(0)=6.2, H(6)=5.8, H(12)=5.4, H(18)=5.0, H(24)=4.8.

[0139] Status classification and suggestions: The health index is gradually approaching the warning threshold H th1 =4.0.

[0140] The system recommends reducing the chemotherapy dose and reducing side effects by using drugs that regulate intestinal pH.

[0141] The contents not described in detail in this specification belong to the prior art known to professional and technical personnel in the field. Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments, or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A system for monitoring and managing the intestinal tract of patients with colorectal tumors, characterized in that: The system includes: Intestinal monitoring module: used to collect the patient's intestinal physiological data in real time, including: intestinal pressure P(t), in mmHg; intestinal temperature T(t), in °C; intestinal pH(t), dimensionless; intestinal peristalsis frequency f(t), in Hz; tumor marker concentration C biomarker (t), unit is ng / mL; Data collection and transmission module: used to transmit the monitoring data to the cloud server via wireless communication, the wireless communication includes Bluetooth or Wi-Fi; Data analysis and decision-making module: used to evaluate the patient's intestinal health status based on the following health index H(t) formula: in: X i (t) represents the i-th monitoring data, including P(t), T(t), pH(t), f(t), C b iomarker(t);X i0 is the normal reference value of the i-th monitoring data; σ i is the standard deviation of the i-th monitoring data; w i is the weight coefficient, indicating the influence of the i-th data on the health index; n is the total number of monitored data; the larger the value of the health index H(t), the higher the health risk; Information management and display module: used to store, analyze and visualize health index and monitoring data; Remote monitoring module: used to realize data interaction and health guidance between doctors and patients.

2. The intestinal monitoring and information management system for colorectal tumor patients according to claim 1, characterized in that: The health index H(t) is obtained by setting the health threshold H th1 and H th2 The status is classified as follows: Where: H th1 is the health warning threshold; H th2 is the health abnormality threshold.

3. The intestinal monitoring and information management system for colorectal tumor patients according to claim 1, characterized in that: The data analysis and decision-making module predicts the health index F(t+n) for the next n time steps based on the time series prediction algorithm, specifically: Where: F(t+n) is the health index predicted for the next n time steps; α k is the regression coefficient, obtained through model training; ΔH(tk) is the change in the historical health index.

4. The intestinal monitoring and information management system for colorectal tumor patients according to claim 3, characterized in that: The time series prediction algorithm uses a long short-term memory network or a gated recurrent unit (GRU) to iteratively optimize the regression coefficient α through machine learning. k , improve prediction accuracy.

5. The intestinal monitoring and information management system for colorectal cancer patients according to claim 1, characterized in that: The intestinal monitoring module adopts micro multi-mode sensor integration technology, and the sensors include: a pressure sensor for collecting P(t); a temperature sensor for collecting T(t); a pH sensor for collecting pH(t); a biosensor for detecting C biomarker (t).

6. The intestinal monitoring and information management system for colorectal tumor patients according to claim 1, characterized in that: The data acquisition and transmission module performs average processing on the data according to the time window Δt based on the time series grouping mechanism. The specific calculation is: Where: X avg (t) is the average value within the time window Δt; X(t) is the monitoring data collected in real time.

7. The intestinal monitoring and information management system for colorectal tumor patients according to claim 1, characterized in that: The remote monitoring module generates personalized health management suggestions G(t), specifically: G(t)=β1·S(t)+β2·R(t)+β3·F(t+n); Where: S(t) is the treatment plan input by the doctor; R(t) is the patient feedback data; F(t+n) is the predicted health index; β1, β2, β3 are the adjustment weight coefficients.

8. The intestinal monitoring and information management system for colorectal cancer patients according to claim 7, characterized in that: The feedback management suggests dynamically adjusting the weights of β1, β2, and β3 through a machine learning model to optimize the health management effect.

9. The intestinal monitoring and information management system for colorectal cancer patients according to claim 2, characterized in that: The health index H(t) exceeds the abnormal threshold H th2 A health alarm is triggered when the following conditions are met: Where: γ is the threshold value of the rate of change of the health index; is the rate of change of the health index.

10. The intestinal monitoring and information management system for colorectal tumor patients according to claim 1, characterized in that: The information management and display module is used to generate health trend graphs, parameter fluctuation graphs and forecast analysis reports, and supports real-time data viewing by doctors and patients.

Images