Intelligent stomach tube gastric juice data monitoring and early warning system

Abstract

The invention discloses an intelligent stomach tube and gastric juice data monitoring and early warning system, and particularly relates to the technical field of gastric juice data monitoring, the system comprises a monitoring extraction module, a stability analysis module, a mixing verification module and an early warning processing module, the monitoring extraction module obtains a monitoring state coefficient according to monitoring feature information of stomach tube and gastric juice data; the stability analysis module obtains a stable response coefficient according to stable flow information of the gastric juice data of the stomach tube, the mixed verification module constructs a verification model according to the monitoring state coefficient and the stable response coefficient, and the gastric juice state and the monitoring efficiency of the patient are comprehensively evaluated by obtaining a mixed verification index of the verification model. And the early warning processing module classifies the monitoring state of the stomach tube and gastric juice data and carries out early warning prompt according to the classification result. According to the invention, the effectiveness and real-time performance of monitoring and processing the stomach tube and gastric juice data are effectively improved, the working pressure of medical personnel is reduced, and the management efficiency of medical equipment is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of gastric juice data monitoring, and more specifically, to an intelligent gastric tube gastric juice data monitoring and early warning system. Background Art

[0002] The intelligent gastric tube gastric juice data monitoring and early warning system combines the Internet of Things and medical technology to monitor the gastric juice data in the patient's gastric tube and provide timely early warning information. It monitors the patient's gastric juice condition in real time through intelligent gastric tube equipment, collects gastric juice data and transmits the data to external monitoring equipment or cloud platforms through sensors. The patient's gastric juice status is evaluated based on the data for analysis and early warning. The existing gastric tube gastric juice data monitoring and early warning focus on the monitoring of the patient's gastric juice status itself, and issue early warnings based on the analysis of the gastric juice status. There is insufficient analysis of the real-time and effectiveness of gastric juice data, which may lead to the failure of early warning management.

[0003] In order to solve the above defects, a technical solution is now proposed. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent gastric tube gastric fluid data monitoring and early warning system to solve the deficiencies in the background technology.

[0005] In order to achieve the above-mentioned object, the present invention provides the following technical solutions: an intelligent gastric tube gastric fluid data monitoring and early warning system, comprising a monitoring extraction module, a stability analysis module, a hybrid verification module, and an early warning disposal module;

[0006] The monitoring extraction module is used to collect monitoring feature information of gastric tube gastric fluid data, obtain monitoring state coefficients according to the monitoring feature information of gastric tube gastric fluid data, and transmit the monitoring state coefficients to the hybrid verification module;

[0007] The stability analysis module is used to collect the stable flow information of the gastric fluid data of the gastric tube, obtain the stable response coefficient according to the stable flow information of the gastric fluid data of the gastric tube, and transmit the stable response coefficient to the hybrid verification module;

[0008] The hybrid verification module is used to construct a verification model based on the monitoring state coefficient and the stable response coefficient, and to comprehensively evaluate the patient's gastric fluid state and monitoring efficiency by obtaining the hybrid verification index of the verification model;

[0009] The early warning and disposal module is used to compare the mixed verification index with the preset mixed verification threshold, classify the status of gastric tube gastric juice data monitoring according to the comparison results, and issue early warning prompts based on the classification results.

[0010] Preferably, the method for obtaining monitoring characteristic information is:

[0011] Obtain the digestion fluctuation coefficient of the gastric juice data in the gastric tube within the cycle time T, and integrate the digestion fluctuation coefficients of the gastric juice data in the gastric tube within several cycle times T into a data set, and mark the data set as St = {ac d}, where d = {1, 2, 3, ..., p}, and p is a positive integer, ac d It represents the digestion fluctuation coefficient of the gastric fluid data in the gastric tube within the dth cycle time T. The calculation expression of the digestion fluctuation coefficient is St = log (pH) Te , where pH represents the acidity and alkalinity of gastric juice, and Te represents the temperature of gastric juice;

[0012] Calculate the standard deviation of the digestion fluctuation coefficient of the gastric juice data in the gastric tube within several cycles of time T. The calculation expression is: Where avg is the average value of the digestion fluctuation coefficient of the gastric fluid data in the gastric tube within several cycles T, and the calculation expression is:

[0013] Preferably, the method for obtaining the monitoring state coefficient according to the monitoring characteristic information is as follows:

[0014] By constructing a logistic regression model and using the monitoring feature information to obtain the monitoring state coefficient, the feature vector X = [D ig ,V o ,C o ], where V o is the volume of gastric fluid, C o is the RGB value converted from the gastric juice color, then the logistic regression model is Where P(y=1|X) is the monitoring state coefficient, y=1 is the abnormal label, indicating that the gastric juice state is abnormal, y=0 is the stable label, indicating that the gastric juice state is stable, and ω is the weight vector.

[0015] Preferably, the method for obtaining stable flow information is:

[0016] Obtain the delayed response coefficient of the gastric fluid data in the gastric tube within the cycle time T, and integrate the delayed response coefficients of the gastric fluid data in the gastric tube within several cycle times T into a data set, and mark the data set as Dr = {re s}, where s = {1, 2, 3, ..., f}, and f is a positive integer, re s It represents the delayed response coefficient of the gastric fluid data in the gastric tube within the sth cycle time T. The calculation expression of the delayed response coefficient is: Where f is the frequency of gastric juice data collection, T sc is the transmission time of gastric juice data.

[0017] Preferably, the method for obtaining the stable response coefficient according to the stable flow information is:

[0018] By establishing a real-time evaluation model and using the stable flow information to obtain the stable response coefficient, the gastric juice data loss rate is calibrated to λ, and the abnormal gastric juice state response time is t rp , then the real-time evaluation model is In the formula, R is the stable response coefficient, α, β, and γ are Dr, The weight coefficient, and α, β, γ are all positive numbers, λ max is the preset gastric juice data loss rate limit, t th It is the preset abnormal gastric fluid status response threshold.

[0019] Preferably, the method for constructing a verification model according to the monitoring state coefficient and the stable response coefficient is:

[0020] The mathematical expression of the verification model is V er =P(y=1|X)R ， Where V er is the mixed verification index, P(y=1|X) is the monitoring state coefficient, and R is the stable response coefficient.

[0021] Preferably, the mixed verification index is compared with a preset mixed verification threshold, and the logic for classifying the state of the gastric tube gastric fluid data monitoring according to the comparison result is:

[0022] Preset hybrid verification threshold V th , preset stable response limit R th , when the calculated hybrid verification index V er Greater than or equal to the mixed verification threshold V th And the stable response coefficient R is greater than or equal to the stable response limit R th When , the monitoring data is marked as the first-level state;

[0023] When the calculated hybrid verification index V er Less than the mixed verification threshold V th And the stable response coefficient R is greater than or equal to the stable response limit R th When , the monitoring data is marked as the secondary state;

[0024] When the stable response coefficient R is less than the stable response limit R th , the monitoring data is marked as level 3 status.

[0025] Preferably, the logic for providing early warning prompts based on the classification results is:

[0026] When the monitoring data is marked as the first-level state, the gastric juice data is recorded and the medical staff is notified of the abnormal gastric juice monitoring;

[0027] When the monitoring data is marked as the secondary state, the gastric fluid data is recorded and the data is marked as stable;

[0028] When the monitoring data is marked as level three, the medical staff is prompted that the gastric juice data monitoring is delayed, and the gastric juice data is recorded and marked as questionable.

[0029] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0030] The present application combines the status monitoring and real-time monitoring of gastric fluid data from a gastric tube to establish a comprehensive evaluation model to comprehensively evaluate the timeliness of the gastric fluid status and gastric fluid data, thereby improving the accuracy of gastric fluid monitoring and verifying the timeliness of the monitoring data, achieving a balance between data accuracy and real-time performance, avoiding false alarms caused by errors in gastric fluid data monitoring, and verifying the effectiveness of the early warning, thereby reducing the attention cost of medical staff and improving the efficiency of gastric fluid monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the embodiments of the present application 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 recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0032] Figure 1 It is a system module diagram of the present invention. DETAILED DESCRIPTION

[0033] 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.

[0034] Example 1: Please refer to Figure 1 As shown, the present invention is an intelligent gastric tube gastric fluid data monitoring and early warning system, including a monitoring extraction module, a stability analysis module, a mixed verification module, and an early warning disposal module;

[0035] The monitoring extraction module is used to collect monitoring feature information of gastric tube gastric fluid data, obtain monitoring state coefficients according to the monitoring feature information of gastric tube gastric fluid data, and transmit the monitoring state coefficients to the hybrid verification module;

[0036] The stability analysis module is used to collect the stable flow information of the gastric fluid data of the gastric tube, obtain the stable response coefficient according to the stable flow information of the gastric fluid data of the gastric tube, and transmit the stable response coefficient to the hybrid verification module;

[0037] The hybrid verification module is used to construct a verification model based on the monitoring state coefficient and the stable response coefficient, and to comprehensively evaluate the patient's gastric fluid state and monitoring efficiency by obtaining the hybrid verification index of the verification model;

[0038] The early warning and disposal module is used to compare the mixed verification index with the preset mixed verification threshold, classify the status of gastric tube gastric juice data monitoring according to the comparison results, and issue early warning prompts based on the classification results.

[0039] It should be noted that the gastric fluid data in the gastric tube in this application includes pH value, temperature, volume and color information;

[0040] Monitoring and analyzing the status of gastric fluid in the gastric tube has important clinical significance and can help early detection and prevention of potential health problems in patients, including in intensive care, postoperative care, and all aspects of the diagnosis and treatment of digestive system diseases;

[0041] Gastric juice is a key physiological indicator that reflects the health of the stomach and digestive system. By monitoring and analyzing parameters such as the pH value, color, temperature, and volume of gastric juice, doctors can detect early-stage gastric diseases in patients. For example, an abnormally high or low pH value of gastric juice may indicate abnormal gastric acid secretion, and the patient may have problems such as gastric ulcers or gastritis. If red blood is detected in gastric juice, it may be a sign of gastric bleeding. If the gastric juice turns green, it may be a symptom of bile reflux into the stomach, indicating that the patient has a bile-related disease. Through early detection and analysis, early warning and intervention can be carried out before the disease worsens, effectively avoiding serious complications.

[0042] After surgical operations such as gastrectomy and gastrointestinal surgery, gastric juice is monitored and early warning is provided. Patients are in a weak state after surgery and are prone to digestive system dysfunction. Real-time monitoring of gastric juice data helps doctors monitor the recovery of gastrointestinal function and determine the recovery speed of the gastrointestinal tract. At the same time, postoperative complications are prevented in a timely manner. Treatment measures are taken in a timely manner based on abnormal gastric juice status to prevent the condition from worsening.

[0043] The characteristics of gastric juice provide doctors with rich clinical information to help diagnose digestive system diseases, such as gastroesophageal reflux disease. If the pH value of gastric juice is low for a long time, it indicates esophageal irritation caused by gastric acid reflux. Long-term monitoring of gastric juice can effectively detect excessive or insufficient gastric acid secretion, which is helpful for the diagnosis and treatment of gastritis. Gastric juice analysis can help distinguish different types of gastrointestinal diseases to support doctors in making more accurate diagnosis and treatment decisions.

[0044] In the ICU intensive care unit, patients are in a weak condition and need to closely monitor their stomach conditions. Abnormal analysis of gastric juice helps medical staff effectively manage patients’ nutrition and drug treatment and prevent digestive system complications by real-time monitoring of gastric juice changes. When gastric juice data is abnormal, it automatically issues an early warning message, allowing medical staff to respond in time and improve the efficiency and accuracy of care.

[0045] Traditional gastric juice monitoring relies on regular manual inspections by medical staff, which carries the risk of delays and misjudgments. The intelligent gastric tube gastric juice data monitoring and early warning system continuously and accurately collects gastric juice data in an automated manner, reducing the frequency of manual intervention and improving monitoring efficiency. It not only reduces the burden on medical staff, but also avoids interference from human errors.

[0046] The monitoring extraction module is used to collect monitoring feature information of gastric tube gastric fluid data, obtain monitoring state coefficients according to the monitoring feature information of gastric tube gastric fluid data, and transmit the monitoring state coefficients to the hybrid verification module;

[0047] The method for obtaining monitoring characteristic information is as follows:

[0048] Obtain the digestion fluctuation coefficient of the gastric juice data in the gastric tube within the cycle time T, and integrate the digestion fluctuation coefficients of the gastric juice data in the gastric tube within several cycle times T into a data set, and mark the data set as St = {ac d}, where d = {1, 2, 3, ..., p}, and p is a positive integer, ac d It represents the digestion fluctuation coefficient of the gastric fluid data in the gastric tube within the dth cycle time T. The calculation expression of the digestion fluctuation coefficient is St = log (pH) Te , where pH represents the acidity and alkalinity of gastric juice, and Te represents the temperature of gastric juice;

[0049] Calculate the standard deviation of the digestion fluctuation coefficient of the gastric juice data in the gastric tube within several cycles of time T. The calculation expression is: Where avg is the average value of the digestion fluctuation coefficient of the gastric fluid data in the gastric tube within several cycles T, and the calculation expression is:

[0050] It should be noted that the pH value, temperature, volume and color data of gastric juice are obtained through special sensors in medical monitoring. The pH probe is used to continuously detect the acidity and alkalinity of gastric juice. The data collected by the pH probe contains the timestamp of each measurement and forms time series data. The gastric juice temperature is obtained through a temperature sensor, and the volume of gastric juice is measured according to the discharge of gastric juice from the gastric tube. The gastric juice color is collected by an optical sensor and analyzed using an image processing algorithm to convert the gastric juice color into RGB values.

[0051] The pH value of gastric juice is mainly determined by its components, especially the content of hydrochloric acid. Hydrochloric acid provides the necessary acidic environment for pepsin and helps digest and sterilize food. The temperature of gastric juice is maintained within the temperature range deep in the human body. This temperature range helps maintain the stability of the stomach environment and promotes digestion and absorption of food. At the same time, suitable temperature is also an important condition for gastric acid to function normally. Therefore, the pH value and temperature data are correlated and extracted to effectively measure the digestive capacity of gastric juice.

[0052] The method for obtaining the monitoring status coefficient according to the monitoring characteristic information is as follows:

[0053] By constructing a logistic regression model and using the monitoring feature information to obtain the monitoring state coefficient, the feature vector X = [D ig ,V o ,C o ], where V o is the volume of gastric fluid, C o is the RGB value converted from the gastric juice color, then the logistic regression model is Where P(y=1|X) is the monitoring state coefficient, y=1 is the abnormal label, indicating that the gastric juice state is abnormal, y=0 is the stable label, indicating that the gastric juice state is stable, and ω is the weight vector.

[0054] The stability analysis module is used to collect the stable flow information of the gastric fluid data of the gastric tube, obtain the stable response coefficient according to the stable flow information of the gastric fluid data of the gastric tube, and transmit the stable response coefficient to the hybrid verification module;

[0055] The method for obtaining stable flow information is:

[0056] Obtain the delayed response coefficient of the gastric fluid data in the gastric tube within the cycle time T, and integrate the delayed response coefficients of the gastric fluid data in the gastric tube within several cycle times T into a data set, and mark the data set as Dr = {re s}, where s = {1, 2, 3, ..., f}, and f is a positive integer, re s It represents the delayed response coefficient of the gastric fluid data in the gastric tube within the sth cycle time T. The calculation expression of the delayed response coefficient is: Where f is the frequency of gastric juice data collection, T sc is the transmission time of gastric juice data.

[0057] The method for obtaining the stable response coefficient based on the stable flow information is:

[0058] By establishing a real-time evaluation model and using the stable flow information to obtain the stable response coefficient, the gastric juice data loss rate is calibrated to λ, and the abnormal gastric juice state response time is t rp , then the real-time evaluation model is In the formula, R is the stable response coefficient, α, β, and γ are Dr, The weight coefficient, and α, β, γ are all positive numbers, λ max is the preset gastric juice data loss rate limit, t th It is the preset abnormal gastric fluid status response threshold.

[0059] It is of great significance to evaluate the real-time monitoring of gastric juice data to verify the validity of the data. The real-time nature of gastric juice data determines the extent to which doctors or nursing staff can obtain timely information on the patient's physiological condition, especially when abnormalities occur. For example, by real-time monitoring of gastric juice pH, temperature, volume, color and other parameters, doctors can quickly detect abnormalities. If gastric juice abnormalities occur, they can intervene quickly. The abnormal gastric juice data is quickly transmitted and reflected in the monitoring in real time, so that medical staff can take immediate measures to avoid worsening of the condition, for example, timely adjustment of medication or emergency treatment;

[0060] Real-time evaluation can ensure that the acquired data is efficient and consistent, thereby improving data reliability. If the data delay is too long, doctors may make wrong decisions based on delayed information. For example, a sudden increase in gastric fluid temperature may indicate infection. If the delay is too long, the infection may have worsened and not be treated in time. Real-time monitoring includes monitoring of data loss rate. If the system loses too much data, some abnormal signals may be missed, thus affecting the accuracy of diagnosis.

[0061] Real-time evaluation helps to accurately adjust treatment plans and ensure that treatment measures can be quickly adjusted according to the patient's specific conditions. By capturing changes in gastric juice data in real time, doctors can effectively and dynamically adjust the patient's drug dosage. For example, for patients with excessive gastric acid, real-time monitoring of gastric juice pH can assist doctors in adjusting the dosage and frequency of antacids. Each patient has different physiological responses. Real-time data monitoring assists doctors in making precise adjustments based on the patient's individualized physiological feedback and providing personalized treatment plans.

[0062] Real-time evaluation can provide technical support for automated intelligent monitoring and early warning systems. Based on real-time data, the system automatically detects abnormalities in gastric juice parameters and issues alarms in a timely manner. For example, when the pH value is too low, the system can immediately remind medical staff to avoid missed diagnoses due to untimely manual observation. By ensuring the real-time and accuracy of the data, it provides reliable data input for the artificial intelligence diagnostic system, helping the system to make more accurate analysis and predictions.

[0063] The hybrid verification module is used to construct a verification model based on the monitoring state coefficient and the stable response coefficient, and to comprehensively evaluate the patient's gastric fluid state and monitoring efficiency by obtaining the hybrid verification index of the verification model;

[0064] The method of constructing a verification model based on the monitoring state coefficient and the stable response coefficient is:

[0065] The mathematical expression of the verification model is V er =P(y=1|X) R , where V er is the mixed verification index, P(y=1|X) is the monitoring state coefficient, and R is the stable response coefficient.

[0066] The early warning and disposal module is used to compare the mixed verification index with the preset mixed verification threshold, classify the state of the gastric tube gastric fluid data monitoring according to the comparison result, and issue an early warning prompt according to the classification result;

[0067] Preset hybrid verification threshold V th , preset stable response limit R th , when the calculated hybrid verification index V er Greater than or equal to the mixed verification threshold V th And the stable response coefficient R is greater than or equal to the stable response limit R th When , the monitoring data is marked as the first-level state;

[0068] When the calculated hybrid verification index V er Less than the mixed verification threshold V th And the stable response coefficient R is greater than or equal to the stable response limit R th When , the monitoring data is marked as the secondary state;

[0069] When the stable response coefficient R is less than the stable response limit R th , the monitoring data is marked as level 3 status.

[0070] The logic of early warning prompts based on the classification results is:

[0071] When the monitoring data is marked as the first-level state, the gastric juice data is recorded and the medical staff is notified of the abnormal gastric juice monitoring;

[0072] When the monitoring data is marked as the secondary state, the gastric fluid data is recorded and the data is marked as stable;

[0073] When the monitoring data is marked as level three, the medical staff is prompted that the gastric juice data monitoring is delayed, and the gastric juice data is recorded and marked as questionable.

[0074] The present application combines the status monitoring and real-time monitoring of gastric fluid data from a gastric tube to establish a comprehensive evaluation model to comprehensively evaluate the timeliness of the gastric fluid status and gastric fluid data, thereby improving the accuracy of gastric fluid monitoring and verifying the timeliness of the monitoring data, achieving a balance between data accuracy and real-time performance, avoiding false alarms caused by errors in gastric fluid data monitoring, and verifying the effectiveness of the early warning, thereby reducing the attention cost of medical staff and improving the efficiency of gastric fluid monitoring.

[0075] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0076] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of computer program goods. The computer program goods include one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0077] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0078] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0079] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0080] If the functions are implemented in the form of software functional units and sold or used as independent goods, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can essentially or in other words, the part that contributes to the prior art or the part of the technical solution can be embodied in the form of software goods, and the computer software goods are stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0081] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. Intelligent gastric tube gastric juice data monitoring and early warning system, characterized by: It includes monitoring extraction module, stability analysis module, hybrid verification module and early warning disposal module; The monitoring extraction module is used to collect monitoring feature information of gastric tube gastric fluid data, obtain monitoring state coefficients according to the monitoring feature information of gastric tube gastric fluid data, and transmit the monitoring state coefficients to the hybrid verification module; The stability analysis module is used to collect the stable flow information of the gastric fluid data of the gastric tube, obtain the stable response coefficient according to the stable flow information of the gastric fluid data of the gastric tube, and transmit the stable response coefficient to the hybrid verification module; The hybrid verification module is used to construct a verification model based on the monitoring state coefficient and the stable response coefficient, and to comprehensively evaluate the patient's gastric fluid state and monitoring efficiency by obtaining the hybrid verification index of the verification model; The early warning and disposal module is used to compare the mixed verification index with the preset mixed verification threshold, classify the status of gastric tube gastric juice data monitoring according to the comparison results, and issue early warning prompts based on the classification results.

2. The intelligent gastric tube gastric fluid data monitoring and early warning system according to claim 1 is characterized in that: The method for obtaining monitoring characteristic information is as follows: Obtain the digestion fluctuation coefficient of the gastric juice data in the gastric tube within the cycle time T, and integrate the digestion fluctuation coefficients of the gastric juice data in the gastric tube within several cycle times T into a data set, and mark the data set as St = {ac d }, where d = {1, 2, 3, ..., p}, and p is a positive integer, ac d It represents the digestion fluctuation coefficient of the gastric fluid data in the gastric tube within the dth cycle time T. The calculation expression of the digestion fluctuation coefficient is St = log (pH) Te , where pH represents the acidity and alkalinity of gastric juice, and Te represents the temperature of gastric juice; Calculate the standard deviation of the digestion fluctuation coefficient of the gastric juice data in the gastric tube within several cycles of time T. The calculation expression is: Where avg is the average value of the digestion fluctuation coefficient of the gastric fluid data in the gastric tube within several cycles T, and the calculation expression is:

3. The intelligent gastric tube gastric fluid data monitoring and early warning system according to claim 2 is characterized in that: The method for obtaining the monitoring status coefficient according to the monitoring characteristic information is as follows: By constructing a logistic regression model and using the monitoring feature information to obtain the monitoring state coefficient, the feature vector X = [D ig ,V o ,C o ], where V o is the volume of gastric fluid, C o is the RGB value converted from the gastric juice color, then the logistic regression model is Where P(y=1|X) is the monitoring state coefficient, y=1 is the abnormal label, indicating that the gastric juice state is abnormal, y=0 is the stable label, indicating that the gastric juice state is stable, and ω is the weight vector.

4. The intelligent gastric tube gastric fluid data monitoring and early warning system according to claim 1, characterized in that: The method for obtaining stable flow information is: Obtain the delayed response coefficient of the gastric fluid data in the gastric tube within the cycle time T, and integrate the delayed response coefficients of the gastric fluid data in the gastric tube within several cycle times T into a data set, and mark the data set as Dr = {re s }, where s = {1, 2, 3, ..., f}, and f is a positive integer, re s It represents the delayed response coefficient of the gastric fluid data in the gastric tube within the sth cycle time T. The calculation expression of the delayed response coefficient is: Where f is the frequency of gastric juice data collection, T sc is the transmission time of gastric juice data.

5. The intelligent gastric tube gastric fluid data monitoring and early warning system according to claim 4 is characterized in that: The method for obtaining the stable response coefficient based on the stable flow information is: By establishing a real-time evaluation model and using the stable flow information to obtain the stable response coefficient, the gastric juice data loss rate is calibrated to λ, and the abnormal gastric juice state response time is t rp , then the real-time evaluation model is In the formula, R is the stable response coefficient, α, β, and γ are Dr, The weight coefficient, and α, β, γ are all positive numbers, λ max is the preset gastric juice data loss rate limit, t th It is the preset abnormal gastric fluid status response threshold.

6. The intelligent gastric tube gastric fluid data monitoring and early warning system according to claim 5, characterized in that: The method of constructing a verification model based on the monitoring state coefficient and the stable response coefficient is: The mathematical expression of the verification model is V er =P(y=1|X) R , where V er is the mixed verification index, P(y=1|X) is the monitoring state coefficient, and R is the stable response coefficient.

7. The intelligent gastric tube gastric fluid data monitoring and early warning system according to claim 6, characterized in that: The mixed verification index is compared with the preset mixed verification threshold, and the logic for classifying the state of gastric tube gastric fluid data monitoring according to the comparison result is: Preset hybrid verification threshold V th , preset stable response limit R th , when the calculated hybrid verification index V er Greater than or equal to the mixed verification threshold V th And the stable response coefficient R is greater than or equal to the stable response limit R th When , the monitoring data is marked as the first-level state; When the calculated hybrid verification index V er Less than the mixed verification threshold V th And the stable response coefficient R is greater than or equal to the stable response limit R th When , the monitoring data is marked as the secondary state; When the stable response coefficient R is less than the stable response limit R th , the monitoring data is marked as level 3 status.

8. The intelligent gastric tube gastric fluid data monitoring and early warning system according to claim 7 is characterized in that: The logic of early warning prompts based on the classification results is: When the monitoring data is marked as the first-level state, the gastric juice data is recorded and the medical staff is notified of the abnormal gastric juice monitoring; When the monitoring data is marked as the secondary state, the gastric fluid data is recorded and the data is marked as stable; When the monitoring data is marked as level three, the medical staff is prompted that the gastric juice data monitoring is delayed, and the gastric juice data is recorded and marked as questionable.

Images