Anesthesia auxiliary early warning method and system based on artificial intelligence

Through an anesthesia-assisted early warning system based on artificial intelligence, the endoscopic operation and patient information are collected and analyzed in real time, the concentration of anesthetic drugs is calculated and the early warning is issued, which solves the problem of difficult adjustment of the dosage of anesthetic drugs in gastroenteroscopy, and improves the safety of the examination and Operational efficiency.

CN118522406BActive Publication Date: 2024-11-12RENMIN HOSPITAL OF WUHAN UNIVERSITY (HUBEI GENERAL HOSPITAL)
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411006778.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-25
Publication Date
2024-11-12
Estimated Expiration
2044-07-25

AI Technical Summary

Technical Problem

During gastroenteroscopy, the dosage of anesthetic drugs is difficult to accurately regulate, resulting in frequent adverse reactions related to sedation. The shortage of doctors leads to the inability to timely understand the diagnosis and treatment process and conduct accurate monitoring, which increases the serious risks of delayed awakening and inhibition of respiratory circulation.

Method used

Adopt anesthesia assisted early warning system based on artificial intelligence, and obtain endoscopic operation information and patient monitoring information through the data acquisition terminal. The drug concentration calculation terminal calculates the concentration of anesthetic drug and issues adjustment instructions. The monitoring terminal issues early warning information, and the monitoring terminal integrates and displays information. Aggregate the terminal data to improve anesthesia safety.

Benefits of technology

It improves the accuracy of anesthesia auxiliary warning, reduces the occurrence of adverse reactions, and ensures the safety and operational efficiency of the gastroenteroscopy clinic.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118522406B_ABST
    Figure CN118522406B_ABST
Patent Text Reader

Abstract

The present application discloses an artificial intelligence anesthesia auxiliary early warning method and system, wherein the artificial intelligence-based anesthesia auxiliary early warning system includes: a data acquisition terminal for collecting endoscopic operation information and current patient monitoring information of the target patient; a drug concentration calculation terminal for determining anesthetic drug concentration adjustment information based on the endoscopic operation information and the current patient monitoring information, and issuing prompt information based on the anesthetic drug concentration adjustment information; an input terminal for adjusting the anesthetic drug concentration in the target patient when the anesthetic drug concentration adjustment instruction based on the prompt information input is obtained; a monitoring terminal for issuing early warning information based on the endoscopic operation information and the current patient monitoring information of the target patient; a monitoring terminal for integrating and displaying the information of the input terminal and the monitoring terminal; and a summary terminal for summarizing and storing the data generated daily by the anesthesia auxiliary early warning system. The present application can improve the accuracy of anesthesia auxiliary early warning.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of anesthesia-assisted early warning technology, and specifically to an anesthesia-assisted early warning method and system based on artificial intelligence. Background Art

[0002] If the digestive tract malignant tumor is diagnosed and treated early, the 5-year survival rate can be greater than 90%; if it progresses to the middle and late stages, the 5-year survival rate is less than 25%. Anesthetic drugs themselves inhibit the cardiovascular system, and different patients have different tolerance to drugs. It is difficult to accurately adjust the dosage of anesthetic drugs, and sedation-related adverse reactions are prone to occur. Secondly, there is a shortage of anesthesiologists in the digestive endoscopy clinic, and it is often necessary to perform anesthesia management for several painless gastrointestinal endoscopy diagnosis and treatment at the same time, resulting in the inability to timely understand the diagnosis and treatment process and conduct accurate monitoring and management, which is prone to serious adverse events such as delayed awakening and respiratory and circulatory depression. Finally, due to gastrointestinal preparation, fasting, drinking, and bowel cleansing, patients undergoing gastrointestinal endoscopy have the risk of hypotension, hypovolemia, hypoglycemia, and the resulting high risk of falling, high nausea and vomiting, which require timely identification and warning to avoid serious complications. Therefore, on the basis of reasonable evaluation, it is of great significance to explore the precise and effective timing of anesthesia intervention and a real-time warning system to ensure the anesthesia safety and operation quality and efficiency of the gastrointestinal endoscopy clinic. Summary of the invention

[0003] The present application intends to provide an artificial intelligence-based anesthesia assisted warning method and system, which can improve the accuracy of anesthesia assisted warning.

[0004] In the first aspect, the anesthesia auxiliary early warning system based on artificial intelligence provided by the present application includes:

[0005] A data collection terminal for collecting endoscopic operation information and current patient monitoring information of the target patient;

[0006] a drug concentration calculation terminal, used to determine anesthetic drug concentration adjustment information based on the endoscopic operation information and the current patient monitoring information, and to issue prompt information based on the anesthetic drug concentration adjustment information;

[0007] an input terminal, for executing the anesthetic drug concentration adjustment instruction to adjust the anesthetic drug concentration in the target patient when the anesthetic drug concentration adjustment instruction based on the prompt information input is obtained;

[0008] A monitoring terminal, configured to issue warning information based on the endoscope operation information and current patient monitoring information of the target patient;

[0009] A monitoring terminal, used for integrating and displaying the information of the incoming terminal and the monitoring terminal;

[0010] The summary terminal is used to summarize and store the data generated daily by the anesthesia auxiliary early warning system.

[0011] Optionally, the drug concentration calculation terminal is used to obtain the current working mode of the anesthesia auxiliary warning system, and the current working mode of the anesthesia auxiliary warning system is any one of a gastroscopy mode, a colonoscopy mode or a gastrointestinal combined mode. The current concentration adjustment strategy is determined based on the current working mode of the anesthesia auxiliary warning system, and the anesthetic drug concentration adjustment information is determined based on the current concentration adjustment strategy, the endoscopic operation information and the current patient monitoring information.

[0012] Optionally, the endoscope operation information includes the operation site and the operation time, the current patient monitoring information includes the body movement information and vital sign information of the target patient, and the monitoring terminal includes a monitor, a first warning module, a second warning module, a third warning module, a fourth warning module and a fifth warning module.

[0013] The monitor is used to monitor and display the information of the target patient, the information of the waiting patient in the waiting state, and the awakening information of the patient in the anesthesia awakening state;

[0014] The first warning module is used to determine whether the waiting patient has an adverse event during the waiting period based on the waiting patient information, and issue a first warning message when the waiting patient has an adverse event during the waiting period, wherein the adverse event during the waiting period includes at least one of a hypoglycemia event during the waiting period, a hypovolemia event during the waiting period, and a fainting event during the waiting period;

[0015] The second warning module is used to determine whether a gastroscopic adverse event occurs to the target patient based on the endoscopic operation information and the current patient monitoring information of the target patient, and to issue a second warning message when a gastroscopic adverse event occurs to the target patient, wherein the gastroscopic adverse event includes at least one of a gastroscopic examination time extension event, a gastroscopic examination time shortening event, reflux, aspiration, choking, a gastroscopic biopsy event, and a gastroscopic premature termination event;

[0016] The third warning module is used to determine whether the target patient has a colonoscopy adverse event based on the endoscopic operation information and the current patient monitoring information of the target patient, and to issue a third warning message when a colonoscopy adverse event occurs to the target patient, wherein the colonoscopy adverse event includes at least one of a colonoscopy time extension event, a colonoscopy time shortening event, a colonoscopy biopsy event, an ileocecal arrival time, and a colonoscopy premature termination event;

[0017] The fourth warning module is used to determine whether the target patient has an abnormal physical sign event based on the current patient monitoring information of the target patient, and to issue a fourth warning message when the target patient has an abnormal physical sign event, wherein the abnormal physical sign event includes at least one of a diastolic blood pressure exceeding 100 mmHg or being lower than 40 mmHg, a systolic blood pressure exceeding 180 mmHg or being lower than 80 mmHg, a heart rate lower than 50 beats / min or higher than 120 beats / min, and a blood oxygen saturation lower than 90%;

[0018] The fifth warning module is used to determine whether the anesthesia recovery patient has an adverse anesthesia recovery event based on the anesthesia recovery patient information, and to issue a fifth warning message when an adverse anesthesia recovery event has occurred to the anesthesia recovery patient, wherein the adverse anesthesia recovery event includes at least one of a delayed recovery event, a nausea and vomiting event, a dizziness event, a fall event, and an abnormal vital sign event.

[0019] Optionally, the concentration adjustment strategy corresponding to the gastroscope mode is:

[0020] During gastroscopy, the initial target concentration of propofol is 2.5ug / ml. If the concentration of the anesthetic drug is adjusted to 2.5-4ug / ml during the gastroscopy mode,

[0021] If more than a preset number of sites are examined in the gastroscopy mode and the target patient is not moving, the endoscope is withdrawn and the anesthetic drug is discontinued; if the examination is continued, the anesthetic drug concentration is maintained at 1.6-2.5ug / ml;

[0022] If the target patient is detected to have body movement in the gastroscopy mode, a single additional anesthetic drug of 30-50 mg is added on the basis of the original anesthetic drug concentration until the target patient has no body movement;

[0023] If a gastroscopic biopsy event is detected in the gastroscopic mode, a single additional anesthetic drug of 30-50 mg is added on the basis of the original anesthetic drug concentration;

[0024] If the gastroscopy operation time is abnormally prolonged in the gastroscopy mode, a second prompt message is issued to remind the anesthesiologist to pay attention to vital signs and the total amount of anesthetic drugs and to adjust the anesthetic drug infusion mode.

[0025] The concentration adjustment strategy corresponding to the colonoscopy mode is:

[0026] The initial target concentration of propofol is 2.5ug / ml. If the concentration of the anesthetic drug is adjusted to 2.5-4ug / ml during the colonoscopy,

[0027] If the target patient is detected to have body movement in the colonoscopy mode, a single additional anesthetic drug of 30-50 mg is added on the basis of the original anesthetic drug concentration until the target patient has no body movement;

[0028] If a colonoscopy biopsy event is detected in the colonoscopy mode, a single additional anesthetic drug of 30-50 mg is administered on the basis of the original anesthetic drug concentration;

[0029] If the ileocecal region is detected in the colonoscopy mode, the anesthetic drug is discontinued if the endoscope is withdrawn directly; if the endoscope is withdrawn for examination, the concentration of the anesthetic drug is adjusted to 1.6-2ug / ml;

[0030] If the colonoscopy operation time is abnormally prolonged in the colonoscopy mode, a second prompt message is issued to remind the anesthesiologist to pay attention to vital signs and the total amount of anesthetic drugs and to adjust the anesthetic drug infusion mode.

[0031] The concentration adjustment strategy corresponding to the gastroscopy combined with colonoscopy mode is:

[0032] The initial target concentration of propofol is 2.5ug / ml. If the concentration of the anesthetic drug is adjusted to 2.5-4ug / ml during the gastroscopy combined with colonoscopy, the concentration of the anesthetic drug is adjusted to 2.5-4ug / ml during the gastroscopy combined with colonoscopy.

[0033] If the target patient is detected to have body movement in the gastroscopy combined with colonoscopy mode, 30-50 mg of anesthetic drug is added once on the basis of the original anesthetic drug concentration until the target patient has no body movement;

[0034] If a gastrointestinal endoscopic biopsy event is detected in the gastroscopy combined with colonoscopy mode, a single additional anesthetic drug of 30-50 mg is added on the basis of the original anesthetic drug concentration;

[0035] If the ileocecal region is detected in the combined gastroscopy and enteroscopy mode, the anesthetic drug is discontinued if the endoscope is withdrawn directly; if the endoscope is withdrawn for examination, the concentration of the anesthetic drug is adjusted to 1.6-2ug / ml;

[0036] If the gastroenteroscopy operation time is abnormally prolonged in the gastroscopy combined with colonoscopy mode, a second prompt message is issued to remind the anesthesiologist to pay attention to vital signs and the total amount of anesthetic drugs and to adjust the anesthetic drug infusion mode.

[0037] Optionally, the monitoring terminal includes a display and a tablet terminal, the display is used to display the information of the incoming terminal and the monitoring terminal, and a preset application is installed on the tablet terminal, and the preset application is used to remotely display the information of the incoming terminal and the monitoring terminal.

[0038] Optionally, the data summarized and stored by the summary terminal include: the number of painless gastroscopy, the number of painless colonoscopy, the amount of anesthetic drugs used, the patient's awakening time, the time of discharge from the hospital, the total daily workload of gastroenteroscopy, the workload of each anesthesiologist, sedation-related adverse events, warning events, response time, and the frequency of anesthetic drug concentration adjustment.

[0039] Optionally, the data acquisition terminal is used to obtain a stomach / intestinal part monitoring model and an inspection timing model, the stomach / intestinal part monitoring model is used to monitor the operation part in the endoscopic operation information, and the inspection timing model is used to detect the endoscopic inspection duration; the second early warning module is used to obtain an instrument intervention model, and the instrument intervention model is used to determine whether a gastroscopic / colonoscopy biopsy event occurs.

[0040] Optionally, the collecting of endoscopic operation information and current patient monitoring information of the target patient includes:

[0041] Acquire a target endoscopic image captured by a target endoscope;

[0042] Using the stomach / intestine monitoring model to determine whether the target endoscopic image contains stomach / intestine features;

[0043] If the target endoscopic image contains stomach / intestinal features, identifying multiple unclean areas on the target endoscopic image;

[0044] Eliminate unclean areas whose areas are smaller than a preset area from among the multiple unclean areas, and calculate the areas of the unclean areas of the multiple unclean areas after elimination;

[0045] Calculate the ratio of the unclean area to the area of ​​the target endoscopic image;

[0046] If the area ratio is less than the preset ratio, the cleanliness category of the target endoscopic image is determined to be clean, and the stomach part / intestinal part monitoring model is used to identify the part in the target endoscopic image to obtain the operation part.

[0047] Optionally, the waiting patient information includes a photographed image of the waiting patient in the preparation room, and judging whether an adverse event of the waiting patient occurs to the waiting patient based on the waiting patient information includes:

[0048] Recognize the face of the captured image and obtain the face area on the captured image;

[0049] Get the channel pixel value of each pixel point in the face area on each RGB channel;

[0050] Determine the standard deviation of the plurality of channel pixel values ​​as the channel pixel standard deviation;

[0051] The face color quantization representation value is determined based on multiple channel pixel values ​​and channel pixel standard deviations, wherein the face color quantization representation value The calculation formula is as follows,

[0052] ,

[0053] in, is the channel pixel value of the jth pixel on the i-th channel in the face area, and N represents the number of pixels in the face area;

[0054] If the quantitative representation value of the facial color is lower than a preset value, it is determined that a hypoglycemia event occurs in the waiting patient during the waiting period.

[0055] In the second aspect, the anesthesia auxiliary early warning method based on artificial intelligence provided by the present application includes:

[0056] Collect endoscopic operation information and current patient monitoring information of the target patient;

[0057] Determining anesthetic drug concentration adjustment information based on the endoscopic operation information and the current patient monitoring information, and issuing prompt information based on the anesthetic drug concentration adjustment information;

[0058] When an anesthetic drug concentration adjustment instruction input based on the prompt information is obtained, executing the anesthetic drug concentration adjustment instruction to adjust the anesthetic drug concentration in the target patient;

[0059] issuing warning information based on the endoscopic operation information and current patient monitoring information of the target patient;

[0060] integrating and displaying the information of the incoming terminal and the monitoring terminal;

[0061] The data generated daily by the anesthesia assistance early warning system are summarized and stored.

[0062] In a third aspect, the electronic device provided in the present application includes a memory and a processor, wherein the memory stores a computer program, and the processor is used to run the computer program in the memory to implement the steps in the artificial intelligence-based anesthesia auxiliary warning method provided in the present application.

[0063] In a fourth aspect, the computer-readable storage medium provided in the present application stores a plurality of instructions, which are suitable for loading by a processor to implement the steps in the artificial intelligence-based anesthesia auxiliary warning method provided in the present application.

[0064] In a fifth aspect, the computer program product provided in the present application includes a computer program or instructions, which, when executed by a processor, implement the steps in the artificial intelligence-based anesthesia assistance warning method provided in the present application.

[0065] In this application, compared with the related art, the anesthesia auxiliary warning system based on artificial intelligence is characterized by including: a data acquisition terminal for collecting endoscopic operation information and current patient monitoring information of the target patient; a drug concentration calculation terminal for determining anesthetic drug concentration adjustment information based on the endoscopic operation information and the current patient monitoring information, and issuing prompt information based on the anesthetic drug concentration adjustment information; an input terminal for executing the anesthetic drug concentration adjustment instruction to adjust the anesthetic drug concentration in the target patient when the anesthetic drug concentration adjustment instruction input based on the prompt information is obtained; a monitoring terminal for issuing warning information based on the endoscopic operation information and the current patient monitoring information of the target patient; a monitoring terminal for integrating and displaying the information of the input terminal and the monitoring terminal; and a summary terminal for summarizing and storing the data generated daily by the anesthesia auxiliary warning system. This application can improve the accuracy of anesthesia auxiliary warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0067] Figure 1 This is a schematic diagram of a scenario of an anesthesia auxiliary early warning system based on artificial intelligence provided in an embodiment of the present application;

[0068] Figure 2 It is a schematic diagram of concentration adjustment strategies corresponding to various working modes in an embodiment of an anesthesia auxiliary warning system based on artificial intelligence provided by an embodiment of the present application;

[0069] Figure 3 It is a schematic diagram of various types of information entering a monitoring terminal in an embodiment of an anesthesia auxiliary early warning system based on artificial intelligence provided by an embodiment of the present application;

[0070] Figure 4 It is a flowchart of an embodiment of an anesthesia auxiliary early warning method based on artificial intelligence provided in an embodiment of the present application;

[0071] Figure 5 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0072] It should be noted that the principles of the present application are illustrated by implementing them in an appropriate computing environment. The following description is based on the illustrated specific embodiments of the present application and should not be considered as limiting other specific embodiments of the present application that are not described in detail herein.

[0073] In the following description of the present application, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it can be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0074] In the following description of the present application, the terms "first\second\third" involved are merely used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that "first\second\third" can be interchanged with a specific order or sequence where permitted, so that the embodiments of the present application described here can be implemented in an order other than that illustrated or described here.

[0075] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0076] In order to improve the effect of anesthesia assisted warning based on artificial intelligence, the embodiments of the present application provide an anesthesia assisted warning method based on artificial intelligence and an anesthesia assisted warning system based on artificial intelligence.

[0077] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0078] Please refer to Figure 1 , the present application also provides an anesthesia auxiliary early warning system based on artificial intelligence, such as Figure 1 As shown, the artificial intelligence-based anesthesia auxiliary warning system includes a data acquisition terminal 110, a drug concentration calculation terminal 120, an input terminal 130, a monitoring terminal 140, a monitoring terminal 150 and a summary terminal 160.

[0079] A data collection terminal 110 is used to collect endoscope operation information and current patient monitoring information of a target patient;

[0080] The drug concentration calculation terminal 120 is used to determine the anesthetic drug concentration adjustment information based on the endoscope operation information and the current patient monitoring information, and to issue a prompt information based on the anesthetic drug concentration adjustment information;

[0081] The input terminal 130 is used to execute the anesthetic concentration adjustment instruction to adjust the anesthetic concentration in the target patient when the anesthetic concentration adjustment instruction based on the prompt information input is obtained;

[0082] A monitoring terminal 140, for issuing warning information based on the endoscope operation information and the current patient monitoring information of the target patient;

[0083] The monitoring terminal 150 is used to integrate and display the information of the incoming terminal 130 and the monitoring terminal 140;

[0084] The summary terminal 160 is used to summarize and store the data generated daily by the anesthesia auxiliary early warning system.

[0085] The artificial intelligence-based anesthesia auxiliary early warning system is connected to the outpatient medical record system and the outpatient imaging management system respectively, which facilitates interaction with the outpatient medical record system and the outpatient imaging management system to obtain corresponding data.

[0086] In addition, the artificial intelligence-based anesthesia auxiliary warning system may also include a memory for storing raw data, intermediate data, and result data.

[0087] In the embodiment of the present application, the memory may be a cloud memory. Cloud storage is a new concept extended and developed from the concept of cloud computing. A distributed cloud storage system (hereinafter referred to as the storage system) refers to a storage system that uses cluster applications, grid technology, and distributed storage file systems to bring together a large number of storage devices of various types (storage devices are also called storage nodes) in the network through application software or application interfaces to work together and provide external data storage and business access functions.

[0088] At present, the storage method of the storage system is: create a logical volume, and when creating a logical volume, allocate physical storage space for each logical volume, and the physical storage space may be composed of disks of a storage device or several storage devices. The client stores data on a logical volume, that is, stores the data on the file system. The file system divides the data into many parts, each of which is an object. The object contains not only data but also additional information such as data identification (ID, ID entity). The file system writes each object into the physical storage space of the logical volume, and the file system records the storage location information of each object, so that when the client requests to access the data, the file system can allow the client to access the data according to the storage location information of each object.

[0089] The process of the storage system allocating physical storage space to a logical volume is as follows: based on the estimated capacity of the objects stored in the logical volume (this estimate often has a large margin relative to the actual capacity of the objects to be stored) and the grouping of independent redundant disk arrays (RAID, Redundant Array of Independent Disks), the physical storage space is divided into stripes in advance. A logical volume can be understood as a stripe, thereby allocating physical storage space to the logical volume.

[0090] It should be noted that Figure 1 The scenario diagram of the artificial intelligence-based anesthesia auxiliary warning system shown is only an example. The artificial intelligence-based anesthesia auxiliary warning system and scenario described in the embodiment of the present application are intended to more clearly illustrate the technical solution of the embodiment of the present application, and do not constitute a limitation on the technical solution provided in the embodiment of the present application. Ordinary technicians in this field can know that with the evolution of the artificial intelligence-based anesthesia auxiliary warning system and the emergence of new business scenarios, the technical solution provided in the embodiment of the present application is also applicable to similar technical problems.

[0091] It should be noted that the serial numbers of the following embodiments are not intended to limit the preferred order of the embodiments.

[0092] In the embodiment of the present application, the data collection terminal 110 is used to collect endoscope operation information and current patient monitoring information of the target patient, wherein the endoscope operation information includes the operation site and operation time, and the current patient monitoring information includes the body movement information and vital sign information of the target patient.

[0093] The operation site can be 26 sites marked by gastroscopy, such as esophagus, dentate line, gastric antrum, etc., or can be the ascending colon, hepatic flexure, transverse colon, splenic flexure, descending colon, sigmoid colon and rectum, ileocecal valve, appendix opening, etc. marked by colonoscopy. The operation time is obtained by statistics of the inspection timing model. The body movement information of the target patient is whether the target patient is moving. The vital signs information of the target patient includes blood pressure, heart rate, blood oxygen saturation and respiratory rate.

[0094] Specifically, a monitoring model under gastroscopy was constructed: the examination timing model, the average time of gastroscopy is about 4-5 minutes, and abnormal extension of time requires the attention of the anesthesiologist, who may need to add anesthetic drugs or pay attention to whether the patient has sedation-related adverse events; gastric site / intestinal site monitoring model; gastric mucosal cleanliness assessment model, gastroscopy requires flushing to expose a clear image of the examination site, and there may be a risk of reflux and aspiration, so the anesthesiologist needs to be reminded to pay attention; instrument intervention model, during gastrointestinal endoscopic diagnosis and treatment, a biopsy may be taken based on the patient's complaints and observations. The stimulation during the biopsy is greater than that of the examination, and the operation time may be prolonged, so the anesthesiologist needs to be reminded to pay attention to drug addition and maintenance of anesthesia depth.

[0095] Construct a monitoring model for colonoscopy: a timing model for insertion and withdrawal of the endoscope, which predicts the timing and dosage of additional anesthetic drugs based on the insertion time and the examination site; an ileocecal recognition model, which identifies the ileocecal region and reminds the anesthesiologist when starting to withdraw the endoscope that it may be necessary to stop or reduce the anesthesia maintenance medication; an intestinal cleanliness model, which means that if the intestinal cleanliness is very poor, the examination may need to be terminated, and the anesthesiologist needs to be reminded to stop the anesthesia maintenance medication in time or not to add any more anesthetic drugs.

[0096] In an embodiment of the present application, the data acquisition terminal 110 is used to obtain a stomach / intestinal part monitoring model and an inspection timing model. The stomach / intestinal part monitoring model is used to monitor the operation part in the endoscopic operation information, and the inspection timing model is used to detect the endoscopic inspection duration.

[0097] Specifically, the endoscope operation information and the current patient monitoring information of the target patient are collected, including:

[0098] (1) Obtain a target endoscopic image captured by a target endoscope.

[0099] In the embodiment of the present application, the target endoscope will be recorded by the doctor or automatically photographed during the endoscopic examination to obtain a target endoscopic image.

[0100] (2) Use the stomach / intestinal monitoring model to determine whether the target endoscopic image contains stomach / intestinal features.

[0101] Specifically, a dirty area segmentation model is trained, and the Unet++ network model is preferably selected. The trained dirty area segmentation model is loaded, and a mask map of multiple dirty areas is segmented from the target endoscopic image.

[0102] (3) If the target endoscopic image contains stomach / intestinal features, multiple unclean areas on the target endoscopic image are identified.

[0103] (4) Eliminate unclean areas whose areas are smaller than a preset area from among the multiple unclean areas, and calculate the unclean area areas of the multiple unclean areas after the elimination.

[0104] In the embodiment of the present application, the area of ​​each unclean area is calculated respectively. The area Si0 of each unclean area in the target endoscopic image j0 is obtained. For example, the preset area is 4. When the noise is filtered out, the sum of the unclean area areas of the multiple unclean areas after elimination is calculated as the unclean area area. .

[0105] ,

[0106] Wherein, Kj0 represents the number of unclean areas remaining after the noise is removed from the target endoscopic image j0.

[0107] (5) Calculate the ratio of the unclean area to the area of ​​the target endoscopic image.

[0108] Then calculate the ratio of the unclean area of ​​the target endoscopic image j0 to the area of ​​the target endoscopic image j0 .

[0109] ,

[0110] in , are the width and height of the target endoscopic image j0, respectively.

[0111] (6) If the area ratio is less than the preset ratio, the cleanliness category of the target endoscopic image is determined to be clean, and the stomach part / intestinal part monitoring model is used to identify the part in the target endoscopic image to obtain the operation part.

[0112] Among them, if the area ratio is less than the preset ratio, the cleanliness category of the target endoscopic image is determined to be clean; if the area ratio is not less than the preset ratio, the cleanliness category of the target endoscopic image is determined to be unclean.

[0113] The preset proportion may be 10%, etc., and may be set according to specific circumstances. If the area proportion is less than the preset proportion, the cleanliness category of the target endoscopic image is determined to be clean; if the area proportion is not less than the preset proportion, the cleanliness category of the target endoscopic image is determined to be unclean.

[0114] In the embodiment of the present application, the drug concentration calculation terminal 120 is used to determine the anesthetic drug concentration adjustment information based on the endoscopic operation information and the current patient monitoring information, and to issue a prompt message based on the anesthetic drug concentration adjustment information.

[0115] Specifically, the prompt information is used to prompt anesthesia personnel to perform processing.

[0116] like Figure 2 As shown, in an embodiment of the present application, the drug concentration calculation terminal 120 is used to obtain the current working mode of the anesthesia auxiliary warning system, and the current working mode of the anesthesia auxiliary warning system is any one of the gastroscopy mode, the colonoscopy mode or the gastrointestinal combined mode. The current concentration adjustment strategy is determined based on the current working mode of the anesthesia auxiliary warning system, and the anesthetic drug concentration adjustment information is determined based on the current concentration adjustment strategy, the endoscopic operation information and the current patient monitoring information.

[0117] In the embodiment of the present application, the concentration adjustment strategy corresponding to the gastroscopic mode is: during gastroscopic examination, the initial target concentration of propofol is 2.5ug / ml, and the anesthetic drug concentration is adjusted to 2.5-4ug / ml when the scope is inserted in the gastroscopic mode; if the inspection of more than a preset number of sites in the gastroscopic mode is completed, and the target patient has no body movement, the scope is withdrawn and the anesthetic drug is discontinued; if the inspection is continued, the anesthetic drug concentration is maintained at 1.6-2.5ug / ml; if the target patient is detected to have body movement in the gastroscopic mode, 30-50mg of anesthetic drug is added on the basis of the original anesthetic drug concentration until the target patient has no body movement; if a endoscopic biopsy event is detected in the gastroscopic mode, 30-50mg of anesthetic drug is added on the basis of the original anesthetic drug concentration; if the gastroscopic operation time is abnormally prolonged in the gastroscopic mode, a second prompt message is issued to remind the anesthesiologist to pay attention to vital signs and the total amount of anesthetic drugs, and adjust the anesthetic drug infusion mode. The concentration adjustment strategy corresponding to the colonoscopy mode is as follows: the initial target concentration of propofol is 2.5ug / ml. If the concentration of the anesthetic drug is adjusted to 2.5-4ug / ml when the endoscope is inserted in the colonoscopy mode; if the target patient is detected to have body movement in the colonoscopy mode, 30-50mg of anesthetic drug is added on the basis of the original anesthetic drug concentration until the target patient has no body movement; if a colonoscopy biopsy event is detected in the colonoscopy mode, 30-50mg of anesthetic drug is added on the basis of the original anesthetic drug concentration; if the ileocecal part is detected in the colonoscopy mode, the anesthetic drug is discontinued if the endoscope is directly withdrawn; if the endoscope is withdrawn for examination, the concentration of the anesthetic drug is adjusted to 1.6-2ug / ml; if the colonoscopy operation time is abnormally prolonged in the colonoscopy mode, a second prompt message is issued to remind the anesthesiologist to pay attention to vital signs and the total amount of anesthetic drugs, and to adjust the anesthetic drug infusion mode. The concentration adjustment strategy corresponding to the gastroscopy combined with colonoscopy mode is as follows: the initial target concentration of propofol is 2.5ug / ml. If the concentration of the anesthetic drug is adjusted to 2.5-4ug / ml when the endoscope is inserted in the gastroscopy combined with colonoscopy mode; if the target patient is detected to have body movement in the gastroscopy combined with colonoscopy mode, 30-50mg of anesthetic drug is added on the basis of the original anesthetic drug concentration until the target patient has no body movement; if a gastrointestinal endoscopic biopsy event is detected in the gastroscopy combined with colonoscopy mode, 30-50mg of anesthetic drug is added on the basis of the original anesthetic drug concentration; if the ileocecal region is detected in the gastroscopy combined with colonoscopy mode, the anesthetic drug is discontinued if the endoscope is directly withdrawn; if the endoscope is continued to be withdrawn for examination, the concentration of the anesthetic drug is adjusted to 1.6-2ug / ml; if the gastrointestinal endoscopic operation time is abnormally prolonged in the gastroscopy combined with colonoscopy mode, a second prompt message is issued to remind the anesthesiologist to pay attention to vital signs and the total amount of anesthetic drugs, and to adjust the anesthetic drug infusion mode.

[0118] Among them, propofol is used as an example of an anesthetic drug. If other drugs are used, the target concentration of the anesthetic drug and the TCI model need to be adjusted accordingly.

[0119] Specifically, the drug concentration calculation terminal 120 includes a controller and a human-computer interaction module. The input end of the controller is set with gastrointestinal endoscope operation steps, propofol input concentration monitoring and patient body movement monitoring. The initial concentration of propofol is 2.5ug / ml, and the target concentration of propofol is adjusted in combination with gastrointestinal endoscope operation, body movement and patient vital signs.

[0120] like Figure 2 As shown, if in the gastroscopy mode, the gastroscopy marks 26 parts such as the esophagus, dentate line, and gastric antrum for simultaneous inspection and timing, the initial target concentration of propofol is 2.5ug / ml, and if the concentration of the anesthetic drug is adjusted to 2.5-4ug / ml when the endoscope is inserted in the gastroscopy mode; when the gastrointestinal endoscope is inspected for more than half of the inspection parts and the patient has no body movement, if it is necessary to continue the inspection, the target concentration is maintained at 1.6-2.5ug / ml, and propofol is discontinued if the endoscope is withdrawn directly. If the patient moves during the gastroscopy, a single additional dose of propofol of 30-50mg is added on the basis of the original propofol target control until the patient has no body movement; a single additional dose of propofol of 30-50mg is added when a biopsy is taken during the inspection; in special circumstances, such as: the gastroscopy operation time is abnormally prolonged, the anesthesiologist needs to be reminded to pay attention to the patient's vital signs and the total amount of propofol at all times, and the propofol infusion mode needs to be adjusted. Or if the patient is assessed to have gastric retention or pyloric obstruction during gastroscopy, the medication should be stopped immediately and the endoscopist should be instructed to aspirate the remaining food, resuscitate the patient, and prevent and treat reflux aspiration.

[0121] If in the colonoscopy mode, the colonoscope marks the ascending colon, hepatic flexure, transverse colon, splenic flexure, descending colon, sigmoid colon and rectum, ileocecal valve, appendix opening, etc. When the colonoscope is inserted for examination, the target concentration of propofol is adjusted to maintain between 2.5-4.5ug / ml. If the patient moves during the colonoscopy, a single additional dose of propofol of 30-50mg is added on the basis of the original propofol target control until the patient has no body movement and can cooperate with the examination; during the examination, a single additional dose of propofol of 30-50mg is added when taking a biopsy. When the scope is withdrawn directly at the ileocecal region, propofol is discontinued; when the ileocecal region is reached and a careful examination is required, the blood concentration of propofol is adjusted to 1.6-2ug / ml.

[0122] If in the gastrointestinal combined mode, adjust the target concentration of propofol (maintained between 2.5-4.5ug / ml), add a single dose of propofol 30-50mg when there is body movement or biopsy during the examination, and adjust the target concentration of propofol according to the colonoscopy standard after reaching the ileocecal region. The above adjustments are combined with vasoactive drugs to make the patient's vital signs change by ±20% compared with the baseline value. The target concentration of propofol is 1.6ug / ml as the patient's awake limit (remind the anesthesiologist that if the operation is still in progress, additional anesthetic drugs need to be given in time), and 1.2ug / ml as the patient's recovery limit (the patient can be transferred to the recovery room for observation).

[0123] In the embodiment of the present application, the input terminal 130 is used to execute the anesthetic concentration adjustment instruction to adjust the anesthetic concentration in the target patient when the anesthetic concentration adjustment instruction based on the prompt information input is obtained.

[0124] like Figure 3 As shown, in the embodiment of the present application, the monitoring terminal 140 is used to issue early warning information based on the endoscopic operation information and the current patient monitoring information of the target patient.

[0125] The monitoring terminal 140 includes a monitor 146 , a first warning module 141 , a second warning module 142 , a third warning module 143 , a fourth warning module 144 and a fifth warning module 145 .

[0126] The monitor 146 is used to monitor and display the target patient's information, the waiting patient information of the waiting patient in the waiting state, and the anesthesia awakening patient information of the anesthesia awakening patient in the anesthesia awakening state.

[0127] The first warning module 141 is used to determine whether an adverse event occurs to the waiting patient based on the waiting patient information, and to issue a first warning message when an adverse event occurs to the waiting patient, wherein the adverse event to the waiting patient includes at least one of a hypoglycemia event during the waiting period, a hypovolemia event during the waiting period, and a fainting event during the waiting period.

[0128] The second warning module 142 is used to determine whether a gastroscopic adverse event occurs in the target patient based on the endoscopic operation information and the current patient monitoring information of the target patient, and to issue a second warning message when a gastroscopic adverse event occurs in the target patient, wherein the gastroscopic adverse event includes at least one of an event of prolonged gastroscopic examination time, an event of shortened gastroscopic examination time, reflux, aspiration, choking, a gastroscopic biopsy event, and an event of premature termination of gastroscopy.

[0129] The third warning module 143 is used to determine whether a colonoscopy adverse event occurs in the target patient based on the endoscopic operation information and the current patient monitoring information of the target patient, and to issue a third warning message when a colonoscopy adverse event occurs in the target patient, wherein the colonoscopy adverse event includes at least one of a colonoscopy time extension event, a colonoscopy time shortening event, a colonoscopy biopsy event, an ileocecal arrival time, and a colonoscopy premature termination event.

[0130] The fourth warning module 144 is used to determine whether the target patient has an abnormal physical sign event based on the current patient monitoring information of the target patient, and to issue a fourth warning message when an abnormal physical sign event occurs in the target patient, wherein the abnormal physical sign event includes at least one of diastolic blood pressure exceeding 100 mmHg or falling below 40 mmHg, systolic blood pressure exceeding 180 mmHg or falling below 80 mmHg, heart rate falling below 50 beats / min or exceeding 120 beats / min, and blood oxygen saturation falling below 90%.

[0131] The fifth warning module 145 is used to determine whether an adverse anesthesia awakening event occurs in the anesthesia awakening patient based on the anesthesia awakening patient information, and to issue a fifth warning message when an adverse anesthesia awakening event occurs in the anesthesia awakening patient, wherein the adverse anesthesia awakening event includes at least one of a delayed awakening event, a nausea and vomiting event, a dizziness event, a fall event, and an abnormal vital sign event.

[0132] Specifically, the first warning information, the second warning information, the third warning information, the fourth warning information, and the fifth warning information can all be displayed as a red flashing LED light while sounding an alarm.

[0133] In a specific embodiment, the waiting patient information includes a photographed image of a waiting patient in a preparation room, and judging whether an adverse event of the waiting patient occurs to the waiting patient based on the waiting patient information includes:

[0134] (1) Recognize the face in the captured image and obtain the face area in the captured image.

[0135] (2) Obtain the channel pixel value of each pixel point in the face area on each RGB channel.

[0136] (3) The standard deviation of the pixel values ​​of multiple channels is determined as the channel pixel standard deviation.

[0137] (4) Determine the quantitative representation value of facial color based on multiple channel pixel values ​​and channel pixel standard deviations.

[0138] Specifically, the quantized representation value of face color The calculation formula is as follows,

[0139] ,

[0140] in, is the channel pixel value of the jth pixel on the i-th channel in the face area, and N represents the number of pixels in the face area.

[0141] (5) If the quantitative representation value of the facial color is lower than a preset value, it is determined that the waiting patient has experienced a hypoglycemia event during the waiting period.

[0142] In the embodiment of the present application, the monitoring terminal 150 is used to integrate and display the information of the incoming terminal 130 and the monitoring terminal 140. The monitoring terminal 150 includes a display and a tablet terminal, the display is used to display the information of the incoming terminal 130 and the monitoring terminal 140, and a preset application is installed on the tablet terminal, and the preset application is used to remotely display the information of the incoming terminal 130 and the monitoring terminal 140.

[0143] Specifically, the monitoring terminal 150 includes a large display and a tablet terminal, which integrates all images and data from the input terminal 130 and the monitoring terminal 140 into the display. At the same time, there will be an app software on the tablet terminal. In addition to all images on the display, all information can be viewed remotely on the tablet, and relevant monitoring and processing data and images can be recorded daily.

[0144] In the embodiment of the present application, the aggregation terminal 160 is used to aggregate and store the data generated daily by the anesthesia auxiliary warning system.

[0145] Specifically, the data summarized and stored by the summary terminal 160 include: the number of painless gastroscopy, the number of painless colonoscopy, the amount of anesthetic drugs used, the patient's awakening time, the time of discharge from the hospital, the total daily workload of gastroenteroscopy, the workload of each anesthesiologist, sedation-related adverse events, warning events, response time, and the frequency of anesthetic drug concentration adjustment.

[0146] Specifically, the summary terminal 160 summarizes the daily data of the previous steps, including the number of painless gastroscopy and colonoscopy, the amount of anesthetic drugs used, the patient's awakening time, discharge time, the total daily workload of gastrointestinal endoscopy and the workload of each anesthesiologist, sedation-related adverse events, warning events and response time, propofol target-controlled TCI adjustment frequency, etc. At the same time, it continuously tests and improves the artificial intelligence-assisted gastrointestinal endoscopy outpatient clinical anesthesia support, warning and quality control system in clinical work.

[0147] Furthermore, the monitoring terminal 140 obtains patient feedback information uploaded by the anesthesiologist and adjusts the concentration adjustment strategy based on the patient feedback information. The patient feedback information includes whether the patient wakes up early, whether there is body movement during the operation, whether there is reflux, aspiration, hypoxia, etc., whether the awakening is delayed, and whether there are postoperative adverse events such as nausea, vomiting, dizziness, and abdominal distension after the operation.

[0148] Further, the aggregation terminal 160 aggregates the daily data to obtain daily aggregated data, and trains a preset neural network model based on the daily aggregated data. The preset neural network model performs drug concentration adjustment and early warning based on the endoscopic operation information and the current patient monitoring information. When new aggregated data is generated daily, the preset neural network model is updated daily based on the new aggregated data.

[0149] See also Figure 4 The present application also provides an artificial intelligence-based anesthesia auxiliary early warning method, which includes:

[0150] 201. Collect endoscopic operation information and current patient monitoring information of the target patient.

[0151] Among them, the endoscopic operation information includes the operation site and operation time, and the current patient monitoring information includes the body movement information and vital signs information of the target patient.

[0152] 202. Determine anesthetic drug concentration adjustment information based on the endoscopic operation information and the current patient monitoring information, and issue prompt information based on the anesthetic drug concentration adjustment information.

[0153] 203. When an anesthetic drug concentration adjustment instruction input based on the prompt information is obtained, the anesthetic drug concentration adjustment instruction is executed to adjust the anesthetic drug concentration in the target patient.

[0154] 204. Issue a warning message based on the endoscopic operation information and the current patient monitoring information of the target patient.

[0155] 205. Integrate and display the information of the incoming terminal and the monitoring terminal.

[0156] In the embodiment of the present application, the monitoring terminal 150 is used to integrate and display the information of the incoming terminal 130 and the monitoring terminal 140. The monitoring terminal 150 includes a display 151 and a tablet terminal 152, the display is used to display the information of the incoming terminal 130 and the monitoring terminal 140, and a preset application is installed on the tablet terminal, and the preset application is used to remotely display the information of the incoming terminal 130 and the monitoring terminal 140.

[0157] Specifically, the monitoring terminal 150 includes a large display and a tablet terminal, which integrates all images and data from the input terminal 130 and the monitoring terminal 140 into the display. At the same time, there will be an app software on the tablet terminal. In addition to all images on the display, all information can be viewed remotely on the tablet, and relevant monitoring and processing data and images can be recorded daily.

[0158] 206. Summarize and store the data generated daily by the anesthesia assistance early warning system.

[0159] In the embodiment of the present application, the aggregation terminal 160 is used to aggregate and store the data generated daily by the anesthesia auxiliary warning system.

[0160] Specifically, the data summarized and stored by the summary terminal 160 include: the number of painless gastroscopy, the number of painless colonoscopy, the amount of anesthetic drugs used, the patient's awakening time, the time of discharge from the hospital, the total daily workload of gastroenteroscopy, the workload of each anesthesiologist, sedation-related adverse events, warning events, response time, and the frequency of anesthetic drug concentration adjustment.

[0161] In this application, compared with the related art, the anesthesia auxiliary early warning system based on artificial intelligence includes: a data acquisition terminal for collecting endoscopic operation information and current patient monitoring information of the target patient; a drug concentration calculation terminal for determining anesthetic drug concentration adjustment information based on the endoscopic operation information and the current patient monitoring information, and issuing prompt information based on the anesthetic drug concentration adjustment information; an input terminal for executing the anesthetic drug concentration adjustment instruction to adjust the anesthetic drug concentration in the target patient when the anesthetic drug concentration adjustment instruction based on the prompt information input is obtained; a monitoring terminal for issuing early warning information based on the endoscopic operation information and the current patient monitoring information of the target patient; a monitoring terminal for integrating and displaying the information of the input terminal and the monitoring terminal; and a summary terminal for summarizing and storing the data generated daily by the anesthesia auxiliary early warning system. This application can improve the accuracy of anesthesia auxiliary early warning.

[0162] The present invention integrates endoscopic image analysis, TCI target control, real-time dynamic monitoring and related early warning, which can enable managers to understand the operating status of the entire clinic in one interface, and integrate relevant data for continuous improvement, which has very important clinical significance and good application prospects. Based on the above clinical needs, the present invention forms a clinical anesthesia support and early warning and quality control system for gastroenteroscopy clinics assisted by artificial intelligence, which aims to safely transmit the patient's monitoring intervention data through the input terminal, monitoring terminal and monitoring terminal, accurately evaluate the patient's surgical progress, understand the working status and duty status of the anesthesiologist, provide timely and accurate clinical anesthesia support, warn of anesthesia risks, provide anesthesia risk emergency plans, improve the quality and efficiency of the digestive clinic operation and shorten the response time of emergency events.

[0163] Please refer to Figure 5 , Figure 5 The electronic device provided in the embodiment of the present application is a schematic diagram of the structure of the electronic device. The electronic device can be any one of the above data acquisition terminal, drug concentration calculation terminal, transmission terminal, monitoring terminal and monitoring terminal.

[0164] The electronic device may include components such as a processor 101 with one or more processing cores, a memory 102 with one or more computer-readable storage media, a power supply 103, and an input unit 104. Those skilled in the art will appreciate that the electronic device structure shown in the figure does not constitute a limitation on the electronic device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently. Among them:

[0165] The processor 101 is the control center of the electronic device, which uses various interfaces and lines to connect various parts of the entire electronic device, and executes various functions of the electronic device and processes data by running or executing software programs and / or modules stored in the memory 102, and calling data stored in the memory 102. Optionally, the processor 101 may include one or more processing cores; optionally, the processor 101 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user interface, and application programs, and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 101.

[0166] The memory 102 can be used to store software programs and modules. The processor 101 executes various functional applications and data processing by running the software programs and modules stored in the memory 102. The memory 102 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 102 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 102 may also include a memory controller to provide the processor 101 with access to the memory 102.

[0167] The electronic device also includes a power supply 103 for supplying power to each component. Optionally, the power supply 103 can be logically connected to the processor 101 through a power management system, so as to manage charging, discharging, and power consumption through the power management system. The power supply 103 can also include one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0168] The electronic device may further include an input unit 104, which may be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0169] Although not shown, the electronic device may also include a display unit, an image acquisition component, etc., which will not be described in detail here. Specifically in this embodiment, the processor 101 in the electronic device will load the executable code corresponding to one or more computer programs into the memory 102 according to the following instructions, and the processor 101 will execute the steps in the artificial intelligence-based anesthesia auxiliary warning method provided in this application, such as:

[0170] Collect endoscopic operation information and current patient monitoring information of the target patient;

[0171] Determine anesthetic drug concentration adjustment information based on endoscopic operation information and current patient monitoring information, and issue prompt information based on the anesthetic drug concentration adjustment information;

[0172] When an anesthetic drug concentration adjustment instruction based on the prompt information input is obtained, the anesthetic drug concentration adjustment instruction is executed to adjust the anesthetic drug concentration in the target patient;

[0173] Issue early warning information based on endoscopic operation information and current patient monitoring information of the target patient;

[0174] Integrate and display information from incoming and monitored terminals;

[0175] The data generated daily by the anesthesia assistance early warning system is summarized and stored.

[0176] It should be noted that the electronic device provided in the embodiment of the present application belongs to the same concept as the artificial intelligence-based anesthesia auxiliary warning method in the above embodiment. Its specific implementation process is detailed in the above related embodiments and will not be repeated here.

[0177] The present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program stored therein is executed on the processor of the electronic device provided in the embodiment of the present application, the processor of the electronic device executes the steps in the artificial intelligence-based anesthesia auxiliary early warning method provided in the present application. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0178] The present application also provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes various optional implementations of the above-mentioned artificial intelligence-based anesthesia auxiliary warning method.

[0179] The above is a detailed introduction to an artificial intelligence-based anesthesia auxiliary warning method and system provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

[0180] It should be noted that when the above embodiments of the present application are applied to specific products or technologies, the relevant data of the user is involved, and the user's permission or consent is required, and the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions.

Claims

1. An artificial intelligence-based anesthesia auxiliary early warning system, It is characterized in that include: A data acquisition terminal is used to collect endoscope operation information and current patient monitoring information of a target patient, wherein the endoscope operation information includes an operation site and an operation time, and the current patient monitoring information includes body movement information and vital sign information of the target patient, wherein the data acquisition terminal is used to obtain a stomach / intestinal site monitoring model and an inspection timing model, wherein the stomach / intestinal site monitoring model is used to monitor the operation site in the endoscope operation information, and the inspection timing model is used to detect the endoscope inspection time; obtain a target endoscope image taken by a target endoscope; and use the stomach / intestinal site monitoring model to determine whether the target endoscopic image contains stomach / intestinal features; if the target endoscopic image contains stomach / intestinal features, identify multiple unclean areas on the target endoscopic image; remove unclean areas whose areas are smaller than a preset area from the multiple unclean areas, and calculate the areas of the unclean areas after removal; calculate the ratio of the area of ​​the unclean areas to the area of ​​the target endoscopic image; if the area ratio is smaller than the preset ratio, determine that the cleanliness category of the target endoscopic image is clean, and use the stomach / intestinal monitoring model to identify the part in the target endoscopic image to obtain the operation part; A drug concentration calculation terminal is used to determine anesthetic drug concentration adjustment information based on the endoscopic operation information and the current patient monitoring information, and to issue a prompt message based on the anesthetic drug concentration adjustment information. The drug concentration calculation terminal is used to obtain the current working mode of the anesthesia auxiliary warning system, and the current working mode of the anesthesia auxiliary warning system is any one of the gastroscopy mode, the colonoscopy mode or the gastrointestinal combined mode. The current concentration adjustment strategy is determined based on the current working mode of the anesthesia auxiliary warning system, and the anesthetic drug concentration adjustment information is determined based on the current concentration adjustment strategy, the endoscopic operation information and the current patient monitoring information, wherein the concentration adjustment strategy corresponding to the gastroscopy mode is: in gastroscopy, the initial target concentration of propofol is 2.5ug / ml. If in the gastroscopy mode The concentration of anesthetic drugs is adjusted to 2.5-4ug / ml when the endoscope is inserted; if the examination of more than a preset number of sites is completed in the gastroscopy mode, and the target patient has no body movement, the endoscope is withdrawn and the anesthetic drugs are stopped; if the examination is continued, the concentration of anesthetic drugs is maintained at 1.6-2.5ug / ml; if the target patient is detected to have body movement in the gastroscopy mode, 30-50mg of anesthetic drugs are added on the basis of the original anesthetic drug concentration until the target patient has no body movement; if a gastroscopy biopsy event is detected in the gastroscopy mode, 30-50mg of anesthetic drugs are added on the basis of the original anesthetic drug concentration; if the gastroscopy operation time is abnormally prolonged in the gastroscopy mode, a second prompt message is issued to remind the anesthesiologist to pay attention to vital signs and the total amount of anesthetic drugs, and adjust the anesthetic drug infusion mode; The concentration adjustment strategy corresponding to the colonoscopy mode is as follows: the initial target concentration of propofol is 2.5ug / ml, and if the concentration of the anesthetic drug is adjusted to 2.5-4ug / ml when the endoscope is inserted in the colonoscopy mode; if the target patient is detected to have body movement in the colonoscopy mode, 30-50mg of anesthetic drug is added on the basis of the original anesthetic drug concentration until the target patient has no body movement; if a colonoscopy biopsy event is detected in the colonoscopy mode, 30-50mg of anesthetic drug is added on the basis of the original anesthetic drug concentration; if the ileocecal part is detected in the colonoscopy mode, the anesthetic drug is discontinued if the endoscope is directly withdrawn; if the endoscope is withdrawn for examination, the concentration of the anesthetic drug is adjusted to 1.6-2ug / ml; if the colonoscopy operation time is abnormally prolonged in the colonoscopy mode, a second prompt message is issued to remind the anesthesiologist to pay attention to vital signs and the total amount of anesthetic drugs, and adjust the anesthetic drug infusion mode; The concentration adjustment strategy corresponding to the gastrointestinal combined mode is as follows: the initial target concentration of propofol is 2.5ug / ml. If the concentration of the anesthetic drug is adjusted to 2.5-4ug / ml when the endoscope is inserted in the gastrointestinal combined mode; if the target patient is detected to have body movement in the gastrointestinal combined mode, 30-50mg of anesthetic drug is added on the basis of the original anesthetic drug concentration until the target patient has no body movement; if a gastrointestinal endoscopic biopsy event is detected in the gastrointestinal combined mode, 30-50mg of anesthetic drug is added on the basis of the original anesthetic drug concentration; if the ileocecal region is detected in the gastrointestinal combined mode, the anesthetic drug is discontinued if the endoscope is directly withdrawn; if the endoscope is withdrawn for examination, the concentration of the anesthetic drug is adjusted to 1.6-2ug / ml; if the gastrointestinal endoscopic operation time is abnormally prolonged in the gastrointestinal combined mode, a second prompt message is issued to remind the anesthesiologist to pay attention to vital signs and the total amount of anesthetic drugs, and to adjust the anesthetic drug infusion mode; an input terminal, for executing the anesthetic drug concentration adjustment instruction to adjust the anesthetic drug concentration in the target patient when the anesthetic drug concentration adjustment instruction based on the prompt information input is obtained; A monitoring terminal is used to issue warning information based on the endoscopic operation information and the current patient monitoring information of the target patient, and the monitoring terminal includes a monitor, a first warning module, a second warning module, a third warning module, a fourth warning module and a fifth warning module. The monitor is used to monitor and display the information of the target patient, the waiting patient information in the waiting state, and the patient awakening information in the anesthesia awakening state; the first warning module is used to determine whether the patient has an adverse event during the waiting period based on the waiting patient information, and issue a first warning message when the waiting patient has an adverse event during the waiting period, wherein the adverse event during the waiting period includes at least one of a hypoglycemia event during the waiting period, a hypovolemia event during the waiting period, and a fainting event during the waiting period; the second warning module is used to determine whether the target patient has an adverse gastroscopy event based on the endoscopic operation information and the current patient monitoring information of the target patient, and issue a second warning message when the target patient has an adverse gastroscopy event, wherein the adverse gastroscopy event includes at least one of an event of prolonged gastroscopy examination time, an event of shortened gastroscopy examination time, reflux, aspiration, choking, gastroscopy biopsy event, and an event of premature end of gastroscopy; the third warning module is used to determine whether the target patient has an adverse gastroscopy event based on the endoscopic operation information and the current patient monitoring information of the target patient, and issue a second warning message when the target patient has an adverse gastroscopy event, wherein the adverse gastroscopy event includes at least one of an event of prolonged gastroscopy examination time, an event of shortened gastroscopy examination time, reflux, aspiration, choking, gastroscopy biopsy event, and an event of premature end of gastroscopy; The fourth warning module is used to judge whether the target patient has an abnormal physical sign event based on the current patient monitoring information of the target patient, and issue a fourth warning message when an abnormal physical sign event occurs to the target patient, wherein the abnormal physical sign event includes at least one of a blood pressure increase, a blood pressure drop, a blood pressure rise, a blood pressure rise, a blood pressure drop ... At least one of diastolic blood pressure exceeding 100 mmHg or being lower than 40 mmHg, systolic blood pressure exceeding 180 mmHg or being lower than 80 mmHg, heart rate lower than 50 beats / min or higher than 120 beats / min, and blood oxygen saturation lower than 90%; the fifth warning module is used to determine whether an adverse event of anesthesia awakening occurs to the anesthesia awakening patient based on the patient awakening information, and to issue the fifth warning information when an adverse event of anesthesia awakening occurs to the anesthesia awakening patient, wherein the adverse event of anesthesia awakening includes at least one of delayed awakening event, nausea and vomiting event, dizziness event, fall event, and abnormal vital sign event; The waiting patient information includes a photographed image of the waiting patient in the preparation room, and judging whether an adverse event occurs to the waiting patient during the waiting period based on the waiting patient information includes: Recognize the face of the captured image and obtain the face area on the captured image; Get the channel pixel value of each pixel point in the face area on each RGB channel; Determine the standard deviation of the plurality of channel pixel values ​​as the channel pixel standard deviation; The face color quantization representation value is determined based on multiple channel pixel values ​​and channel pixel standard deviations, wherein the face color quantization representation value The calculation formula is as follows, , in, is the channel pixel value of the jth pixel on the i-th channel in the face area, and N represents the number of pixels in the face area; If the quantitative representation value of the face color is lower than the preset value, it is determined that the waiting patient has a hypoglycemia event during the waiting period; A monitoring terminal, used for integrating and displaying the information of the incoming terminal and the monitoring terminal; The summary terminal is used to summarize and store the data generated daily by the anesthesia auxiliary early warning system, and train a preset neural network model based on the daily summary data. The preset neural network model adjusts the drug concentration and issues early warning based on the endoscopic operation information and the current patient monitoring information; when new summary data is generated daily, the preset neural network model is updated daily based on the new summary data.

2. The anesthesia assistance warning system according to claim 1, It is characterized in that The monitoring terminal includes a display and a tablet terminal, wherein the display is used to display, integrate and display the information of the incoming terminal and the monitoring terminal, and a preset application is installed on the tablet terminal, and the preset application is used to remotely display the information of the incoming terminal and the monitoring terminal.

3. The anesthesia assistance warning system according to claim 2, It is characterized in that The data summarized and stored in the summary terminal include: the number of painless gastroscopy, the number of painless colonoscopy, the amount of anesthetic drugs used, the patient's awakening time, the time of discharge from the hospital, the total daily workload of gastroenteroscopy, the workload of each anesthesiologist, sedation-related adverse events, warning events, response time, and the frequency of anesthetic drug concentration adjustment.

4. The anesthesia assistance warning system according to claim 3, It is characterized in that The second early warning module is used to obtain an instrument intervention model, and the instrument intervention model is used to determine whether a gastroscopic / colonoscopy biopsy event occurs.

5. An artificial intelligence-based anesthesia auxiliary early warning method, It is characterized in that The artificial intelligence-based anesthesia auxiliary early warning method comprises: Collect endoscopic operation information and current patient monitoring information of the target patient, the endoscopic operation information includes the operation site and operation time, and the current patient monitoring information includes the body movement information and vital sign information of the target patient, wherein a stomach / intestinal site monitoring model and an inspection timing model are obtained, the stomach / intestinal site monitoring model is used to monitor the operation site in the endoscopic operation information, and the inspection timing model is used to detect the endoscopic inspection time; obtain a target endoscopic image taken by a target endoscope; use the stomach / intestinal site monitoring model to determine whether the target endoscopic image contains stomach / intestinal site features; if the target endoscopic image contains stomach / intestinal site features, identify multiple unclean areas on the target endoscopic image; remove unclean areas whose areas are smaller than a preset area from the multiple unclean areas, and calculate the unclean area areas of the multiple unclean areas after removal; calculate the ratio of the unclean area area to the area of ​​the target endoscopic image; if the area ratio is smaller than the preset ratio, determine that the cleanliness category of the target endoscopic image is clean, and use the stomach / intestinal site monitoring model to identify the site in the target endoscopic image to obtain the operation site; Anesthetic drug concentration adjustment information is determined based on the endoscopic operation information and the current patient monitoring information, and prompt information is issued based on the anesthetic drug concentration adjustment information to obtain the current working mode of the anesthesia auxiliary early warning system, wherein the current working mode of the anesthesia auxiliary early warning system is any one of the gastroscopy mode, the colonoscopy mode or the gastrointestinal combined mode, and the current concentration adjustment strategy is determined based on the current working mode of the anesthesia auxiliary early warning system, and the anesthetic drug concentration adjustment information is determined based on the current concentration adjustment strategy, the endoscopic operation information and the current patient monitoring information, wherein the concentration adjustment strategy corresponding to the gastroscopy mode is: in gastroscopy, the initial target concentration of propofol is 2.5ug / ml, if the anesthetic drug concentration is adjusted when the endoscope is inserted in the gastroscopy mode The concentration of the anesthetic drug is 2.5-4ug / ml; if the examination of more than the preset number of parts is completed in the gastroscopic mode, and the target patient has no body movement, the scope is withdrawn and the anesthetic drug is stopped; if the examination is continued, the concentration of the anesthetic drug is maintained at 1.6-2.5ug / ml; if the target patient is detected to have body movement in the gastroscopic mode, 30-50mg of anesthetic drug is added on the basis of the original anesthetic drug concentration until the target patient has no body movement; if a gastroscopic biopsy event is detected in the gastroscopic mode, 30-50mg of anesthetic drug is added on the basis of the original anesthetic drug concentration; if the gastroscopic operation time is abnormally prolonged in the gastroscopic mode, a second prompt message is issued to remind the anesthesiologist to pay attention to vital signs and the total amount of anesthetic drugs, and adjust the anesthetic drug infusion mode; The concentration adjustment strategy corresponding to the colonoscopy mode is as follows: the initial target concentration of propofol is 2.5ug / ml, and if the concentration of the anesthetic drug is adjusted to 2.5-4ug / ml when the endoscope is inserted in the colonoscopy mode; if the target patient is detected to have body movement in the colonoscopy mode, 30-50mg of anesthetic drug is added on the basis of the original anesthetic drug concentration until the target patient has no body movement; if a colonoscopy biopsy event is detected in the colonoscopy mode, 30-50mg of anesthetic drug is added on the basis of the original anesthetic drug concentration; if the ileocecal part is detected in the colonoscopy mode, the anesthetic drug is discontinued if the endoscope is directly withdrawn; if the endoscope is withdrawn for examination, the concentration of the anesthetic drug is adjusted to 1.6-2ug / ml; if the colonoscopy operation time is abnormally prolonged in the colonoscopy mode, a second prompt message is issued to remind the anesthesiologist to pay attention to vital signs and the total amount of anesthetic drugs, and adjust the anesthetic drug infusion mode; The concentration adjustment strategy corresponding to the gastrointestinal combined mode is as follows: the initial target concentration of propofol is 2.5ug / ml. If the concentration of the anesthetic drug is adjusted to 2.5-4ug / ml when the endoscope is inserted in the gastrointestinal combined mode; if the target patient is detected to have body movement in the gastrointestinal combined mode, 30-50mg of anesthetic drug is added on the basis of the original anesthetic drug concentration until the target patient has no body movement; if a gastrointestinal endoscopic biopsy event is detected in the gastrointestinal combined mode, 30-50mg of anesthetic drug is added on the basis of the original anesthetic drug concentration; if the ileocecal region is detected in the gastrointestinal combined mode, the anesthetic drug is discontinued if the endoscope is directly withdrawn; if the endoscope is withdrawn for examination, the concentration of the anesthetic drug is adjusted to 1.6-2ug / ml; if the gastrointestinal endoscopic operation time is abnormally prolonged in the gastrointestinal combined mode, a second prompt message is issued to remind the anesthesiologist to pay attention to vital signs and the total amount of anesthetic drugs, and to adjust the anesthetic drug infusion mode; When an anesthetic drug concentration adjustment instruction input based on the prompt information is obtained, executing the anesthetic drug concentration adjustment instruction to adjust the anesthetic drug concentration in the target patient; The monitoring terminal includes a monitor, a first warning module, a second warning module, a third warning module, a fourth warning module and a fifth warning module. The monitor is used to monitor and display the information of the target patient, the waiting patient information in the waiting state, and the patient awakening information in the anesthesia awakening state; the first warning module is used to determine whether the patient has an adverse event during the waiting period based on the waiting patient information, and issue a first warning message when the waiting patient has an adverse event during the waiting period, wherein the adverse event during the waiting period includes at least one of a hypoglycemia event during the waiting period, a hypovolemia event during the waiting period, and a fainting event during the waiting period; the second warning module is used to determine whether the target patient has an adverse gastroscopy event based on the endoscopic operation information and the current patient monitoring information of the target patient, and issue a second warning message when the target patient has an adverse gastroscopy event, wherein the adverse gastroscopy event includes at least one of an event of prolonged gastroscopy examination time, an event of shortened gastroscopy examination time, reflux, aspiration, choking, gastroscopy biopsy event, and an event of premature end of gastroscopy; the third warning module is used to determine whether the target patient has an adverse event during the waiting period based on the endoscopic operation information and the current patient monitoring information of the target patient, and issue a second warning message when the target patient has an adverse gastroscopy event, wherein the adverse gastroscopy event includes at least one of an event of prolonged gastroscopy examination time, an event of shortened gastroscopy examination time, reflux, aspiration, choking, gastroscopy biopsy event, and an event of premature end of gastroscopy; The fourth warning module is used to determine whether the target patient has an abnormal physical sign event based on the current patient monitoring information of the target patient, and issue a fourth warning message when the target patient has an abnormal physical sign event, wherein the abnormal physical sign event includes at least one of a diastolic blood pressure event, a diastolic blood pressure event, a diastolic blood pressure event, and a diastolic blood pressure event. at least one of a blood pressure exceeding 100 mmHg or being lower than 40 mmHg, a systolic blood pressure exceeding 180 mmHg or being lower than 80 mmHg, a heart rate lower than 50 beats / min or higher than 120 beats / min, and a blood oxygen saturation lower than 90%; the fifth warning module is used to judge whether an adverse event of anesthesia awakening occurs in an anesthesia awakening patient based on the patient awakening information, and to issue a fifth warning message when an adverse event of anesthesia awakening occurs in the anesthesia awakening patient, wherein the adverse event of anesthesia awakening includes at least one of a delayed awakening event, a nausea and vomiting event, a dizziness event, a fall event, and an abnormal vital sign event; The waiting patient information includes a photographed image of the waiting patient in the preparation room, and judging whether an adverse event occurs to the waiting patient during the waiting period based on the waiting patient information includes: Recognize the face of the captured image and obtain the face area on the captured image; Get the channel pixel value of each pixel point in the face area on each RGB channel; Determine the standard deviation of the plurality of channel pixel values ​​as the channel pixel standard deviation; The face color quantization representation value is determined based on multiple channel pixel values ​​and channel pixel standard deviations, wherein the face color quantization representation value The calculation formula is as follows, , in, is the channel pixel value of the jth pixel on the i-th channel in the face area, and N represents the number of pixels in the face area; If the quantitative representation value of the face color is lower than the preset value, it is determined that the waiting patient has a hypoglycemia event during the waiting period; Integrate and display the information of the monitoring terminal; The data generated daily by the anesthesia auxiliary early warning system is summarized and stored, and a preset neural network model is trained based on the daily summarized data. The preset neural network model adjusts drug concentration and issues early warning based on endoscopic operation information and current patient monitoring information. When new summarized data is generated daily, the preset neural network model is updated daily based on the new summarized data.