Intelligent nursing method and system for anesthesia resuscitation based on artificial intelligence

Abstract

The invention provides an anesthesia resuscitation intelligent nursing method and system based on artificial intelligence, and the method comprises the steps: a data collection module comprises various sensors and monitoring equipment, and is used for collecting various physiological data and activity data of a patient; the data processing module receives various data from the data acquisition module and preprocesses the data; the decision-making auxiliary module receives a judgment result transmitted by the data processing module; the communication module realizes data interaction and communication between the system and a hospital information management system, an electronic medical record system and other medical information systems, relates to the technical field of medical monitoring, and solves the problems of insufficient medical care manpower, untimely monitoring, inaccurate room leaving judgment and the like in the existing anesthesia resuscitation monitoring. Comprehensive, real-time and intelligent monitoring of the anesthetic resuscitation patient is achieved through the artificial intelligence technology, the monitoring efficiency and accuracy are improved, the risk of the patient in the anesthetic resuscitation period is reduced, and the safety of the patient is guaranteed.

Description

Technical Field

[0001] This invention relates to the field of medical monitoring technology, and in particular to an intelligent nursing method and system for anesthesia resuscitation based on artificial intelligence. Background Technology

[0002] In modern medical systems, the anesthesia resuscitation process is crucial. It requires frequent monitoring of patients and rapid response to any abnormalities. However, the current situation presents a significant challenge: a shortage of medical staff coupled with a surge in the number of patients.

[0003] During the recovery period from anesthesia, patients are prone to respiratory amnesia, which means weakened or stopped spontaneous breathing. This can lead to hypoxemia or even respiratory failure, seriously threatening the patient's life and health. At the same time, patients are often confused during the recovery period, making them highly susceptible to accidents such as falling out of bed.

[0004] Currently, traditional monitoring methods mainly rely on manual observation by medical staff. However, due to limited time and energy, it is difficult for medical staff to provide real-time and comprehensive monitoring of patients, often failing to detect abnormalities and intervene effectively in a timely manner. Furthermore, the criteria for patients leaving the room after anesthesia recovery need to comprehensively consider factors such as electrocardiogram data, vital signs, and postoperative observation records. However, in clinical practice, due to differences in the experience of medical staff, the judgment of patient exit criteria is often inconsistent, which greatly increases the risk of complications after the patient leaves the room.

[0005] Traditional monitoring equipment also has significant limitations, with limited functionality and high reliance on manual intervention. For example, identifying conditions such as airway obstruction, dislodgement, and respiratory amnesia requires comprehensive analysis of multiple parameters, including respiration and blood oxygenation. Traditional equipment struggles to achieve automatic correlation and judgment, thus failing to meet the actual needs of anesthesia resuscitation monitoring. Summary of the Invention

[0006] To overcome existing problems, this application provides an intelligent anesthesia resuscitation monitoring method and system based on artificial intelligence. This system addresses issues such as insufficient medical staff, untimely monitoring, and inaccurate exit judgment in existing anesthesia resuscitation monitoring. By using artificial intelligence technology, it achieves comprehensive, real-time, and intelligent monitoring of anesthesia resuscitation patients, improving monitoring efficiency and accuracy, reducing patient risks during anesthesia resuscitation, and ensuring patient safety.

[0007] The technical solution adopted by the embodiments of this application to solve its technical problem is:

[0008] The AI-based intelligent nursing method and system for anesthesia resuscitation includes: a data acquisition module, a data processing module, a decision support module, and a communication module.

[0009] The data acquisition module includes various sensors and monitoring devices for collecting multiple physiological and activity data of the patient. The data acquisition module starts automatically, and the physiological sensors and body motion sensing devices collect data at a preset frequency. After encryption, the data is transmitted to the data processing module in real time via the network.

[0010] The data processing module receives various types of data from the data acquisition module, preprocesses the data to remove noise and abnormal data, and improves data quality. After receiving the data, the preprocessing unit first performs noise reduction, cleaning and normalization operations, and then inputs the data into the deep learning model. The model uses a combination of convolutional neural network and recurrent neural network architecture to extract features and dynamically analyze time series data, and outputs risk assessment results.

[0011] The decision support module receives the judgment results transmitted by the data processing module and presents the patient's physiological status, abnormal situation warning information, and room exit possibility assessment report to medical staff in an intuitive interface and manner. The decision support module includes an audible and visual alarm device. When an abnormal situation is detected in the patient, the audible and visual alarm device is triggered to issue an alarm signal. After receiving the risk assessment results, the decision support module displays the patient monitoring data and warning information on the medical staff workstation interface. When an emergency such as respiratory amnesia occurs, the system immediately triggers an audible and visual alarm and pushes a warning notification to the mobile terminal of the on-duty medical staff, while recording the event time, type, and handling process.

[0012] The communication module enables data interaction and communication between the system and the hospital information management system, electronic medical record system, and other medical information systems. Based on the patient's continuous monitoring data, the system generates a visual assessment report. After medical staff confirm that the patient has left the room, the communication module synchronizes all monitoring data during the resuscitation period to the hospital's electronic medical record system to complete data archiving and traceability.

[0013] The data acquisition module includes a physiological data acquisition sensor unit and an activity data sensing unit;

[0014] The physiological data acquisition sensor unit includes a blood oxygen saturation sensor, an airway pressure sensor, an end-tidal carbon dioxide sensor, a blood pressure monitor, and an electrocardiograph, which are responsible for acquiring blood oxygen saturation, airway pressure, end-tidal carbon dioxide waveform, blood pressure changes, and electrocardiogram vital signs data.

[0015] The activity data sensing unit includes a sensor installed on the patient's chest to monitor chest rise and fall, and sensing devices installed around the bed and on key parts of the patient's body to monitor the amplitude of body movement, thereby enabling real-time monitoring of the patient's respiratory status and physical activity.

[0016] The data processing module includes a preprocessing unit and an artificial intelligence model unit;

[0017] The preprocessing unit is used to perform data cleaning, filtering and normalization operations on the collected data, remove noise from the signal, eliminate abnormal data points through data cleaning algorithms, and normalize the data to make it within a suitable numerical range.

[0018] The artificial intelligence model unit contains a multi-layered neural network structure. Through learning from a large amount of training data, it can automatically extract data features and establish the correlation between various parameters. Based on the analysis results, it can judge the patient's physiological state and activity status and transmit the judgment results to the decision support module.

[0019] Includes the following steps:

[0020] Step 1, Pre-extubation assessment: When a patient under general anesthesia is extubated in the recovery room, the system collects the patient's monitoring data and inputs the collected data into an artificial intelligence model built based on deep learning algorithms. The real-time collected data is compared and analyzed with the training data, and the analysis results are presented to medical staff in a timely and visual manner. The abnormal situations judged by the artificial intelligence model include extubation, airway obstruction, recovery of spontaneous breathing, and cardiovascular abnormalities.

[0021] Step 2, Post-extubation respiratory amnesia monitoring: The system monitors chest rise and fall in real time through the sensing unit. The system uses a preset algorithm to process and analyze the data to determine the patient's respiratory status. When the system detects that the patient's spontaneous breathing has weakened or stopped, it issues an alert signal through the decision support module.

[0022] Step 3, Fall Risk Monitoring: The sensing unit transmits the collected body movement data to the system, which analyzes the patient's body movement based on preset body movement amplitude thresholds and movement pattern judgment rules.

[0023] Step 4: Assisted Judgment of Exit Criteria: The artificial intelligence system continuously collects the patient's vital signs data and the patient's activity data obtained through the sensing unit. The system compares and analyzes these data with the pre-set exit criteria, assesses whether the patient meets the exit requirements from multiple dimensions, and generates an exit probability assessment report.

[0024] Preferably, the exit probability assessment report is generated using the following formula:

[0025]

[0026] in, Score the likelihood of leaving the room. To assess the number of indicators, For the first The weight of each evaluation indicator, For the first The actual values ​​of each evaluation indicator.

[0027] Preferably, the evaluation indicators include heart rate, blood pressure, respiratory rate, blood oxygen saturation, and body movement amplitude, and their weighting calculation formula is as follows:

[0028]

[0029] in, For the first The weight of each evaluation indicator, For the first The standard deviation of each evaluation indicator The number of evaluation indicators involved in the weighting calculation.

[0030] Preferably, the bed fall risk monitoring and judgment is achieved through the following formula:

[0031] =

[0032] in, This represents the risk value for falling out of bed. For body acceleration, The duration of the body movement. For body motion velocity, This is a risk assessment function trained based on historical bed fall data.

[0033] The advantages of the embodiments of this application are:

[0034] By automatically analyzing various physiological and activity data of patients using artificial intelligence technology, it is possible to quickly and accurately identify various abnormalities that occur in patients during anesthesia recovery, such as dislodgement, airway obstruction, respiratory amnesia, and cardiovascular abnormalities. This overcomes the problems of limited energy and easy omission of abnormalities in traditional manual monitoring, greatly improving the efficiency and accuracy of monitoring and buying time for timely treatment of patients.

[0035] By using a sensing unit to monitor the patient's respiratory status and physical activity in real time, timely warnings can be issued for risks such as respiratory amnesia and falls from the bed. This effectively reduces the serious consequences caused by respiratory problems and accidents during anesthesia recovery and ensures the patient's safety.

[0036] The AI-based exit criteria-assisted judgment function comprehensively analyzes patients' vital signs and activity data and compares them with scientifically established exit criteria. This reduces inconsistencies in exit judgments caused by differences in the experience of medical staff, making exit decisions more objective and accurate, and lowering the risk of complications after patients leave the room. Attached Figure Description

[0037] Figure 1 This is a schematic diagram of the intelligent anesthesia resuscitation care method based on artificial intelligence according to the present invention;

[0038] Figure 2 This is a schematic diagram of the process of the AI-based intelligent anesthesia resuscitation care system of the present invention. Detailed Implementation

[0039] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention. In addition, for the sake of convenience, the terms "upper," "lower," "left," and "right" are equivalent to the upper, lower, left, and right directions of the accompanying drawings themselves, and the terms "first," "second," etc., are used for descriptive purposes and have no other special meaning.

[0040] This application provides an AI-based intelligent anesthesia resuscitation monitoring method and system, addressing existing technical problems. By automatically analyzing various physiological and activity data of patients using AI technology, it can quickly and accurately identify various abnormalities during anesthesia resuscitation, such as dislodgement, airway obstruction, respiratory abnormalities, and cardiovascular abnormalities. This overcomes the limitations of traditional manual monitoring, which is prone to overlooking abnormalities, significantly improving monitoring efficiency and accuracy and saving valuable time for timely treatment. The system utilizes sensing units to monitor patients' respiratory status and physical activity in real time, providing timely warnings of risks such as respiratory amnesia and falls from bed, effectively reducing serious consequences caused by respiratory problems and accidents during anesthesia resuscitation and ensuring patient safety. Furthermore, the AI-based exit criteria assistance function comprehensively analyzes patients' vital signs and activity data and compares them with scientifically established exit criteria, reducing inconsistencies in exit judgments due to differences in medical staff experience. This makes exit decisions more objective and accurate, reducing the risk of post-exit complications.

[0041] The technical solution in this application is to solve the above problems, and the overall approach is as follows:

[0042] Example 1

[0043] This embodiment presents an intelligent nursing method for anesthesia resuscitation based on artificial intelligence, such as... Figure 1 As shown, it includes the following steps:

[0044] Step 1: Pre-extubation assessment: When a patient under general anesthesia is extubated in the recovery room, the system collects the patient's monitoring data and inputs the collected data into an artificial intelligence model built based on deep learning algorithms. The real-time collected data is compared and analyzed with the training data, and the analysis results are presented to medical staff in a timely and visual manner. Abnormal situations identified by the artificial intelligence model include extubation, airway obstruction, recovery of spontaneous breathing, and cardiovascular abnormalities.

[0045] Step 2, Post-extubation respiratory amnesia monitoring: The system monitors chest rise and fall in real time through the sensing unit. The system uses a preset algorithm to process and analyze the data to determine the patient's respiratory status. When the system detects that the patient's spontaneous breathing has weakened or stopped, it issues an alert signal through the decision support module.

[0046] The formula for calculating chest wall rise and fall is as follows:

[0047] Let the thoracic displacement signal collected by the sensing unit be... The difference between the maximum and minimum displacement per unit time is the fluctuation range. :

[0048]

[0049] The larger the chest, the more pronounced the chest rise and fall, reflecting the intensity of breathing.

[0050] Respiratory rate calculation:

[0051] For time window The number of fluctuation cycles within the respiratory rate was counted. for:

[0052] *60

[0053] for The number of complete fluctuation cycles within the inner period, such as =10 seconds, =2, then =12 times / minute.

[0054] Rules for judging respiratory status:

[0055] Preset normal breathing amplitude threshold and frequency threshold An error is considered to be an anomaly when the following conditions are met:

[0056] The amplitude remains below the threshold: < And duration > ,

[0057] Frequency deviates from normal range: < .

[0058] Data processing: The displacement signals of the thoracic cavity movement are acquired in real time through sensing units (such as pressure sensors and infrared monitoring) and converted into quantifiable values. .

[0059] Feature extraction: through amplitude and frequency Two core indicators reflect the "intensity" and "rhythm" of breathing.

[0060] Anomaly detection: When the amplitude is too small or the frequency is abnormal, combine it with the duration threshold. A comprehensive assessment is made to determine if there is a risk of respiratory amnesia, and medical staff are promptly alerted.

[0061] Step 3, Fall Risk Monitoring: The sensing unit transmits the collected body movement data to the system, which analyzes the patient's body movement based on preset body movement amplitude thresholds and movement pattern judgment rules.

[0062] Step 4: Assisted Judgment of Exit Criteria: The artificial intelligence system continuously collects the patient's vital signs data and the patient's activity data obtained through the sensing unit. The system compares and analyzes these data with the pre-set exit criteria, assesses whether the patient meets the exit requirements from multiple dimensions, and generates an exit probability assessment report.

[0063] The possibility of leaving the room assessment report is generated using the following formula:

[0064]

[0065] in, Score the likelihood of leaving the room. To assess the number of indicators, For the first The weight of each evaluation indicator, For the first The actual values ​​of each evaluation indicator.

[0066] The assessment indicators include heart rate, blood pressure, respiratory rate, blood oxygen saturation, and amplitude of body movement. The weighting formula is as follows:

[0067]

[0068] in, For the first The weight of each evaluation indicator, For the first The standard deviation of each evaluation indicator The number of evaluation indicators involved in the weighting calculation.

[0069] The risk assessment for bed falls is achieved using the following formula:

[0070] =

[0071] in, This represents the risk value for falling out of bed. For body acceleration, The duration of the body movement. For body motion velocity, This is a risk assessment function trained based on historical bed fall data.

[0072] By adopting the above technical solution:

[0073] Before extubation, the data acquisition module collects the patient's blood oxygen saturation, airway pressure, end-tidal carbon dioxide waveform, blood pressure, and electrocardiogram data, and transmits them to the data processing module. The preprocessing unit filters and denoises the data to remove interference signals caused by slight patient movement. Then, the data is input into the artificial intelligence model unit. The decision support module immediately displays the specific abnormal parameters on the medical workstation to help medical staff adjust the extubation plan.

[0074] After the patient completes the extubation procedure, the chest wall rise and fall sensor continuously monitors the patient's respiratory movements. When the patient enters a light sleep state, the preset algorithm in the data processing module identifies abnormal breathing status. The decision support module triggers the audible and visual alarm device, which emits a continuous beeping sound and flashing light. At the same time, it sends a warning text message to the handheld terminal of the nurse in charge of the patient, reminding the nurse to perform timely respiratory support intervention.

[0075] During resuscitation, the patient suddenly exhibited significant limb movement due to confusion. The body motion sensor at the edge of the bed detected that the patient's center of gravity had shifted 30% outside the safe area of ​​the bed, and the body motion acceleration reached 2 m / s². Based on the preset bed fall risk assessment rules, the system calculated that the bed fall risk value had reached the high-risk threshold. The decision support module immediately activated the bedside alarm and marked the patient's abnormal situation in the hospital nursing management system. Nearby medical staff quickly arrived, moved the patient back to a safe position, and took restraint measures.

[0076] Thirty minutes after resuscitation, the system continuously collects vital signs data such as heart rate, blood pressure, respiratory rate, and blood oxygen saturation, as well as activity data such as body movement amplitude obtained through the activity data sensing unit. The decision support module generates a leave-from-room probability assessment report, indicating to medical staff that the patient meets the leave-from-room criteria. After confirmation by the doctor, the patient is safely transferred to a general ward.

[0077] Example 2

[0078] This embodiment presents an intelligent anesthesia resuscitation monitoring system based on artificial intelligence, such as... Figure 2 As shown, it includes: a data acquisition module, a data processing module, a decision support module, and a communication module;

[0079] The data acquisition module includes various sensors and monitoring devices for collecting a variety of physiological and activity data from patients. The data acquisition module starts automatically, and the physiological sensors and body motion sensors collect data at a preset frequency. After encryption, the data is transmitted to the data processing module in real time via the network.

[0080] The data processing module receives various types of data from the data acquisition module, preprocesses the data to remove noise and abnormal data, and improves data quality. After receiving the data, the preprocessing unit first performs noise reduction, cleaning and normalization operations, and then inputs the data into the deep learning model. The model uses a combination of convolutional neural network and recurrent neural network architecture to extract features and dynamically analyze time series data, and outputs risk assessment results.

[0081] The decision support module receives the judgment results transmitted by the data processing module and presents the patient's physiological status, abnormal situation warning information, and room exit possibility assessment report to medical staff in an intuitive interface and manner. The decision support module includes an audible and visual alarm device. When an abnormal situation is detected in the patient, the audible and visual alarm device is triggered to issue an alarm signal. After receiving the risk assessment results, the decision support module displays the patient monitoring data and warning information on the medical staff workstation interface. When an emergency such as respiratory amnesia occurs, the system immediately triggers an audible and visual alarm and pushes a warning notification to the mobile terminal of the on-duty medical staff, while recording the event time, type, and handling process.

[0082] The communication module enables data interaction and communication between the system and the hospital information management system, electronic medical record system, and other medical information systems. Based on the patient's continuous monitoring data, the system generates a visual assessment report. After medical staff confirm that the patient has left the room, the communication module synchronizes all monitoring data during the resuscitation period to the hospital's electronic medical record system to complete data archiving and traceability.

[0083] The data acquisition module includes a physiological data acquisition sensor unit and an activity data sensing unit;

[0084] The physiological data acquisition sensor unit includes a blood oxygen saturation sensor, an airway pressure sensor, an end-tidal carbon dioxide sensor, a blood pressure monitor, and an electrocardiograph, which are responsible for collecting blood oxygen saturation, airway pressure, end-tidal carbon dioxide waveform, blood pressure changes, and electrocardiogram vital signs data.

[0085] The activity data sensing unit includes a sensor installed on the patient's chest to monitor chest rise and fall, and sensing devices installed around the bed and on key parts of the patient's body to monitor the amplitude of body movement, enabling real-time monitoring of the patient's respiratory status and physical activity.

[0086] The data processing module includes a preprocessing unit and an artificial intelligence model unit;

[0087] The preprocessing unit is used to perform data cleaning, filtering and normalization operations on the collected data, remove noise from the signal, remove abnormal data points through data cleaning algorithms, and normalize the data to make it within a suitable numerical range.

[0088] The artificial intelligence model unit contains a multi-layered neural network structure. Through learning from a large amount of training data, it can automatically extract data features and establish the correlation between various parameters. Based on the analysis results, it can judge the patient's physiological state and activity status and transmit the judgment results to the decision support module.

[0089] By adopting the above technical solution:

[0090] Physiological data acquisition sensor units, such as blood oxygen saturation sensors, airway pressure sensors, and end-tidal carbon dioxide sensors, are correctly attached or connected to corresponding locations on the patient's fingers, airway inlets, etc.; motion data sensing units for monitoring chest wall movement are fixed on the patient's chest; and body movement amplitude sensors are installed at the edge of the bed and on key locations such as the patient's wrists and ankles. Through the hospital's internal network, the data acquisition module is networked with the data processing module, decision support module, and communication module, and interfaces with the hospital's information management system and electronic medical record system to ensure that the patient's preoperative information can be retrieved smoothly and that postoperative monitoring data can be uploaded and archived in real time.

[0091] The data acquisition module collects physiological and activity data from each patient in parallel and transmits it to the data processing module. The artificial intelligence model unit of the data processing module quickly identifies abnormal conditions in each patient. The decision support module distinguishes alarms by different colors and numbers. The decision support module receives the judgment results transmitted by the data processing module and presents the patient's physiological status, abnormal condition warning information, and room exit probability assessment report to medical staff in an intuitive interface and manner. The decision support module includes an audible and visual alarm device. When an abnormal condition of a patient is detected, the audible and visual alarm device is triggered to issue an alarm signal. After receiving the risk assessment results, the decision support module displays the patient monitoring data and warning information on the medical staff workstation interface. When an emergency such as respiratory amnesia occurs, the system immediately triggers an audible and visual alarm and pushes a warning notification to the mobile terminal of the on-duty medical staff. At the same time, it records the event time, type, and handling process. Medical staff handle the alarms according to their priority. During this process, the communication module uploads the abnormal events and handling processes of each patient to the hospital information management system in real time, which facilitates subsequent medical record analysis and medical quality improvement.

[0092] Finally, it should be noted that the above embodiments are merely examples for clearly illustrating the present invention and are not intended to limit the implementation. Those skilled in the art will recognize that other variations or modifications can be made based on the above description. It is neither necessary nor possible to exhaustively list all possible implementations. However, obvious variations or modifications derived therefrom are still within the scope of protection of this invention.

Claims

1. An intelligent anesthesia resuscitation monitoring system based on artificial intelligence, characterized in that, include: Data acquisition module, data processing module, decision support module, and communication module; The data acquisition module includes various sensors and monitoring devices for collecting a variety of physiological and activity data from patients. The data processing module receives various types of data from the data acquisition module, preprocesses the data to remove noise and abnormal data, and improves data quality. The decision support module receives the judgment results transmitted by the data processing module and presents the patient's physiological status, abnormal situation warning information, and room exit possibility assessment report to medical staff in an intuitive interface and manner. The communication module enables data interaction and communication between the system and the hospital information management system, electronic medical record system, and other medical information systems.

2. The intelligent anesthesia resuscitation monitoring system based on artificial intelligence according to claim 1, characterized in that, The data acquisition module includes a physiological data acquisition sensor unit and an activity data sensing unit; The physiological data acquisition sensor unit includes a blood oxygen saturation sensor, an airway pressure sensor, an end-tidal carbon dioxide sensor, a blood pressure monitor, and an electrocardiograph. The activity data sensing unit includes a sensor installed on the patient's chest to monitor chest rise and fall, and sensing devices installed around the bed and on key parts of the patient's body to monitor the amplitude of body movement.

3. The intelligent anesthesia resuscitation monitoring system based on artificial intelligence according to claim 1, characterized in that, The data processing module includes a preprocessing unit and an artificial intelligence model unit; The preprocessing unit is used to perform data cleaning, filtering, and normalization operations on the collected data. The artificial intelligence model unit contains a multi-layered neural network structure. Through learning from a large amount of training data, it can automatically extract data features and establish the correlation between various parameters.

4. The intelligent anesthesia resuscitation monitoring system based on artificial intelligence according to claim 1, characterized in that, The decision support module includes an audible and visual warning device, which is triggered to issue a warning signal when an abnormal condition of the patient is detected.

5. An AI-based intelligent anesthesia resuscitation care method based on the system described in any one of claims 1-4, characterized in that, Includes the following steps: Step 1, Pre-extubation assessment: When a patient under general anesthesia is extubated in the recovery room, the system collects the patient's monitoring data, inputs the collected data into an artificial intelligence model built based on deep learning algorithms, compares and analyzes the real-time collected data with the training data, and promptly presents the analysis results to medical staff in a visual manner. Step 2, Post-extubation respiratory amnesia monitoring: The system monitors chest rise and fall in real time through a sensing unit, and uses a preset algorithm to process and analyze the data to determine the patient's respiratory status. Step 3, Fall Risk Monitoring: The sensing unit transmits the collected body movement data to the system, which analyzes the patient's body movement based on preset body movement amplitude thresholds and movement pattern judgment rules. Step 4: Assisted Judgment of Exit Criteria: The artificial intelligence system continuously collects the patient's vital signs data and the patient's activity data obtained through the sensing unit. The system compares and analyzes these data with the pre-set exit criteria, assesses whether the patient meets the exit requirements from multiple dimensions, and generates an exit probability assessment report.

6. The intelligent anesthesia resuscitation monitoring method based on artificial intelligence according to claim 5, characterized in that, In the pre-extubation assessment step of step one, the abnormal situations identified by the artificial intelligence model include tube dislodgement, airway obstruction, recovery of spontaneous breathing, and cardiovascular abnormalities.

7. The intelligent anesthesia resuscitation monitoring method based on artificial intelligence according to claim 5, characterized in that, In the second step of extubation respiratory amnesia monitoring, when the patient's spontaneous breathing is detected to be weakened or stopped, an alarm signal is issued through the decision support module.

8. The intelligent anesthesia resuscitation monitoring method based on artificial intelligence according to claim 5, characterized in that, The exit probability assessment report is generated using the following formula: in, Score the likelihood of leaving the room. To assess the number of indicators, For the first The weight of each evaluation indicator, For the first The actual values ​​of each evaluation indicator.

9. The intelligent anesthesia resuscitation monitoring method based on artificial intelligence according to claim 8, characterized in that, The assessment indicators include heart rate, blood pressure, respiratory rate, blood oxygen saturation, and body movement amplitude, and their weighting formulas are as follows: in, For the first The weight of each evaluation indicator, For the first The standard deviation of each evaluation indicator The number of evaluation indicators involved in the weighting calculation.

10. The intelligent anesthesia resuscitation monitoring method based on artificial intelligence according to claim 5, characterized in that, The risk assessment for bed falls is achieved using the following formula: = in, This represents the risk value for falling out of bed. For body acceleration, The duration of the body movement. For body motion velocity, This is a risk assessment function trained based on historical bed fall data.

Images