EICU patient body constraint decision support method and system

Abstract

The invention discloses an EICU patient body constraint decision support method and system, and relates to the technical field of digital health, and the method comprises the steps: collecting the basic information of a patient, continuously monitoring the real-time vital sign data and behavior pattern of the patient, analyzing the emotional state and potential demand of the patient through an artificial intelligence algorithm, and recognizing the current situation of the patient; generating a personalized intervention strategy in combination with individual differences and current situations of the patients; predicting future behavior trends and potential risks of the patient based on the historical data and the current situation; dynamically adjusting an execution plan and a body constraint threshold value of an intervention strategy according to a prediction result; patient feedback information is continuously collected, and the model and the intervention strategy are optimized. The personalized intervention strategy is generated in combination with the individual difference of the patient and the current situation, the future behavior trend and potential risk of the patient are predicted based on the historical data and the current situation, the most suitable nursing measures are provided for the specific situation of each patient, and the nursing safety and effectiveness are improved.

Description

Technical Field

[0001] The present invention relates to the field of digital health technology, and in particular to a method and system for supporting physical restraint decision making for EICU patients. Background Art

[0002] In the field of critical care medicine, physical restraint management of patients is a critical and complex task. Traditional physical restraint strategies often rely on the subjective judgment and routine protocols of medical staff, which in turn affects the safety and recovery process of patients. In recent years, with the rapid development of digital health technology and artificial intelligence, intelligent decision-making support systems have begun to emerge, providing new perspectives and solutions for critical care. However, existing technologies still have limitations in the following key aspects, which urgently need to be broken through.

[0003] First, traditional physical restraint decisions often lack a deep understanding of the patient's emotional state and potential needs, resulting in a disconnect between intervention measures and the patient's real needs. Second, current decision support systems are inadequate in dealing with individual differences and lack the ability to generate personalized intervention strategies. In addition, existing technologies have limited ability to predict patients' future behavioral trends and potential risks, limiting their utility in crisis management and early warning. Summary of the invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the present invention provides a method and system for supporting physical restraint decisions for EICU patients to solve the problem of improper physical restraint in the EICU environment due to lack of personalization and situational adaptability.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: In a first aspect, an embodiment of the present invention provides a method for supporting physical restraint decisions for EICU patients, which includes collecting basic information of the patient and continuously monitoring the patient's real-time vital sign data and behavior patterns, using an artificial intelligence algorithm to analyze the patient's emotional state and potential needs, and identifying the patient's current situation; Generate personalized intervention strategies based on individual patient differences and current situations; Predict patients’ future behavior trends and potential risks based on historical data and current situations; Dynamically adjust the execution plan and physical restraint threshold of the intervention strategy based on the prediction results; Continuously collect patient feedback to optimize models and intervention strategies.

[0007] As a preferred solution of the EICU patient physical restraint decision support method of the present invention, wherein: the patient basic information includes age, gender and medical history; The real-time vital sign data include heart rate, respiratory rate, body temperature and blood oxygen saturation.

[0008] As a preferred solution of the EICU patient physical restraint decision support method of the present invention, wherein: using an artificial intelligence algorithm to analyze the patient's emotional state and potential needs, identifying the patient's current situation includes the following steps: When the patient is admitted, basic information and current vital signs data are collected and recorded to create an electronic patient file; Continuously collect real-time vital sign data of patients, identify facial expressions and body postures, and use deep learning models to assess patients' emotional states and potential needs; The expression of the patient's emotional state index is: ; in, is the patient's emotional state index, Indicates the length of the time window of the data, represents the weight coefficient of the emotional state, represents the patient's emotional state function, The patient at the time point Heart rate, is the respiratory rate, is the blood oxygen saturation; The expression of the patient's potential demand index is: ; in, represents the potential demand index, represents the weight coefficient of potential demand, Indicates the patient's medical history, represents the potential demand function; Combine vital sign data with emotional state to identify situations that cause patient discomfort and agitation; Integrate real-time vital sign data and situational analysis results into a comprehensive situational report.

[0009] As a preferred solution of the EICU patient physical restraint decision support method of the present invention, wherein: combining individual differences of patients and current situations, generating a personalized intervention strategy includes the following steps: Based on the patient's emotional state index ESI and potential demand index NDI, combined with historical medical records, preference information and physical restraint experience, a feature vector is constructed; Build a machine learning model and use successful intervention cases and failure cases in historical data sets to train the machine learning model; Input the feature vector of the current situation into the trained model to obtain a personalized intervention strategy, which is expressed as: ; in, Indicates intervention strategy, represents the non-drug intervention strategy function, Represents historical medical data, Represents personalized parameters, Indicates experience of physical restraint, represents the drug intervention strategy function, represents the body restraint strategy function; The system dynamically adjusts intervention strategies based on the patient’s real-time vital signs data and situational changes; The system continuously monitors the patient's real-time vital signs and emotional state to evaluate the effectiveness of interventions.

[0010] As a preferred solution of the EICU patient physical restraint decision support method of the present invention, wherein: based on historical data and current situation, predicting the patient's future behavior trend and potential risks includes the following steps: A risk prediction function is introduced to quantify the risk of agitation and self-harm in patients in the future. The expression is: ; in, represents the risk predictor, Indicates the impact on physiological indicators, Indicates the impact on behavioral indicators, Represents the sigmoid function, which is used to map the difference between 0 and 1 to reflect the relative risk of deviation. Indicates at a point in time The emotional state index, Indicates at a point in time The potential demand index, and They represent the average emotional state index and average potential demand index during the entire observation period respectively.

[0011] As a preferred solution of the EICU patient physical restraint decision support method of the present invention, wherein: dynamically adjusting the execution plan of the intervention strategy and the physical restraint threshold according to the prediction results includes the following steps: Define a dynamic intervention adjustment function to dynamically adjust the execution plan of the intervention strategy according to the result of the risk prediction function. The expression is: ; in, represents the adjusted intervention strategy, Indicates balance implications for intervention strategies; Dynamically adjust the triggering threshold of physical restraints based on risk prediction; In high-risk situations, the system will lower the trigger threshold for physical restraints, making them more likely to be triggered to reduce potential injuries; In low-risk situations, the system will increase the trigger threshold for physical restraints and reduce unnecessary use of physical restraints to maintain the patient's comfort and dignity.

[0012] As a preferred solution of the EICU patient physical restraint decision support method of the present invention, wherein: continuously collecting patient feedback information, optimizing the model and intervention strategy includes the following steps: Use monitoring devices and technology to continuously track patients’ real-time vital signs, emotional states, and other key indicators; Record the patient's real-time vital signs over time to assess the effectiveness of interventions; Regularly assess the patient's emotional and psychological state through questionnaires, observations, and communication to understand their subjective feelings about nursing care; Combine physiological data and patient feedback to assess the overall impact of interventions on patient health status; Enter all collected feedback information into the system database in a timely manner, use statistical and machine learning methods to analyze feedback data, and identify patterns and trends in intervention effects; Set up an early warning system to automatically identify any changes in vital signs that deviate from the normal range and notify nursing staff in a timely manner.

[0013] In a second aspect, the present invention provides an EICU patient physical restraint decision support system, comprising: Data collection and analysis module: collects basic patient information and continuously monitors patients' real-time vital signs and behavior patterns, uses artificial intelligence algorithms to analyze patients' emotional states and potential needs, and identifies patients' current situations; Personalized intervention strategy generation module: Generates personalized intervention strategies based on individual patient differences and current situations; Predictive analysis and risk assessment module: predicts patients’ future behavior trends and potential risks based on historical data and current situations; Dynamic adjustment and execution planning module: dynamically adjust the execution plan and physical constraint threshold of the intervention strategy based on the prediction results; Feedback loop and model optimization module: continuously collect patient feedback information to optimize models and intervention strategies.

[0014] In a third aspect, an embodiment of the present invention provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program is executed by the processor, any step of the EICU patient physical restraint decision support method as described in the first aspect of the present invention is implemented.

[0015] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, any step of the EICU patient physical restraint decision support method as described in the first aspect of the present invention is implemented.

[0016] The beneficial effects of the present invention are as follows: by collecting basic information of patients and continuously monitoring real-time vital signs data and behavioral patterns, a comprehensive grasp of the health status of patients is achieved; artificial intelligence algorithms are used to analyze the emotional state and potential needs of patients, identify the current situation of patients, and achieve a new level of emotional intelligent nursing; personalized intervention strategies are generated based on individual differences of patients and current situations; future behavioral trends and potential risks of patients are predicted based on historical data and current situations; the two work together to form a forward-looking, customized nursing plan; the execution plan and physical restraint threshold of the intervention strategy are dynamically adjusted according to the prediction results; and patient feedback information is continuously collected to optimize the model and intervention strategy, thereby improving the accuracy and applicability of decision-making, reducing unnecessary physical restraints, and increasing the humanistic care of nursing. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0018] Figure 1 This is a flow chart of the EICU patient physical restraint decision support method in Example 1.

[0019] Figure 2 This is a module diagram of the EICU patient physical restraint decision support method in Example 1. DETAILED DESCRIPTION

[0020] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0021] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0022] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0023] Example 1, reference Figure 1 and Figure 2 , which is the first embodiment of the present invention, provides a method for supporting physical restraint decisions for EICU patients, comprising the following steps: S1, basic patient information includes age, gender and medical history; real-time vital signs data include heart rate, respiratory rate, body temperature and blood oxygen saturation.

[0024] Using artificial intelligence algorithms to analyze the patient's emotional state and potential needs, identifying the patient's current situation includes the following steps: When patients check in, basic information and current vital signs data are collected and recorded to create electronic patient files; real-time vital signs data of patients are continuously collected to identify facial expressions and body postures of patients, and deep learning models are used to assess patients’ emotional states and potential needs; The expression of the patient's emotional state index is: ; in, is the patient's emotional state index, Indicates the length of the time window of the data, The weight coefficient of the emotional state is used to reflect the importance of the data at that time point in the overall evaluation. represents the patient's emotional state function, The patient at the time point Heart rate, is the respiratory rate, is the blood oxygen saturation; The expression of the patient's potential demand index is: ; in, represents the potential demand index, represents the weight coefficient of potential demand, Indicates the patient's medical history, represents the potential demand function, which incorporates the medical history in addition to heart rate, respiratory rate, and blood oxygen saturation , to assess the potential needs of patients; Combine real-time vital signs data and emotional state to identify situations that may cause discomfort and agitation in patients; integrate real-time vital signs data and situational analysis results to form a comprehensive situational report, including the patient's vital signs trends, emotional state changes and potential needs assessment, to provide a basis for subsequent personalized intervention strategies.

[0025] Furthermore, the expression of the emotional state function is: ; in, Indicates the parameters for adjusting the heart rate. represents the parameter for adjusting the respiratory rate, Indicates the parameters for adjusting blood oxygen saturation; The expression of potential demand function is: ; and The value range is [0,1], where a value close to 0 indicates stable emotions and low demand; a value close to 1 indicates large emotional fluctuations, high potential demand, and may require immediate intervention.

[0026] S2, combining individual differences of patients and current situations, generates personalized intervention strategies including the following steps: Based on the patient's emotional state index ESI and potential demand index NDI, combined with historical medical records, preference information and physical restraint experience, a feature vector is constructed, including the patient's age, gender, medical history, historical intervention effects, preferred music type, light preference, temperature preference, etc.; a machine learning model is constructed, and the successful intervention cases and failed cases in the historical data set are used to train the machine learning model; The feature vector of the current situation is input into the trained model to obtain personalized intervention strategies, including playing light music, adjusting the brightness of the ward, adjusting the room temperature, using a specific dose of sedatives, etc. The expression is: ; in, Indicates intervention strategy, represents a non-drug intervention strategy function based on the patient's emotional state index , Potential Demand Index , historical medical data Personal Preference and physical restraint experiences to determine the type and intensity of nonpharmacological interventions (eg, music therapy, light adjustment, temperature control), Represents historical medical data, represents personalized parameters to suit the characteristics of a specific patient, Indicates experience of physical restraint, represents a drug intervention strategy function that determines the necessity and dosage of drug intervention (such as the timing and dosage of sedatives) based on the same set of variables. represents the body restraint strategy function, based on and , which is used to assess whether physical restraint is necessary and the extent of the restraint; The system dynamically adjusts the intervention strategy based on the patient's real-time vital signs data and situational changes. If the patient's emotional state deteriorates or potential needs increase, the system will adjust the intervention measures in a timely manner, such as using sedatives in advance or increasing the dosage. The system continuously monitors the patient's real-time vital signs and emotional state and evaluates the effectiveness of the intervention. If the intervention effect is not good, the system will adjust the strategy, such as changing the type of non-drug intervention or adjusting the drug dosage.

[0027] Furthermore, the expression of the non-drug intervention strategy function is: ; in, To adjust the degree of influence of medical history factors on the tendency of non-drug intervention, To control for the influence of patient preferences on the preference for non-pharmacological intervention, To adjust for the effects of physical restraint experience on the preference for nonpharmacological intervention; The expression of drug intervention strategy function is: ; in, To adjust the effect of medical history factors on the tendency of drug intervention, To control for the extent to which physical restraint experience affects the tendency to intervene with medication; The expression of the body restraint strategy function is: ; The value range is [0,1]. A value close to 0 indicates that no special intervention is needed in the current situation, and a value close to 1 indicates that urgent and comprehensive intervention measures are needed.

[0028] S3, based on historical data and current situation, predicting the patient's future behavior trends and potential risks includes the following steps: A risk prediction function is introduced to quantify the risk of agitation and self-harm in patients in the future. The expression is: ; in, represents the risk predictor, Indicates the impact on physiological indicators, Indicates the impact on behavioral indicators, Represents the sigmoid function, which is used to map the difference between 0 and 1 to reflect the relative risk of deviation. Indicates at a point in time The emotional state index, Indicates at a point in time The potential demand index, and They represent the average emotional state index and average potential demand index during the entire observation period respectively.

[0029] S4, based on the prediction results, dynamically adjusting the execution plan and physical restraint threshold of the intervention strategy includes the following steps: Define a dynamic intervention adjustment function to dynamically adjust the execution plan of the intervention strategy according to the result of the risk prediction function. The expression is: ; in, represents the adjusted intervention strategy, Indicates balance implications for intervention strategies; Based on risk prediction, the trigger threshold of physical restraints will be dynamically adjusted; in high-risk situations, the system will lower the trigger threshold of physical restraints to make physical restraints easier to trigger in order to reduce potential injuries; in low-risk situations, the system will increase the trigger threshold of physical restraints to reduce unnecessary use of physical restraints in order to maintain the comfort and dignity of patients.

[0030] Furthermore, the expression of the body constraint threshold adjustment function is: ; in, represents the body constraint threshold adjustment function, represents the physical restraint triggering threshold, Indicates a high risk threshold, represents a low risk threshold, is the threshold used to distinguish between high-risk and low-risk states.

[0031] S5, continuously collect patient feedback information, optimize the model and intervention strategy including the following steps, Use advanced monitoring equipment and technology to continuously track patients' real-time vital signs (blood pressure, heart rate, respiratory rate, etc.), emotional states and other key indicators; record changes in patients' real-time vital signs over time to evaluate the effectiveness of intervention measures; regularly assess patients' emotions and psychological states through questionnaires, observations and communication to understand their subjective feelings about nursing; comprehensively analyze physiological data and patient feedback to evaluate the overall impact of intervention measures on patients' health status; enter all collected feedback information into the system database in a timely manner, use statistical and machine learning methods to analyze feedback data, and identify patterns and trends in intervention effects; set up an early warning system to automatically identify any changes in vital signs that deviate from the normal range and notify nursing staff in a timely manner.

[0032] This embodiment also provides an EICU patient physical restraint decision support system, comprising: Data collection and analysis module: collects basic patient information and continuously monitors the patient's real-time vital signs data and behavioral patterns, uses artificial intelligence algorithms to analyze the patient's emotional state and potential needs, and identifies the patient's current situation; Personalized intervention strategy generation module: combines individual differences of patients and current situations to generate personalized intervention strategies; Predictive analysis and risk assessment module: based on historical data and current situations, predicts patients' future behavioral trends and potential risks; Dynamic adjustment and execution planning module: dynamically adjusts the execution plan and physical constraint threshold of the intervention strategy based on the prediction results; Feedback loop and model optimization module: continuously collects patient feedback information and optimizes models and intervention strategies.

[0033] This embodiment also provides a computer device, which is applicable to the EICU patient physical restraint decision support method, including: a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute the computer executable instructions to implement the EICU patient physical restraint decision support method proposed in the above embodiment.

[0034] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0035] This embodiment also provides a storage medium, on which a computer program is stored. When the program is executed by a processor, the method for implementing the EICU patient physical restraint decision support method proposed in the above embodiment is implemented; the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0036] In summary, the present invention achieves a comprehensive grasp of the patient's health status by collecting basic information of the patient and continuously monitoring real-time vital signs data and behavioral patterns. It uses artificial intelligence algorithms to analyze the patient's emotional state and potential needs, identify the patient's current situation, and achieve a new level of emotional intelligent nursing. It generates personalized intervention strategies based on individual differences of patients and current situations, and predicts the patient's future behavioral trends and potential risks based on historical data and current situations. The two work together to form a forward-looking, customized nursing plan, dynamically adjust the execution plan and physical restraint threshold of the intervention strategy according to the prediction results, and continuously collect patient feedback information to optimize the model and intervention strategy, thereby improving the accuracy and applicability of decision-making, reducing unnecessary physical constraints, and increasing the humanistic care of nursing.

[0037] Example 2, referring to Table 1, is the second example of the present invention. To further verify the advancement of the present invention, experimental simulation data of the EICU patient physical restraint decision support method are provided.

[0038] In a three-month study, 30 adult patients in a hospital intensive care unit were selected as research subjects to verify the effectiveness of an AI-based personalized intervention system in improving patients' emotional state and meeting potential needs. The study was divided into two groups: the experimental group used the personalized intervention system of the present invention, and the control group used traditional nursing intervention methods. Patients in the experimental group began to collect and record basic information (including age, gender, and medical history) and real-time vital signs data (heart rate, respiratory rate, body temperature, and blood oxygen saturation) when they were admitted. Using a deep learning model, the system continuously monitors the patient's emotional state and potential needs, updates the patient's emotional state index (ESI) and potential demand index (NDI) every hour, and dynamically adjusts the intervention strategy based on these indices.

[0039] During the study, the effects of all interventions were systematically recorded, including non-pharmacological interventions (such as music therapy, light adjustment, temperature control) and pharmacological interventions (timing and dosage of sedatives), as well as the use of physical restraints. In addition, patients' feedback on nursing interventions was collected through questionnaires and observations to assess their emotional state and psychological satisfaction.

[0040] The details are shown in Table 1: Table 1 Experimental record table Patient number age gender Heart rate (BPM) Respiratory rate (times / minute) Blood oxygen saturation (%) ESI NDI Type of intervention Sedative dose (mg) Number of physical restraints Experimental group P01 45 M 78 16 97 0.4 0.5 Music Therapy 0 2 Experimental group P02 62 F 82 18 95 0.6 0.7 Light Adjustment 2 1 Experimental group P03 38 M 75 15 98 0.3 0.4 Temperature control 0 0 Control group P04 54 F 80 17 96 0.5 0.6 None (traditional care) 1 3 Control group P05 48 M 76 16 97 0.7 0.8 None (traditional care) 3 4 Control group P06 58 F 83 19 94 0.8 0.9 None (traditional care) 4 5 It can be clearly seen from the above table that the patients in the experimental group who adopted the personalized intervention system of the present invention showed significant advantages in emotional stability and potential demand satisfaction compared with the control group. For example, although the heart rate and respiratory rate of patients P01 and P02 were higher than the normal range, their ESI and NDI were kept at a low level due to timely music therapy and light adjustment, indicating that their emotions were effectively soothed and their potential needs were properly handled. In particular, for patient P02, although his heart rate and respiratory rate were high, the side effects of the drugs were avoided by adjusting the light instead of directly using sedatives, and only a small amount of sedatives was used, which reduced the number of physical restraints and improved the patient's comfort.

[0041] In contrast, when faced with similar abnormal vital signs, patients in the control group had higher emotional state index and potential demand index than those in the experimental group due to the lack of personalized intervention, resulting in a significant increase in the use of sedatives and the number of physical restraints, which had an adverse effect on the patients' long-term rehabilitation and mental health.

[0042] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for supporting physical restraint decisions for EICU patients, characterized by: include, Collect basic patient information and continuously monitor patients' real-time vital signs and behavior patterns, use artificial intelligence algorithms to analyze patients' emotional states and potential needs, and identify patients' current situations; Generate personalized intervention strategies based on individual patient differences and current situations; Predict patients’ future behavior trends and potential risks based on historical data and current situations; Dynamically adjust the execution plan and physical restraint threshold of the intervention strategy based on the prediction results; Continuously collect patient feedback to optimize models and intervention strategies.

2. The EICU patient physical restraint decision support method according to claim 1, characterized in that: The patient's basic information includes age, gender and medical history; The real-time vital sign data include heart rate, respiratory rate, body temperature and blood oxygen saturation.

3. The EICU patient physical restraint decision support method according to claim 1, characterized in that: Using artificial intelligence algorithms to analyze the patient's emotional state and potential needs, identifying the patient's current situation includes the following steps: When the patient is admitted, basic information and current vital signs data are collected and recorded to create an electronic patient file; Continuously collect real-time vital sign data of patients, identify facial expressions and body postures, and use deep learning models to assess patients' emotional states and potential needs; The expression of the patient's emotional state index is: ； in, is the patient's emotional state index, Indicates the length of the time window of the data, represents the weight coefficient of the emotional state, represents the patient's emotional state function, The patient at the time point Heart rate, is the respiratory rate, is the blood oxygen saturation; The expression of the patient's potential demand index is: ； in, represents the potential demand index, represents the weight coefficient of potential demand, Indicates the patient's medical history, represents the potential demand function; Combine real-time vital sign data with emotional state to identify situations that cause patient discomfort and agitation; Integrate real-time vital sign data and situational analysis results into a comprehensive situational report.

4. The EICU patient physical restraint decision support method according to claim 3, characterized in that: Combining individual patient differences and current situations, generating a personalized intervention strategy includes the following steps: Based on the patient's emotional state index ESI and potential demand index NDI, combined with historical medical records, preference information and physical restraint experience, a feature vector is constructed; Build a machine learning model and use successful intervention cases and failure cases in historical data sets to train the machine learning model; Input the feature vector of the current situation into the trained model to obtain a personalized intervention strategy, which is expressed as: ； in, Indicates intervention strategy, represents the non-drug intervention strategy function, Represents historical medical data, Represents personalized parameters, Indicates experience of physical restraint, represents the drug intervention strategy function, represents the body restraint strategy function; The system dynamically adjusts intervention strategies based on the patient’s real-time vital signs data and situational changes; The system continuously monitors the patient's real-time vital signs and emotional state to evaluate the effectiveness of interventions.

5. The EICU patient physical restraint decision support method according to claim 4, characterized in that: Based on historical data and current situation, predicting the patient's future behavior trends and potential risks includes the following steps: A risk prediction function is introduced to quantify the risk of agitation and self-harm in patients in the future. The expression is: ； in, represents the risk predictor, Indicates the impact on physiological indicators, Indicates the impact on behavioral indicators, Represents the sigmoid function, which is used to map the difference between 0 and 1 to reflect the relative risk of deviation. Indicates at a point in time The emotional state index, Indicates at a point in time The potential demand index, and They represent the average emotional state index and average potential demand index during the entire observation period respectively.

6. The EICU patient physical restraint decision support method according to claim 5, characterized in that: According to the prediction results, dynamically adjusting the execution plan and physical restraint threshold of the intervention strategy includes the following steps: Define a dynamic intervention adjustment function to dynamically adjust the execution plan of the intervention strategy according to the result of the risk prediction function. The expression is: ； in, represents the adjusted intervention strategy, Indicates balance implications for intervention strategies; Dynamically adjust the triggering threshold of physical restraints based on risk prediction; In high-risk situations, the system will lower the trigger threshold for physical restraints, making them more likely to be triggered to reduce potential injuries; In low-risk situations, the system will increase the trigger threshold for physical restraints and reduce unnecessary use of physical restraints to maintain the patient's comfort and dignity.

7. The EICU patient physical restraint decision support method according to claim 6, characterized in that: Continuously collecting patient feedback and optimizing the model and intervention strategy include the following steps: Use monitoring devices and technology to continuously track patients’ real-time vital signs, emotional states, and other key indicators; Record the patient's real-time vital signs over time to assess the effectiveness of interventions; Regularly assess the patient's emotional and psychological state through questionnaires, observations, and communication to understand their subjective feelings about nursing care; Combine physiological data and patient feedback to assess the overall impact of interventions on patient health status; Enter all collected feedback information into the system database in a timely manner, use statistical and machine learning methods to analyze feedback data, and identify patterns and trends in intervention effects; Set up an early warning system to automatically identify any changes in vital signs that deviate from the normal range and notify nursing staff in a timely manner.

8. An EICU patient physical restraint decision support system, based on the EICU patient physical restraint decision support method according to any one of claims 1 to 7, characterized in that: include, Data collection and analysis module: collects basic patient information and continuously monitors patients' real-time vital signs and behavior patterns, uses artificial intelligence algorithms to analyze patients' emotional states and potential needs, and identifies patients' current situations; Personalized intervention strategy generation module: Generates personalized intervention strategies based on individual patient differences and current situations; Predictive analysis and risk assessment module: predicts patients’ future behavior trends and potential risks based on historical data and current situations; Dynamic adjustment and execution planning module: dynamically adjust the execution plan and physical constraint threshold of the intervention strategy based on the prediction results; Feedback loop and model optimization module: continuously collect patient feedback information to optimize models and intervention strategies.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the EICU patient physical restraint decision support method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the EICU patient physical restraint decision support method described in any one of claims 1 to 7 are implemented.

Images