Control methods, devices, electronic equipment, and storage media for ICU intelligent restraint straps

Abstract

This application discloses a control method, device, electronic device, and storage medium for intelligent restraint straps in the ICU, relating to the field of control technology. The control method includes: real-time monitoring of pressure data at the patient's restraint site, flow parameters of erythrocytes in subcutaneous capillaries, and skin temperature; analysis of the flow parameters to obtain the minimum diastolic flow velocity and spatial perfusion uniformity; if the minimum diastolic flow velocity is less than a preset flow velocity and the spatial perfusion uniformity is less than a preset uniformity, a rapid relaxation strategy is triggered; if the minimum diastolic flow velocity is greater than or equal to the preset flow velocity and the pressure data is lower than a reasonable pressure value, a gradual tightening strategy is triggered based on the rate of change of skin temperature. Thus, through real-time monitoring, precise analysis, a dual triggering mechanism, multi-parameter fusion, and dynamic adjustment, the safety, effectiveness, and intelligence level of ICU patient restraint management are effectively improved, providing strong support for patient care.

Description

Technical Field

[0001] This application relates to the field of control technology, and in particular to a control method, device, electronic device and storage medium for an ICU smart restraint belt. Background Technology

[0002] In the field of medical care, restraint straps are a commonly used nursing tool, primarily used to control patients' dangerous behaviors and prevent accidents. In the Intensive Care Unit (ICU), patients often require prolonged bed rest for treatment and care, and some may experience prolonged coma, critical illness, or lack of caregivers. This can lead to anxiety, agitation, and intolerance of pain, potentially resulting in self-harm, falls from bed, resistance to treatment, unplanned extubation, damage to medical equipment, and attacks on medical staff and family members. To mitigate these risks, restraining patients' dangerous behaviors with restraint straps has become a necessary nursing intervention.

[0003] Currently, wrist restraints are primarily used to restrain patients. These restraints consist of a wide band made of cotton or nylon, a metal or plastic ring buckle, and a disposable snap fastener. In use, the band is wrapped around the patient's wrist, the tightness is adjusted using the ring buckle, and then secured with the snap fastener. The end of the band is then tied to the bed rail or edge, achieving a rigid connection between the limb and the bed frame, effectively restraining the patient's dangerous behaviors. However, this type of wrist restraint has several limitations in practical application. For example, the tightness of the wrist restraint is not very precise; nurses cannot accurately adjust it based on experience, which may result in the restraint being too tight or too loose, affecting the patient's comfort and safety.

[0004] To address this issue, the development of intelligent restraints has gradually become a focus of market attention. Among related technologies, intelligent restraints have relatively simple control strategies, typically relying on passive adjustments based solely on pressure data at the restraint site. This lack of comprehensive assessment of the patient's condition makes adjustments imprecise and untimely, failing to meet the complex and ever-changing needs of ICU patients. Furthermore, existing intelligent restraints do not adequately consider patient safety and comfort during restraint, lacking real-time monitoring of physiological responses and corresponding safety mechanisms.

[0005] Therefore, there is an urgent need for a control strategy for intelligent restraints in the ICU to achieve dynamic and precise control of the restraints, ensure patient safety and comfort, and provide a reliable and intelligent solution for the care of ICU patients. Summary of the Invention

[0006] In view of this, embodiments of this application provide a control method, device, electronic device, and storage medium for ICU smart restraint straps, to achieve dynamic and precise control of the smart restraint straps, ensure patient safety and comfort, and provide a reliable and intelligent solution for the care of ICU patients.

[0007] On the one hand, embodiments of this application provide a control method for intelligent restraint straps in an ICU, including:

[0008] Real-time monitoring of pressure data at the patient's restraint site, flow parameters of red blood cells in subcutaneous capillaries, and skin temperature;

[0009] The flow parameters were analyzed to obtain the minimum diastolic velocity and spatial perfusion uniformity.

[0010] If the minimum diastolic flow rate is less than the preset flow rate and the spatial perfusion uniformity is less than the preset uniformity, then a rapid relaxation strategy is triggered.

[0011] If the minimum diastolic flow rate is greater than or equal to the preset flow rate and the pressure data is lower than the reasonable pressure value, a gradual tightening strategy is triggered based on the rate of change of skin temperature.

[0012] In one possible implementation, triggering the rapid relaxation strategy includes:

[0013] A single pulse current is output to the shape memory alloy unit, causing the alloy wire to contract within a corresponding first time and drive the constraint band to release a first distance. The shape memory alloy unit is used to execute a rapid relaxation strategy.

[0014] After the pulse current returns to zero, the alloy wire elastically resets, causing the constraint band to loosen, and it is determined whether the peak value of the pressure data is lower than the reasonable pressure value.

[0015] If so, then stop triggering the next pulse current and stop the rapid relaxation strategy;

[0016] If not, output the next pulse current and continue executing the rapid relaxation strategy.

[0017] In one possible embodiment, before determining whether the peak value of the pressure data is lower than a reasonable pressure value, the method further includes:

[0018] Construct the variance matrix corresponding to the stress data;

[0019] Determine whether the diagonal elements of the variance matrix are greater than a preset threshold. The diagonal elements reflect the degree of fluctuation of the pressure data.

[0020] If so, the pressure sensor that acquires the pressure data is recalibrated, and the calibrated pressure data is collected.

[0021] If not, the variance matrix is ​​applied to the Kalman filter algorithm to filter the pressure data.

[0022] In one possible embodiment, the variance matrix is ​​applied to a Kalman filter algorithm to filter the pressure data, including:

[0023] Based on prior values, the state vector and covariance matrix of the Kalman filter are initialized to obtain the initialization result; the state vector includes the pressure value and the rate of pressure change.

[0024] Based on the initialization results, predict the current pressure value and pressure change rate, and update the covariance matrix;

[0025] Based on the prediction results and the pressure data collected at the current moment, the prediction error is calculated, and the Kalman gain is calculated based on the prediction error and the variance matrix.

[0026] The state vector and covariance matrix are updated based on Kalman gain, and the calibrated pressure value and pressure change rate are obtained and output, thereby realizing the filtering processing of pressure data.

[0027] In one possible implementation, triggering the progressive tightening strategy includes:

[0028] Determine whether the rate of change in skin temperature is greater than the first rate of change and persists for a second time period;

[0029] If so, the microstepping motor unit is driven to tighten according to the preset step distance and step frequency until the peak pressure data reaches a reasonable pressure value. The microstepping motor unit is used to execute the progressive tightening strategy.

[0030] If the skin temperature change rate is less than the second change rate in the third time after tightening, the microstepping motor unit is driven to reverse and retract a second distance to release the predicted overpressure.

[0031] In one possible embodiment, the control method further includes:

[0032] When implementing rapid relaxation or progressive tightening strategies, the patient's physiological response data is recorded in real time, including heart rate, blood oxygen saturation, and electromyographic signals.

[0033] If a heart rate exceeding 120 beats per minute or a blood oxygen saturation below 90% is detected, the current strategy is paused, the safety release mechanism is triggered, the restraints are completely loosened, and an alarm is issued to notify medical staff.

[0034] On one hand, embodiments of this application provide a control device for an ICU smart restraint belt, comprising:

[0035] The monitoring module is used to monitor the pressure data of the patient's restraint site, the flow parameters of red blood cells in the subcutaneous capillaries, and the skin temperature in real time.

[0036] The analysis module is used to analyze the flow parameters to obtain the minimum diastolic velocity and spatial perfusion uniformity.

[0037] The relaxation module is used to trigger a rapid relaxation strategy if the minimum diastolic flow rate is less than the preset flow rate and the spatial perfusion uniformity is less than the preset uniformity.

[0038] The tightening module is used to trigger a progressive tightening strategy based on the rate of change of skin temperature if the minimum diastolic flow rate is greater than or equal to the preset flow rate and the pressure data is lower than the reasonable pressure value.

[0039] On one hand, embodiments of this application provide an electronic device, which includes a processor and a memory, wherein the memory stores program code, and when the program code is executed by the processor, the processor performs any of the above-described control methods.

[0040] On the one hand, this application provides a computer-readable storage medium including program code, which, when the storage medium is running on an electronic device, is used to cause the electronic device to perform any of the above-mentioned control methods.

[0041] On the one hand, embodiments of this application provide an ICU smart restraint belt, including a restraint belt body, a monitoring module, and a control module;

[0042] The restraint strap itself is used to restrain the patient;

[0043] The monitoring module is used to monitor pressure data at the restraint site, flow parameters of red blood cells in subcutaneous capillaries, and skin temperature.

[0044] The control module, connected to the constraint belt body and the monitoring module, is used to execute any of the above control methods.

[0045] The beneficial effects of this application are as follows:

[0046] This application provides a control method, device, electronic equipment, and storage medium for intelligent restraints in the ICU. By integrating multiple physiological parameters such as pressure data, blood flow parameters, and skin temperature, it achieves multi-dimensional patient status assessment. This multi-parameter fusion approach avoids misjudgments caused by fluctuations in a single parameter, improving the reliability of decision-making. By comprehensively analyzing the correlation between different physiological parameters, it can more comprehensively reflect the physiological state of the control strategy at the patient's restraint site, providing a reliable basis for the development of personalized nursing plans. Furthermore, by analyzing flow parameters, two key indicators—the minimum diastolic flow velocity and spatial perfusion uniformity—are obtained, providing a precise basis for subsequent control and improving accuracy. In addition, two triggering mechanisms—a rapid relaxation strategy and a gradual tightening strategy—can flexibly respond to different physiological states. When the minimum diastolic flow velocity and spatial perfusion uniformity are lower than preset values, the rapid relaxation strategy can promptly alleviate the problem of poor blood circulation that may be caused by excessive restraint. Conversely, when the minimum diastolic flow velocity is normal and the pressure data is below a reasonable value, the gradual tightening strategy dynamically adjusts the tightness of the restraints according to the rate of change in skin temperature, ensuring the safety and effectiveness of patient restraint. Both rapid relaxation and gradual tightening strategies can be executed automatically based on changes in the patient's physiological state, without the need for frequent manual intervention by medical staff. Attached Figure Description

[0047] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are only embodiments of this application. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0048] Figure 1 This is a flowchart illustrating the steps of a control method for an intelligent restraint belt according to an embodiment of this application.

[0049] Figure 2 This is a schematic diagram of the structure of a smart restraint belt in an embodiment of this application.

[0050] Figure 3 This is a schematic diagram of the structure of a control device for an intelligent restraint belt according to an embodiment of this application.

[0051] Figure 4 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions in the embodiments of this application 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 this application, and not all of them. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application. Unless otherwise specified, the embodiments and features in the embodiments of this application can be arbitrarily combined with each other. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than that shown here.

[0053] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in sequences other than those illustrated or described herein.

[0054] The design concept of the embodiments of this application is briefly introduced below:

[0055] In the field of medical care, restraint straps are a commonly used nursing tool, primarily used to control patients' dangerous behaviors and prevent accidents. In the Intensive Care Unit (ICU), patients often require prolonged bed rest for treatment and care, and some may experience prolonged coma, critical illness, or lack of caregivers. This can lead to anxiety, agitation, and intolerance of pain, potentially resulting in self-harm, falls from bed, resistance to treatment, unplanned extubation, damage to medical equipment, and attacks on medical staff and family members. To mitigate these risks, restraining patients' dangerous behaviors with restraint straps has become a necessary nursing intervention.

[0056] Currently, wrist restraints are primarily used to restrain patients. These restraints consist of a wide band made of cotton or nylon, a metal or plastic ring buckle, and a disposable snap fastener. In use, the band is wrapped around the patient's wrist, the tightness is adjusted using the ring buckle, and then secured with the snap fastener. The end of the band is then tied to the bed rail or edge, achieving a rigid connection between the limb and the bed frame, effectively restraining the patient's dangerous behaviors. However, this type of wrist restraint has several limitations in practical application. For example, the tightness of the wrist restraint is not very precise, and nurses cannot accurately adjust it based on experience, which may result in the restraint being too tight or too loose, affecting the patient's comfort and safety.

[0057] To address this issue, the development of intelligent restraints has gradually become a focus of market attention. Among related technologies, intelligent restraints have relatively simple control strategies, typically relying on passive adjustments based solely on pressure data at the restraint site. This lack of comprehensive assessment of the patient's condition makes the restraints insufficiently precise and timely, failing to meet the complex and ever-changing needs of ICU patients. Furthermore, existing intelligent restraints do not adequately consider patient safety and comfort during the restraint process, lacking real-time monitoring of physiological responses and corresponding safety mechanisms.

[0058] In view of this, embodiments of this application provide a control method, device, electronic device, and storage medium for intelligent restraint straps in the ICU. The control method includes: real-time monitoring of pressure data at the patient's restraint site, flow parameters of red blood cells in subcutaneous capillaries, and skin temperature; analysis of the flow parameters to obtain the minimum diastolic flow velocity and spatial perfusion uniformity; if the minimum diastolic flow velocity is less than a preset flow velocity and the spatial perfusion uniformity is less than a preset uniformity, a rapid relaxation strategy is triggered; if the minimum diastolic flow velocity is greater than or equal to the preset flow velocity and the pressure data is lower than a reasonable pressure value, a gradual tightening strategy is triggered based on the rate of change of skin temperature. Thus, through real-time monitoring, precise analysis, a dual triggering mechanism, multi-parameter fusion, and dynamic adjustment, the safety, effectiveness, and intelligence level of ICU patient restraint management are effectively improved, providing strong support for patient care.

[0059] The preferred embodiments of this application are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit this application. Furthermore, the embodiments and features in the embodiments of this application can be combined with each other without conflict.

[0060] like Figure 1 As shown in the figure, this application provides a control method for intelligent restraint straps in an ICU, including the following steps:

[0061] S101 monitors pressure data at the patient's restraint site, flow parameters of red blood cells in subcutaneous capillaries, and skin temperature in real time.

[0062] S102, analyze the flow parameters to obtain the minimum diastolic velocity and spatial perfusion uniformity;

[0063] S103, if the minimum diastolic flow rate is less than the preset flow rate and the spatial perfusion uniformity is less than the preset uniformity, then the rapid relaxation strategy is triggered.

[0064] S104 If the minimum diastolic flow rate is greater than or equal to the preset flow rate and the pressure data is lower than the reasonable pressure value, then a progressive tightening strategy is triggered based on the rate of change of skin temperature.

[0065] Preferably, the preset flow rate is 1 cm / s and the preset uniformity is 0.6.

[0066] Optionally, triggering the rapid relaxation strategy includes: outputting a single pulse current to the shape memory alloy unit, causing the alloy wire to contract within a corresponding first time interval and driving the strap to release a first distance. This first distance is preferably 5mm, but can also be 3mm, 4mm, or 6mm. The first time interval is less than the duration of the single pulse, which can be 118ms, 119ms, 200ms, etc. The pulse current can be 0.7A, 0.8A, or 0.9A. These specific parameters can be adaptively adjusted without specific limitations. After the pulse current returns to zero, the alloy wire elastically resets, causing the restraint strap to relax, and it is determined whether the peak pressure data is lower than a reasonable pressure value. The reasonable pressure value here is preferably selected as 25 mmHg, and the specific value can be adjusted comprehensively according to the patient's acceptance and actual effect. If the reasonable pressure value is less than or equal to 25 mmHg, the next pulse current is not triggered, and the rapid relaxation strategy is stopped; if the reasonable pressure value is greater than 25 mmHg, the next pulse current is output, and the rapid relaxation strategy continues. Optionally, the reasonable pressure value here can be the correlation number of the pressure data peak, such as 70% of the peak.

[0067] In one embodiment, to ensure the accuracy and reliability of the pressure data, a preprocessing step of data calibration and filtering is added before determining whether the peak value of the pressure data is lower than the reasonable pressure value. Specifically, before determining whether the peak value of the pressure data is lower than the reasonable pressure value, the following steps are also included: constructing the variance matrix corresponding to the pressure data; determining whether the diagonal elements of the variance matrix are greater than a preset threshold; if so, recalibrating the pressure sensor that acquired the pressure data and collecting the calibrated pressure data; if not, applying the variance matrix to the Kalman filtering algorithm to filter the pressure data.

[0068] For example, pressure sensors on a smart restraint strap collect a set of pressure data. This data may be affected by external factors, such as sensor noise or environmental factors, leading to errors. To assess the reliability of this data, a variance matrix corresponding to the pressure data is first constructed. The diagonal elements of the variance matrix reflect the variance of each pressure data point, i.e., the degree of data fluctuation. Here, a preset threshold is set to judge the reliability of the data. In this example, all diagonal elements of the variance matrix are less than the preset threshold; therefore, we determine that the pressure data from the pressure sensor is reliable and does not require recalibration. Next, we apply this variance matrix to a Kalman filter algorithm to filter the pressure data, dynamically adjusting the pressure data using the variance matrix. In this example, the Kalman filter algorithm calculates a smoother and more accurate set of pressure data, which more accurately reflects the actual pressure at the patient's restraint site. This example demonstrates that the added data calibration and filtering preprocessing steps can effectively improve the accuracy and reliability of the pressure data, thus providing more reliable data support for subsequent control strategies.

[0069] In one embodiment, applying the variance matrix to the Kalman filter algorithm to filter pressure data includes: initializing the state vector and covariance matrix of the Kalman filter based on prior values ​​to obtain an initialization result; the state vector contains the pressure value and pressure change rate; predicting the pressure value and pressure change rate at the current moment based on the initialization result, and updating the covariance matrix; calculating the prediction error based on the prediction result and the pressure data collected at the current moment, and calculating the Kalman gain based on the prediction error and the variance matrix; updating the state vector and covariance matrix based on the Kalman gain to obtain and output the calibrated pressure value and pressure change rate, thereby achieving the filtering processing of the pressure data.

[0070] Next, we will continue with the above example and explain in detail how to apply the constructed variance matrix to the Kalman filter algorithm to filter the pressure data and achieve more accurate data estimation.

[0071] First, initialize the state vector and covariance matrix of the Kalman filter.

[0072] Suppose we initialize the state vector and covariance matrix of the Kalman filter based on prior knowledge or empirical values. The state vector contains the current pressure value and the rate of change of pressure. For example, we initialize the state vector as: X0=[100,0], where the first element 100 is the initial pressure value and the second element 0 is the initial rate of change of pressure. The covariance matrix is ​​initialized as: P0=[2 0,0 2], where the diagonal elements represent the uncertainty of the initial state estimate.

[0073] Then, the pressure value and rate of change of pressure at the current moment are predicted; this stage is the prediction stage. Based on the state vector of the previous moment, the system dynamic model is used to predict the pressure value and rate of change of pressure at the current moment. Assume the system dynamic model is as follows: x k =F x k-1 +Bu k-1 Where F is the state transition matrix, B is the input matrix, and u is the input vector. Assuming there is no external input, then Bu... k-1 = 0. The state transition matrix F for a constant velocity model can be expressed as: F = [1 ∆t, 0 1] where ∆t is the time step. Assuming ∆t = 1 minute, the predicted state vector at the current moment is: x k - =F x k-1 =[1 1,0 1][100,0]=[100,0]. Simultaneously, update the covariance matrix: P k - =FP k-1 F T +Q, where Q is the process noise covariance matrix, assumed to be Q=[0.1 0,00.1]. The updated covariance matrix for the prediction stage is calculated as follows: P k - =[1 1,0 1][2 0,0 2][1 0,1 1]+[0.10,0 0.1]=[4.1 2,2 2.1].

[0074] Furthermore, assuming the collected pressure data at the current moment is 102 mmHg, we now compare this measured value with the predicted value and calculate the prediction error: y k = z k -H x k - =102-1×100=2mmHg, where H is the observation matrix, which is simplified to 1 here because only the pressure value is measured.

[0075] Furthermore, the Kalman gain is calculated based on the prediction error and variance matrix: K k = P k - H T (H P k - H T +R) -1 ,

[0076] Where R is the measurement noise covariance matrix, which is assumed to be 1 mmHg here. 2 Substitute the known matrix into the formula: K k =[4.1 + 2] × (4.1 + 1) -1= [0.8039 0.3922].

[0077] Further, the state vector and covariance matrix are updated; this stage is the update stage. Specifically, the Kalman gain is used to correct the predicted values, updating the state vector and covariance matrix. The updated state vector in this stage is: x k = x k - +K k y k =[100 0]+[0.8039 0.3922]×2=[101.6078 0.7844], the updated covariance matrix is: P k =(IK k H) P k - ≈[0.804 -0.392, -0.392 1.316].

[0078] Finally, the calibrated pressure value and pressure change rate are output, yielding a calibrated pressure value of 101.6078 mmHg and a pressure change rate of 0.7844 mmHg / min. This calibrated data will be used in subsequent control strategies, such as triggering rapid relaxation or gradual tightening.

[0079] In this way, we can understand how the Kalman filter algorithm dynamically adjusts pressure data using the variance matrix and improves data accuracy through prediction and update steps. This filtering process not only improves the reliability of pressure data but also provides a solid data foundation for subsequent intelligent control strategies.

[0080] In one embodiment, triggering the progressive tightening strategy includes: determining whether the skin temperature change rate is greater than a first change rate and persists for a second time, wherein the first change rate is 0.3℃ / s, but could also be 0.2℃ / s or 0.4℃ / s, and the second time is 1.5s, 2s, or 2.5s, etc., which can be adjusted according to actual conditions. If so, the microstepping motor unit is driven to tighten according to a preset step distance and step frequency until the peak pressure data reaches a reasonable pressure value; the preset step distance and step frequency are generally selected as 0.1 mm / step, 20 Hz, but could also be 0.15 mm / step, 22 Hz or 0.12 mm / step, 24 Hz, and are not specifically limited here. If the rate of change of skin temperature is less than the second rate of change within the third time after tightening, the microstepping motor unit will reverse and retract a second distance to release the pre-judgment overpressure. Here, the third time is 0.4s, 0.5s, 0.6s, etc., and the second distance is 0.5mm, 0.6mm, 0.7mm, etc. There is no specific limitation here, but the second distance is required to be less than the first distance.

[0081] This approach is applicable to real-time frequency-time domain joint analysis of flow parameters, achieving a closed-loop self-limiting mechanism of "noise warning - submillimeter correction - temperature confirmation," ensuring a dynamic balance between preventing cannula pull-out and preventing pressure injuries. It addresses the long-standing contradiction between "cannula pull-out prevention effectiveness" and "ischemic injury risk." This scheme uses a dual threshold of flow velocity and uniformity to identify compensatory ischemia in advance (e.g., a 30% decrease in diastolic flow velocity, but pressure only reaching 80% of the threshold), reducing the incidence of pressure injuries. Furthermore, through a temperature change rate inverse correction algorithm, if a negative correlation coefficient of 0.7 is found between the temperature change rate and subsequent pressure peaks, a backoff mechanism is used to avoid misjudged overpressure.

[0082] In one embodiment, the control method further includes: recording the patient's physiological response data in real time, including heart rate, blood oxygen saturation, and electromyography signals, while executing a rapid relaxation strategy or a progressive tightening strategy; if a heart rate exceeding 120 beats / minute or blood oxygen saturation below 90% is detected, pausing the current strategy, triggering a safety release mechanism to completely loosen the restraints, and issuing an alarm to notify medical staff.

[0083] On the other hand, such as Figure 2 As shown in the figure, an intelligent restraint strap 200 for ICU provided in this application embodiment includes a restraint strap body 201, a monitoring module 202, and a control module 203; the restraint strap body 201 is used to restrain the patient; the monitoring module 202 is used to monitor pressure data, red blood cell flow parameters in subcutaneous capillaries, and skin temperature at the restraint site; the control module 203 is connected to the restraint strap body 201 and the monitoring module 202, and is used to dynamically adjust the tightness of the restraint strap body 201 based on pressure data, flow parameters, and skin temperature.

[0084] Optionally, the restraint strap body 201 includes a restraint racket 201a and a long strap 201b. The restraint racket 201a is made of silicone material with anti-slip texture on the surface, ensuring good contact with the restrained area. The long strap 201b is made of cotton fabric, providing good warmth and softness. Its ends are connected to the restraint racket 201a via Velcro, facilitating easy assembly, disassembly, and use. The Velcro has an embedded Radio Frequency Identification (RFID) tag on the back, used to record the number of times the restraint strap is used and the disinfection time. It automatically prompts for replacement after a set number of uses, preventing fixation failure due to material aging.

[0085] Optionally, the monitoring module 202 includes a pressure sensor and a temperature sensor; the pressure sensor is located on the inside of the restraint belt body 201 and is used to monitor the pressure data of the restraint area in real time; the temperature sensor is located on the inside of the restraint belt body 201 and is used to monitor the skin temperature.

[0086] Optionally, the restraint racket 201a has a through-type cable tray inside. The control module 203 and the smart restraint strap 200 are set separately. The signal lines of the pressure sensor and temperature sensor are gathered through the cable tray to the waterproof connector at the end of the restraint racket 201b, and form a pluggable interface with the external control module 203, so as to realize the quick separation of the monitoring module 202 and the control module 203, and facilitate the cleaning and disinfection of the restraint strap body.

[0087] Optionally, the pressure sensor is a matrix MEMS device with a sensing unit density of ≥4 points / cm², which can generate a two-dimensional pressure cloud map. The control module 203 automatically identifies high pressure points based on the gradient of the cloud map, and prioritizes to initiate local relaxation actions when the high pressure point lasts for more than 3 seconds, so as to achieve point-to-surface coordinated pressure reduction.

[0088] Optionally, the temperature sensor uses an infrared thin-film sensor with a response time of <1 s and a resolution of 0.1 ℃, which can obtain surface temperature without contacting the skin, reducing thermal conduction errors; the sensor window is flush with the surface of the constrained racket 201b to avoid irritation from protrusions.

[0089] Optionally, the long strap 201b has a hidden airbag channel on the inside, which is connected to an air pump. It can be pre-inflated by 0.5 mL before the tightening strategy is executed, so as to reduce the coefficient of friction between the strap and the skin and reduce the skin shearing injury caused by instant tightening. After the airbag is deflated, the strap returns to a soft and fit.

[0090] Optionally, the restraint racket 201a has a U-shaped observation window on its outer edge. The window is made of transparent medical thermoplastic polyurethane (TPU) film, allowing nurses to directly observe skin color and probe coupling status without untying the restraints, thus shortening inspection time. Alternatively, the restraint racket 201a has a U-shaped zipper on its outer edge. When the zipper is open, the blood circulation at the restraint site can be observed based on the U-shaped zipper.

[0091] In one possible embodiment, the restraint band also includes a heating wire made of nickel-chromium alloy, which, together with a temperature sensor, forms a heating module capable of rapid heating within a range of 40-45°C. The heating module, through feedback from the temperature sensor and the heating temperature of the heating wire, achieves a warming and thermotherapy effect on the restrained area.

[0092] In one possible embodiment, the restraint strap also includes a medical conditioning pack; the traditional Chinese medicine conditioning pack is embedded in the restraint strap body 201 and is filled with natural Chinese medicinal materials, the main ingredients of which are mugwort leaves, cinnamon twigs, ginger slices, garlic, light soy sauce, eggs, etc., and has anti-inflammatory, sedative and wind-dispelling effects; the material of the traditional Chinese medicine conditioning pack is a waterproof and breathable membrane, which can maintain the durability and stability of the medicinal effect.

[0093] Optionally, the control module 203 uses a flexible printed circuit (FPC) directly embedded in the constraint racket 201a or the proximal strap interlayer, and is connected to the monitoring module 202 and the composite actuator via a flexible ribbon cable, with no visible protrusion. This composite actuator, used to contract and relax the constraint strap, is integrated inside the constraint strap body 201 and includes at least a shape memory alloy unit and a micro-stepping motor unit. The shape memory alloy unit is used to execute a rapid relaxation strategy; the micro-stepping motor unit is used to execute a gradual tightening strategy. The shape memory alloy unit and the micro-stepping motor unit are arranged in series along the same force line and driven in a time-sharing manner.

[0094] Optionally, control module 203 is configured to execute Figure 1 The control method shown.

[0095] This application provides an intelligent restraint strap for ICU patients. The control module simultaneously acquires three types of data at the restraint site: pressure data, capillary erythrocyte flow parameters, and skin temperature. It then instantly calculates and outputs tightening and loosening instructions, eliminating errors caused by traditional methods relying on manual experience. This stabilizes the restraint pressure within a safe range, preventing pressure injuries from excessive tightness or unplanned extubation from excessive looseness. Specifically, the subcutaneous capillary erythrocyte flow parameters directly reflect the local perfusion status, providing greater reliability than visual observation and significantly reducing the incidence of pressure injuries. Skin temperature change rate indirectly reflects sympathetic nerve excitation and agitation precursors. Based on this tightening strategy, catheters can be stabilized before the patient begins to struggle but before significant displacement occurs, reducing accidental extubation. Furthermore, the restraint strap no longer maintains the same pressure continuously but is continuously fine-tuned according to physiological changes, reducing blood stasis, swelling, and pain caused by prolonged immobilization, improving ICU patient comfort, and reducing sedation drug dosage. In addition, pressure data, flow parameters, skin temperature, and adjustment actions are all recorded electronically, replacing paper-based inspections and providing quantitative evidence for nursing quality assessment, accountability, and research analysis.

[0096] Based on the same inventive concept, such as Figure 3 As shown in the figure, a control device for an ICU smart restraint belt is also provided in an embodiment of this application, comprising:

[0097] Monitoring module 301 is used to monitor pressure data at the patient's restraint site, flow parameters of red blood cells in subcutaneous capillaries, and skin temperature in real time.

[0098] The analysis module 302 is used to analyze the flow parameters to obtain the minimum diastolic velocity and spatial perfusion uniformity.

[0099] The relaxation module 303 is used to trigger a rapid relaxation strategy if the minimum diastolic flow rate is less than the preset flow rate and the spatial perfusion uniformity is less than the preset uniformity.

[0100] The tightening module 304 is used to trigger a progressive tightening strategy based on the rate of change of skin temperature if the minimum diastolic flow rate is greater than or equal to the preset flow rate and the pressure data is lower than the reasonable pressure value.

[0101] In one possible embodiment, the relaxation module 303 is used for:

[0102] A single pulse current is output to the shape memory alloy unit, causing the alloy wire to contract within a corresponding first time and drive the constraint band to release a first distance. The shape memory alloy unit is used to execute a rapid relaxation strategy.

[0103] After the pulse current returns to zero, the alloy wire elastically resets, causing the constraint band to loosen, and it is determined whether the peak value of the pressure data is lower than the reasonable pressure value.

[0104] If so, then stop triggering the next pulse current and stop the rapid relaxation strategy;

[0105] If not, output the next pulse current and continue executing the rapid relaxation strategy.

[0106] In one possible embodiment, the relaxation module 303 is further configured to:

[0107] Construct the variance matrix corresponding to the stress data;

[0108] Determine whether the diagonal elements of the variance matrix are greater than a preset threshold. The diagonal elements reflect the degree of fluctuation of the pressure data.

[0109] If so, the pressure sensor that acquires the pressure data is recalibrated, and the calibrated pressure data is collected.

[0110] If not, the variance matrix is ​​applied to the Kalman filter algorithm to filter the pressure data.

[0111] In one possible embodiment, the relaxation module 303 is further configured to:

[0112] Based on prior values, the state vector and covariance matrix of the Kalman filter are initialized to obtain the initialization result; the state vector includes the pressure value and the rate of pressure change.

[0113] Based on the initialization results, predict the current pressure value and pressure change rate, and update the covariance matrix;

[0114] Based on the prediction results and the pressure data collected at the current moment, the prediction error is calculated, and the Kalman gain is calculated based on the prediction error and the variance matrix.

[0115] The state vector and covariance matrix are updated based on Kalman gain, and the calibrated pressure value and pressure change rate are obtained and output, thereby realizing the filtering processing of pressure data.

[0116] In one possible embodiment, the tightening module 304 is used for:

[0117] Determine whether the rate of change in skin temperature is greater than the first rate of change and persists for a second time period;

[0118] If so, the microstepping motor unit is driven to tighten according to the preset step distance and step frequency until the peak pressure data reaches a reasonable pressure value. The microstepping motor unit is used to execute the progressive tightening strategy.

[0119] If the rate of change in skin temperature is less than the second rate of change in the third time after tightening, the microstepping motor unit will reverse and retract the second distance to release the predicted overpressure.

[0120] In one possible embodiment, the control device further includes:

[0121] The recording module is used to record the patient's physiological response data in real time when performing rapid relaxation or progressive tightening strategies. The physiological response data includes heart rate, blood oxygen saturation, and electromyographic signals.

[0122] The alarm module is used to pause the current strategy, trigger the safety release mechanism, completely loosen the restraints, and issue an alarm to notify medical staff if the heart rate is detected to exceed 120 beats per minute or the blood oxygen saturation is below 90%.

[0123] The technical effects achieved by the above control devices can be referred to in the control method section, and will not be elaborated here.

[0124] In some possible implementations, the control device according to this application may include at least a processor and a memory. The memory stores program code that, when executed by the processor, causes the processor to perform the steps of the control methods described in this specification according to various exemplary embodiments of this application. For example, the processor may perform actions such as... Figure 1 The steps are shown in the figure.

[0125] Based on the same inventive concept, this application also provides an electronic device that can implement the functions of the aforementioned control method. (Refer to...) Figure 4 Electronic devices include:

[0126] At least one processor 401 and a memory 402 connected to at least one processor 401. In this embodiment, the specific connection medium between the processor 401 and the memory 402 is not limited. Figure 4 Taking the connection between processor 401 and memory 402 via bus 400 as an example. Bus 400 in... Figure 4 The connections between other components are shown in bold lines only and are not intended to be limiting. The 400 bus can be divided into address bus, data bus, and other bus types; for ease of representation, these are not shown in bold. Figure 4 The term "processor" is represented by a single thick line, but this does not imply that there is only one bus or one type of bus. Alternatively, processor 401 can also be called a device; there is no restriction on the name.

[0127] In this embodiment, memory 402 stores instructions executable by at least one processor 401. By executing the instructions stored in memory 402, at least one processor 401 can perform the control method described above. Processor 401 can implement... Figure 3 The functions of each module in the control device shown.

[0128] The processor 401 is the center of the control device. It can connect to various parts of the device through various interfaces and lines. By running or executing instructions stored in memory 402 and calling data stored in memory 402, the control device performs various functions and processes data, thereby monitoring the device as a whole.

[0129] In one possible design, processor 401 may include one or more processing units. Processor 401 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless communication. It is understood that the modem processor may also not be integrated into processor 401. In some embodiments, processor 401 and memory 402 may be implemented on the same chip; in some embodiments, they may also be implemented on separate chips.

[0130] Processor 401 can be a general-purpose processor, such as a central processing unit (CPU), digital signal processor, application-specific integrated circuit, field-programmable gate array or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component, capable of implementing or executing the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the control methods disclosed in the embodiments of this application can be directly manifested as being executed by a hardware processor, or executed by a combination of hardware and software modules within the processor.

[0131] Memory 402, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules. Memory 402 may include at least one type of storage medium, such as flash memory, hard disk, multimedia card, card-type memory, random access memory (RAM), static random access memory (SRAM), programmable read-only memory (PROM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), magnetic storage, magnetic disk, optical disk, etc. Memory 402 can be any other medium capable of carrying or storing desired program code in the form of instructions or data structures that can be accessed by a computer, but is not limited thereto. In the embodiments of this application, memory 402 can also be a circuit or any other device capable of implementing storage functions for storing program instructions and / or data.

[0132] By designing and programming the processor 401, the code corresponding to the control method described in the foregoing embodiments can be embedded into the chip, enabling the chip to execute the code during operation. Figure 1 The steps of the control method in the illustrated embodiment are as follows. How to design and program the processor 401 is a technique well-known to those skilled in the art and will not be described further here.

[0133] Based on the same inventive concept, embodiments of this application also provide a storage medium storing computer instructions that, when executed on a computer, cause the computer to perform the control method described above.

[0134] In some possible implementations, various aspects of the control method provided in this application may also be implemented as a program product comprising program code that, when the program product is run on a device, causes the device to perform the steps of the control method according to the various exemplary embodiments of this application described above.

[0135] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0136] This application is described with reference to flowchart illustrations and / or block diagrams of control methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, as well as combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the control method, apparatus, and computer program product according to embodiments of this application. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0137] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0138] These computer program instructions can also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0139] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A control method for intelligent restraint straps in an ICU, characterized in that, include: Pressure data at the patient's restraint site is monitored in real time using a pressure sensor configured as a matrix MEMS device, and the flow parameters of red blood cells in the subcutaneous capillaries and skin temperature at the restraint site are also monitored. The flow parameters were analyzed to obtain the minimum diastolic velocity and spatial perfusion uniformity. If the minimum diastolic flow rate is less than the preset flow rate and the spatial perfusion uniformity is less than the preset uniformity, then a rapid relaxation strategy is triggered. If the minimum diastolic flow rate is greater than or equal to the preset flow rate, and the pressure data is lower than a reasonable pressure value, then a progressive tightening strategy is triggered based on the rate of change of skin temperature.

2. The control method as described in claim 1, characterized in that, The triggering rapid relaxation strategy includes: A single pulse current is output to the shape memory alloy unit, causing the alloy wire to contract within a corresponding first time and drive the constraint band to release a first distance. The shape memory alloy unit is used to execute the rapid relaxation strategy. After the pulse current returns to zero, the alloy wire elastically resets, causing the constraint band to loosen, and it is determined whether the peak value of the pressure data is lower than the reasonable pressure value. If so, then stop triggering the next pulse current and stop the rapid relaxation strategy; If not, output the next pulse current and continue executing the rapid relaxation strategy.

3. The control method as described in claim 2, characterized in that, Before determining whether the peak value of the pressure data is lower than a reasonable pressure value, the method further includes: Construct the variance matrix corresponding to the pressure data; Determine whether the diagonal elements of the variance matrix are greater than a preset threshold, where the diagonal elements reflect the degree of fluctuation of the pressure data; If so, the pressure sensor that acquires the pressure data is recalibrated, and the calibrated pressure data is collected. If not, the variance matrix is ​​applied to the Kalman filter algorithm to filter the pressure data.

4. The control method as described in claim 3, characterized in that, The step of applying the variance matrix to the Kalman filter algorithm to filter the pressure data includes: Based on prior values, the state vector and covariance matrix of the Kalman filter are initialized to obtain the initialization result; the state vector includes the pressure value and the rate of pressure change. Based on the initialization results, predict the current pressure value and pressure change rate, and update the covariance matrix; Based on the prediction results and the pressure data collected at the current moment, the prediction error is calculated, and the Kalman gain is calculated based on the prediction error and the variance matrix. The state vector and covariance matrix are updated based on the Kalman gain to obtain and output the calibrated pressure value and pressure change rate, thereby achieving filtering of the pressure data.

5. The control method as described in claim 1, characterized in that, The triggering progressive tightening strategy includes: Determine whether the rate of change in skin temperature is greater than the first rate of change and persists for a second time period; If so, the microstepping motor unit is driven to tighten according to the preset step distance and step frequency until the peak value of the pressure data reaches the reasonable pressure value. The microstepping motor unit is used to execute the progressive tightening strategy. If the skin temperature change rate is less than the second change rate within the third time after tightening, the microstepping motor unit is driven to reverse and retract a second distance to release the predicted overpressure.

6. The control method as described in claim 1, characterized in that, Also includes: When performing the rapid relaxation strategy or the progressive tightening strategy, the patient's physiological response data is recorded in real time, including heart rate, blood oxygen saturation, and electromyographic signals. If the heart rate is detected to exceed 120 beats per minute or the blood oxygen saturation is detected to be below 90%, the current strategy is paused, the safety release mechanism is triggered, the restraints are completely loosened, and an alarm is issued to notify medical staff.

7. A control device for an intelligent restraint belt in an ICU, characterized in that, include: The monitoring module is used to monitor the pressure data of the patient's restraint site in real time through a pressure sensor configured as a matrix MEMS device, and to monitor the flow parameters of red blood cells in the subcutaneous capillaries of the restraint site and the skin temperature. The analysis module is used to analyze the flow parameters to obtain the minimum diastolic velocity and spatial perfusion uniformity. The relaxation module is used to trigger a rapid relaxation strategy if the minimum diastolic flow rate is less than a preset flow rate and the spatial perfusion uniformity is less than a preset uniformity. The tightening module is used to trigger a progressive tightening strategy based on the rate of change of skin temperature if the minimum diastolic flow rate is greater than or equal to the preset flow rate and the pressure data is lower than a reasonable pressure value.

8. An electronic device, characterized in that, It includes a processor and a memory, wherein the memory stores program code that, when executed by the processor, causes the processor to perform any of the control methods described in claims 1 to 6.

9. A computer-readable storage medium, characterized in that, Includes program code, which, when the storage medium is running on an electronic device, is used to cause the electronic device to execute any of the control methods described in claims 1 to 6.

10. An intelligent restraint belt for ICU, characterized in that, It includes the restraint belt body, monitoring module, and control module; The restraint strap body is used to restrain the patient; The monitoring module is used to monitor pressure data at the constraint site using a pressure sensor configured as a matrix MEMS device, and to monitor the flow parameters of red blood cells in the subcutaneous capillaries and skin temperature at the constraint site. The control module is connected to the constraint belt body and the monitoring module, and is used to execute any of the control methods described in claims 1 to 6.

Images