Postoperative nursing sickbed for cardiopulmonary surgery

Abstract

The invention discloses a postoperative nursing sickbed for the cardiopulmonary surgery department, and belongs to the technical field of electric sickbeds. The sickbed comprises a bed board angle adjusting system, and a multi-level risk assessment model is constructed through a physical sign analysis module, a bed position safety evaluation module and a body position evaluation module; combining a comprehensive safety evaluation module and an edge-height matching module to output a collaborative safety coefficient; and finally, the bed board angle optimization module generates a target bed board angle based on the physical sign data, the safety coefficient and the current angle, and automatic adjustment of the body position is achieved. Meanwhile, the system triggers audio early warning in real time through threshold comparison, the problems that monitoring of a traditional sickbed lags behind and depends on manpower are solved, and the safety and nursing efficiency of the patient are remarkably improved.

Description

Technical Field

[0001] This invention belongs to the field of electric hospital bed technology, and in particular relates to a postoperative nursing bed for cardiopulmonary surgery. Background Technology

[0002] Postoperative care beds in cardiopulmonary surgery are crucial equipment in the patient's recovery process, and their functionality directly affects patient safety and rehabilitation efficiency. Postoperative patients often face multiple risks such as respiratory depression, falls from the bed, and pressure sores; therefore, the beds must have real-time monitoring and automatic adjustment capabilities to ensure the quality of care.

[0003] Existing electric hospital beds mostly employ single-parameter monitoring or fixed-threshold early warning mechanisms, such as triggering alarms solely based on bed height or the number of times patients leave the bed. Some beds support manual angle adjustment, but they lack collaborative analysis of multi-dimensional data. Traditional technologies rely on regular rounds by medical staff and manual judgment, with bed adjustments primarily based on preset programs, failing to dynamically respond to real-time changes in the patient's condition.

[0004] Existing technologies have significant drawbacks: First, monitoring is lagging, failing to integrate parameters such as vital signs, postural pressure, and bed exit behavior in real time, leading to incomplete risk assessment. Second, reliance on manual intervention results in delayed responses that can easily cause secondary injuries. Third, protective measures are static; for example, the height of bed rails is poorly matched to the patient's position, making adaptive adjustments difficult. These shortcomings limit the improvement of nursing efficiency and patient safety. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides a postoperative care bed for cardiopulmonary surgery, which solves the aforementioned problems.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a postoperative nursing bed for cardiopulmonary surgery, comprising:

[0007] The bed board angle adjustment system is used to adjust the angle of the bed board to change the patient's supine position, including:

[0008] The vital signs analysis module constructs a vital signs analysis model based on respiratory rate and blood oxygen saturation, and outputs vital signs analysis coefficients.

[0009] The bed safety evaluation module constructs a bed safety evaluation model based on the number of times people get out of bed per unit time and the bed height, and outputs the bed safety coefficient.

[0010] The postural evaluation module constructs a postural evaluation model based on the maximum static time and the maximum pressure gradient of the body position, and outputs postural evaluation coefficients.

[0011] The comprehensive safety evaluation module constructs a comprehensive safety evaluation model based on the bed safety factor and the body position evaluation factor, and outputs the comprehensive safety evaluation factor.

[0012] The edge-height analysis module constructs an edge-height matching model based on the edge distance (distance between the bedridden person and the edge of the bed) and the height of the bed rails under the comprehensive safety evaluation coefficient, and outputs the edge-height matching degree.

[0013] The bed board angle optimization module constructs an angle optimization model based on the physical characteristic analysis coefficient, edge-height matching degree, and the current bed board angle, and outputs the target bed board angle.

[0014] Based on the above technical solutions, the present invention also provides the following optional technical solutions:

[0015] Further technical solution: The steps of the bed board angle optimization module are as follows:

[0016] Import the current vital signs analysis coefficients into the formula. Obtain the reference angle, where, Indicates the minimum permissible bed board angle. This indicates the degree of angle adjustment, controlling the angle. This represents the current vital sign analysis coefficient;

[0017] Import the current vital sign analysis coefficients and the current edge-height matching degree into the formula. Obtain the safety adjustment factor. This represents the sensitivity coefficient to physical signs and safety. This indicates the threshold for the safety factor of vital signs. This represents the current vital sign analysis coefficient. Indicates the current edge-height matching degree;

[0018] The current bed board angle, safety adjustment factor, and reference angle are imported into the angle optimization model to output the target bed board angle. The angle optimization model is expressed as follows:

[0019]

[0020] in, Indicates the target bed board angle. Indicates the degree of angle adjustment. Indicates the safety adjustment factor. Indicates the reference angle. This indicates the current angle of the bed board.

[0021] Further technical solution: The working steps of the edge-height analysis module are as follows:

[0022] The edge distance and bed rail height are processed by maximum-min normalization to obtain the edge distance index and bed rail height index;

[0023] An edge-height matching model is constructed based on the comprehensive safety evaluation coefficient, edge distance index, and bed rail height index. The edge-height matching model is expressed as follows:

[0024]

[0025] in, Indicates edge-height matching degree. Indicates the edge distance index. Indicates the bed rail height index. The comprehensive safety evaluation coefficient is represented by the following. Furthermore, the larger the value, the better the synergy between the edge distance and the bed rail height;

[0026] Import the current comprehensive safety evaluation coefficient, current edge distance index, and current bed rail height index into the edge-height matching model to obtain the current edge-height matching degree;

[0027] The current edge-height matching degree is compared with the preset edge-height matching degree threshold. If the current edge-height matching degree is not within the edge-height matching degree threshold, an alarm message is generated.

[0028] Further technical solution: The working steps of the vital sign analysis module are as follows:

[0029] The respiratory rate index is obtained by performing maximum-min normalization on the respiratory rate.

[0030] Import blood oxygen saturation into the formula Blood oxygen saturation was obtained from the blood oxygen saturation index. Indicates blood oxygen sensitivity. Indicates blood oxygen saturation. This indicates the safe value for blood oxygen saturation;

[0031] A vital signs analysis model is constructed based on the respiratory rate index and blood oxygen index. The vital signs analysis model is expressed as follows:

[0032]

[0033] in, This represents the coefficient of vital sign analysis. Indicates respiratory rate index, This indicates the blood oxygen index. Represents the weight coefficient and The Furthermore, the higher the value, the more stable the vital signs;

[0034] Import the current respiratory rate index and current blood oxygen index into the vital signs analysis model to output the vital signs analysis coefficients;

[0035] The current vital sign analysis coefficient is compared with the preset vital sign coefficient threshold. If the current vital sign analysis coefficient is not within the threshold, an alarm message is generated.

[0036] Further technical solution: The working steps of the comprehensive safety evaluation module are as follows:

[0037] The current bed safety factor and the current body position evaluation factor are imported into the comprehensive safety evaluation model to obtain the current comprehensive safety evaluation factor. The comprehensive safety evaluation model (harmonic average) is expressed as follows:

[0038]

[0039] in, This represents the comprehensive safety evaluation coefficient. Indicates the safety factor of the bed. The body position evaluation coefficient is represented by the following. Furthermore, the higher the value, the higher the overall security.

[0040] The current comprehensive safety evaluation coefficient is compared with the preset comprehensive safety evaluation coefficient threshold. If the current comprehensive safety evaluation coefficient is not within the comprehensive safety evaluation coefficient threshold, an alarm message is generated.

[0041] Further technical solution: The working steps of the bed safety evaluation module are as follows:

[0042] Import the number of times the bed gets up per unit time into the formula. Obtain the bed exit frequency index, where, Indicates sensitivity to the number of times one gets out of bed. This indicates the number of times a person gets out of bed per unit of time. Indicates the standard number of times a person gets out of bed;

[0043] Import bed height into the formula Obtain the bed height index, among which, Indicates a high sensitivity coefficient. Indicates bed height. Indicates the ideal safe height for a bed;

[0044] A bed safety model is constructed based on the bed departure frequency index and the bed height index. The bed safety model is expressed as follows:

[0045]

[0046] in, Indicates the safety factor of the bed. Indicates the bed departure frequency index. Indicates the bed height index. Represents the weight coefficient and The The higher the value, the lower the risk of falling out of bed;

[0047] Import the current bed departure frequency index and the current bed height index into the bed safety model to output the current bed safety coefficient;

[0048] The current bed safety factor is compared with the preset bed safety factor threshold. If the current bed safety factor is not within the bed safety factor threshold, an alarm message is generated.

[0049] Further technical solution: The working steps of the posture evaluation module are as follows:

[0050] The maximum pressure gradient in body position is normalized by the minimum to obtain the pressure gradient exponent in body position.

[0051] Import the maximum static time into the formula Obtain the postural rest time index, where, Indicates static time sensitivity. Indicates the maximum resting time in the body position. Indicates the duration of stillness in the standard body position;

[0052] A postural evaluation model is constructed based on the pressure gradient index and the postural rest time index. The postural evaluation model is expressed as follows:

[0053]

[0054] in, This represents the body position evaluation coefficient. Indicates the index of static body position. Indicates the pressure gradient exponent. Represents the weight coefficient and The Furthermore, the higher the value, the lower the risk associated with bed rest.

[0055] Import the current pressure gradient index and the current body position rest time index into the body position evaluation model to output the current body position evaluation coefficient;

[0056] The current posture evaluation coefficient is compared with the preset previous posture evaluation coefficient threshold. If the current posture evaluation coefficient is not within the posture evaluation coefficient threshold, an alarm message is generated.

[0057] A postoperative care bed for cardiopulmonary surgery, using the aforementioned postoperative care bed for cardiopulmonary surgery.

[0058] This invention provides a postoperative care bed for cardiopulmonary surgery, which has the following advantages compared with the prior art:

[0059] 1. This invention calculates risk coefficients in real time through a vital sign analysis model (respiration, blood oxygen), a bed safety model (frequency of getting out of bed, height), and a body position evaluation model (pressure gradient, rest time), thereby achieving a comprehensive safety assessment. At the same time, it can automatically generate alarm information such as bed falls and pressure sores based on the comparison of coefficient thresholds output by multiple modules, thus improving the response speed.

[0060] 2. This invention integrates vital sign data, edge-height matching degree, and current angle, and dynamically adjusts the target bed board angle through an optimized model to reduce nursing burden. At the same time, it can improve overall safety and reduce human intervention by utilizing the edge-height matching model (the synergy between distance and bed rail height) and the comprehensive safety evaluation coefficient (harmonic average algorithm). Attached Figure Description

[0061] Figure 1 This is a flowchart illustrating the bed board angle adjustment system of the present invention. Detailed Implementation

[0062] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0063] The specific implementation of the present invention will be described in detail below with reference to specific embodiments.

[0064] Please see Figure 1 According to one embodiment of the present invention, a postoperative nursing bed for cardiopulmonary surgery includes:

[0065] A bed board angle adjustment system is used to adjust the angle of the bed board to change the patient's supine position, including:

[0066] The vital signs analysis module constructs a vital signs analysis model based on respiratory rate and blood oxygen saturation, and outputs vital signs analysis coefficients.

[0067] The bed safety evaluation module constructs a bed safety evaluation model based on the number of times people get out of bed per unit time and the bed height, and outputs the bed safety coefficient.

[0068] The postural evaluation module constructs a postural evaluation model based on the maximum static time and the maximum pressure gradient of the body position, and outputs postural evaluation coefficients.

[0069] The comprehensive safety evaluation module constructs a comprehensive safety evaluation model based on the bed safety factor and the body position evaluation factor, and outputs the comprehensive safety evaluation factor.

[0070] The edge-height analysis module constructs an edge-height matching model based on the edge distance (distance between the bedridden person and the edge of the bed) and the height of the bed rails under the comprehensive safety evaluation coefficient, and outputs the edge-height matching degree.

[0071] The bed board angle optimization module constructs an angle optimization model based on the physical characteristic analysis coefficient, edge-height matching degree, and the current bed board angle, and outputs the target bed board angle.

[0072] The system comprises several modules: **Vitality Analysis Module:** This module calculates the stability of a patient's vital signs using respiratory rate and blood oxygen saturation. It can be implemented using normalization and weighted fusion algorithms to provide physiological data for adjusting the bed angle. **Bed Safety Evaluation Module:** This module assesses the risk of falls from bed using the number of times the patient gets out of bed and bed height. It can be implemented using exponential transformation and linear combination models to address the limitations of single-parameter assessments. **Position Evaluation Module:** This module assesses the risk of pressure ulcers using postural rest time and pressure gradient. It can be implemented using time decay functions and pressure gradient normalization methods to prevent tissue damage caused by prolonged static positioning. **Comprehensive Safety Evaluation Module:** This module integrates the bed safety factor and the position evaluation factor. It can be implemented using a harmonic mean algorithm to form a global safety evaluation index. **Edge-Height Analysis Module:** This module calculates the degree of synergy between edge distance and bed rail height. It can be implemented using a normalized difference calculation model to dynamically adjust bed protection parameters. The bed board angle optimization module is a module that outputs the target angle based on the fusion of multiple parameters. Specifically, it can be implemented by superimposing a reference angle and a dynamic adjustment factor algorithm to achieve a balance between safety and comfort.

[0073] Specifically, the vital signs analysis module converts physiological parameters into standardized indices by normalizing respiratory rate and blood oxygen saturation, and then generates vital signs analysis coefficients through weighted fusion. The bed safety assessment module converts the number of times the patient gets out of bed into a frequency index and the bed height into a height index, quantifying the risk of falling out of bed through linear combination. The position assessment module constructs a pressure ulcer risk assessment model by normalizing the exponential decay function of the static time and the pressure gradient. The comprehensive safety assessment module harmonizes and averages the bed safety coefficient and the position assessment coefficient to form a comprehensive safety assessment coefficient. The edge-height analysis module normalizes the edge distance and bed rail height, and then calculates the matching degree in conjunction with the comprehensive safety assessment coefficient. The bed board angle optimization module generates a baseline angle based on the vital signs analysis coefficients and the edge-height matching degree, then corrects the current angle through a dynamic adjustment factor, and finally outputs the target bed board angle.

[0074] Compared to existing technologies, traditional hospital beds only support single-parameter monitoring or manual adjustment, while this solution achieves synergistic optimization of vital signs, safety status, and patient comfort through multi-dimensional parameter fusion and a hierarchical evaluation model. Existing technologies rely on manual judgment of the matching relationship between bed rail height and bed height, while this solution automatically assesses the rationality of protective parameters through an edge-height matching degree model. Existing technologies use fixed thresholds to trigger alarms, while this solution achieves adaptive control of the angle adjustment range through dynamic adjustment factors.

[0075] Through the above technical solution, this application can monitor key parameters such as the patient's respiratory rate, blood oxygen saturation, and number of times the patient gets out of bed in real time, automatically assess the risk level of falling out of bed and pressure ulcers, dynamically optimize the bed board angle and bed rail protection status, reduce the frequency of medical staff patrols, reduce the risk of secondary injury caused by response delays, and maintain the balance between the patient's lying comfort and safety through a closed-loop adjustment mechanism.

[0076] Preferably, the working steps of the vital sign analysis module are as follows:

[0077] The respiratory rate index is obtained by performing maximum-min normalization on the respiratory rate.

[0078] Importing blood oxygen saturation into the blood oxygen index formula Blood oxygen saturation was obtained from the blood oxygen saturation index. Indicates blood oxygen sensitivity. Indicates blood oxygen saturation. This indicates the safe value for blood oxygen saturation;

[0079] A vital signs analysis model is constructed based on the respiratory rate index and blood oxygen index. The vital signs analysis model is expressed as follows:

[0080]

[0081] in, This represents the coefficient of vital sign analysis. Indicates respiratory rate index, This indicates the blood oxygen index. Represents the weight coefficient and The Furthermore, the higher the value, the more stable the vital signs;

[0082] Import the current respiratory rate index and current blood oxygen index into the vital signs analysis model to output the vital signs analysis coefficients;

[0083] The current vital sign analysis coefficient is compared with the preset vital sign coefficient threshold. If the current vital sign analysis coefficient is not within the threshold, an alarm message is generated.

[0084] The maximum-minimum normalization process involves linearly transforming the raw respiratory rate data according to a preset respiratory rate range, mapping the result to the 0-1 interval. Specifically, this can be achieved by subtracting the minimum respiratory rate from the measured respiratory rate and then dividing by the difference between the maximum and minimum respiratory rate values, thus eliminating the influence of individual patient differences on the data dimensions. The blood oxygen index (SOS) is a standardized index that converts blood oxygen saturation into a 0-1 interval through a nonlinear transformation containing an exponential function. Specifically, it can be achieved by using the relative deviation between the measured and safe blood oxygen saturation values ​​as input and adjusting the steepness of the blood oxygen sensitivity parameter control function curve, thereby enhancing sensitivity to abnormal blood oxygen values. The vital sign analysis model generates vital sign analysis coefficients by linearly combining the respiratory rate index and blood oxygen index according to preset weights. Specifically, it can be achieved by using a weighted summation method, adjusting the weight coefficients to balance the contribution of respiratory and blood oxygen indices to the overall stability of vital signs, and comprehensively assessing the stability of the patient's vital signs. The steepness adjustment method for the blood oxygen index formula is as follows: If... An increase in blood oxygen saturation leads to a steeper slope in the blood oxygen saturation index curve, corresponding to... More sensitive to change; assuming ,in for Clinically permissible range of fluctuation (e.g.) hour A 10% drop in blood oxygen levels triggers a penalty alert.

[0085] Specifically, after respiratory rate is collected, it is first converted into a respiratory rate index, which uses a max-min normalization method to eliminate the influence of individual patient differences on the data. Blood oxygen saturation data undergoes a nonlinear transformation to generate a blood oxygen saturation index. This transformation uses an exponential function to enhance sensitivity to deviations from safe thresholds; when blood oxygen levels fall below the safe threshold, the index value decreases rapidly. The respiratory rate index and blood oxygen saturation index are linearly combined according to preset weights to generate a vital sign analysis coefficient that comprehensively reflects the vital signs status. This coefficient is compared with preset thresholds in real time, and an alarm is automatically triggered when it exceeds the safe range. The entire process achieves quantitative assessment of vital signs through mathematical modeling, replacing the subjective judgment of traditional manual observation.

[0086] Compared to existing technologies, traditional hospital beds rely on medical staff to periodically check respiratory and blood oxygen data, resulting in long monitoring intervals and delayed detection of abnormalities. This solution achieves continuous monitoring and immediate early warning of vital signs by collecting data in real time and automatically performing mathematical modeling and analysis, thus solving the problem of low efficiency in manual rounds. Traditional methods cannot quantify and assess the correlation between vital sign data, while this solution establishes a collaborative analysis model of multi-dimensional vital sign parameters through normalization processing and weighted fusion mechanisms, improving the ability to identify complex abnormalities in vital signs.

[0087] Through the above technical solution, this application achieves real-time dynamic monitoring of the patient's respiratory rate and blood oxygen saturation. It automatically generates a vital sign safety factor through mathematical modeling and immediately triggers an alarm when abnormal breathing or insufficient blood oxygen is detected. This solution can promptly detect the risk of respiratory depression or decreased blood oxygen due to improper positioning, avoid monitoring gaps caused by manual rounds, and effectively reduce safety accidents caused by the failure to address abnormal vital signs in a timely manner.

[0088] Preferably, the working steps of the bed safety evaluation module are as follows:

[0089] Import the number of times the bed gets up per unit time into the formula. Obtain the bed exit frequency index, where, Indicates sensitivity to the number of times one gets out of bed. This indicates the number of times a person gets out of bed per unit of time. Indicates the standard number of times a person gets out of bed;

[0090] Import bed height into the formula Obtain the bed height index, among which, Indicates a high sensitivity coefficient. Indicates bed height. Indicates the ideal safe height for a bed;

[0091] A bed safety model is constructed based on the bed departure frequency index and the bed height index. The bed safety model is expressed as follows:

[0092]

[0093] in, Indicates the safety factor of the bed. Indicates the bed departure frequency index. Indicates the bed height index. Represents the weight coefficient and The The higher the value, the lower the risk of falling out of bed;

[0094] Import the current bed departure frequency index and the current bed height index into the bed safety model to output the current bed safety coefficient;

[0095] The current bed safety factor is compared with the preset bed safety factor threshold. If the current bed safety factor is not within the bed safety factor threshold, an alarm message is generated.

[0096] Among these, the sensitivity of bed-leaving frequency refers to a non-linear parameter that adjusts the impact of bed-leaving frequency on the safety factor. It can be determined using empirical values ​​or machine learning optimization methods, and is used to control the sensitivity of the exponential function to high-frequency bed-leaving behavior. The standard bed-leaving frequency refers to the baseline value of the number of bed-leavings allowed per unit time for normal nursing operations. It can be set according to the patient's activity level classification and is used to establish an assessment benchmark for bed-leaving behavior. The height sensitivity coefficient refers to the risk response intensity parameter when the bed height deviates from the ideal value. It can be determined through expert experience calibration or experimental data fitting, and is used to enhance the ability to identify abnormal height conditions. The ideal safe bed height refers to a preset reference height based on the patient's body type and nursing requirements. It can use the recommended values ​​in clinical nursing guidelines and is used to establish a baseline for height safety assessment.

[0097] Specifically, by collecting data on the number of times a person gets out of bed per unit time, this data is input into an exponential decay function for nonlinear transformation. When the actual number of times a person gets out of bed exceeds a standard value, the bed-getting frequency index rapidly approaches 1, highlighting the negative impact of abnormal bed-getting behavior on the safety factor. Simultaneously, the bed height is measured in real time and input into an S-shaped function for normalization. When the actual height is lower than the ideal safe height, the bed height index decreases nonlinearly as the height difference increases, strengthening the risk identification of low-height situations. The two indices are linearly combined according to preset weights to generate a bed safety factor that comprehensively reflects the risk of falling from bed. The weighting coefficients can be adjusted according to clinical needs to determine the contribution ratio of bed-getting behavior and height factors. By continuously monitoring the deviation between the safety factor and the threshold, a tiered early warning signal is triggered.

[0098] Compared to existing technologies, traditional bed safety assessments rely solely on a single height threshold or manual observation of bed-leaving behavior, failing to quantify the dynamic correlation between bed-leaving frequency and height changes. This proposed solution achieves multi-parameter fusion assessment through nonlinear function transformation, preserving the risk sensitivity of high-frequency bed-leaving behavior while enhancing the accuracy of identifying abnormal height states, thus overcoming the limitations of single-parameter assessments.

[0099] Through the above technical solution, this application can monitor the dynamic relationship between the frequency of patient getting out of bed and the bed height in real time, automatically calculate the comprehensive safety factor and trigger an early warning. When bedridden patients frequently get out of bed and the bed height is not set properly, the system can quickly identify the risk superposition state through a nonlinear model, issue an alarm in a timely manner to prompt medical staff to intervene, and effectively reduce the probability of bed falls caused by mismatch between getting out of bed and bed height.

[0100] Preferably, the working steps of the body position evaluation module are as follows:

[0101] The maximum pressure gradient in body position is normalized by the minimum to obtain the pressure gradient exponent in body position.

[0102] Import the maximum static time into the formula Obtain the postural rest time index, where, Indicates static time sensitivity. Indicates the maximum resting time in the body position. Indicates the duration of stillness in the standard body position;

[0103] A postural evaluation model is constructed based on the pressure gradient index and the postural rest time index. The postural evaluation model is expressed as follows:

[0104]

[0105] in, This represents the body position evaluation coefficient. Indicates the index of static body position. Indicates the pressure gradient exponent. Represents the weight coefficient and The Furthermore, the higher the value, the lower the risk associated with bed rest.

[0106] Import the current pressure gradient index and the current body position rest time index into the body position evaluation model to output the current body position evaluation coefficient;

[0107] The current posture evaluation coefficient is compared with the preset previous posture evaluation coefficient threshold. If the current posture evaluation coefficient is not within the posture evaluation coefficient threshold, an alarm message is generated.

[0108] Among them, the maximum pressure gradient of body position refers to the rate of pressure change between different areas within a unit area. Specifically, a pressure sensor array can be used to collect the pressure distribution data of the patient's body surface in real time, and the gradient value can be obtained by calculating the pressure difference between adjacent areas to reflect the degree of pressure on local tissues.

[0109] The maximum static time refers to the maximum duration for which a patient remains still in the same position. Specifically, it can be achieved by using an inertial measurement unit or image recognition technology to monitor changes in position and recording the duration of stillness with a timer, in order to assess the risk of pressure ulcers caused by prolonged stillness.

[0110] Among them, the body position pressure gradient index refers to a standardized index that maps the original pressure gradient value to the range of 0-1 through maximum-minimum normalization. Specifically, linear transformation can be used to eliminate dimensional differences and is used to quantify the uniformity of pressure distribution under different body positions.

[0111] Among them, the postural rest time index refers to converting rest time into a non-linear decay index through an exponential function. Specifically, the sensitivity coefficient can be adjusted using a preset standard time base to reflect the degree to which the rest time deviates from the safety threshold.

[0112] Among them, the positional assessment model refers to a comprehensive evaluation function constructed based on the weighted sum of squares of the pressure gradient index and the resting time index. Specifically, the risk deviation can be calculated using Euclidean distance and the weight allocation can be adjusted by coefficients to comprehensively judge the risk level of pressure ulcers.

[0113] Among them, the weighting coefficient It refers to the parameter used to adjust the importance of different factors in decision-making, and can be assigned values ​​through preset strategies or dynamic algorithms.

[0114] Specifically, a pressure sensor array collects real-time data on the patient's surface pressure distribution, calculates the maximum pressure gradient between different regions, and normalizes it to convert it into a pressure gradient exponent within the 0-1 range, eliminating the influence of different measurement units on the assessment results. Simultaneously, an inertial measurement unit monitors changes in patient position and records the maximum resting time. This is converted into a resting time exponent using an exponential function, which adjusts the response strength to time extension using a sensitivity coefficient. Both exponents are input into the positional assessment model, and a positional assessment coefficient is calculated using the square root of a weighted sum of squares. The weighting coefficients are optimized based on clinical data to balance the risk contribution of pressure distribution and resting time. When the assessment coefficient falls below a preset threshold, an alarm is triggered, prompting medical staff to adjust the patient's position or take decompression measures.

[0115] Compared to existing technologies, traditional hospital beds rely on manual, periodic checks of patient position and skin condition, failing to monitor pressure gradient changes and the cumulative effect of resting time in real time. This solution automatically quantifies pressure distribution and resting duration using sensor data, and dynamically assesses risk using nonlinear functions and weighted models. This solves the monitoring blind spot problem during manual inspection intervals, enabling early warning of pressure ulcer risk.

[0116] Through the above technical solution, this application can automatically trigger an early warning when there is abnormal pressure distribution on the patient's body surface or prolonged stillness, reducing the risk of pressure ulcers caused by delayed manual inspections. By normalizing and exponentially transforming the data, the differences in the dimensions of different parameters are eliminated, and the sensitivity to high-risk conditions is enhanced, ensuring the objectivity and timeliness of the assessment results. The introduction of a weighted model allows the risk contribution of pressure gradient and stillness time to be flexibly adjusted according to clinical needs, improving the accuracy of the assessment.

[0117] Preferably, the working steps of the comprehensive safety evaluation module are as follows:

[0118] The current bed safety factor and the current body position evaluation factor are imported into the comprehensive safety evaluation model to obtain the current comprehensive safety evaluation factor. The comprehensive safety evaluation model (harmonic average) is expressed as follows:

[0119]

[0120] in, This represents the comprehensive safety evaluation coefficient. Indicates the safety factor of the bed. The body position evaluation coefficient is represented by the following. Furthermore, the higher the value, the higher the overall security.

[0121] The current comprehensive safety evaluation coefficient is compared with the preset comprehensive safety evaluation coefficient threshold. If the current comprehensive safety evaluation coefficient is not within the comprehensive safety evaluation coefficient threshold, an alarm message is generated.

[0122] The bed safety factor is a quantitative value of the risk of falling out of bed calculated using parameters such as frequency of getting out of bed and bed height. It reflects the probability of a patient falling out of bed due to frequent getting out of bed or an excessively high bed. The positional evaluation factor is a quantitative value of the risk of pressure ulcers calculated using parameters such as positional pressure gradient and resting time. It can be implemented using a Euclidean distance model and reflects the risk of tissue damage caused by excessive local pressure or prolonged fixation in a position. The comprehensive safety evaluation factor is a synergistic assessment index that integrates bed safety and positional safety. It can be implemented using a harmonic mean model. When either safety factor decreases significantly, this index will respond quickly and trigger an alarm.

[0123] Specifically, during the dynamic assessment process, the harmonic mean formula is used to integrate the bed safety factor and the patient position evaluation factor. When the bed safety factor decreases due to a sudden increase in the number of times patients get out of bed, or when the patient position evaluation factor decreases due to excessive pressure gradient, the harmonic mean model causes the overall safety evaluation factor to exhibit a non-linear decay characteristic. This characteristic can detect situations where a single safety indicator is within the acceptable range but the overall safety status is abnormal. For example, when the bed height is within the safe range but the patient's position pressure continues to exceed the standard, the system can still generate an alarm in a timely manner based on the decrease in the overall coefficient. Furthermore, by setting a dynamic threshold comparison mechanism, when the overall safety evaluation factor falls below a preset lower limit threshold, an audible and visual warning signal is immediately triggered to prompt medical staff to intervene.

[0124] Compared to existing technologies, traditional hospital beds rely on a single indicator threshold to determine safety status, such as monitoring bed height or the number of times patients get out of bed, failing to identify risks coupled with multiple parameters. The arithmetic mean method used in existing technologies suffers from the drawback of high-risk parameters being diluted by low-risk parameters when calculating comprehensive safety indicators. This solution strengthens the weight of high-risk parameters through a harmonic mean model, enabling the system to respond quickly and issue warnings when any dimension of bed safety or patient positioning safety becomes abnormal.

[0125] Through the above technical solution, this application solves the problem that traditional hospital beds cannot dynamically assess the synergistic state of bed safety and postural risk, and achieves integrated monitoring of multi-dimensional safety parameters. When a patient exhibits a combined risk of frequent bed-leaning behavior and persistently excessive postural pressure, the system can trigger an early warning by rapidly decreasing the comprehensive safety coefficient, avoiding misjudgments caused by a single indicator being within acceptable limits. Furthermore, this solution reduces the risk of response delays caused by excessively long intervals between manual rounds during nighttime monitoring, providing real-time decision-making basis for pressure ulcer prevention and fall protection.

[0126] Preferably, the working steps of the edge-height analysis module are as follows:

[0127] The edge distance and bed rail height are processed by maximum-min normalization to obtain the edge distance index and bed rail height index;

[0128] An edge-height matching model is constructed based on the comprehensive safety evaluation coefficient, edge distance index, and bed rail height index. The edge-height matching model is expressed as follows:

[0129]

[0130] in, Indicates edge-height matching degree. Indicates the edge distance index. Indicates the bed rail height index. The comprehensive safety evaluation coefficient is represented by the following. Furthermore, the larger the value, the better the synergy between the edge distance and the bed rail height;

[0131] Import the current comprehensive safety evaluation coefficient, current edge distance index, and current bed rail height index into the edge-height matching model to obtain the current edge-height matching degree;

[0132] The current edge-height matching degree is compared with the preset edge-height matching degree threshold. If the current edge-height matching degree is not within the edge-height matching degree threshold, an alarm message is generated.

[0133] Among them, edge distance refers to the actual physical distance between the bedridden person and the edge of the bed, which can be achieved using laser rangefinders or image recognition technology. This involves measuring the straight-line distance between the patient's body edge and the bed rail in real time, providing raw data for normalization processing. Bed rail height refers to the vertical height of the guardrails on both sides of the bed, which can be achieved using ultrasonic sensors or mechanical encoders. This involves converting the displacement of the bed rail lifting device into a height value. Maximum-minimum normalization processing involves linearly mapping the raw data to the [0,1] interval to eliminate the incomparability between parameters of different dimensions. The comprehensive safety evaluation coefficient is a quantitative indicator reflecting the overall safety status of the bed. It can be generated by fusing the bed safety coefficient and the body position evaluation coefficient using a harmonic mean model, and is used to dynamically adjust the matching relationship between edge distance and bed rail height.

[0134] Specifically, this technical solution first normalizes the edge distance and bed rail height, converting the raw physical quantities into standardized indices. The edge distance index reflects the patient's relative position from the bed edge, while the bed rail height index reflects the actual height of the guardrail. These two indices, along with a comprehensive safety evaluation coefficient, are then input into a matching model. By calculating the deviation between the standardized distance and the dynamically adjusted ideal height, an edge-height matching degree is generated. The closer the matching degree is to 1, the better the coordination between the patient's position and the bed rail height, and the lower the risk of falling out of bed. When the matching degree falls below a preset threshold, the system automatically triggers an alarm, prompting medical staff to intervene and make adjustments. During this process, the comprehensive safety evaluation coefficient acts as a dynamic adjustment factor, adaptively adjusting the sensitivity of the matching model based on the overall safety status of the bed. For example, when the comprehensive safety evaluation coefficient is low, the system will enhance its monitoring sensitivity for insufficient bed rail height.

[0135] Compared to existing technologies, traditional hospital beds rely solely on static monitoring of bed rail height or patient position using a single parameter, failing to quantify the synergistic relationship between the two. For example, existing technologies typically set a fixed height threshold, triggering only a simple alarm when a patient approaches the bed edge, without considering the dynamic changes in protection requirements under different bed safety conditions. This solution constructs a matching model to transform the interaction between edge distance and bed rail height into a quantifiable matching index, and combines this with a comprehensive safety evaluation coefficient to achieve dynamic risk assessment. This multi-parameter coupled analysis method overcomes the shortcomings of traditional technologies, such as high false alarm rates and poor adaptability.

[0136] Through the above technical solution, this application can quantitatively assess the dynamic matching relationship between the patient's distance from the bed edge and the bed rail height in real time, and automatically calculate the cooperative safety level during changes in patient position or adjustments to bed height. When the matching degree deviates from the safe range, the system immediately generates an alarm message, effectively solving the problem of delayed bed fall warnings caused by static monitoring in traditional hospital beds. For example, when a patient turns over, causing an increase in the distance from the edge, the system automatically determines whether to raise the bed rails or issue an alarm based on the current bed safety status, thereby reducing the risk of bed falls caused by delayed protective measures.

[0137] Preferably, the steps of the bed board angle optimization module are as follows:

[0138] Import the current vital signs analysis coefficients into the formula. Obtain the reference angle, where, Indicates the minimum permissible bed board angle. This indicates the degree of angle adjustment, controlling the angle. This represents the current vital sign analysis coefficient;

[0139] Import the current vital sign analysis coefficients and the current edge-height matching degree into the formula. Obtain the safety adjustment factor. This represents the sensitivity coefficient to physical signs and safety. This indicates the threshold for the safety factor of vital signs. This represents the current vital sign analysis coefficient. Indicates the current edge-height matching degree;

[0140] The current bed board angle, safety adjustment factor, and reference angle are imported into the angle optimization model to output the target bed board angle. The angle optimization model is expressed as follows:

[0141]

[0142] in, Indicates the target bed board angle. Indicates the degree of angle adjustment. Indicates the safety adjustment factor. Indicates the reference angle. This indicates the current angle of the bed board.

[0143] The minimum allowable bed board angle refers to the minimum angle value that the system allows for adjustment. This can be achieved using a preset fixed angle value or a threshold dynamically adjusted based on the patient's weight, preventing discomfort or respiratory obstruction caused by excessively low angles. The angle adjustment range control angle refers to the adjustment range of the baseline angle relative to the minimum angle. This can be achieved using a linear coefficient correlated with the range of fluctuations in the patient's vital signs, controlling the sensitivity of changes in vital signs to angle adjustments. The safety adjustment factor is an adjustment parameter that considers the overall safety status of vital signs and the degree of matching with the bed's edge. This can be achieved using a nonlinear function to dynamically suppress deviations of vital signs from the safety threshold, automatically reducing the angle adjustment range when vital signs are abnormal. The angle optimization model is a mathematical model that makes incremental adjustments based on the difference between the current state and the target state, specifically using a sign function. The adjustment direction is determined and combined with a safety factor scaling step size to balance adjustment efficiency and operational safety. The sign function... Represented as:

[0144]

[0145] in, Indicates the reference angle. This indicates the current angle of the bed board.

[0146] Specifically, during the baseline angle generation process, a target reference value is formed by multiplying the vital sign analysis coefficient with the angle adjustment range control angle and then superimposing the minimum allowable angle, thus balancing the patient's physiological state with a safety baseline. During the safety adjustment factor calculation, the vital sign analysis coefficient and the edge-height matching degree are multiplied to reflect the overall safety level. A logical function then performs nonlinear suppression on the degree of vital sign deviation from the threshold. When the vital signs approach the danger threshold, the function output tends towards zero to limit the adjustment range. During angle optimization, a sign function determines the adjustment direction between the current angle and the baseline angle. A fixed step size is multiplied by the safety adjustment factor to form a dynamic adjustment amount, achieving an optimization mechanism that maintains the adjustment trend while automatically adjusting the step size according to the safety status.

[0147] Compared to existing technologies, traditional bed angle adjustments rely solely on preset programs or single sensor signals, failing to coordinate dynamic changes in vital signs and bed safety parameters. This proposed solution generates a safety adjustment factor through the coupled calculation of vital sign coefficients and edge matching degrees. It simultaneously considers the patient's physiological state and the risk of falling from bed during angle adjustment, employing a nonlinear inhibition mechanism to prevent misoperation in high-risk conditions. Compared to existing technologies, this solution offers advantages in multi-dimensional parameter collaborative control and safety self-adaptation.

[0148] Through the above technical solution, this application achieves the technical effect of dynamically adjusting the bed board angle according to the patient's real-time vital signs and bed safety status. When the vital signs are abnormal or the edge matching degree is insufficient, the adjustment range is automatically reduced, avoiding the risk of sudden changes in body position caused by single parameter control of traditional electric hospital beds. At the same time, the gradual adjustment mechanism takes into account both the efficiency and safety of body position optimization and reduces the frequency of manual intervention by medical staff.

[0149] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus.

[0150] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A heart-lung surgery postoperative care bed, characterized in that, The application relates to a bed plate angle adjusting system for adjusting a bed plate angle to change a patient lying angle, comprising: a sign analysis module for constructing a sign analysis model based on a breathing frequency and a blood oxygen saturation to output a sign analysis coefficient; a bed safety evaluation module for constructing a bed safety evaluation model based on a bed leaving frequency per unit time and a bed height to output a bed safety coefficient; a body position evaluation module for constructing a body position evaluation model based on a maximum body position static time and a body position maximum pressure gradient to output a body position evaluation coefficient; a comprehensive safety evaluation module for constructing a comprehensive safety evaluation model based on the bed safety coefficient and the body position evaluation coefficient to output a comprehensive safety evaluation coefficient; an edge-height analysis module for constructing an edge-height matching model based on an edge distance under the comprehensive safety evaluation coefficient and a bed rail height to output an edge-height matching degree; an angle optimization module for constructing an angle optimization model based on the sign analysis coefficient, the edge-height matching degree and a current bed plate angle to output a target bed plate angle. The working steps of the angle optimization module are as follows:

2. The cardio-surgical post-operative care bed of claim 1, wherein, the current bed plate angle, a safety adjusting factor and a reference angle are introduced into the angle optimization model to output the target bed plate angle, and the angle optimization model is expressed as: Importing the current sign analysis coefficient into the formula acquiring a reference angle, wherein denotes the minimum allowed bed plate angle, denotes the angle adjustment range control angle, denotes the current sign analysis coefficient; introducing the current sign analysis coefficient and the current edge-height match degree into the formula obtaining a safety regulation factor, representing a sign safety sensitivity coefficient, representing a sign safety coefficient threshold value, representing a current sign analysis coefficient, representing a current edge-height match degree; The working steps of the edge-height analysis module are as follows: wherein, represents a target deck angle, represents an angle adjustment magnitude, represents a safety adjustment factor, represents a reference angle, represents a current deck angle.

3. A cardio-respiratory post-operative surgical care bed according to claim 2, characterised in that, the edge distance and the bed rail height are subjected to maximum-minimum normalization processing to obtain an edge distance index and a bed rail height index; an edge-height matching model is constructed based on the comprehensive safety evaluation coefficient, the edge distance index and the bed rail height index, and the edge-height matching model is expressed as: the current comprehensive safety evaluation coefficient, the current edge distance index and the current bed rail height index are introduced into the edge-height matching model to obtain the current edge-height matching degree; wherein, represents the edge-height matching degree, represents the edge-distance index, represents the bedrail-height index, represents the comprehensive safety evaluation coefficient, the and the greater the value, the better the synergy of the edge distance and the bedrail height. the current edge-height matching degree is compared with a preset edge-height matching degree threshold value, and if the current edge-height matching degree is not within the edge-height matching degree threshold value, an alarm information is generated. The working steps of the sign analysis module are as follows:

4. A cardio-respiratory post-operative surgical care bed according to claim 3, characterised in that, a breathing frequency is subjected to maximum-minimum normalization processing to obtain a breathing frequency index; a sign analysis model is constructed based on the breathing frequency index and a blood oxygen index, and the sign analysis model is expressed as: The blood oxygen saturation is introduced into the formula to obtain the blood oxygen index, wherein, represents the blood oxygen sensitivity, represents the blood oxygen saturation, represents the blood oxygen saturation safety value; the current breathing frequency index and the current blood oxygen index are introduced into the sign analysis model to output the current sign analysis coefficient; wherein, represents a sign of the analysis coefficient, represents a sign of the respiratory rate index, represents a sign of the blood oxygen index, represents a sign of the weight coefficient and , the and the greater the value, the more stable the vital signs. the obtained current sign analysis coefficient is compared with a preset sign coefficient threshold value, and if the current sign analysis coefficient is not within the sign analysis coefficient threshold value, an alarm information is generated. The working steps of the comprehensive safety evaluation module are as follows:

5. A cardio-respiratory post-operative surgical care bed according to claim 4, characterised in that, the current bed safety coefficient and the current body position evaluation coefficient are introduced into the comprehensive safety evaluation model to obtain the current comprehensive safety evaluation coefficient, and the comprehensive safety evaluation model (harmonic average) is expressed as: the obtained current comprehensive safety evaluation coefficient is compared with a preset comprehensive safety evaluation coefficient threshold value, and if the current comprehensive safety evaluation coefficient is not within the comprehensive safety evaluation coefficient threshold value, an alarm information is generated. wherein, represents a comprehensive safety evaluation coefficient, represents a bed safety coefficient, represents a body position evaluation coefficient, and the and the greater the value, the higher the comprehensive safety. The working steps of the bed safety evaluation module are as follows:

6. A cardio-respiratory post-operative surgical care bed according to claim 5, characterised in that, a bed safety model is constructed based on the bed leaving frequency index and the bed height index, and the bed safety model is expressed as: The number of bed exits per unit time is introduced into the equation The bed exit frequency index is obtained, where, represents the bed exit number sensitivity, represents the bed exit number per unit time, represents the standard bed exit number; Introducing bed height into the equation Obtaining a bed height index, wherein, represents a height sensitivity coefficient, represents a bed height, represents a bed ideal safety height; ​ wherein, represents a bed safety coefficient, represents a bed exit frequency index, represents a bed height index, represents a weight coefficient and , said and the greater the value, the lower the risk of falling out of bed; The current bed leaving frequency index and the current bed height index are introduced into the bed safety model to output a current bed safety coefficient; The obtained current bed safety coefficient is compared with a preset bed safety coefficient threshold value, and if the current bed safety coefficient is not within the bed safety coefficient threshold value, an alarm information is generated.

7. The cardio-respiratory post-operative surgical care bed of claim 5, wherein, The working steps of the body position evaluation module are: The body position maximum pressure gradient is subjected to maximum-minimum normalization processing to obtain a body position pressure gradient index; Introducing the maximum positional stillness time into the equation Obtaining the positional stillness time index, wherein, represents the stillness time sensitivity, represents the maximum positional stillness time, represents the standard positional stillness time; A body position evaluation model is constructed based on the pressure gradient index and the body position static time index, and the body position evaluation model is represented as: wherein, represents a body position evaluation coefficient, represents a body position rest time index, represents a pressure gradient index, represents a weight coefficient and , the and the greater the value, the lower the risk of lying in bed position; The current pressure gradient index and the current body position static time index are introduced into the body position evaluation model to output a current body position evaluation coefficient; The obtained current body position evaluation coefficient is compared with a preset body position evaluation coefficient threshold value, and if the current body position evaluation coefficient is not within the body position evaluation coefficient threshold value, an alarm information is generated.

Images