Nursing sickbed safety monitoring system

Abstract

The invention discloses a safety monitoring system for a nursing sickbed. The safety monitoring system comprises a sensing module, a data transmission module, a data processing module, an alarm module and a display and interaction module. The sensing module collects physiological data and environmental data of a patient on a sickbed, the data transmission module transmits the data to the data processing module through wireless communication, and the data processing module performs anomaly detection and trend prediction based on the collected data and calculates a safety risk score of the patient. When the safety risk score exceeds a preset threshold value, the alarm module sends out an alarm signal. And the display and interaction module displays the real-time data, the risk score and the prediction result of the patient to a nurse, and supports the nurse to carry out interaction operation through a terminal. According to the system, by integrating various sensors and an advanced data processing technology, comprehensive monitoring and accurate early warning on the safety of a patient are achieved, the falling risk of the patient is effectively reduced, the nursing quality is improved, the workload of nursing personnel is relieved, and the medical cost is reduced.

Description

Technical Field

[0001] The invention relates to medical equipment, and in particular to a nursing bed safety monitoring system. Background Art

[0002] With the aging of the population and the shortage of medical resources, the demand for nursing care for the elderly and patients is growing. Traditional nursing methods often rely on manual monitoring, which not only increases the workload of nursing staff, but also poses safety risks due to untimely monitoring. In recent years, with the development of the Internet of Things, sensor technology and artificial intelligence, intelligent nursing systems have gradually become an important means to improve the quality and efficiency of nursing. However, the existing nursing bed monitoring systems often have single functions, cannot fully monitor the physiological and environmental status of patients, and have deficiencies in risk assessment and early warning. Therefore, it is of great practical significance to develop a nursing bed safety monitoring system that can monitor patients' physiological and environmental data in real time, accurately assess patients' safety risks, and issue early warnings in a timely manner. Summary of the invention

[0003] The purpose of the present invention is to provide a nursing bed safety monitoring system.

[0004] To achieve the above object, the present invention is implemented according to the following technical solutions:

[0005] The present invention includes a perception module, a data transmission module, a data processing module, an alarm module, and a display and interaction module. The perception module collects physiological data of a patient on a hospital bed and environmental data around the hospital bed; the data transmission module transmits the physiological data and environmental data to the processing module through wireless communication; the data processing module performs abnormality detection and trend prediction based on the collected physiological data and environmental data, and calculates the patient's safety risk score according to a preset algorithm; when the alarm module detects that the patient's safety risk score exceeds a preset threshold, it sends an alarm signal; the display and interaction module displays the patient's real-time data, risk score and prediction results to nursing staff, and supports nursing staff to perform interactive operations through a terminal.

[0006] Specifically, the sensing module includes a body motion sensor, a heart rate sensor, a breathing monitoring sensor, a body temperature sensor, a urine wetness alarm sensor, an ambient temperature sensor, an ambient humidity sensor, a light intensity sensor, a bed rail status sensor, and an under-bed pressure sensor.

[0007] The beneficial effects of the present invention are:

[0008] The present invention is a nursing bed safety monitoring system. Compared with the prior art, the present invention has the following significant technical effects:

[0009] Comprehensive monitoring: The system integrates multiple sensors to comprehensively collect the patient's physiological data (such as heart rate, respiration, body temperature, etc.) and environmental data (such as temperature and humidity, light intensity, etc.), providing all-round monitoring for patient safety.

[0010] Real-time risk assessment: The system can calculate the patient's safety risk score in real time based on the collected data, and take corresponding early warning measures according to the score to effectively prevent safety accidents such as falls.

[0011] Accurate early warning: Through advanced data processing and machine learning algorithms, the system can accurately identify abnormal vital signs of patients, predict future trends, and achieve accurate early warning.

[0012] Intelligent interaction: The system supports intelligent interaction with nursing staff, and displays patient data and warning information in real time through mobile apps and web interfaces, improving nursing response speed and efficiency.

[0013] Improve nursing quality: Through real-time monitoring and early warning, the system significantly improves the accuracy and efficiency of nursing work, reduces the workload of nursing staff, and improves patients' nursing experience.

[0014] Reduce medical costs: The system reduces medical costs and risks of medical institutions by reducing medical accidents caused by untimely monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a system structure principle block diagram of the present invention. DETAILED DESCRIPTION

[0016] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments. The illustrative embodiments and descriptions of the present invention are used to explain the present invention but are not intended to limit the present invention.

[0017] like Figure 1 As shown: the present invention includes a perception module, a data transmission module, a data processing module, an alarm module, and a display and interaction module. The perception module collects physiological data of the patient on the bed and environmental data around the bed; the data transmission module transmits the physiological data and environmental data to the processing module through wireless communication; the data processing module performs abnormality detection and trend prediction based on the collected physiological data and environmental data, and calculates the patient's safety risk score according to a preset algorithm; when the alarm module detects that the patient's safety risk score exceeds a preset threshold, it sends an alarm signal; the display and interaction module displays the patient's real-time data, risk score and prediction results to the nursing staff, and supports the nursing staff to perform interactive operations through the terminal.

[0018] Specifically, the sensing module includes a body motion sensor, a heart rate sensor, a breathing monitoring sensor, a body temperature sensor, a urine wetness alarm sensor, an ambient temperature sensor, an ambient humidity sensor, a light intensity sensor, a bed rail status sensor, and an under-bed pressure sensor.

[0019] Body motion sensor: embedded in the mattress of the nursing bed, it collects the patient's body motion data in real time, including the movement of getting out of bed and the frequency of turning over.

[0020] Heart rate and respiration monitoring sensors: The patient's heart rate and respiration rate are collected through non-contact infrared sensors and piezoelectric sensors.

[0021] Environmental sensors: monitor the temperature, humidity, light intensity, and bed rail status (whether they are raised) in the ward.

[0022] Data acquisition controller: uniformly collects and preliminarily processes the data of the above sensors, and converts the raw data into standardized digital signals.

[0023] Data transmission module: Wi-Fi and ZigBee wireless communication protocols are used to transmit data from the sensing module to the local server or cloud. The data transmission module has network disconnection detection and data caching functions. It caches data when the network is abnormal and re-uploads it after recovery.

[0024] Furthermore, the data processing module calculates the fall risk score in real time based on the patient's motion data and the pressure distribution data under the bed; the algorithm adopts a risk scoring model (RSM) with multi-feature fusion, combined with dynamic time warping (DTW) technology, to quantify the deviation between the patient's behavior and normal behavior.

[0025] Trend prediction: Based on the LSTM model, the patient's future heart rate and respiratory rate change trends are predicted. The model input is the physiological data sequence of the past 30 minutes, and the output is the trend prediction value of the next 10 minutes.

[0026] The fall risk score formula is:

[0027] R fall =α·D act +β·P dev +γ·V bed

[0028] Where: R fall : Fall risk score (0-1), the closer to 1, the higher the risk; D act : Action deviation distance, calculated by the dynamic time warping (DTW) algorithm, represents the difference between the current action and the safety template; P dev : The deviation of the pressure distribution under the bed, indicating the change of the body's center of gravity, is calculated through the body motion sensor data; Vbed : speed of getting out of bed, calculated using acceleration sensor data; α, β, γ: weight parameters, determined by regression optimization of historical data, satisfying α+β+γ=1; optimized through historical data, the values ​​are 0.4, 0.3, and 0.3 respectively.

[0029] Action deviation distance:

[0030]

[0031] Where: x i : The i-th feature point of the current action sequence; T i : the i-th feature point of the security template sequence; N: the length of the time series;

[0032] Deviation of pressure distribution under the bed:

[0033]

[0034] Where: p，x , σ p，y : standard deviation of pressure distribution in x and y directions; μ p，x , μ p，y : The mean of pressure distribution in x and y directions;

[0035] Bed exit speed:

[0036]

[0037] Where: Acceleration in three axes.

[0038] The alarm module detects the patient safety risk score using heart rate (HR), respiratory rate (RR) and body temperature (TEMP) data to detect anomalies and predict future vital signs trends; the algorithm is based on the long short-term memory network (LSTM) and the autoregressive integrated moving average model (ARIMA) to achieve anomaly detection and prediction of time series;

[0039] Anomaly detection model: Use Z-score to normalize vital sign data and trigger an alarm when it exceeds a certain range:

[0040]

[0041] Where: Z x : Vital sign x at the tth moment t Z score; μ x : mean of the time series; σ x : Standard deviation of the time series; if |Z x |>k, (usually k=2.5), it is judged as abnormal and the alarm module is triggered;

[0042] When the fall risk score R fall >0.8 or when vital signs are abnormal, the alarm module starts:

[0043] 1. The sound and light alarm device sends out an alarm signal.

[0044] 2. The system pushes risk alert information to the nursing staff’s mobile app, displaying the patient’s current status, risk cause, and recommended actions.

[0045] Trend prediction model:

[0046]

[0047] Where: x t+k : predict the vital sign value at the future time t+k; p, q: the order of autoregression (AR) and moving average (MA), determined by AIC or BIC method; φ i : autoregressive parameter; θ j : Moving average parameter; ∈ t-j : Residual sequence;

[0048] Time series forecasting, trend forecasting by training LSTM model: its update formula is:

[0049] f t =σ(W f ·[h t-1 ,x t ]+b f )

[0050] i t =σ(W i ·[h t-1 ,x t ]+b i )

[0051] o t =σ(W o ·[h t-1 ,x t ]+b o )

[0052]

[0053] h t =o t ☉tanh(C t )

[0054] Where: f t ,i t , o t : The activation values ​​of the forget gate, input gate, and output gate; W f , W i , Wo , W C : weight matrix; b f , b i , b o , b C : bias term; C t : unit status; h t : Output status.

[0055] Model optimization and integration:

[0056] Optimize weight parameters: Use patient historical data to optimize the weight parameters α, β, and γ of RSM through the gradient descent method; Model evaluation: Use cross-validation to evaluate model performance; Use RMSE (root mean square error) to measure the accuracy of the trend prediction model:

[0057]

[0058] Model integration: The results of RSM and LSTM are combined, and the weight distribution is dynamically adjusted according to the risk scenario.

[0059] Display and interaction module: The display and interaction module provides a nursing terminal (mobile phone app and web interface) with the following functions: Real-time viewing of the patient's physiological data (heart rate, respiratory rate, body movement, etc.) and trend prediction curves. Receive alarm information and risk scores. Support voice interaction, adjust system settings through voice commands, such as modifying alarm thresholds or obtaining specific patient reports.

[0060] System operation example:

[0061] A patient is lying on a smart nursing bed, and the system monitors the patient's heart rate, respiratory rate, number of turns, and bed rail status in real time. The system operation scenarios are as follows:

[0062] Normal state: patient's heart rate is 70 times / minute, respiratory rate is 18 times / minute, and there is no abnormal alarm.

[0063] Potential risk: The system detects that the patient is moving frequently while the bed rails are down. The calculated fall risk score is 0.85. The system pushes an alarm message to the nursing staff terminal that "the patient may try to get out of bed."

[0064] Abnormal status: Heart rate suddenly rises to 110 times / minute, respiratory rate drops to 10 times / minute. The system triggers an abnormal vital sign alarm, and it is recommended that nursing staff go to check immediately.

[0065] The implementation of this system can effectively reduce the risk of patients falling, monitor vital signs in real time, provide accurate risk assessment and trend prediction, and improve the efficiency and accuracy of nursing work.

[0066] The technical solution of the present invention is not limited to the above-mentioned specific embodiments. All technical variations made according to the technical solution of the present invention fall within the protection scope of the present invention.

Claims

1. A nursing bed safety monitoring system, characterized in that: It includes a perception module, a data transmission module, a data processing module, an alarm module, and a display and interaction module. The perception module collects the physiological data of the patient on the bed and the environmental data around the bed; the data transmission module transmits the physiological data and environmental data to the processing module through wireless communication; the data processing module performs abnormality detection and trend prediction based on the collected physiological data and environmental data, and calculates the patient's safety risk score according to a preset algorithm; When the alarm module detects that the patient's safety risk score exceeds a preset threshold, it sends an alarm signal; the display and interaction module displays the patient's real-time data, risk score and prediction results to the nursing staff, and supports the nursing staff to perform interactive operations through the terminal.

2. The nursing bed safety monitoring system according to claim 1, characterized in that: The sensing module includes a body motion sensor, a heart rate sensor, a breathing monitoring sensor, a body temperature sensor, a urine wetness alarm sensor, an ambient temperature sensor, an ambient humidity sensor, a light intensity sensor, a bed rail status sensor, and an under-bed pressure sensor.

3. The nursing bed safety monitoring system according to claim 2, characterized in that: The data processing module calculates the fall risk score in real time based on the patient's motion data and the pressure distribution data under the bed; the fall risk score formula is: R fall =α·D act +β·P dev +γ·V bed Where: R fall : Fall risk score; D act : Action deviation distance; P dev : Deviation of pressure distribution under the bed, indicating the change of body center of gravity; V bed : bed exit speed, calculated using acceleration sensor data; α, β, γ: weight parameters, determined by regression optimization of historical data; Action deviation distance: Where: x i : The i-th feature point of the current action sequence; T i : the i-th feature point of the security template sequence; N: the length of the time series; Deviation of pressure distribution under the bed: Where: p，x , σ p，y : standard deviation of pressure distribution in x and y directions; μ p，x , μ p，y : The mean of pressure distribution in x and y directions; Speed ​​of getting out of bed: Where: Acceleration in three axes.

4. The nursing bed safety monitoring system according to claim 3, characterized in that: The alarm module detects that the patient safety risk score uses heart rate, respiratory rate and temperature data to detect abnormalities and predict future vital sign trends; Anomaly detection model: Use Z-score to normalize vital sign data and trigger an alarm when it exceeds a certain range: Where: Z x : Vital sign x at the tth moment t Z score; μ x : mean of the time series; σ x : Standard deviation of the time series; if |Z x |>k, it is considered abnormal; Trend prediction model: Where: x t+k : predict the vital sign value at the future time t+k; p, q: the order of autoregression and moving average; φ i : autoregressive parameter; θ j : Moving average parameter; ∈ t-j : Residual sequence; Time series forecasting: Its update formula is: f t =σ(W f ·[h t-1 ,x t ]+b f ) i t =σ(W i ·[h t-1 ,x t ]+b i ) the t =σ(W o ·[h t-1 ,x t ]+b o ) h t =o t ☉tanh(C t ) Where: f t ,i t , o t : The activation values ​​of the forget gate, input gate, and output gate; W f , W i , W o , W C : weight matrix; b f , b i , b o , b C : bias term; C t : unit status; h t : Output status.

Images