Wireless monitoring and early warning system for vital signs of critical patients on emergency transfer bed

Abstract

This invention provides a wireless monitoring and early warning system for vital signs on a transport bed for critically ill patients in the emergency department. The system collects vital sign signals from patients non-contactly or semi-contactly through a wireless sensor array integrated into the transport bed. After preprocessing by a bedside edge computing node, the signals are transmitted to a central monitoring server via a dual-mode wireless communication network. The server runs intelligent analysis algorithms to perform real-time analysis and risk assessment of the data. When an abnormality is detected, a tiered early warning is triggered, and the information is pushed to the terminals of relevant medical staff. Simultaneously, the system automatically records all data and synchronizes it to the hospital information system, achieving continuous monitoring and traceable management throughout the entire process.

Description

Technical Field

[0001] This invention relates to the field of emergency transport equipment technology, and in particular to a wireless monitoring and early warning system for vital signs on an emergency critical patient transport bed. Background Technology

[0002] Intra-hospital transport of critically ill emergency patients is a high-risk aspect of emergency medical care. According to statistics from the American College of Emergency Physicians, approximately 15%-20% of critically ill emergency patients experience varying degrees of deterioration during transport, and 60% of these adverse events are directly related to discontinuous vital sign monitoring and untimely warnings during transport.

[0003] Currently, emergency patient transport mainly relies on traditional portable monitors, which have the following fatal flaws: 1. Severe lead wire constriction and high risk of missed lead wire dislodgement: Traditional monitors require 5-7 leads. During transport, changes in patient position, stretcher handling, and bed transfers can easily cause lead wire dislodgement and electrode displacement, resulting in data interruption or errors. Statistics show that lead wire dislodgement causes monitoring interruptions in traditional transport monitoring up to 35%, making it the most common adverse transport event.

[0004] 2. Discontinuous monitoring and blind spots: During the transfer of patients from the emergency room to examination departments (CT, MRI, DSA) or the ICU, the monitor leads need to be repeatedly plugged and unplugged, resulting in patients being unmonitored during bed transfers, elevator rides, and examinations. On average, each transfer creates a 15-20 minute blind spot. Changes in the patient's condition during this period cannot be detected in time, which can easily lead to serious consequences.

[0005] 3. Limited warning functions and low level of intelligence: Traditional monitors can only implement single-parameter fixed threshold alarms, and cannot dynamically adjust based on the patient's underlying diseases, disease severity, and transport risks. For special patients such as those with hypertension or arrhythmia, fixed thresholds are prone to generating a large number of false alarms, leading to alarm fatigue among medical staff and causing genuine danger signals to be ignored.

[0006] 4. Data cannot be shared in real time, resulting in low collaboration efficiency: Data from traditional portable monitors can only be displayed locally and cannot be transmitted to the nursing station and receiving department in real time. Changes in the patient's condition during transport can only be communicated verbally by medical staff, leading to inaccurate and untimely information transmission and potential handover errors.

[0007] 5. Lack of location tracking capabilities and slow emergency response: When an emergency occurs during patient transport, medical staff cannot quickly locate the patient's exact location, delaying rescue time. This is especially true in large tertiary hospitals with complex departmental layouts, where locating the patient often takes 5-10 minutes, severely impacting rescue efficiency.

[0008] 6. Data cannot be automatically archived, making it difficult to trace medical quality: Data from traditional patient monitors cannot be automatically synchronized to the hospital's HIS and EMR systems during transport. This requires manual recording by medical staff, increasing workload and increasing the risk of errors and omissions. The inability to fully trace medical data during transport hinders medical quality control and dispute resolution.

[0009] In recent years, although some wireless monitoring products have emerged, they still have significant shortcomings: most products only achieve wireless data transmission without solving the problems of lead wire constraints and repeated plugging and unplugging; a few wireless sensing products have problems such as low measurement accuracy, short battery life, and poor anti-interference ability, which cannot meet the requirements of medical-grade applications; they lack intelligent early warning and location tracking functions, and the data cannot be seamlessly integrated with hospital information systems. Summary of the Invention

[0010] To address the technical problems existing in the prior art, the present invention provides the following technical solution: A wireless monitoring and early warning system for vital signs on an emergency critical patient transport bed includes: The transport bed integrates a wireless sensor array module, which is integrated into the adjustable bed rail of the transport bed, for non-contact acquisition of non-invasive blood pressure, pulse oximetry, three-lead ECG and body temperature signals of patients. The bedside edge computing and wireless transmission module is built into the transport bed rail and is electrically connected to the wireless sensor array module. It is used to preprocess and extract features from the collected raw signals and upload the data to the central monitoring server through LoRa+WiFi dual-mode communication. The central monitoring server module, deployed in the hospital's central computer room, is wirelessly connected to the edge computing module. It is used to receive, store, and analyze vital sign data, run intelligent early warning algorithms, trigger tiered early warnings, and manage all devices and users of the system. The multi-terminal interaction module includes a central monitoring screen at the nurse station, a mobile terminal for medical staff, and a local terminal for the transport bed. It is communicatively connected to the central monitoring server module and is used to display real-time vital signs data, receive early warning information, and perform human-computer interaction. The hospital information system interface module communicates with the central monitoring server module to enable data interaction and sharing between this system and the hospital's HIS and EMR systems.

[0011] Preferably, the integrated wireless sensor array module of the transfer bed includes: The non-invasive blood pressure sensing unit consists of two symmetrically distributed auto-inflating airbags and pressure sensors, integrated into the upper arm support of the bed rail, and is used to collect the patient's systolic blood pressure, diastolic blood pressure and mean arterial pressure. The pulse oximetry sensing unit consists of two reflective photoelectric sensors integrated into the bed rail armrest, used to collect the patient's blood oxygen saturation and pulse rate; The three-lead ECG sensing unit consists of three capacitively coupled electrodes integrated into the back of the bed rail for non-contact acquisition of the patient's ECG signals. The infrared body temperature sensing unit consists of a non-contact infrared temperature sensor integrated above the bed rail to collect the patient's core body temperature. The UWB indoor positioning unit consists of a UWB tag integrated into the bottom of the bed rail for real-time location of the patient.

[0012] Preferably, the bedside edge computing and wireless transmission module includes: The main control unit uses an STM32H743ZI microcontroller for logic control and data processing; The signal preprocessing unit is used to amplify, filter, and denoise the raw physiological signals; The feature extraction unit is used to extract clinical feature parameters from the preprocessed signal; The dual-mode wireless communication unit integrates a LoRa module and a WiFi module, automatically detects signal strength and switches communication modes to achieve seamless coverage throughout the hospital. The power management unit uses a 10000mAh lithium polymer battery, which can work continuously for 72 hours on a single charge; The local alarm and display unit is used to display vital sign data and trigger local audible and visual alarms.

[0013] Preferably, the central monitoring server module includes: The data receiving and storage unit uses a MySQL relational database and an InfluxDB time-series database to store patients' basic information, vital signs data, and early warning events. The real-time analysis engine, based on the Apache Flink real-time computing framework, continuously analyzes real-time data and calculates the patient's comprehensive transport risk score. The intelligent early warning system, based on a multi-parameter weighted risk scoring algorithm, enables tiered intelligent early warning and pushes the warning information to relevant terminals. The location service unit, based on UWB positioning technology, enables real-time location tracking and dynamic path planning for patients.

[0014] Preferably, the multi-terminal interaction module includes: The central monitoring screen at the nurses' station is used to display the vital signs, location, and status of all transferred patients globally, and to handle early warning events. Medical mobile terminals are carried by medical staff to view real-time data of the patients they are responsible for, receive early warning push notifications, and handle early warning events. The local terminal for the transport bed is used to display the patient's basic vital signs and equipment status, and to trigger audible and visual alarms locally.

[0015] Preferably, the working mechanism of the dual-mode wireless communication unit is as follows: when the WiFi signal strength is ≥-70dBm, WiFi is used to transmit data; when the WiFi signal strength is <-70dBm, it automatically switches to LoRa communication.

[0016] Preferably, the intelligent early warning system employs a dynamic threshold adjustment method, calculating the early warning threshold for each parameter based on the patient's basic vital signs and APACHE II score:

[0017] in, Let i be the warning threshold for the i-th parameter. This is the patient's baseline value. This represents the normal standard deviation of the parameter. This is the adjustment factor determined based on the APACHE II score.

[0018] Preferably, the intelligent early warning system uses a multi-parameter weighted risk scoring algorithm to calculate the comprehensive transportation risk score:

[0019] in, , , , , These are standardized scores for systolic blood pressure, heart rate, blood oxygen saturation, body temperature, and arrhythmia. , , , , These are the weighting coefficients for each parameter; based on TRS, the warning is divided into four levels: low, medium, high, and extremely high risk.

[0020] Preferably, the hospital information system interface module adopts the HL7 v3.0 standard protocol, which automatically synchronizes vital sign data, early warning events and transfer handover reports during the transfer process to the patient's electronic medical record, so as to realize the permanent archiving and traceability of data.

[0021] Preferably, the transfer and handover method of the system is as follows: after the transfer is completed, the system automatically generates a standardized electronic transfer and handover report, which includes the patient's basic information, vital sign trends, early warning events and handling measures; after both parties confirm the transfer by electronic signature on their mobile terminals, the report is automatically archived and synchronized to the electronic medical record.

[0022] The beneficial effects of the technical solutions provided by the embodiments of the present invention include at least the following: 1. Integrated leadless sensor technology completely solves the problem of lead wire constraints: This invention is the first to integrate non-invasive blood pressure, blood oxygen, ECG, and body temperature sensors onto the transport bed rail, achieving vital sign acquisition without lead wires or electrode pads. Patients only need to lie on the transport bed for automatic monitoring, completely avoiding the problems of lead wire detachment and repeated plugging and unplugging in traditional monitors, reducing the monitoring interruption rate to 0%.

[0023] 2. Edge computing + dual-mode communication architecture enables seamless continuous monitoring throughout the hospital: Utilizing a bedside edge computing architecture, raw signals are pre-processed locally, reducing data transmission volume by 90% and controlling end-to-end latency to within 100ms. Innovative LoRa + WiFi dual-mode communication technology automatically switches to LoRa communication in areas with weak WiFi signals, achieving zero communication blind spots throughout the hospital and ensuring continuous monitoring from the emergency room to examination departments or ICUs, eliminating safety blind spots.

[0024] 3. A tiered intelligent early warning system based on multi-parameter weighted risk scoring significantly reduces the false alarm rate: A dynamic early warning threshold model combining the patient's underlying disease and the severity of their condition, along with a multi-parameter weighted risk scoring algorithm, was constructed to achieve accurate tiered intelligent early warning. The false alarm rate was reduced to below 15%, effectively avoiding alarm fatigue among medical staff and improving the accuracy and reliability of the early warning system.

[0025] 4. UWB high-precision indoor positioning and dynamic path planning significantly shorten emergency response time: Integrating UWB indoor positioning technology, the system achieves a positioning accuracy of 30cm. When an emergency alert is issued, the system automatically displays the patient's precise location and the location of the nearest emergency personnel, and plans the shortest rescue route. The average alert response time is reduced from 5-30 minutes to 1-2 minutes, gaining valuable time for the rescue of critically ill patients.

[0026] 5. Automatic synchronization and end-to-end traceability of medical data improves medical quality and handover efficiency: Seamless integration with hospital HIS and EMR systems via the HL7 standard protocol automatically synchronizes all transfer data and alert events to electronic medical records. Standardized electronic transfer handover reports are generated, enabling full traceability of the transfer process. The average transfer handover time has been reduced from approximately 20 minutes to less than 5 minutes, and the handover error rate has been reduced to zero, improving medical quality and work efficiency.

[0027] 6. Low power consumption and long battery life design to meet the needs of 24-hour uninterrupted use in emergency rooms: Utilizing low-power sensors and advanced power management technology, it can work continuously for more than 72 hours on a single charge. Supports wireless charging and fast charging to meet the needs of 24-hour uninterrupted use in emergency rooms.

[0028] 7. Modular design, easy deployment and expansion: The system adopts a modular design, and the sensor array and edge computing module can be customized and installed according to different models of transport beds, without the need for large-scale modification of the transport beds. The system supports smooth expansion, and the number of transport bed terminals can be increased according to the needs of the hospital, making it suitable for promotion and application in hospitals at all levels.

[0029] 8. Significant Socioeconomic Benefits: The application of this system can significantly reduce the incidence of adverse transport events and medical disputes, and shorten patients' hospital stays and medical expenses. At the same time, it improves the work efficiency of medical staff and alleviates the shortage of emergency medical personnel, thus demonstrating good social and economic benefits. Attached Figure Description

[0030] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0031] Figure 1 This is a design highlight diagram of the system; Figure 2 This is a schematic diagram of a system architecture provided by the present invention; Figure 3 This is a schematic diagram of the blood pressure sensor layout and control of the present invention; Figure 4 This is a schematic diagram of the system deployment of the UWB indoor positioning unit of the present invention; Figure 5 This is a schematic diagram of the control system for the bedside edge computing and wireless transmission module of the present invention. Detailed Implementation

[0032] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0033] In embodiments of the present invention, words such as "exemplarily," "for example," etc., are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "exemplary" is intended to present the concept in a concrete manner. Furthermore, in embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one.

[0034] In the embodiments of this invention, the terms "image" and "picture" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning. Similarly, the terms "of," "corresponding (relevant)," and "corresponding" may sometimes be used interchangeably. It should be noted that, without emphasizing the distinction between them, they convey the same meaning.

[0035] In this embodiment of the invention, sometimes a subscript such as W1 may be mistakenly written as a non-subscript form such as W1. When the difference is not emphasized, the meaning they express is the same.

[0036] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0037] I. System Design Highlights of this Application This invention discloses a wireless monitoring and early warning system for vital signs on an emergency critical patient transport bed. The system integrates non-invasive blood pressure, pulse oximetry, three-lead ECG and infrared body temperature sensors on the adjustable bed rails of the transport bed to form an integrated wireless sensor array. The patient only needs to lie on the transport bed to automatically complete the collection of vital signs without the need to stick or unplug any lead wires.

[0038] The edge computing nodes built into the bed rails perform real-time preprocessing and feature extraction on the collected raw signals, and transmit the data to the central monitoring server via a LoRa+WiFi dual-mode wireless communication module. The central monitoring server runs an intelligent early warning algorithm based on a multi-parameter weighted risk score, dynamically adjusting the early warning threshold based on the patient's underlying diseases and the severity of their condition. When any parameter exceeds the threshold or the comprehensive risk score reaches the warning level, the system automatically triggers a tiered audible and visual alarm and pushes the patient's real-time vital signs, location information, and warning level to the central monitoring screen at the nurses' station and the mobile terminals of medical staff.

[0039] The system automatically records all transport data, generates standardized transport handover reports, and synchronizes them in real time to the hospital's HIS and EMR systems via the HL7 protocol, achieving permanent archiving and traceability of transport data. This invention completely solves the problems of lead wire constraints, discontinuous monitoring, untimely early warning, and inability to share data in traditional transport monitoring. It achieves seamless and continuous monitoring from the emergency room to the examination department or ICU, significantly reducing the incidence of adverse transport events and improving the transport safety of critically ill emergency patients.

[0040] This system can significantly reduce the incidence of adverse transport events, improve the safety and efficiency of emergency transport, and safeguard the lives of critically ill patients.

[0041] like Figure 1The design innovations shown are explained below. The specific innovations of this system are as follows: 1. Integrated leadless sensor array, completely eliminating the constraints of lead wires: All vital sign sensors are integrated into the adjustable bed rails of the transport bed. Patients do not need to attach any electrode pads or lead wires; they can automatically complete vital sign collection simply by lying on the transport bed. This completely solves the problem of lead wires falling off and requiring repeated plugging and unplugging in traditional monitors, reducing the monitoring interruption rate to below 0.5%.

[0042] 2. Bedside edge computing architecture for low-latency real-time monitoring: Edge computing nodes are built into the transport bed rails to perform local preprocessing and feature extraction of raw physiological signals, uploading only the analyzed feature data to the server. Data transmission volume is reduced by 90%, and end-to-end latency is controlled within 100ms, meeting the requirements of real-time monitoring.

[0043] 3. LoRa+WiFi dual-mode wireless communication for seamless coverage throughout the facility: Utilizing a dual-mode communication architecture that combines LoRa long-range, low-power communication with WiFi high-speed communication. High-definition data is transmitted via WiFi in areas with strong WiFi signal, while automatically switching to LoRa communication in areas with weak WiFi signal (such as elevators, stairwells, and basements), ensuring no communication blind spots throughout the facility.

[0044] 4. Tiered intelligent early warning algorithm to reduce false alarms and improve accuracy: An intelligent early warning model based on multi-parameter weighted risk scores is constructed, and the early warning threshold is dynamically adjusted in combination with the patient's underlying diseases, disease severity, and transfer risks. Early warnings are divided into four levels: low, medium, high, and extremely high risk, with different alarm methods and response procedures, reducing the false alarm rate by more than 75%.

[0045] 5. Real-time location tracking and emergency response system: Each transport bed is equipped with a built-in UWB indoor positioning module, achieving a positioning accuracy of 30cm. In the event of an emergency alert, the system automatically displays the patient's precise location and the location of the nearest medical staff, guiding them to the scene quickly, reducing emergency response time by 60%.

[0046] 6. Automatic Synchronization and Full Traceability of Medical Data: The system seamlessly integrates with the hospital's HIS and EMR systems via the HL7 v3.0 standard protocol, automatically synchronizing all transfer data and alert events to the patient's electronic medical record. It generates standardized transfer and handover reports, achieving full traceability of the transfer process and improving medical quality and handover efficiency.

[0047] 7. Low power consumption and long battery life design to meet the needs of long-term transport: Utilizing low-power sensors and power management technology, and a built-in high-capacity lithium battery, it can work continuously for more than 72 hours on a single charge. Supports wireless charging and fast charging to meet the needs of 24-hour uninterrupted use in emergency departments.

[0048] The specific application components and working principle of this system will be introduced below.

[0049] II. System Principles The core working principle of this system is to collect patients' vital signs signals non-contactly or semi-contactly through a wireless sensor array integrated into the transport bed. After preprocessing by bedside edge computing nodes, the signals are transmitted to the central monitoring server via a dual-mode wireless communication network. The server runs intelligent analysis algorithms to perform real-time analysis and risk assessment of the data. When an abnormality is detected, a tiered warning is triggered, and the information is pushed to the terminals of relevant medical staff. Simultaneously, the system automatically records all data and synchronizes it to the hospital information system, achieving continuous monitoring and traceable management throughout the entire process.

[0050] III. System Composition like Figure 2 As shown, this system mainly consists of a transfer bed integrated wireless sensor array module, a bedside edge computing and wireless transmission module, a central monitoring server module, and a multi-terminal interaction module.

[0051] (a) Integrated wireless sensor array module for transfer bed This module, integrated into the adjustable bed rails of the transport bed, serves as the system's sensing layer, responsible for non-contact acquisition of the patient's vital signs. Its modular design allows for customized installation to different transport bed models, eliminating the need for extensive modifications to the transport bed itself.

[0052] 1. Non-invasive blood pressure sensing unit Non-invasive blood pressure measurement uses the oscillation method. An air bladder integrated into both sides of the bed automatically inflates and pressurizes, blocking blood flow to the brachial artery, and then slowly deflates. During deflation, the pulsation of the artery causes pressure oscillations within the air bladder. Pressure sensors collect the pressure change signals within the air bladder, and by analyzing the amplitude and frequency of the oscillation waves, the systolic blood pressure (SBP), diastolic blood pressure (DBP), and mean arterial pressure (MAP) are calculated.

[0053] like Figure 3 The diagram shows the layout and control of the blood pressure sensor. This unit consists of two symmetrically distributed self-inflating airbags, a high-precision pressure sensor (example model: Freescale MPXV5050GP, hereinafter the same), an inflation pump, and a deflation valve. The airbags are integrated into the upper arm support of the bed rail, so that the upper arm rests naturally on the airbag when the patient is lying on the transport bed. The measurement range is 0-300 mmHg, the accuracy is ±2 mmHg, the measurement cycle is adjustable from 1 to 5 minutes, and the inflation time is <10 seconds.

[0054] Once the system is started, the inflation pump automatically inflates the cuff to a preset pressure (30 mmHg higher than the patient's systolic blood pressure) and then slowly deflates it. Pressure sensors collect real-time pressure change signals within the cuff (sampling frequency 100 Hz) and transmit them to an edge computing node for processing, calculating the systolic blood pressure, diastolic blood pressure, and mean arterial pressure.

[0055] 2. Pulse oxygenation sensor unit Pulse oximetry was measured using photoplethysmography (PPG). Light-emitting diodes integrated into the bed rails emitted 660nm red light and 940nm infrared light, which were transmitted through the patient's skin and received by photodiodes. Since oxyhemoglobin and deoxyhemoglobin have different absorption coefficients for different wavelengths of light, the changes in the absorption intensity of the two types of light were analyzed to calculate blood oxygen saturation (SpO2) and pulse rate (PR).

[0056] In practical implementation, it can consist of two reflective photoelectric sensors (model: TIOPT3001) integrated into the bed rails, corresponding to the patient's left and right hands respectively. Each sensor includes a 660nm red LED, a 940nm infrared LED, and a photodiode. The blood oxygen saturation measurement range is 70%-100%, with an accuracy of ±2%; the pulse rate measurement range is 30-250 beats / min, with an accuracy of ±1 beat / min.

[0057] An LED emits light of a specific wavelength, which shines onto the patient's finger skin. A photodiode receives the reflected light (sampling frequency 200Hz). Because oxyhemoglobin and deoxyhemoglobin have different absorption coefficients for different wavelengths of light, the intensity of the reflected light varies with the pulse cycle. By analyzing the intensity changes of the two types of light, blood oxygen saturation and pulse rate are calculated.

[0058] 3. Three-lead ECG sensing unit Three-lead ECG measurement employs capacitively coupled non-contact ECG sensing technology. Three capacitive electrodes integrated into the back of the bed rail form coupling capacitance with the patient's body through their clothing, detecting the weak electric field changes generated by the heart's electrical activity. After amplification, filtering, and A / D conversion, the signal is reconstructed to reproduce a standard lead II ECG waveform, from which heart rate (HR) and arrhythmia events can be calculated.

[0059] For clinical application, it consists of three capacitively coupled electrodes (model: TIADS1292R) integrated into the back of the bed rail, corresponding to the electrode positions of the right arm (RA), left arm (LA), and left leg (LL), respectively. The electrodes are made of conductive silicone material with an insulating layer on the surface, eliminating the need for direct contact with the skin.

[0060] The electrode technical parameters are as follows: input impedance ≥1GΩ, common mode rejection ratio ≥110dB, sampling frequency 1000Hz, bandwidth 0.05-100Hz.

[0061] When the patient lies on the transport bed with their back in contact with the bed rails, electrodes form a coupling capacitance with the body through clothing, detecting the weak electric field changes generated by the heart's electrical activity (sampling frequency 1000Hz). After differential amplification, filtering, and A / D conversion, the signal is restored to a standard lead II ECG waveform, and the output is a digital ECG signal.

[0062] The following is a method for processing electrocardiogram (ECG) signals. R-wave detection is fundamental to electrocardiogram (ECG) signal analysis. This system employs an R-wave detection algorithm based on wavelet transform and adaptive thresholding, with the following steps: The preprocessed electrocardiogram signal was decomposed into 3-level db6 wavelet decomposition to obtain the detail coefficients D1, D2, D3 and approximation coefficients A3 of each level; For detail coefficient D2 (obtained by multiple sampling) Squaring D3 and D3 (similarly processed) enhances the characteristics of the R-wave. ; Adding the squared detail coefficients together yields the comprehensive feature signal: ; Perform a sliding window integration on the comprehensive feature signal, with a window length of 80ms: , k represents the kth time, where, For window length, The sampling frequency; Calculate the adaptive threshold: The threshold is dynamically adjusted according to the maximum signal value within the first 200ms to adapt to the amplitude of the ECG signal of different patients. When the integral signal Exceeding the threshold When the refractory period condition is met (interval with the previous R wave > 200ms), it is determined that an R wave has been detected. Calculate heart rate based on the position of the R wave: in, This represents the number of sampling points between two adjacent R-waves.

[0063] The algorithm achieves an R-wave detection accuracy of over 99.5% and can effectively resist motion artifacts and noise interference.

[0064] 4. Infrared body temperature sensing unit Body temperature measurement employs non-contact infrared thermometry technology. An infrared temperature sensor integrated above the bed rail measures the infrared radiation energy from the patient's forehead and calculates the patient's core body temperature (T) using the blackbody radiation law. The measurement accuracy reaches ±0.2℃, and the response time is less than 1 second.

[0065] The infrared body temperature sensing unit consists of a non-contact infrared temperature sensor (model: Melexis MLX90614, measurement range 32-42℃, accuracy ±0.2℃, response time <1 second, measurement distance 5-30cm) integrated above the bed rail. The sensor can be adjusted up, down, left and right to be aimed at the patient's forehead.

[0066] The sensor receives infrared radiation energy emitted from the patient's forehead, converts the radiation energy into a temperature value using the blackbody radiation law, and outputs a digital body temperature signal with a sampling frequency of 1Hz. The system automatically compensates for the influence of ambient temperature to improve measurement accuracy.

[0067] 5. UWB Indoor Positioning Unit The UWB indoor positioning unit consists of a UWB tag (model: Decawave DW1000) integrated into the bottom of the bed rail and UWB base stations deployed on various floors of the hospital (deployment and control diagram shown). Figure 4 (As shown).

[0068] UWB tags have a positioning accuracy of ±30cm, an update frequency of 1Hz, and a communication distance of 100 meters. The UWB tag periodically transmits ultra-wideband pulse signals. After receiving the signals, the base station calculates the time difference of arrival (TDOA) to determine the tag's precise location, outputting the patient's real-time location coordinates (X, Y, Z). Location information is uploaded to the central server via edge computing nodes.

[0069] The principle of its base station positioning can be understood by combining it with the working principle of UWB tags.

[0070] (ii) Bedside edge computing and wireless transmission module This module is built into the control box of the transfer bed rail and is the edge processing layer of the system. It is responsible for preprocessing, feature extraction and wireless transmission of the raw signals collected by the sensor array.

[0071] like Figure 5 As shown, this module includes the following facilities: 1. Main control unit It is responsible for the logic control, data processing, and task scheduling of the entire module. After acquiring and processing the digital signals from each sensing unit, it outputs preprocessed feature data and control commands.

[0072] The main control unit can be a microcontroller (such as STMicroelectronics STM32H743ZI), based on the ARM Cortex-M7 core, with a main frequency of 400MHz, and built-in 2MB Flash and 1MB RAM.

[0073] 2. Signal preprocessing unit The raw physiological signals are amplified, filtered, converted from digital to digital (A / D), and denoised to improve signal quality.

[0074] The raw physiological signal contains a large amount of noise interference, such as power frequency interference, motion artifacts, and baseline drift. Edge computing nodes use digital signal processing algorithms to preprocess the raw signal to improve signal quality. The preprocessing method is not detailed here.

[0075] 3. Feature Extraction Unit The feature extraction unit extracts clinically useful feature parameters from the preprocessed signal (features can be extracted using statistical models or conventional methods). The extracted features can be: Blood pressure: systolic pressure, diastolic pressure, mean arterial pressure, pulse pressure; Blood oxygen: blood oxygen saturation, pulse rate, perfusion index; ECG: Heart rate, PR interval, QRS width, QT interval, arrhythmic events; Body temperature: core body temperature, rate of change of body temperature.

[0076] 4. Dual-mode wireless communication unit The dual-mode wireless communication unit consists of a LoRa module (model: Semtech SX1278) and a WiFi module (model: Espressif ESP32), used to enable wireless communication between edge computing nodes and a central monitoring server.

[0077] The system automatically detects the surrounding WiFi signal strength. When the WiFi signal strength is ≥-70dBm, it uses WiFi to transmit data; when the WiFi signal strength is <-70dBm, it automatically switches to LoRa communication. The WiFi transmission rate is 150Mbps with a communication distance of 100 meters; the LoRa transmission rate is 0.3-37.5kbps with a communication distance of 3000 meters.

[0078] 5. Power Management Unit The power management unit (PMU) provides a stable power supply to the entire module and manages the battery's charging and discharging. The PMU consists of a 10000mAh lithium polymer battery, a charging management chip (TI BQ24075), and a power management chip (TITPS65910), providing the required DC voltages (3.3V and 5V) for each unit. Reference can be made to existing electronic device charging modules. A single charge provides up to 72 hours of continuous operation, supports wireless charging and USB-C fast charging, and charging time is less than 2 hours.

[0079] 6. Local alarm and display unit The local alarm and display unit displays the patient's basic vital signs and equipment status, and triggers audible and visual alarms locally. It consists of a 0.96-inch OLED display, tri-color LED indicators, and a buzzer.

[0080] When abnormal parameters are detected, the LED indicator displays different colors according to the warning level (green - normal, yellow - medium risk, red - high risk, flashing red - extremely high risk), and the buzzer emits alarm sounds at different frequencies.

[0081] (III) Central Monitoring Server Module The central monitoring server is deployed in the hospital's central computer room and is the core processing layer of the system, responsible for data reception, storage, analysis, and early warning.

[0082] like Figure 2 As shown, the central monitoring server has the following functional service units deployed: 1. Data receiving and storage unit The data receiving and storage unit consists of a data receiving server and a database server. It is used to receive data uploaded by each edge computing node, perform data parsing, format conversion, and storage.

[0083] Database design: MySQL 8.0 relational database and InfluxDB time-series database are used. The relational database stores basic patient information, equipment information, and early warning events; the time-series database stores high-frequency vital sign data, supporting fast querying and statistical analysis.

[0084] Data storage period: Raw vital signs data is stored for 1 year, and characteristic data and early warning events are stored for 15 years, which meets the requirements for medical data preservation.

[0085] 2. Real-time analytics engine The real-time analytics engine consists of the real-time computing framework Apache Flink and intelligent analytics algorithms. It continuously analyzes real-time uploaded vital sign data to calculate the patient's comprehensive risk score.

[0086] Detailed analysis will follow.

[0087] 3. Intelligent Early Warning System The intelligent early warning system triggers tiered early warnings based on real-time analysis results and early warning rules, and pushes the warning information to relevant terminals. Early warning process: The rules engine determines whether parameters exceed dynamic thresholds or whether the comprehensive risk score reaches the warning level. Generate early warning events and record the warning time, abnormal parameters, and risk level; The corresponding alarm method is triggered based on the warning level; Push warning information to designated terminal devices; Record the response time and processing results of medical staff.

[0088] This system employs a hierarchical intelligent early warning algorithm based on multi-parameter weighted risk scores, which comprehensively considers the patient's vital signs, underlying diseases, and transport risks to achieve accurate early warning.

[0089] (1) Calculation of single-parameter dynamic threshold First, based on the patient's basic vital signs and underlying diseases, calculate the dynamic early warning threshold for each parameter: in, Let i be the warning threshold for the i-th parameter. This is the patient's baseline value (calculated from monitoring data in the emergency room). This represents the normal standard deviation of the parameter. To adjust the coefficients, for example, based on the severity of the patient's condition (APACHE II score): Low-risk patients (APACHE II < 10):

[0090] Intermediate-risk patients (10≤APACHE II<20):

[0091] High-risk patients (20≤APACHE II<30):

[0092] Very high-risk patients (APACHE II ≥ 30):

[0093] For example, if a hypertensive patient has a baseline systolic blood pressure of 160 mmHg and an APACHE II score of 18 (intermediate risk), then the high-risk warning threshold for their systolic blood pressure is: The low warning threshold is Instead of the common 140 / 90 mmHg threshold.

[0094] (2) Multi-parameter weighted risk score Calculate the patient's Comprehensive Transport Risk Score (TRS): in: , , , , The standardized scores for systolic blood pressure, heart rate, blood oxygen saturation, body temperature, and arrhythmia range from 0 to 4 points, with higher scores indicating more severe abnormalities.

[0095] , , , , The weight coefficients for each parameter are determined using the Analytic Hierarchy Process (AHP) and are 0.3, 0.25, 0.25, 0.1, and 0.1, respectively.

[0096] The Comprehensive Transit Risk Score (TRS) is obtained by weighting standardized scores from five parameters. The standardized scoring rules for each parameter are shown in the table below:

[0097] The weighting coefficients were determined using the analytic hierarchy process (AHP). Twenty emergency medicine experts and ten cardiovascular experts were invited to conduct pairwise comparisons of the importance of each parameter, constructing a judgment matrix to calculate the weight of each parameter. Systolic blood pressure: 0.3 Heart rate: 0.25 Blood oxygen saturation: 0.25 Body temperature: 0.1 Cardiac arrhythmia: 0.1 The consistency test result CR=0.03<0.1, indicating that the judgment matrix has satisfactory consistency.

[0098] (3) Classification of early warning levels Based on the comprehensive risk score (TRS), early warnings are divided into four levels: Low-risk warning (0≤TRS<1): The system records the event but does not trigger an alarm; Medium-risk warning (1≤TRS<2): Local audible and visual alarm on the transport bed, push message to the responsible nurse's mobile terminal; High-risk warning (2≤TRS<3): The central monitoring screen at the nurse station will sound and light an alarm, and push the message to the mobile terminals of the responsible nurse and doctor; Extremely high risk warning (TRS≥3): The entire hospital broadcasts an alarm, pushes the message to the mobile terminals of the emergency department director, head nurse, and the nearest emergency personnel, and displays the patient's precise location.

[0099] The specific warning threshold can be adjusted according to the current situation.

[0100] When a warning event is detected, a warning is triggered, as follows: Anomaly detection: The real-time analysis engine determines whether parameters exceed dynamic thresholds or whether the comprehensive risk score reaches the warning level.

[0101] Early warning event generation: Generate a unique early warning event ID and record the early warning time, device ID, patient ID, abnormal parameters, risk level, and current location.

[0102] Local alarm: Send an alarm command to the edge computing node of the transfer bed to trigger a local audible and visual alarm.

[0103] Multi-terminal push: Based on the warning level, the warning information is pushed to the corresponding terminals. Medium-risk warning: Pushed to the responsible nurse's mobile terminal High-risk alerts: Push notifications to the central monitoring screen at the nurses' station and to the mobile terminals of the responsible nurses and doctors. Extremely high risk warning: Pushed to all relevant terminals throughout the hospital, and dynamic path planning is initiated. Response and Handling: After receiving the alert, medical staff confirm receipt on their terminals and proceed to the scene to handle the situation. Once the alert is completed, the results are recorded on the terminals.

[0104] Warning Cancellation: When the patient's vital signs return to normal or the medical staff manually cancels the warning, the system ends the warning event and records the timeline of the entire process.

[0105] 4. Location Service Unit The location service unit consists of a location computing engine and an electronic map service. Based on the signal data uploaded by the UWB base station, it calculates the patient's real-time location and displays it on the electronic map, providing real-time location tracking, historical trajectory playback, electronic fences, and dispatch of the nearest medical staff.

[0106] A dynamic path planning algorithm is used for location planning and positioning.

[0107] When an extremely high-risk warning is issued, the system automatically activates a dynamic path planning algorithm to plan the shortest path from the current location to the patient's location for emergency responders. Construct an indoor map topology of the hospital, abstracting corridors, staircases, elevators and other passages as edges, and intersections, department entrances and other locations as nodes.

[0108] Real-time access status of each node and edge, such as whether the elevator is running or whether the corridor is congested.

[0109] The shortest path is calculated using an improved A* algorithm: in, The actual cost from the starting point to node n. The estimated cost from node n to the destination is calculated using Manhattan distance:

[0110] Considering the impact of travel status, the cost of the edges is weighted: in, Let e ​​be the length of edge e. Let w be the passage weight of edge e. When the path is unobstructed, w=1; when it is congested, w=2; and when it is impassable, w=∞.

[0111] Output the shortest path and display the navigation route on the electronic map of the mobile terminal.

[0112] (iv) Multi-terminal interaction module This module is the system's user interaction layer, providing corresponding user interfaces and functions for users with different roles. Below are several interaction methods for different user roles. 1. Central monitoring screen at the nurse station Deployment locations: Emergency Department nurse station, ICU nurse station.

[0113] Hardware configuration: 55-inch 4K touch screen, industrial-grade host.

[0114] Function: The system displays the vital signs, location, and status of all transferred patients globally. Highlight the information and abnormal parameters of patients under warning; View the patient's historical data and trend charts; Handle early warning events and record the results; Statistical analysis of transport data and adverse events.

[0115] 2. Mobile terminals for medical staff Hardware: PDAs or smartphones carried by medical staff (refer to existing medical staff PDA devices).

[0116] Software: A dedicated mobile monitoring app that supports Android and iOS systems.

[0117] Function: View the patient's real-time vital signs and location; Receive alert push notifications and voice reminders; Handle early warning events and report the results. View the patient's electronic medical records and transport records Initiate emergency calls and personnel dispatch.

[0118] 3. Local terminal for transport bed Hardware: OLED display screen and buttons on the transport bed rails.

[0119] Function: Display the patient's current vital signs; Displays device status and battery level; Locally triggered audible and visual alarm; Manually start / stop monitoring and blood pressure measurement.

[0120] 4. Hospital Information System Interface Module This module is responsible for seamlessly integrating this system with the hospital's existing information systems, enabling data sharing and business collaboration.

[0121] Integration systems: HIS system, EMR system, LIS system, PACS system.

[0122] Communication protocol: Adopts HL7 v3.0 international standard medical data exchange protocol and DICOM standard.

[0123] Data interaction content: Obtain the patient's basic information, diagnosis, medical orders, and basic vital signs from the HIS / EMR system; Synchronize vital signs data, early warning events, and transfer reports during the transfer process to the HIS / EMR system; Obtain the patient's laboratory test results from the LIS / PACS system.

[0124] All data is transmitted in JSON format, which offers good readability and scalability. For example, here's an example of the format used for transmitting vital signs data: JSON{ "deviceId": "TB001", "patientId": "10086", "timestamp": "2024-06-01T10:30:00.123Z", "vitals": { "sbp": 125, "dbp": 82, "map": 96, "hr": 78,"spo2": 98, "pr": 78, "temp": 36.8}, "ecg": { "hr": 78, "pr": 160, "qrs":85, "qt": 380, "arrhythmia": "none"}, "location": { "x": 125.6, "y": 89.3, "floor": 3, "area": "Emergency Department Corridor"}, "battery": 85, "status": "normal"}. Example 1 This embodiment uses the emergency department of a tertiary hospital as an application scenario. This emergency department receives approximately 200,000 patients annually, and transports approximately 15,000 critically ill patients annually. Traditional transport methods suffer from problems such as high adverse event rates, low handover efficiency, and lack of data traceability.

[0125] Deployment plan: Deployment of transport bed terminals: Integrated wireless sensor arrays and edge computing modules were installed on all 50 transport beds in the emergency department.

[0126] UWB positioning system deployment: 200 UWB base stations were deployed in the emergency department, various examination departments, ICU and main corridors of the hospital to achieve indoor positioning coverage throughout the hospital.

[0127] Central server deployment: Two application servers (primary and backup), two database servers (primary and backup), and one location server are deployed in the hospital's central computer room. A Huawei USG6300 firewall is configured to ensure system security.

[0128] Terminal equipment deployment: One 55-inch central monitoring screen is deployed at each of the emergency department nurse station and the ICU nurse station. Mobile terminals (PDAs) are provided to 30 doctors and 50 nurses in the emergency department.

[0129] System integration: Complete the interface integration between the system and the hospital's HIS, EMR, LIS, and PACS systems to achieve data interconnection and interoperability.

[0130] Staff training: All medical staff in the emergency department will receive system operation training for 8 hours to ensure that all staff can use the system proficiently.

[0131] Emergency critical patient transfer early warning process: Taking the transfer of patient Li as an example, the basic patient information of this system is described in detail: Li, male, 62 years old, was admitted to the hospital due to "sudden chest pain for 2 hours" and diagnosed with acute ST-segment elevation myocardial infarction. APACHE II score was 16 (intermediate risk), baseline blood pressure was 150 / 90 mmHg, heart rate was 85 bpm, blood oxygen saturation was 98%, and body temperature was 36.5℃. Doctor's order: Emergency transfer to the catheterization laboratory for PCI treatment.

[0132] System initialization and binding: The nurse enters Li's information on the central monitoring screen, and the system automatically assigns transport bed TB025 and binds Li's ID to TB025. Based on his / her risk level, the system automatically calculates the warning thresholds: systolic blood pressure 120-180 mmHg, heart rate 60-120 beats / min, and blood oxygen saturation ≥90%.

[0133] Pre-transfer preparation: The nurse transferred Mr. Li to bed TB025 and adjusted the bed rails. Pressing the "Start" button, the system automatically performed a self-check and completed the initial measurements: blood pressure 148 / 92 mmHg, heart rate 88 bpm, blood oxygen 98%, body temperature 36.6℃. The nurse confirmed the data was normal and confirmed the transfer had begun on the mobile terminal, with the destination being the catheterization lab and an estimated transfer time of 10 minutes. The system automatically sent a pre-notification to the catheterization lab.

[0134] Monitoring during transport: The system continuously monitored Li's vital signs during the transport. When the elevator was reached, the WiFi signal weakened, and the system automatically switched to LoRa communication, ensuring uninterrupted data transmission.

[0135] Warning Triggering and Handling: During the transfer to the 3rd-floor corridor, Li suddenly experienced ventricular tachycardia, with his heart rate rising to 165 beats / min, blood pressure dropping to 85 / 50 mmHg, and blood oxygen saturation dropping to 88%. The system calculated the comprehensive risk score TRS = 0.3×3 + 0.25×4 + 0.25×2 + 0.1×0 + 0.1×4 = 2.8, triggering a high-risk warning.

[0136] The TB025 transfer bed emitted a red light and a rapid beeping sound.

[0137] The central monitoring screen at the nurses' station displayed Li's information and sounded an alarm.

[0138] The mobile terminals of the responsible nurse and the attending physician received push messages displaying Li's vital signs, abnormal parameters and current location (3rd floor corridor, coordinates X=156.2, Y=98.5).

[0139] The attending physician immediately initiated resuscitation efforts at the bedside, administering amiodarone intravenously. The nurse recorded the resuscitation measures using a mobile terminal.

[0140] Transfer completed and handover: After emergency treatment, Li's heart rate recovered to 95 beats / min, blood pressure rose to 110 / 70 mmHg, and blood oxygen saturation rose to 96%. The system automatically lifted the high-risk warning and changed it to a medium-risk warning.

[0141] The transport personnel delivered Li to the catheterization lab and handed him over to the lab nurses.

[0142] The system automatically generates a transfer and handover report, which includes vital sign trends, ventricular tachycardia events, resuscitation measures, and current condition during the transfer process.

[0143] Both parties confirm the handover by electronically signing on their mobile devices.

[0144] The system automatically synchronized the entire transfer data and handover report to Li's electronic medical record.

[0145] Data Archiving: After the transfer is completed, the system automatically archives all data and generates a transfer record. Administrators can view the detailed process and data of this transfer in the system.

[0146] The deployment and application of the above systems can significantly reduce the incidence of adverse events during the transfer of critically ill patients in the emergency department, improve the speed of early warning response and handover efficiency, solve problems such as lead wire confinement, discontinuous monitoring and untimely early warning in traditional transfer monitoring, ensure the safety of patient transfer and improve the quality of medical services.

[0147] The above embodiments can be implemented, in whole or in part, by software, hardware (such as circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive.

[0148] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0149] In this invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.

[0150] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0151] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0152] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the devices, apparatuses, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0153] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0154] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0155] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0156] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0157] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A wireless monitoring and early warning system for vital signs on an emergency critical patient transport bed, characterized in that, include: The transport bed integrates a wireless sensor array module, which is integrated into the adjustable bed rail of the transport bed, for non-contact acquisition of non-invasive blood pressure, pulse oximetry, three-lead ECG and body temperature signals of patients. The bedside edge computing and wireless transmission module is built into the transport bed rail and is electrically connected to the wireless sensor array module. It is used to preprocess and extract features from the collected raw signals and upload the data to the central monitoring server through LoRa+WiFi dual-mode communication. The central monitoring server module, deployed in the hospital's central computer room, is wirelessly connected to the edge computing module. It is used to receive, store, and analyze vital sign data, run intelligent early warning algorithms, trigger tiered early warnings, and manage all devices and users of the system. The multi-terminal interaction module includes a central monitoring screen at the nurse station, a mobile terminal for medical staff, and a local terminal for the transport bed. It is communicatively connected to the central monitoring server module and is used to display real-time vital signs data, receive early warning information, and perform human-computer interaction. The hospital information system interface module communicates with the central monitoring server module to enable data interaction and sharing between this system and the hospital's HIS and EMR systems.

2. The system according to claim 1, characterized in that, The integrated wireless sensor array module of the transfer bed includes: The non-invasive blood pressure sensing unit consists of two symmetrically distributed auto-inflating airbags and pressure sensors, integrated into the upper arm support of the bed rail, and is used to collect the patient's systolic blood pressure, diastolic blood pressure and mean arterial pressure. The pulse oximetry sensing unit consists of two reflective photoelectric sensors integrated into the bed rail armrest, used to collect the patient's blood oxygen saturation and pulse rate; The three-lead ECG sensing unit consists of three capacitively coupled electrodes integrated into the back of the bed rail for non-contact acquisition of the patient's ECG signals. The infrared body temperature sensing unit consists of a non-contact infrared temperature sensor integrated above the bed rail to collect the patient's core body temperature. The UWB indoor positioning unit consists of a UWB tag integrated into the bottom of the bed rail for real-time location of the patient.

3. The system according to claim 1, characterized in that, The bedside edge computing and wireless transmission module includes: The main control unit uses an STM32H743ZI microcontroller for logic control and data processing; The signal preprocessing unit is used to amplify, filter, and denoise the raw physiological signals; The feature extraction unit is used to extract clinical feature parameters from the preprocessed signal; The dual-mode wireless communication unit integrates a LoRa module and a WiFi module, automatically detects signal strength and switches communication modes to achieve seamless coverage throughout the hospital. The power management unit uses a 10000mAh lithium polymer battery, which can work continuously for 72 hours on a single charge; The local alarm and display unit is used to display vital sign data and trigger local audible and visual alarms.

4. The system according to claim 1, characterized in that, The central monitoring server module includes: The data receiving and storage unit uses a MySQL relational database and an InfluxDB time-series database to store patients’ basic information, vital signs data and early warning events; The real-time analysis engine, based on the Apache Flink real-time computing framework, continuously analyzes real-time data and calculates the patient's comprehensive transport risk score. The intelligent early warning system, based on a multi-parameter weighted risk scoring algorithm, enables tiered intelligent early warning and pushes the warning information to relevant terminals. The location service unit, based on UWB positioning technology, enables real-time location tracking and dynamic path planning for patients.

5. The system according to claim 1, characterized in that, The multi-terminal interaction module includes: The central monitoring screen at the nurses' station is used to display the vital signs, location, and status of all transferred patients globally, and to handle early warning events. Medical mobile terminals are carried by medical staff to view real-time data of the patients they are responsible for, receive early warning push notifications, and handle early warning events. The local terminal for the transport bed is used to display the patient's basic vital signs and equipment status, and to trigger audible and visual alarms locally.

6. The system according to claim 1, characterized in that, The working mechanism of the dual-mode wireless communication unit is as follows: when the WiFi signal strength is ≥-70dBm, WiFi is used to transmit data; when the WiFi signal strength is <-70dBm, it automatically switches to LoRa communication.

7. The system according to claim 4, characterized in that, The intelligent early warning system employs a dynamic threshold adjustment method, calculating the early warning threshold for each parameter based on the patient's baseline vital signs and APACHE II score. in, Let i be the warning threshold for the i-th parameter. This is the patient's baseline value. This represents the normal standard deviation of the parameter. This is the adjustment factor determined based on the APACHE II score.

8. The system according to claim 4, characterized in that, The intelligent early warning system uses a multi-parameter weighted risk scoring algorithm to calculate the comprehensive transportation risk score. in, , , , , These are standardized scores for systolic blood pressure, heart rate, blood oxygen saturation, body temperature, and arrhythmias. , , , , These are the weighting coefficients for each parameter; based on TRS, the warning is divided into four levels: low, medium, high, and extremely high risk.

9. The system according to claim 1, characterized in that, The hospital information system interface module adopts the HL7 v3.0 standard protocol, which automatically synchronizes vital sign data, early warning events and transfer handover reports during the transfer process to the patient's electronic medical record, realizing permanent archiving and traceability of data.

10. The system according to claim 1, characterized in that, The system's transfer and handover method is as follows: After the transfer is completed, the system automatically generates a standardized electronic transfer and handover report, which includes the patient's basic information, vital sign trends, early warning events, and handling measures; after both parties electronically sign and confirm the transfer on their mobile terminals, the report is automatically archived and synchronized to the electronic medical record.

Images