Pressure injury risk early warning method and equipment

Abstract

The invention discloses a pressure injury risk early warning method and equipment, and relates to the technical field of medical monitoring instruments. The pressure sensor array layout can be self-adaptive to the body shape of a patient, a key osseous process part is covered, no monitoring dead angle is ensured, a temperature compensation mechanism is built in, environmental interference is reduced, the measurement precision is improved, an abnormal pressure threshold value can be dynamically set based on individual medical record data, data verification is performed before early warning is triggered, false alarm is avoided, and the array structure is light, thin and flexible. The mask is comfortable to fit skin, supports long-term wearing and is easy to disinfect and maintain; environment temperature and humidity parameters and pressure data are subjected to fusion analysis, the influence of a high-temperature and high-humidity environment on skin microcirculation can be recognized, the risk of pressure sores can be evaluated in an auxiliary mode, a calibration algorithm is built in a sensor, environment fluctuation interference is reduced, and data reliability is ensured; and the early warning unit comprises sound-light alarm equipment which supports a multi-stage alarm mode and is used for triggering an early warning signal and pushing information when the risk index exceeds a threshold value, so that the early warning timeliness is ensured and the false alarm risk is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical monitoring devices, in particular to a pressure injury risk early warning method and device. BACKGROUND

[0002] Pressure injury refers to a localized injury to the skin and / or subcutaneous tissue caused by intense and / or long-term pressure or pressure combined with shear force, usually occurring at bony prominences, under the skin in contact with medical devices or other devices / items. The main manifestations are local tissue damage, intact or open ulcer, and may be accompanied by pain, including skin pressure injury and mucosal pressure injury.

[0003] Nowadays, pressure ulcer patients often occur and need to be turned over regularly to prevent pressure ulcers. With the cross-fusion of multidisciplinary, some researchers combine information technology with pressure injury early warning, which can improve the risk identification rate to a certain extent. However, these studies all integrate the pressure injury risk assessment form into the information system construction, supplemented by quality monitoring and dynamic monitoring to realize the collection of pressure injury occurrence and strengthen management. This method reduces the problems of document recording and data archiving, and reduces the phenomenon of re-reporting and missing reporting caused by bed moving or transferring. However, due to the subjectivity of the evaluation method of the assessment tool, the system is not enough for the real situation of the patient and the real-time change of the pressure ulcer, and also lacks learning and timely feedback. It cannot timely identify and early warn the events of staff concealing and missing reporting, and cannot automatically obtain information to realize dynamic and real-time pressure ulcer assessment. Therefore, we propose a pressure injury risk early warning method and device. SUMMARY

[0004] The purpose of the present application is to solve the problems mentioned in the background art. The present application provides a pressure injury risk early warning method and device.

[0005] In order to achieve the above purpose, the present application specifically adopts the following technical scheme: A pressure injury risk early warning method, comprising the following steps: Step 1, collecting patient body surface pressure distribution data, including real-time monitoring of pressure value, time duration and environmental temperature and humidity parameters of patient body position contact point; Step 2, calculating the pressure injury risk index based on the collected data, using a preset algorithm to analyze the pressure peak value, cumulative pressure time and skin tolerance threshold to generate a risk assessment result; Step 3, triggering an early warning signal according to the risk assessment result, and pushing early warning information through an audible and visual alarm device or a mobile terminal when the risk index exceeds the threshold; Step 4, continuously updating the monitoring data and dynamically adjusting the risk model, and combining the changes of patient physiological parameters for real-time feedback optimization; Step 5, regularly calibrate the pressure sensor and environmental temperature and humidity sensor, verify the data collection accuracy through standard test tools, and reduce measurement errors; Step 6, generate personalized intervention suggestions based on risk assessment results, including body position adjustment plan and nursing measures, and push to medical staff through mobile terminal; Step 7, store historical monitoring data and establish database for long-term trend analysis and model optimization, support training and update of machine learning algorithm; Step 8, integrate system self-checking function, monitor equipment running state in real time, automatically trigger maintenance alarm when abnormal, ensure early warning continuity; Step 9, dynamically correct skin tolerance threshold combined with patient clinical information such as age, body mass index and medical history, improve the individualization level of risk assessment; Step 10, record response time and intervention effect after early warning signal triggering, form closed-loop feedback mechanism for subsequent model iteration and performance evaluation.

[0006] Further, the step 2 adopts preset algorithm to analyze pressure peak value, cumulative pressure time and skin tolerance threshold, and the calculation formula of risk index R is: R=\alpha\times\frac{P_{\text{max}}}{T_{\text{th}}}\timesT_{\text{cumulative}}, Wherein, P_{\text{max}} represents the pressure peak value; T_{\text{cumulative}} represents the cumulative pressure time; T_{\text{th}} represents the skin tolerance threshold, which is dynamically corrected according to the patient's clinical information in step 9 to ensure the individualized applicability of the formula; \alpha is the adjustable weight coefficient for calibrating the risk level of different patient groups; The algorithm also includes normalization processing of risk index R, which maps the result to the interval [0, 1] by dividing the maximum possible value, which is convenient for threshold comparison and early warning triggering.

[0007] Further, in step 3, the triggering mechanism of the early warning signal includes dynamically adjusting the alarm threshold, automatically optimizing the response strategy according to the real-time risk index of the patient; the sound and light alarm device adopts a multi-level alarm mode, including low-frequency vibration and high-frequency sound, to adapt to different environmental noise conditions; the mobile terminal supports cross-platform notifications, integrating SMS, APP pop-up windows, and email, and is compatible with iOS and Android systems, ensuring that information is conveyed to medical staff in real time; at the same time, the early warning information includes patient location identification and risk level details, facilitating rapid positioning and intervention; in addition, the system automatically records the early warning trigger time and response delay for subsequent feedback analysis.

[0008] Further, in step 4, the dynamic adjustment of the risk model includes introducing machine learning algorithms to train prediction models using historical data, and optimizing the correlation between stress distribution and physiological parameters in real time; the physiological parameters include heart rate, blood oxygen saturation, and skin temperature, which are continuously collected by wireless sensors and analyzed in combination with stress data to improve risk assessment accuracy; the model update frequency is adaptively set according to the patient's activity state, with lower sampling rate for energy saving when stationary and higher real-time performance when moving.

[0009] Further, in step 6, the generation of personalized intervention recommendations includes automatically recommending the best turning angle and interval time based on the patient's body position stress heat map; the nursing measures include local decompression pad usage recommendations and skin care plans, which are pushed in the form of graphics and text through the mobile terminal, supporting multi-language switching to meet the needs of different medical staff; intervention recommendations are also combined with electronic medical record data to dynamically adjust priorities, ensuring that high-risk patients are prioritized.

[0010] Further, in step 8, the system self-checking function includes periodic hardware diagnosis to detect sensor failures or abnormal battery levels; the maintenance alarm notifies the technical support team through cloud platform remote notification technology, and automatically switches to backup devices to maintain monitoring continuity; the self-checking frequency is set to once every hour, and detailed logs including device serial number and error codes are generated in case of abnormalities to facilitate quick repairs.

[0011] A pressure injury risk warning device, the device comprising: a pressure sensor array for real-time monitoring of pressure values and time duration at patient body position contact points; an environmental temperature and humidity sensor for collecting environmental temperature and humidity parameters; a data processing unit for receiving data from the sensor module and calculating a pressure injury risk index according to a preset algorithm; a warning unit for issuing an alarm signal when the risk index exceeds a threshold; a data storage unit for storing historical monitoring data and establishing a database to support long-term trend analysis and model optimization; a display unit for displaying the pressure distribution, risk index and warning information in real time; a self-checking unit for monitoring the running state of the device in real time and automatically triggering a maintenance alarm when an abnormality occurs; an information integration interface unit for dynamically correcting the skin tolerance threshold in combination with clinical information and improving the level of personalization.

[0012] Further, the warning unit includes an audible and visual alarm device supporting a multi-level alarm mode, and a mobile terminal communication interface for triggering a warning signal and pushing information when the risk index exceeds the threshold.

[0013] Further, the device further includes a power module for providing stable power supply for the device, and the power module has a redundant power supply design, including a built-in rechargeable battery and an external power supply interface, supporting seamless switching to cope with power interruption; at the same time, an intelligent power saving management system is integrated, which dynamically adjusts power consumption according to device load to prolong the endurance time; and is equipped with a power state monitoring function, which automatically triggers a maintenance alarm when detecting unstable voltage or insufficient battery power.

[0014] Further, the device further integrates a wireless communication module to ensure cross-platform compatibility with mobile terminals, support iOS and Android systems, and periodically calibrate sensors to reduce measurement errors.

[0015] The beneficial effects of the present application are as follows: The pressure sensor array of the present application monitors the pressure value and time duration of the patient's body position contact point in real time, and generates a dynamic pressure distribution heat map. The array layout can adapt to the patient's body shape, cover the key bony parts, ensure that there is no dead angle in monitoring, reduce environmental interference, improve measurement accuracy, and dynamically set the abnormal pressure threshold based on individual medical record data. Data verification is performed before triggering the warning to avoid false alarms; the array structure is light, thin and flexible, comfortable to fit the skin, supports long-term wear and is easy to disinfect and maintain.

[0016] The present application fuses and analyzes environmental temperature and humidity parameters and pressure data, which can identify the influence of high temperature and high humidity environment on skin microcirculation, assist in evaluating the risk of pressure ulcers, and the sensor has a built-in calibration algorithm to reduce environmental fluctuation interference and ensure data reliability.

[0017] The warning unit of the present application includes an audible and visual alarm device supporting a multi-level alarm mode, and a mobile terminal communication interface for triggering a warning signal and pushing information when the risk index exceeds the threshold, and is linked with the information integration interface unit to dynamically optimize the alarm threshold parameters based on real-time clinical data, supports pushing through SMS, email or special application program, ensures the timeliness of the warning and reduces the risk of false alarms. BRIEF DESCRIPTION OF DRAWINGS

[0018] Figure 1 is a method flowchart of the present application; Figure 2 is a system block diagram of the present application; Figure 3 is a working block diagram of the system in the present application. DETAILED DESCRIPTION

[0019] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application.

[0020] Referring to Figure 1 , the present application provides a pressure injury risk early warning method, comprising the following steps: Step 1, collecting patient body surface pressure distribution data, including real-time monitoring of pressure values, time duration and environmental temperature and humidity parameters of patient body position contact points; Step 2, calculating a pressure injury risk index based on the collected data, using a preset algorithm to analyze pressure peak value, cumulative pressure time and skin tolerance threshold, and generating a risk assessment result; Step 3, triggering an early warning signal according to the risk assessment result, when the risk index exceeds the threshold value, pushing early warning information through a sound and light alarm device or a mobile terminal; Step 4, continuously updating monitoring data and dynamically adjusting the risk model, combining patient physiological parameter changes for real-time feedback optimization; Step 5, regularly calibrating pressure sensors and environmental temperature and humidity sensors, verifying data collection accuracy through standard test tools, and reducing measurement errors; Step 6, generating personalized intervention suggestions based on the risk assessment result, including body position adjustment scheme and nursing measures, and pushing to medical staff through a mobile terminal; Step 7, storing historical monitoring data and establishing a database for long-term trend analysis and model optimization, supporting training and updating of machine learning algorithms; Step 8, integrating system self-checking function, real-time monitoring of device running state, automatic triggering of maintenance alarm in case of abnormality, and ensuring early warning continuity; Step 9, dynamically correcting the skin tolerance threshold in combination with patient clinical information such as age, body mass index and medical history, and improving the personalized level of risk assessment; Step 10, after the early warning signal is triggered, recording the response time and intervention effect, forming a closed-loop feedback mechanism for subsequent model iteration and performance evaluation.

[0021] In this embodiment, preferably, step 2 uses a preset algorithm to analyze pressure peak value, cumulative pressure time and skin tolerance threshold, and the calculation formula of the risk index R is: R = a x P max / T th x T cumulative, where P max represents the pressure peak value; T cumulative represents the cumulative pressure time; T th represents the skin tolerance threshold, which is dynamically corrected according to the patient's clinical information in step 9 to ensure personalized applicability of the formula; a is an adjustable weight coefficient for calibrating the risk level of different patient groups; The algorithm also includes normalization of the risk index R, which maps the result to the [0, 1] interval by dividing the maximum possible value, facilitating threshold comparison and early warning triggering.

[0022] In this embodiment, preferably, in step 3, the triggering mechanism of the early warning signal includes dynamically adjusting the alarm threshold to automatically optimize the response strategy according to the real-time risk index of the patient; the sound and light alarm device adopts a multi-level alarm mode, including low-frequency vibration and high-frequency sound, to adapt to different environmental noise conditions; the mobile terminal push supports cross-platform notifications, integrating SMS, APP pop-up windows and email, and compatible with iOS and Android systems, ensuring that information is conveyed to medical staff in real time; at the same time, the early warning information contains patient location identification and risk level details, facilitating quick positioning and intervention; in addition, the system automatically records the early warning trigger time and response delay for subsequent feedback analysis.

[0023] In this embodiment, preferably, the dynamic adjustment of the risk model in step 4 includes introducing machine learning algorithms to train prediction models using historical data to optimize the correlation between pressure distribution and physiological parameters in real time; physiological parameters include heart rate, blood oxygen saturation and skin temperature, which are continuously collected by wireless sensors and fused with pressure data for analysis to improve risk assessment accuracy; the model update frequency is adaptively set according to the patient's activity state, with lower sampling rate for energy saving when stationary and higher real-time performance when moving.

[0024] In this embodiment, preferably, the generation of personalized intervention recommendations in step 6 includes automatically recommending the best turning angle and interval time based on the patient's body position pressure heat map; nursing measures include local decompression pad usage recommendations and skin care programs, which are pushed in the form of text and pictures through mobile terminals, supporting multi-language switching to meet the needs of different medical staff; intervention recommendations also combine electronic medical record data to dynamically adjust priorities, ensuring that high-risk patients are given priority.

[0025] In this embodiment, preferably, the system self-check function in step 8 includes periodic hardware diagnostics, detects sensor failure or abnormal battery power; maintenance alerts are remotely notified to the technical support team through the cloud platform, and automatically switch to the backup device to maintain monitoring continuity; the self-check frequency is set to once an hour, and detailed logs are generated when an exception occurs, including device serial number and error code, to facilitate quick repair. Please refer to Figure 2 Figure 3 The present application also provides a pressure injury risk early warning device, comprising: A pressure sensor array is used to monitor the pressure value and time duration of the patient's body position contact point in real time and generate a dynamic pressure distribution heat map; data is wirelessly transmitted to the central processing unit through the low-power Bluetooth module, integrated with the physiological parameter acquisition module, and multi-modal information fusion is achieved; the array layout can adapt to the patient's body shape, covering key bony sites to ensure that there are no dead angles in monitoring; at the same time, a temperature compensation mechanism is built-in to reduce environmental interference and improve measurement accuracy; the sampling frequency is intelligently adjusted according to the patient's activity state, reduced to 1 Hz when stationary to save energy, and increased to 10 Hz when moving to ensure real-time performance; the abnormal pressure threshold can be dynamically set based on individual medical record data, and data verification is performed before triggering the warning to avoid false alarms; the array structure is light, thin, flexible, comfortable to adhere to the skin, supports long-term wear, and is easy to disinfect and maintain.

[0026] An environmental temperature and humidity sensor is used to collect environmental temperature and humidity parameters. The sensor is designed with high precision and digital, monitors the temperature range (-10°C to 50°C) and relative humidity (0% to 100%) of the environment where the patient is located in real time, and transmits the data wirelessly to the central processing unit through the low-power Bluetooth module; environmental temperature and humidity parameters are fused and analyzed with pressure data to identify the impact of high temperature and humidity environment on skin microcirculation, assisting in assessing the risk of pressure ulcers; the sensor has a built-in calibration algorithm to reduce environmental fluctuation interference and ensure data reliability; the default sampling frequency is once every minute, which automatically increases to once every 10 seconds when an abnormal value is detected (such as temperature exceeding 35°C or humidity higher than 80%) to enhance the timeliness of the warning; at the same time, the sensor shell is made of medical-grade waterproof material, which is easy to clean and disinfect, and supports long-term stable operation.

[0027] A data processing unit is used to receive data from the sensor module and calculate a pressure injury risk index according to a preset algorithm; the algorithm fuses the pressure distribution, duration parameters collected by the pressure sensor and the temperature, humidity data obtained by the environmental temperature and humidity sensor, dynamically generates a risk score through a weighted average model or machine learning analysis; at the same time, the data processing unit performs real-time data verification, including abnormal value filtering and noise suppression, to ensure the reliability of the input data; the unit also integrates a risk threshold comparison module that triggers an early warning signal when the calculated risk index exceeds the preset dynamic threshold.

[0028] ​An early warning unit for issuing an alarm signal when the risk index exceeds a threshold value.

[0029] A data storage unit for storing historical monitoring data and establishing a database to support long-term trend analysis and model optimization; adopts a distributed storage architecture to ensure high availability and fault tolerance of data, reduces storage space occupation through regular data archiving and compression mechanisms, while supporting multi-user concurrent access; the database design integrates time series analysis functions to facilitate the extraction of long-term monitoring data and identify the cumulative impact of seasonal temperature and humidity changes on skin microcirculation, thereby optimizing the risk prediction model; in addition, the unit provides data export interfaces to allow researchers or system administrators to retrain machine learning models based on historical data sets, improving the adaptability and accuracy of the early warning algorithm; security mechanisms include end-to-end encryption and access control policies to prevent unauthorized operations and protect patient privacy and data compliance.

[0030] A display unit for real-time display of pressure distribution, risk index and early warning information; adopts a graphical user interface to visualize the pressure distribution heat map in real time, dynamically updates the risk index value curve, and highlights the early warning information such as flashing icons and color-coded warnings when the risk index exceeds the threshold value; at the same time, it supports user interaction functions, including zooming in and out of the pressure distribution map, switching between time series views to view historical trends, and customizing display parameters such as alarm threshold adjustments, to facilitate medical personnel to intuitively monitor patient status; the unit also integrates multi-terminal compatibility design, ensuring clear presentation of data on mobile tablets, fixed monitoring screens and other devices through adaptive resolution technology, and has an offline caching mechanism to maintain display continuity during network fluctuations.

[0031] A self-checking unit that monitors the device's running state in real time, periodically scans hardware components (such as processor load, storage space, battery level and sensor accuracy) through built-in sensors, and performs software health checks (including key process running state and algorithm module integrity), automatically triggers maintenance alarms when abnormalities occur, through sound beeper, visual flashing indicator light and background push notifications (such as emails or SMS to administrator terminals), with detailed diagnostic reports and repair suggestions (such as replacing parts or restarting services), to ensure device running stability, avoid false positives or false negatives, and improve overall system reliability and maintenance efficiency.

[0032] An information integration interface unit is used to dynamically correct the skin tolerance threshold by combining clinical information such as patient age, weight, medical history and current physiological indicators, analyze data changes in real time through built-in algorithm models, and automatically optimize threshold parameters. At the same time, the unit also supports seamless docking with the electronic health record system, extracts key clinical features such as skin type, activity ability and complication risk, and generates personalized early warning strategies. In addition, the unit integrates a feedback mechanism, allowing medical staff to input observation results or adjustment suggestions for iterative optimization of the model, thereby significantly reducing the false alarm rate, enhancing patient-specific adaptability, and ensuring that the early warning results are more in line with individual clinical needs.

Claims

1. A method for early warning of pressure injury risk, characterized in that, Includes the following steps: Step 1: Collect data on the pressure distribution on the patient's body surface, including real-time monitoring of the pressure value, duration of contact time, and environmental temperature and humidity parameters at the patient's body position contact points; Step 2: Calculate the pressure injury risk index based on the collected data, and use a preset algorithm to analyze the pressure peak, cumulative pressure time and skin tolerance threshold to generate risk assessment results; Step 3: Trigger an early warning signal based on the risk assessment results. When the risk index exceeds the threshold, push early warning information through sound and light alarm devices or mobile terminals. Step 4: Continuously update monitoring data and dynamically adjust the risk model, and optimize it in real time by combining changes in patients' physiological parameters; Step 5: Regularly calibrate the pressure sensor and the ambient temperature and humidity sensor, and verify the data acquisition accuracy using standard testing tools to reduce measurement errors; Step 6: Generate personalized intervention recommendations based on the risk assessment results, including postural adjustment plans and nursing measures, and push them to medical staff via mobile devices; Step 7: Store historical monitoring data and establish a database for long-term trend analysis and model optimization, supporting the training and updating of machine learning algorithms; Step 8: Integrate the system's self-test function to monitor the equipment's operating status in real time and automatically trigger maintenance alarms when abnormalities occur, ensuring continuous early warning. Step 9: Combine patient clinical information, such as age, body mass index and medical history, to dynamically adjust the skin tolerance threshold and improve the personalization of risk assessment. Step 10: After the warning signal is triggered, record the response time and intervention effect to form a closed-loop feedback mechanism for subsequent model iteration and performance evaluation.

2. The method for early warning of pressure injury risk according to claim 1, characterized in that, Step 2 uses a preset algorithm to analyze the peak pressure, cumulative pressure exposure time, and skin tolerance threshold. The risk index R is calculated using the formula: R = \alpha\times\frac{P_{\text{max}}}{T_{\text{th}}}\timesT_{\text{cumulative}}, Where P_{\text{max}} represents the peak pressure; T_{\text{cumulative}} represents the cumulative pressure time; T_{\text{th}} represents the skin tolerance threshold, which is dynamically adjusted based on the patient's clinical information in step 9 to ensure the personalized applicability of the formula; \alpha is an adjustable weighting coefficient used to calibrate the risk levels of different patient groups; The algorithm also includes normalization of the risk index R, which maps the result to the [0,1] interval by dividing by the maximum possible value, making it easier to compare thresholds and trigger warnings.

3. The method for early warning of pressure injury risk according to claim 1, characterized in that, In step 3, the triggering mechanism for the warning signal includes dynamically adjusting the alarm threshold and automatically optimizing the response strategy based on changes in the patient's real-time risk index. The audible and visual alarm device adopts a multi-level alarm mode, including low-frequency vibration and high-frequency sound, to adapt to different environmental noise conditions. The mobile terminal push supports cross-platform notifications, integrating SMS, APP pop-ups, and email, and is compatible with iOS and Android systems, ensuring that information is delivered to medical staff in real time. At the same time, the warning information includes the patient's location identifier and risk level details, facilitating rapid location and intervention. In addition, the system automatically records the warning trigger time and response delay for subsequent feedback analysis.

4. The method for early warning of pressure injury risk according to claim 1, characterized in that, The dynamic risk adjustment model in step 4 includes introducing machine learning algorithms, using historical data to train a prediction model, and optimizing the correlation between stress distribution and physiological parameters in real time. The physiological parameters include heart rate, blood oxygen saturation, and skin temperature, which are continuously collected by wireless sensors and fused with stress data for analysis to improve the accuracy of risk assessment. The model update frequency is adaptively set according to the patient's activity status, reducing the sampling rate to save energy when the patient is stationary and increasing real-time performance when the patient is moving.

5. The method for early warning of pressure injury risk according to claim 1, characterized in that, The personalized intervention recommendations in step 6 include automatically recommending the optimal turning angle and interval based on the patient's postural pressure heat map; the nursing measures include recommendations for the use of local pressure-reducing pads and skin care plans, which are pushed out in a graphic and textual format via mobile terminals and support multilingual switching to meet the needs of different medical staff; the intervention recommendations also combine electronic medical record data to dynamically adjust priorities and ensure that high-risk patients are treated first.

6. The method for early warning of pressure injury risk according to claim 1, characterized in that, The system self-test function in step 8 includes periodic hardware diagnostics to detect sensor failures or abnormal battery power; the maintenance alarm is remotely notified to the technical support team via the cloud platform and automatically switches to backup equipment to maintain monitoring continuity. The self-test frequency is set to once per hour. When an anomaly occurs, a detailed log is generated, including the device serial number and error code, to facilitate rapid repair.

7. A pressure injury risk early warning device, characterized in that, The device includes: A pressure sensor array is used to monitor the pressure value and duration of contact at the patient's body position in real time. An ambient temperature and humidity sensor is used to collect ambient temperature and humidity parameters. The data processing unit is used to receive data from the sensor module and calculate the pressure injury risk index according to a preset algorithm. An early warning unit is used to issue an alarm signal when the risk index exceeds a threshold. Data storage unit is used to store historical monitoring data and establish a database to support long-term trend analysis and model optimization; The display unit is used to display the pressure distribution, risk index, and early warning information in real time. The self-testing unit monitors the equipment's operating status in real time and automatically triggers maintenance alarms when abnormalities occur. The information integration interface unit is used to dynamically adjust the skin tolerance threshold by combining clinical information, thereby improving the level of personalization.

8. The pressure injury risk early warning device according to claim 7, characterized in that, The early warning unit includes an audible and visual alarm device that supports multiple alarm modes, and a mobile terminal communication interface, which is used to trigger an early warning signal and push information when the risk index exceeds a threshold.

9. A pressure injury risk early warning device according to claim 7, characterized in that, The device also includes a power module for providing a stable power supply to the device. The power module has a redundant power design, including a built-in rechargeable battery and an external power interface, supporting seamless switching to cope with power interruptions. It also integrates an intelligent power-saving management system to dynamically adjust power consumption according to the device load and extend battery life. Furthermore, it is equipped with a power status monitoring function that automatically triggers a maintenance alarm when unstable voltage or insufficient battery power is detected.

10. A pressure injury risk warning device according to claim 7, characterized in that, The device also integrates a wireless communication module to ensure cross-platform compatibility with mobile terminals, supporting iOS and Android systems, and periodically calibrates the sensor to reduce measurement errors.

Images