Nursing intervention system for monitoring vital signs of a patient based on a biosensor

Abstract

The application discloses a nursing intervention system based on a biosensor for monitoring vital signs of a patient, and relates to the technical field of nursing monitoring.The application comprises a biosensor module, a data processing module, a central control module, a nursing intervention module and a data storage and communication module; the biosensor module is used for collecting multiple vital sign parameters of a patient in real time, such as physiological data of heart rate, blood pressure, blood oxygen saturation and body temperature; the data processing module is connected with the biosensor module, and is used for filtering, amplifying, analog-digital converting and feature extracting the collected original physiological data, and converting the original physiological data into identifiable digital signals.The application breaks through the limitation of single index monitoring of a traditional system by integrating a multi-parameter biosensor module, and can synchronously collect multiple key vital sign parameters, such as heart rate, blood pressure, blood oxygen saturation and body temperature, so as to provide a data basis for comprehensively evaluating the health state of the patient.

Description

Technical Field

[0001] This invention belongs to the field of nursing monitoring, specifically, it relates to a nursing intervention system based on biosensors for monitoring patients' vital signs. Background Technology

[0002] With the increasing aging of the global population and the continued rise in the prevalence of chronic diseases, the traditional hospital-centered healthcare model is facing severe challenges. To address the strain on medical resources, the excessive workload of nursing staff, and the growing demand for personalized medicine, healthcare systems are gradually shifting towards home-care and point-of-care. Against this backdrop, technologies capable of continuous, real-time, non-invasive or minimally invasive monitoring of physiological parameters have become a research hotspot. Among these, wearable monitoring systems based on biosensors are considered one of the key pathways to solving these problems.

[0003] However, existing biosensor monitoring systems are often limited to the collection and transmission of physiological data, lacking deep integration with clinical nursing decisions. Most systems can only monitor a single or a few physiological indicators (such as heart rate and blood oxygen), and data interpretation relies on the experience and judgment of medical staff, making it difficult to achieve dynamic assessment of patients' health status and early warning of potential risks. In addition, the inconsistent data formats and poor communication protocol compatibility between different sensor devices make it difficult to effectively integrate multi-source physiological data, forming "information silos" that restrict the timeliness and accuracy of nursing interventions. More importantly, current systems are mostly passive in generating intervention strategies, that is, they only trigger alarms when monitoring data is abnormal, lacking the ability to proactively recommend personalized nursing plans based on individual patient historical data, disease characteristics, and lifestyle habits, making it difficult to meet the needs of intelligent and automated interventions in home care scenarios.

[0004] In view of this, the present invention is proposed. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to overcome the shortcomings of the prior art and provide a nursing intervention system based on biosensors to monitor patients' vital signs, thereby solving the problems mentioned in the background art.

[0006] To solve the above-mentioned technical problems, the basic concept of the technical solution adopted by the present invention is as follows: A nursing intervention system based on biosensors for monitoring patients' vital signs includes: a biosensor module, a data processing module, a central control module, a nursing intervention module, and a data storage and communication module; The biosensor module is used to collect multiple vital signs parameters of the patient in real time, such as physiological data of heart rate, blood pressure, blood oxygen saturation, and body temperature. The data processing module is connected to the biosensor module and performs filtering, amplification, analog-to-digital conversion, and feature extraction on the collected raw physiological data, converting it into a recognizable digital signal. The central control module receives digital signals transmitted by the data processing module and compares and analyzes them with preset normal vital sign threshold ranges. The nursing intervention module is connected to the central control module. When the central control module detects that the patient's vital signs parameters exceed the threshold range, it can automatically trigger corresponding nursing intervention measures, such as issuing an audible and visual alarm signal to remind medical staff, generating a nursing suggestion plan, or starting an automatic drug delivery device. The data storage and communication module is used to store the patient's vital sign monitoring data and system operation logs, and can transmit the data to the hospital information management system or the mobile terminal of medical staff via wireless network to realize real-time data sharing and remote monitoring.

[0007] Optionally, the biosensor module adopts a flexible wearable design, uses medical-grade silicone material, has good skin fit and biocompatibility, and is suitable for monitoring sites on the wrist and chest of patients of different body types. It also has a built-in low-power Bluetooth chip, supports stable data acquisition for more than 72 hours continuously, and the sampling frequency can be flexibly adjusted in the range of 1Hz-100Hz according to clinical needs to ensure the timeliness and accuracy of physiological signal capture.

[0008] Optionally, the data processing module incorporates an adaptive filtering algorithm that can effectively filter out noise signals such as motion artifacts and electromagnetic interference. It also adopts a multi-channel parallel processing architecture, which can simultaneously extract and analyze the characteristic parameters of heart rate variability, blood pressure fluctuation curves, and blood oxygen waveforms. The data processing delay is controlled within 50ms, ensuring the real-time performance and reliability of the monitoring data.

[0009] Optionally, the central control module is equipped with an anomaly warning model based on deep learning. This model is built by training a large amount of clinical case data and can dynamically adjust the threshold according to the patient's age, underlying diseases, and real-time vital sign changes. For example, for elderly patients with cardiovascular diseases, the system will automatically widen the normal threshold range of blood pressure fluctuations and strengthen the abnormal identification weight of heart rate variability. The central control module also has a multi-parameter joint analysis function, which can correlate and calculate the data of heart rate, blood oxygen, and body temperature. When a single parameter slightly exceeds the threshold but multiple parameters are abnormal in synergy, the warning mechanism can still be triggered to avoid the risk of missed detection.

[0010] Optionally, the nursing intervention module includes a graded response mechanism that automatically matches the intervention level based on the severity of the abnormal vital signs. A Level 1 warning corresponds to a slight deviation of the parameter from the threshold; the system flashes a notification on the bedside display screen and pushes a text message to the responsible nurse's mobile terminal. A Level 2 warning targets moderate abnormalities; in addition to audible and visual alarms, it automatically retrieves the patient's recent medical records and medication records to generate preliminary nursing suggestions, such as adjusting the patient's position or supplementing fluids. A Level 3 warning is applicable to life-threatening parameter mutations; it immediately activates audible and visual alarms, simultaneously dials the department's on-call phone, and sends an emergency notification containing real-time monitoring data to the attending physician via the hospital intranet. Simultaneously, it links with the ward's intelligent infusion system to adjust the drug administration rate or suspend the infusion operation according to a preset emergency plan, buying time for rescue.

[0011] Optionally, the data storage and communication module adopts a distributed storage architecture, equipped with a 128GB local high-speed flash memory chip for real-time data caching, and supports encrypted data synchronization with the hospital cloud server. It uses the AES-256 encryption algorithm to ensure the security of data transmission and storage, complying with the requirements of the "Guidelines for Health and Medical Data Security". The data storage and communication module also has data visualization capabilities, automatically generating patient vital sign trend curves and parameter comparison analysis reports. This allows medical staff to access historical data at any time through system terminals or mobile devices, intuitively grasping the patterns of changes in patients' conditions and providing data support for optimizing clinical diagnosis and treatment plans.

[0012] By adopting the above technical solution, the present invention has the following beneficial effects compared with the prior art. Of course, any product implementing the present invention does not necessarily need to achieve all of the following advantages at the same time: This invention, by integrating a multi-parameter biosensor module, overcomes the limitations of traditional systems that monitor only a single indicator. It can simultaneously collect multiple key vital signs parameters such as heart rate, blood pressure, blood oxygen saturation, and body temperature, providing a data foundation for comprehensively assessing a patient's health status. Secondly, the data processing module employs an adaptive filtering algorithm and a multi-channel parallel processing architecture, effectively improving data quality and processing efficiency, ensuring the real-time nature and reliability of the monitoring data, and laying a solid foundation for subsequent precise analysis and intervention. The central control module, equipped with a deep learning-based anomaly warning model, achieves dynamic threshold adjustment and multi-parameter joint analysis, not only improving the accuracy of anomaly identification but also effectively avoiding the risk of missed detections, realizing a shift from passive alarm to proactive warning. Finally, the nursing intervention module's tiered response mechanism matches appropriate intervention measures according to the severity of the anomaly. From mild alerts to emergency rescue coordination, this invention ensures the timeliness and accuracy of interventions, meeting the needs of different clinical scenarios. The distributed storage architecture, encrypted data synchronization, and data visualization functions of the data storage and communication modules not only guarantee the secure storage and sharing of data but also provide medical staff with intuitive and convenient data query and analysis tools, helping to optimize clinical diagnosis and treatment plans. In summary, this invention, through the collaborative work of its various modules, achieves integrated intelligent management of physiological data collection, processing, analysis, early warning, and intervention. It effectively solves the problems of insufficient integration with clinical nursing decision-making, difficulties in integrating multi-source data, and passive intervention strategies in existing systems, significantly improving the intelligence and accuracy of nursing interventions. It is particularly suitable for various scenarios such as home care and hospital clinical practice, and has significant clinical application value and promising prospects for promotion.

[0013] The specific embodiments of the present invention will now be described in further detail with reference to the accompanying drawings. Attached Figure Description

[0014] The accompanying drawings described below are merely some embodiments. Those skilled in the art can obtain other drawings based on these drawings without any creative effort. In the drawings: Figure 1 This is a schematic diagram of a nursing intervention system.

[0015] It should be noted that these accompanying drawings and textual descriptions are not intended to limit the scope of the invention in any way, but rather to illustrate the concept of the invention to those skilled in the art by referring to specific embodiments. Detailed Implementation

[0016] The invention will now be described in further detail with reference to the accompanying drawings.

[0017] Please see Figure 1As shown, this embodiment provides a nursing intervention system based on biosensors to monitor patients' vital signs, including: a biosensor module, a data processing module, a central control module, a nursing intervention module, and a data storage and communication module; The biosensor module is used to collect multiple vital signs parameters of patients in real time, such as physiological data of heart rate, blood pressure, blood oxygen saturation, and body temperature. The data processing module, connected to the biosensor module, performs filtering, amplification, analog-to-digital conversion, and feature extraction on the collected raw physiological data, converting it into a recognizable digital signal. The central control module receives digital signals transmitted by the data processing module and compares and analyzes them with the preset normal vital sign threshold range. The nursing intervention module is connected to the central control module. When the central control module detects that the patient's vital signs parameters exceed the threshold range, it can automatically trigger corresponding nursing intervention measures, such as issuing an audible and visual alarm signal to remind medical staff, generating a nursing suggestion plan, or starting the automatic drug delivery device. The data storage and communication module is used to store patients' vital sign monitoring data and system operation logs, and can transmit the data to the hospital information management system or the mobile terminals of medical staff via wireless network, so as to realize real-time data sharing and remote monitoring.

[0018] The biosensor module in this embodiment adopts a flexible wearable design and is made of medical-grade silicone material, which has good skin fit and biocompatibility. It is suitable for monitoring sites on the wrist and chest of patients of different body types. It also has a built-in low-power Bluetooth chip, which supports stable data acquisition for more than 72 hours continuously. The sampling frequency can be flexibly adjusted in the range of 1Hz-100Hz according to clinical needs to ensure the timeliness and accuracy of physiological signal capture.

[0019] The data processing module of this embodiment has a built-in adaptive filtering algorithm, which can effectively filter out noise signals such as motion artifacts and electromagnetic interference. At the same time, it adopts a multi-channel parallel processing architecture, which can simultaneously extract and analyze the characteristic parameters of heart rate variability, blood pressure fluctuation curve and blood oxygen waveform. The data processing delay is controlled within 50ms, ensuring the real-time performance and reliability of the monitoring data. The data processing module is equipped with an adaptive Kalman filter algorithm and wavelet transform denoising technology, which can effectively filter out noise signals such as motion artifacts and electromagnetic interference. Simultaneously, it uses a 16-bit high-precision analog-to-digital converter to convert analog physiological signals into digital signals, and then utilizes a deep learning model to extract key features such as heart rate variability and blood pressure fluctuation trends, keeping data processing latency within 50ms, providing a high-quality data foundation for subsequent analysis. The central control module uses an STM32H743 microcontroller as its core and has a built-in dynamic threshold database for patient vital signs. It can automatically adjust the threshold range according to individual differences such as patient age, underlying diseases, and treatment stage. When abnormal parameters are detected, it can complete multi-dimensional analysis within one second, accurately determining the type of abnormality and risk level, such as distinguishing physiological... For hypertension fluctuations and pathological hypertensive crises, the nursing intervention module includes a three-level alarm mechanism. The first-level alarm is triggered by a local buzzer and red LED light on the device. The second-level alarm automatically sends text and voice reminders to the responsible nurse's smart wristband. The third-level alarm is linked to the hospital's nursing station's audio-visual alarm system and simultaneously retrieves the patient's recent medical records and medication records to generate a preliminary intervention plan. The plan details the recommended monitoring frequency, body positioning methods, and emergency handling procedures. For scenarios equipped with automatic drug delivery devices, the system can activate a micro-infusion pump for precise drug delivery after remote authorization from medical staff, based on preset drug delivery rules. The data storage and communication module uses a 128GB industrial-grade SD card for local data backup and supports automatic saving of monitoring data every 5 minutes. It also connects to the hospital's local area network via Wi-Fi 6 and 5G dual-mode communication protocols, achieving seamless integration with the electronic medical record system and nursing information system. Medical staff can view the patient's vital sign curves, historical data trend charts, and abnormal event records in real time via computer terminals or mobile apps. The system also features encrypted data transmission and access control functions to ensure the security of patient privacy information.

[0020] The central control module in this embodiment is equipped with an anomaly warning model based on deep learning. This model is built by training a large amount of clinical case data and can dynamically adjust the threshold according to the patient's age, underlying diseases, and real-time vital sign changes. For example, for elderly patients with cardiovascular diseases, the system will automatically widen the normal threshold range of blood pressure fluctuations and strengthen the abnormal identification weight of heart rate variability. The central control module also has a multi-parameter joint analysis function, which can correlate and calculate the data of heart rate, blood oxygen, and body temperature. When a single parameter slightly exceeds the threshold but multiple parameters are abnormal in synergy, the warning mechanism can still be triggered to avoid the risk of missed detection.

[0021] The nursing intervention module in this embodiment includes a graded response mechanism, which automatically matches the intervention level according to the severity of the abnormal vital signs. The first-level warning corresponds to a slight deviation of the parameter from the threshold. The system will flash the warning on the bedside display screen in the ward and push a text message to the responsible nurse's mobile terminal. The second-level warning is for moderate abnormalities. In addition to the audible and visual alarm, it will automatically retrieve the patient's recent medical records and medication records to generate preliminary nursing suggestions, such as adjusting the body position and supplementing fluids. The third-level warning is applicable to life-threatening parameter mutations. It will immediately activate the audible and visual alarm, simultaneously dial the department's on-call phone, and send an emergency notification containing real-time monitoring data to the attending physician through the hospital intranet. At the same time, it will link with the ward's intelligent infusion system to adjust the drug administration rate or suspend the infusion operation according to the preset emergency plan, so as to buy time for rescue.

[0022] Among its features, the system has dynamic priority handling capabilities when implementing graded responses. When multiple warning events occur simultaneously in the same department, the system will automatically sort the response order based on factors such as the severity of the patient's condition, the warning level, and the distance to the bedside. For example, when a level 3 warning and a level 2 warning are triggered at the same time, the system will prioritize dispatching medical and nursing resources to handle patients with level 3 warnings and display a prompt to postpone handling of level 2 warnings on the nurse's terminal. In addition, the nursing intervention module also supports the manual intervention override function. Medical and nursing staff can temporarily adjust the warning threshold or turn off alarms for specific parameters through authorization authentication to avoid false alarms caused by physiological fluctuations in postoperative recovery patients. At the same time, all manual operations will be recorded by the system and included in the operation log for easy subsequent quality traceability and process optimization.

[0023] The data storage and communication module in this embodiment adopts a distributed storage architecture and is equipped with a 128GB local high-speed flash memory chip for real-time data caching. It also supports encrypted data synchronization with the hospital cloud server and uses the AES-256 encryption algorithm to ensure the security of data transmission and storage, which complies with the requirements of the "Guidelines for Health and Medical Data Security". The data storage and communication module also has data visualization functions, which can automatically generate patient vital sign trend curves and parameter comparison analysis reports. It allows medical staff to access historical data at any time through system terminals or mobile devices, intuitively grasp the pattern of changes in patients' conditions, and provide data support for the optimization of clinical diagnosis and treatment plans.

[0024] In terms of communication protocols, this module is compatible with the HL7 FHIR international medical data exchange standard, enabling seamless integration with existing hospital HIS (Hospital Information System), LIS (Laboratory Information System), and EMR (Electronic Medical Record System). This allows for the interconnection and interoperability of patient basic information, examination and test results, and vital sign data, avoiding information silos. The module features built-in dual-redundant communication links: the primary link uses a gigabit Ethernet connection, while the backup link is secured via a 5G / 4G cellular network. In the event of a primary link failure, automatic switching to the backup link ensures continuous and reliable data transmission, meeting the needs of 24 / 7 uninterrupted clinical monitoring. Furthermore, the system supports offline data caching and breakpoint resume functionality. In the event of a network interruption, locally stored monitoring data is automatically re-uploaded to the cloud platform after network recovery, ensuring the integrity of data records.

[0025] The system in this embodiment also has adaptive learning capabilities, allowing for functional expansion and parameter customization based on the clinical needs of different departments. For example, for ICU patients, the system can add monitoring modules for special parameters such as intracranial pressure and central venous pressure, and strengthen the early warning model for multiple organ failure. In general ward scenarios, some monitoring indicators can be simplified, with a focus on optimizing battery life and wearability. In addition, the system supports seamless integration with existing hospital HIS and LIS systems, enabling automatic association of patient basic information, test results, and medication records, avoiding data silos, and improving the efficiency of medical and nursing work. In terms of user permission management, a role-based access control strategy is adopted to strictly distinguish the data operation permissions of different roles such as doctors, nurses, and administrators, ensuring the privacy and security of medical data and its standardized use.

[0026] By integrating a multi-parameter biosensor module, the limitations of traditional systems that only monitor single indicators are overcome. It can simultaneously collect multiple key vital signs parameters such as heart rate, blood pressure, blood oxygen saturation, and body temperature, providing a data foundation for a comprehensive assessment of patient health status. Secondly, the data processing module employs an adaptive filtering algorithm and a multi-channel parallel processing architecture, effectively improving data quality and processing efficiency, ensuring the real-time nature and reliability of monitoring data, and laying a solid foundation for subsequent precise analysis and intervention. The central control module, equipped with a deep learning-based anomaly warning model, achieves dynamic threshold adjustment and multi-parameter joint analysis, not only improving the accuracy of anomaly identification but also effectively avoiding the risk of missed detections, realizing a shift from passive alarm to proactive warning. The nursing intervention module's tiered response mechanism matches appropriate intervention measures according to the severity of the anomaly. From mild alerts to emergency rescue coordination, this invention ensures the timeliness and accuracy of interventions, meeting the needs of different clinical scenarios. The distributed storage architecture, encrypted data synchronization, and data visualization functions of the data storage and communication modules not only guarantee the secure storage and sharing of data but also provide medical staff with intuitive and convenient data query and analysis tools, helping to optimize clinical diagnosis and treatment plans. In summary, this invention, through the collaborative work of its various modules, achieves integrated intelligent management of physiological data collection, processing, analysis, early warning, and intervention. It effectively solves the problems of insufficient integration with clinical nursing decision-making, difficulties in integrating multi-source data, and passive intervention strategies in existing systems, significantly improving the intelligence and accuracy of nursing interventions. It is particularly suitable for various scenarios such as home care and hospital clinical practice, and has significant clinical application value and promising prospects for promotion.

[0027] This invention is not limited to the embodiments described above. Anyone should understand that structural changes made under the guidance of this invention, and any technical solutions that are the same as or similar to this invention, fall within the protection scope of this invention. Technical aspects, shapes, and structures not described in detail in this invention are all publicly known technologies.

Claims

1. A nursing intervention system based on biosensors for monitoring patients' vital signs, characterized in that, include: The system includes a biosensor module, a data processing module, a central control module, a nursing intervention module, and a data storage and communication module. The biosensor module is used to collect multiple vital signs parameters of the patient in real time, such as physiological data of heart rate, blood pressure, blood oxygen saturation, and body temperature. The data processing module is connected to the biosensor module and performs filtering, amplification, analog-to-digital conversion, and feature extraction on the collected raw physiological data, converting it into a recognizable digital signal. The central control module receives digital signals transmitted by the data processing module and compares and analyzes them with preset normal vital sign threshold ranges. The nursing intervention module is connected to the central control module. When the central control module detects that the patient's vital signs parameters exceed the threshold range, it can automatically trigger corresponding nursing intervention measures, such as issuing an audible and visual alarm signal to remind medical staff, generating a nursing suggestion plan, or starting an automatic drug delivery device. The data storage and communication module is used to store the patient's vital sign monitoring data and system operation logs, and can transmit the data to the hospital information management system or the mobile terminal of medical staff via wireless network to realize real-time data sharing and remote monitoring.

2. The nursing intervention system based on biosensors for monitoring patient vital signs according to claim 1, characterized in that, The biosensor module adopts a flexible wearable design and is made of medical-grade silicone, which has good skin fit and biocompatibility. It is suitable for monitoring sites on the wrist and chest of patients of different body types. It also has a built-in low-power Bluetooth chip, which supports stable data acquisition for more than 72 hours continuously. The sampling frequency can be flexibly adjusted in the range of 1Hz-100Hz according to clinical needs to ensure the timeliness and accuracy of physiological signal capture.

3. The nursing intervention system based on biosensors for monitoring patient vital signs according to claim 1, characterized in that, The data processing module incorporates an adaptive filtering algorithm that can effectively filter out noise signals such as motion artifacts and electromagnetic interference. It also adopts a multi-channel parallel processing architecture, which can simultaneously extract and analyze the characteristic parameters of heart rate variability, blood pressure fluctuation curves, and blood oxygen waveforms. The data processing latency is controlled within 50ms, ensuring the real-time performance and reliability of the monitoring data.

4. The nursing intervention system based on biosensors for monitoring patient vital signs according to claim 1, characterized in that, The central control module is equipped with a deep learning-based anomaly warning model. This model is built by training on a large amount of clinical case data and can dynamically adjust thresholds according to the patient's age, underlying diseases, and real-time vital sign changes. For example, for elderly patients with cardiovascular diseases, the system will automatically widen the normal threshold range for blood pressure fluctuations and strengthen the weight of abnormal heart rate variability identification. The central control module also has a multi-parameter joint analysis function, which can correlate and calculate data of heart rate, blood oxygen, and body temperature. When a single parameter slightly exceeds the threshold but multiple parameters are abnormal in synergy, the warning mechanism can still be triggered to avoid the risk of missed detection.

5. A nursing intervention system based on biosensors for monitoring patient vital signs according to claim 1, characterized in that, The nursing intervention module includes a graded response mechanism that automatically matches the intervention level based on the severity of the abnormal vital signs.

6. A nursing intervention system based on biosensors for monitoring patient vital signs according to claim 5, characterized in that, A Level 1 warning corresponds to a slight deviation of the parameter from the threshold. The system will flash a notification on the bedside display screen in the ward and push a text message to the responsible nurse's mobile terminal.

7. A nursing intervention system based on biosensors for monitoring patient vital signs according to claim 6, characterized in that, The Level 2 warning is for moderate abnormalities. In addition to audible and visual alarms, it automatically retrieves the patient's recent medical records and medication records to generate preliminary nursing suggestions, such as adjusting body position and supplementing fluids.

8. A nursing intervention system based on biosensors for monitoring patient vital signs according to claim 7, characterized in that, Level 3 early warning is applicable to life-threatening parameter mutations. It immediately activates audible and visual alarms, simultaneously dials the department's on-duty phone, and sends an emergency notification containing real-time monitoring data to the attending physician through the hospital intranet. At the same time, it links with the ward's intelligent infusion system to adjust the drug administration rate or suspend the infusion operation according to the preset emergency plan, thus buying time for rescue.

9. A nursing intervention system based on biosensors for monitoring patient vital signs according to claim 1, characterized in that, The data storage and communication module adopts a distributed storage architecture and is equipped with a 128GB local high-speed flash memory chip for real-time data caching. It also supports encrypted data synchronization with the hospital cloud server and uses the AES-256 encryption algorithm to ensure the security of data transmission and storage, which complies with the requirements of the "Guideline for Health and Medical Data Security".

10. A nursing intervention system based on biosensors for monitoring patient vital signs according to claim 9, characterized in that, The data storage and communication module also has data visualization capabilities, which can automatically generate trend curves of patients' vital signs and parameter comparison and analysis reports. It allows medical staff to access historical data at any time through system terminals or mobile devices, intuitively grasp the patterns of changes in patients' conditions, and provide data support for optimizing clinical diagnosis and treatment plans.

Images