Pathophysiology parameter real-time monitoring and intelligent analysis system

Abstract

The invention relates to the technical field of medical treatment, and particularly discloses a pathophysiology parameter real-time monitoring and intelligent analysis system which comprises a data management module, a real-time monitoring module, a data review module, a communication management module, a privacy protection module and an analysis decision module. The real-time monitoring module is responsible for collecting and processing physiological parameter data of a patient in real time, the data review module reviews the physiological parameter data in real time to form a statistical analysis report, and the communication management module is responsible for real-time message transmission to ensure data security and integrity; the key physiological parameters of the patient can be continuously tracked, and the abnormal physiological parameters can be rapidly detected through intelligent analysis, so that the medical staff can make diagnosis and treatment decisions more rapidly, the medical quality and efficiency are effectively improved, the risk of human errors is reduced through the automatic monitoring and analysis process, and the accuracy of diagnosis and treatment is improved. Meanwhile, the safety of the patient in the medical treatment process can be ensured.

Description

Technical Field

[0001] The present invention belongs to the field of medical technology, and in particular relates to a real-time monitoring and intelligent analysis system for pathophysiological parameters. Background Art

[0002] Clinical event risk refers to adverse outcomes that occur in the clinical medical system, such as cardiac arrest, epileptic seizures, or accidental death. Studies have shown that 59.4% of in-hospital cardiac arrests are preceded by abnormalities in ECG, blood pressure, body temperature, etc., 25% of emergency patients will have at least one abnormal vital sign, and patients with more than two abnormalities will have a 4.4-fold increase in the probability of emergency hospitalization. Therefore, monitoring changes in vital signs can help detect or predict clinical event risks in advance.

[0003] Physiological signals usually cover the body's bioelectric activity, temperature, pressure and other physical information, such as electromyography, electrocardiography, electroencephalography, electrooculography, and body position and movement signals. This physiological signal composed of continuous sampling points can characterize the intrinsic characteristics of the body's complex system. It is usually a high-dimensional, non-stationary, nonlinear, multimodal and heterogeneous expression. The special signal feature change pattern can be used as a basic indicator to reflect the health status of the human body. With the deepening of medical research and the diversification of clinical needs, the monitoring of physiological parameters is no longer limited to a single indicator, but requires the simultaneous monitoring of multiple physiological parameters, such as electrocardiogram, blood pressure, respiratory rate, blood oxygen content, body temperature, etc. There are differences in the physiological signals of different users. The reasons for the differences may be gender, age, etc. The differences in physiological signals make the probability distribution of data different. It is difficult for existing systems to collect and process multiple physiological parameters at the same time. The differences in physiological signals will make the system unable to accurately process physiological signals. Monitoring multiple physiological parameters requires integration and compatibility of different devices, which will consume additional resources and time.

[0004] Therefore, it is necessary to propose a real-time monitoring and intelligent analysis system for pathophysiological parameters to at least partially solve the problems existing in the prior art.

[0005] The above information disclosed in this background technology is only used to increase the understanding of the background technology of the present invention and therefore, it may include information that does not constitute the prior art known to ordinary technicians in this field. Summary of the invention

[0006] The purpose of the present invention is to provide a real-time monitoring and intelligent analysis system for pathophysiological parameters to solve the problems raised in the above-mentioned background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] The real-time monitoring and intelligent analysis system of pathophysiological parameters includes: a data management module, a real-time monitoring module, a data review module, a communication management module, a privacy protection module, and an analysis and decision module. The data management module is responsible for managing a large amount of physiological parameter data that can be collected by the system, the real-time monitoring module is responsible for collecting and processing the patient's physiological parameter data in real time, the data review module reviews the physiological parameter data in real time to form a statistical analysis report, the communication management module is responsible for real-time message transmission to ensure data security and integrity, the privacy protection module protects the privacy of the patient's personal data and provides reliable parameter information for treatment, and the analysis and decision module conducts in-depth analysis and decision-making on the patient's data to provide useful medical information or suggestions.

[0009] Preferably, the real-time monitoring module establishes a monitoring network through IoT and wireless communication to achieve data sharing and collaboration, uses Hadoop to process and analyze large-scale physiological parameter data, and supports failover and backup mechanisms to prevent data loss or service interruption due to system failure.

[0010] The physiological parameter information collected in real time is visualized. The main waveforms displayed include ECG waveform, respiration waveform, acceleration waveform, and exercise intensity waveform; the main parameters displayed include heart rate, respiration rate, body surface temperature, body movement intensity value, human posture parameters, pH value, blood oxygen saturation, carbon dioxide partial pressure (PaCO2), plasma osmotic pressure, serum potassium ion (K + ), serum sodium ion (Na + ), serum calcium ions (Ca 2+ ) and regularly check the equipment operating status and data transmission efficiency to ensure that the monitoring equipment can operate stably and reliably and meet the requirements of clinical use.

[0011] Preferably, the data management module uses JOSN to standardize the data of different sensors, integrates multi-source heterogeneous data and uses a data warehouse to store and manage the integrated data, and accesses and calls the integrated data through a unified data access interface.

[0012] Multi-source heterogeneous data include physiological parameter data, electronic health records, and omics data. During the integration process, data cleaning and preprocessing are used to ensure data consistency and reliability, and RESTful API is used to build a unified API interface for data interaction.

[0013] Preferably, the data review module uses data mining and machine learning algorithms to mine hidden associations and patterns, and displays them to medical staff in the form of charts and trend graphs through data visualization technology combined with real-time physiological parameter updates.

[0014] The report content includes the total number of heart beats, normal / abnormal heart beats, fastest / slowest heart rate, respiratory rate, body surface temperature, activity intensity and time, abnormal ECG events and related parameter statistics, etc., and the personal information reported is blurred or masked by combining anonymization and desensitization.

[0015] Preferably, the privacy protection module uses anonymization and desensitization to hide sensitive information in physiological parameter data to reduce the risk of exposure of personal identity information, encrypts personal data through ECDSA encryption, configures access control policies according to user roles and permissions, and records logs of all data access and operations.

[0016] Preferably, the communication management module completes the real-time transmission of physiological parameter data through Bluetooth wireless communication and TCP forwarding, adopts FIFO cache strategy in the intermediate stage to improve transmission efficiency, and can transmit various types of data to various components and modules in the system.

[0017] Preferably, the analysis and decision module uses a domain adaptation algorithm that combines features and maximizes classifier differences to determine the physiological states of different users, generates corresponding decision outputs based on the analysis results, provides medical advice or action guidelines, generates alarms for detected abnormal conditions, and notifies medical staff.

[0018] For multiple physiological parameter data, a convolutional network is used for feature extraction. Each physiological parameter is used as a channel of convolution input, and the physiological parameter data arrives in time sequence. In this way, LSTM is used to extract time series features, and the number of channels is used as the input dimension of LSTM. The number of LSTM recursions is determined according to the set length of the physiological parameter data. The attention mechanism is introduced to perform weighted splicing based on the calculated two feature weights to obtain the fused combined features. Two task classifiers are used to classify the target domain combined features, and then the target domain samples that cause confusion are located based on the classification differences of the two classifiers. Continuous adversarial training is performed to keep these confused samples away from the classifier decision boundary, so that the algorithm can adapt to the differences in physiological signals brought by new users, and can extract more distinguishing combined features to make accurate judgments on the user's current physical state.

[0019] Preferably, the system establishes data intercommunication and collaboration with existing medical information technology systems through the HL7 standard, and utilizes wireless communications to enable doctors to remotely monitor patient data, making it easier for patients in remote areas or with limited mobility to obtain timely diagnosis and guidance.

[0020] Compared with the prior art, the present invention has the following beneficial effects:

[0021] The present invention can continuously track the key physiological parameters of patients and quickly detect abnormal physiological parameters through intelligent analysis, so that medical staff can make diagnosis and treatment decisions more quickly, effectively improving the quality and efficiency of medical care. The automated monitoring and analysis process reduces the risk of human error, while ensuring the safety of patients during the medical process, reducing unnecessary monitoring cycles, reducing the incidence of complications, and increasing bed turnover, thereby reducing the overall cost of medical services.

[0022] The above summary is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments and features described above, further aspects, embodiments and features of the present invention will be readily apparent by reference to the accompanying drawings and the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a framework diagram of the real-time monitoring and intelligent analysis system of pathophysiological parameters of the present invention. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] Example:

[0026] See also Figure 1 As shown, the real-time monitoring and intelligent analysis system of pathophysiological parameters includes:

[0027] The real-time monitoring module is responsible for collecting and processing the patient's physiological parameter data in real time, establishing a monitoring network through IoT and wireless communications to achieve data sharing and collaboration, using Hadoop to process and analyze large-scale physiological parameter data, and supporting failover and backup mechanisms to prevent data loss or service interruption due to system failure.

[0028] Select appropriate sensors and IoT devices according to monitoring needs, such as physiological parameter monitoring equipment, environmental sensors, etc., to ensure that they can meet the wireless communication requirements of the communication management module. Arrange IoT devices reasonably based on actual conditions to ensure that the devices can effectively cover the monitoring area. IoT devices collect real-time data through sensors, and then transmit the data to the intermediate stage cache through Bluetooth wireless communication. After that, the cached data is forwarded to the system server at one time through TCP. Then, according to the preset data sharing strategy, different users can access and use real-time data as needed.

[0029] The intermediate stage cache can be to set up a data node in the applied IoT device, temporarily store the current sensor data in the node, and forward the cached data to the system server once via TCP after a fixed time period or when the data volume is reached. Relay software can also be designed and applied in the smart device used to complete the above operations. It introduces an automation engine to automatically control the entire process without the need for user management.

[0030] The data management module is responsible for managing the large amount of physiological parameter data that the system can collect, using JOSN to standardize the data of different sensors, integrating multi-source heterogeneous data and using a data warehouse to store and manage the integrated data, and accessing and calling the integrated data through a unified data access interface.

[0031] The data review module reviews physiological parameter data in real time to form a statistical analysis report, uses data mining and machine learning algorithms to discover hidden associations and patterns, and combines data visualization technology with real-time physiological parameter updates to present them to medical staff in the form of charts and trend graphs.

[0032] The privacy protection module protects the privacy and security of patients' personal data and provides reliable parameter information for treatment. It uses anonymization and desensitization to hide sensitive information in physiological parameter data to reduce the risk of exposure of personal identity information. It encrypts personal data through ECDSA encryption, configures access control policies based on user roles and permissions, and records logs of all data access and operations.

[0033] The communication management module is responsible for real-time message transmission to ensure data security and integrity. It completes the real-time transmission of physiological parameter data through Bluetooth wireless communication and TCP forwarding. It adopts FIFO cache strategy in the intermediate stage to improve transmission efficiency and can transmit various types of data to various components and modules in the system.

[0034] Set abnormal alarms based on actual information: set upper and lower limits of normal heart rate, upper and lower limits of normal respiratory rate, abnormal ECG event alarms, etc.; the personnel and equipment binding settings are responsible for displaying the binding status of personnel information and equipment on the real-time monitoring interface.

[0035] The analysis and decision-making module conducts in-depth analysis and decision-making on patient data to provide useful medical information or suggestions. It uses a domain adaptation algorithm that combines features and maximizes classifier differences to determine the physiological states of different users, generates corresponding decision outputs based on the analysis results, provides medical advice or action guidelines, generates alarms for detected abnormalities, and notifies medical staff.

[0036] Let {x s ,y s} represents the labeled source domain {Xs ,Y s}, and x t represents the target domain {X t}, the feature extractor G converts x s or x t Mapped to feature x, then two classifiers F1 and F2 classify feature x into K classes. Here p1(y|x) and p2(y|x) are used to represent the K-dimensional probability outputs of classifiers F1 and F2 respectively. Then the classification difference between classifiers F1 and F2 can be expressed by the following formula:

[0037]

[0038] The closer x is to the decision boundary, the greater the difference between p1(y|x) and p2(y|x). To alleviate this boundary confusion problem, classifiers F1 and F2 and feature generator G are trained in the following three steps:

[0039] Step 1: Train the classifier and feature generator simultaneously, so that the entire model can classify the labeled source domain data as accurately as possible;

[0040] Step 2: Fix the parameters of the feature generator G, train classifiers F1 and F2, increase the difference between the two classifiers, and locate those target domain samples that are easily confused;

[0041] Step 3: Fix classifiers F1 and F2, and train feature generator G to reduce the difference between the two classifiers calculated in the second step, so that feature generator G remaps the confused samples and gradually approaches the source domain density area.

[0042] Under the premise of ensuring accurate classification of the source domain, the second and third steps are repeated alternately, which is an adversarial training process, gradually mapping easily confused samples to densely distributed areas in the source domain to achieve the goal of reducing feature confusion.

[0043] The system establishes data interoperability and collaboration with existing medical information technology systems through the HL7 standard, and uses wireless communications to enable doctors to remotely monitor patient data, making it easier for patients in remote areas or with limited mobility to receive timely diagnosis and guidance.

[0044] From the above, it can be seen that the present invention can continuously track the patient's key physiological parameters and quickly detect abnormal physiological parameters through intelligent analysis, so that medical staff can make diagnosis and treatment decisions more quickly, effectively improving the quality and efficiency of medical care. The automated monitoring and analysis process reduces the risk of human error, while ensuring the safety of patients during the medical process, reducing unnecessary monitoring cycles, reducing the incidence of complications, and increasing bed turnover, thereby reducing the overall cost of medical services.

[0045] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples" or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.

[0046] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems) and computer program products according to embodiments of the present invention. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions.

[0047] In the drawings of the embodiments disclosed in the present invention, only the structures involved in the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other.

[0048] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. Pathophysiological parameters real-time monitoring and intelligent analysis system, characterized by: include: Data management module, real-time monitoring module, data review module, communication management module, privacy protection module, analysis and decision-making module. The data management module is responsible for managing a large amount of physiological parameter data that the system can collect. The real-time monitoring module is responsible for collecting and processing the patient's physiological parameter data in real time. The data review module reviews the physiological parameter data in real time to form a statistical analysis report. The communication management module is responsible for real-time message transmission to ensure data security and integrity. The privacy protection module protects the privacy of the patient's personal data and provides reliable parameter information for treatment. The analysis and decision-making module conducts in-depth analysis and decision-making on the patient's data to provide useful medical information or suggestions.

2. The real-time monitoring and intelligent analysis system for pathophysiological parameters according to claim 1, characterized in that: The real-time monitoring module establishes a monitoring network through IoT and wireless communication to achieve data sharing and collaboration, uses Hadoop to process and analyze large-scale physiological parameter data, and supports failover and backup mechanisms to prevent data loss or service interruption due to system failure.

3. The real-time monitoring and intelligent analysis system for pathophysiological parameters according to claim 2, characterized in that: The data management module uses JOSN to standardize the data of different sensors, integrates multi-source heterogeneous data and uses a data warehouse to store and manage the integrated data, and accesses and calls the integrated data through a unified data access interface.

4. The real-time monitoring and intelligent analysis system for pathophysiological parameters according to claim 3, characterized in that: The data review module uses data mining and machine learning algorithms to mine hidden associations and patterns, and displays them to medical staff in the form of charts and trend graphs through data visualization technology combined with real-time physiological parameter updates.

5. The real-time monitoring and intelligent analysis system for pathophysiological parameters according to claim 4, characterized in that: The privacy protection module uses anonymization and desensitization to hide sensitive information in physiological parameter data to reduce the risk of exposure of personal identity information, encrypts personal data through ECDSA encryption, configures access control policies according to user roles and permissions, and records logs of all data access and operations.

6. The real-time monitoring and intelligent analysis system for pathophysiological parameters according to claim 5, characterized in that: The communication management module completes the real-time transmission of physiological parameter data through Bluetooth wireless communication and TCP forwarding, adopts FIFO buffering strategy in the intermediate stage to improve transmission efficiency, and can transmit various types of data to various components and modules in the system.

7. The real-time monitoring and intelligent analysis system for pathophysiological parameters according to claim 6, characterized in that: The analysis and decision module uses a domain adaptation algorithm that combines features and maximizes classifier differences to determine the physiological states of different users, generates corresponding decision outputs based on the analysis results, provides medical advice or action guidelines, generates alarms for detected abnormal conditions, and notifies medical staff.

8. The real-time monitoring and intelligent analysis system for pathophysiological parameters according to claim 7, characterized in that: The system establishes data interoperability and collaboration with existing medical information technology systems through the HL7 standard, and uses wireless communications to enable doctors to remotely monitor patient data, making it easier for patients in remote areas or with limited mobility to receive timely diagnosis and guidance.

Images