Medical monitoring data transmission method, monitoring method and application method

Abstract

The application belongs to the technical field of data transmission, and particularly relates to a medical monitoring data transmission method, a monitoring method and an application method, which performs standardized conversion in a data transmission link, and comprises the following steps: adapting the connection modes of different devices through a physical interface or a wireless communication protocol and establishing a communication link; obtaining an analysis result by analyzing key parameters in a data stream in real time through a lightweight neural network model, automatically identifying potential semantic features of the data stream through multi-modal signal analysis to obtain an identification result, and dynamically generating temporary analysis rules based on the analysis result and the identification result; and recombining the decomposed independent parameters according to a unified standard format. In the application, the hardware of the device does not need to be modified, a standardized data stream transmission channel is automatically established, the continuous data transmission of various devices is ensured, the workload of manually configuring analysis rules can be reduced, the risk of misanalysis caused by waveform distortion can be reduced through multi-modal signal analysis, and finally the differences in private formats of the devices are eliminated.

Description

Technical Field

[0001] The present invention belongs to the technical field of data transmission, and in particular relates to a medical monitoring data transmission method, a monitoring method and an application method. Background Art

[0002] The core process of medical monitoring data transmission includes: real-time collection of patient physiological data through equipment, transmission to the cloud or server using reliable protocols after operations such as cleaning, encryption and formatting, and storage for analysis, visualization and abnormal warning. At the same time, data security is guaranteed through backup, permission control and system maintenance.

[0003] However, in the above process, the heterogeneity of medical devices may make data integration difficult. Specifically, since different types of monitoring equipment, such as ECG monitors and ventilators, often use private data formats or dedicated communication protocols, additional adapter interfaces need to be developed when transmitting to a unified platform. This not only increases the complexity of the system, but may also cause key indicators to be lost or misjudged due to data parsing errors, such as arrhythmia waveforms, thereby affecting the timeliness of clinical decision-making. The above is particularly prominent in cross-departmental or multi-institutional collaboration scenarios, which may lead to delayed diagnosis and treatment or the risk of misdiagnosis. Summary of the Invention

[0004] The present invention provides a medical monitoring data transmission method, a monitoring method and an application method, which can effectively solve the problems in the background technology.

[0005] To achieve the above object, the technical solution of the present invention is as follows:

[0006] Medical monitoring data transmission method, standardization conversion in the data transmission link, including:

[0007] Adapt the connection methods of different devices through physical interfaces or wireless communication protocols, and establish communication links for data stream transmission;

[0008] parse key parameters in the data stream in real time using a lightweight neural network model to obtain parsing results, automatically identify potential semantic features of the data stream through multimodal signal analysis to obtain recognition results, and dynamically generate temporary parsing rules based on the parsing and recognition results to decompose the data stream into independent parameters;

[0009] The independent parameters are reorganized into a unified standard format and pushed to the target system through a standardized interface.

[0010] Furthermore, multimodal signal analysis is used to automatically identify the potential semantic features of the data stream, including:

[0011] Cutting the data stream into adaptive time windows;

[0012] Distinguish the data mode of the current time window, extract corresponding features based on the differentiation results, and combine them with the context to obtain a multi-dimensional feature tensor;

[0013] Based on the multidimensional feature tensor, a rule engine is used to identify semantic features of the data stream.

[0014] Furthermore, based on the multidimensional feature tensor, using a rule engine to identify semantic features of the data stream includes:

[0015] Using the parsing result as dynamic input for semantic reasoning of the rule engine;

[0016] Using predefined rules as static input for semantic reasoning by the rule engine;

[0017] The rule engine performs a structured analysis on the data stream based on the multidimensional feature tensor to obtain an analysis result, and matches the dynamic input with the static input based on the analysis result to identify the semantic feature.

[0018] Furthermore, the lightweight network model performs the following tasks:

[0019] Receive the data stream, extract local temporal features in the data stream through a convolution operation, model temporal dependencies through a gated recurrent unit, and capture long temporal dependencies through a temporal convolutional network, and output temporal features; compress the temporal features into a vector of fixed length to obtain pooled features; map the pooled features to output parameters to generate structured key parameters;

[0020] The convolution kernel size and step size of the convolution operation are optimized for key waveform features in the data stream, and / or, when compressing the timing features, the neurons or channels that contribute most to the prediction of key parameters are preferentially retained.

[0021] Furthermore, the convolution kernel size and step size of the convolution operation are optimized for key waveform features in the data stream, including:

[0022] Identify key waveform features in data streams through data visualization tools;

[0023] Calculate the initial value of the convolution kernel based on the width and sampling rate of the key waveform features;

[0024] Calculate the initial value of the step size based on the interval and sampling rate of the key waveform features;

[0025] A grid search method is used to automatically search for the optimal convolution kernel size and step size based on the initial value within the preset parameter range.

[0026] Furthermore, temporary parsing rules are dynamically generated, including:

[0027] Initialize the basic parsing rule template according to the device type;

[0028] Modify the field mapping relationship in the basic parsing rule template according to the recognition result;

[0029] The modified parameter calculation logic is optimized according to the analysis result, and the temporary analysis rule is generated.

[0030] Furthermore, during the process of establishing a communication link, the device type is automatically identified based on the device's unique identification code and / or communication characteristics, and authentication and authority management are completed.

[0031] Furthermore, the method further includes calculating a confidence score for each parsing result when executing the temporary parsing rule;

[0032] When the confidence score is lower than a set threshold, manual confirmation and feedback is triggered.

[0033] The medical monitoring method adopts the medical monitoring data transmission method as described above to transmit monitoring data.

[0034] The application method of the medical monitoring data transmission method described above is to synchronously transmit monitoring data of at least two of the electrocardiogram monitor, ventilator, blood oxygen monitor, blood pressure monitor, electroencephalogram monitor, blood glucose monitor, body temperature monitor, infusion pump, and anesthesia machine to the same target system.

[0035] The technical solution of the present invention can achieve the following technical effects:

[0036] In the present invention, in order to solve the data integration problem caused by the heterogeneity of equipment during the transmission of medical monitoring data, a data standardization conversion mechanism is introduced to achieve unified analysis, disassembly and reorganization of data from different equipment, such as electrocardiogram monitors, ventilators, etc., so as to ensure that key information is not lost, the risk of misjudgment is minimized, and the timeliness of clinical decision-making is improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0038] Figure 1 A flowchart of a method for transmitting medical monitoring data;

[0039] Figure 2 Flowchart for automatically identifying latent semantic features of data streams through multimodal signal analysis;

[0040] Figure 3 A flowchart for identifying semantic features of data streams using a rule engine based on a multi-dimensional feature tensor;

[0041] Figure 4 Flowchart for optimizing the kernel size and stride of a convolution operation for key waveform features in a data stream. DETAILED DESCRIPTION

[0042] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0043] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which this invention pertains. The terms used in this specification are for the purpose of describing specific embodiments only and are not intended to limit the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0044] Example 1

[0045] Medical monitoring data transmission method, standardized conversion in the data transmission link, such as Figure 1 Shown, including:

[0046] Adapt the connection methods of different devices through physical interfaces or wireless communication protocols, and establish communication links for data stream transmission;

[0047] The system uses a lightweight neural network model to parse key parameters in the data stream in real time to obtain parsing results. It then automatically identifies the potential semantic features of the data stream through multimodal signal analysis to obtain recognition results. Based on the parsing and recognition results, it dynamically generates temporary parsing rules to decompose the data stream into independent parameters.

[0048] The independent parameters are reorganized into a unified standard format and pushed to the target system through a standardized interface.

[0049] In the present invention, in order to solve the data integration problem caused by the heterogeneity of equipment during the transmission of medical monitoring data, a data standardization conversion mechanism is introduced to achieve unified analysis, disassembly and reorganization of data from different equipment, such as electrocardiogram monitors, ventilators, etc., so as to ensure that key information is not lost, the risk of misjudgment is minimized, and the timeliness of clinical decision-making is improved.

[0050] In the implementation process, different monitoring devices are connected through physical interfaces or wireless communication protocols to build a stable communication link. This step ensures that even if there are differences in connection methods between devices, the data collected by each device can be transmitted to the platform. Through the established data link, real-time transmission of physiological data of patients is realized. In order to achieve better implementation effect, the data is preferably pre-cleaned, encrypted and formatted during transmission to ensure data integrity and security during transmission.

[0051] In the data transmission link, a lightweight neural network model is used to analyze the data stream in real time, which can efficiently extract key parameters such as heart rate and blood oxygen saturation, while ensuring low latency and being suitable for real-time monitoring scenarios. For various signals that may exist in the data stream, such as waveforms and noise information, a multi-modal signal analysis technique is used to automatically identify their potential semantic features. This step helps to discover abnormal waveforms, such as arrhythmia, and other clinically important implicit information, ensuring more comprehensive and accurate data analysis. The application of lightweight neural network model makes real-time analysis of key physiological parameters possible, and the multi-modal signal analysis effectively identifies the potential semantic information in the data stream, thereby avoiding important indicators from being lost or misjudged due to analysis errors, and improving the timeliness and accuracy of clinical decision-making.

[0052] Based on the analysis results and semantic recognition results, the system dynamically generates temporary analysis rules that adapt to the current data characteristics. This adaptive mechanism enables the system to handle situations where data formats are not unified or data analysis is difficult. The mechanism of dynamically generating temporary analysis rules enables the system to have high adaptability, and can quickly adjust the analysis strategy regardless of the device or data format changes, thereby ensuring good scalability and long-term adaptability. Using the generated temporary analysis rules, the original data stream is disassembled into independent parameter units, ensuring that each parameter can be accurately captured and processed, thereby avoiding key indicators from being missed or misjudged due to improper data integration. Finally, the disassembled independent parameters are reorganized according to the predefined standard format, and the standardized data has good interoperability, facilitating unified processing and analysis by various backend systems.

[0053] As a preferred embodiment of the above embodiment, as shown in Figure 2 The potential semantic features of the data stream are automatically identified through multi-modal signal analysis, including:

[0054] The data stream is cut into adaptive time windows, which can be cut according to the signal characteristics and dynamic changes of the data stream. The data in each time window has relatively stable characteristics, which is helpful for subsequent analysis. The adaptive window can automatically adjust the window length according to the actual fluctuation of the data, so that signals with different rhythms or change rates can be effectively captured.

[0055] Distinguish the data modality of the current time window, extract corresponding features based on the differentiation results, and combine them with the context to obtain a multidimensional feature tensor. In specific implementations, the signal type of the data in the current window can be identified, such as ECG waveform, respiratory signal, noise, etc. Based on the differentiation results, corresponding features such as waveform shape, spectral characteristics, statistical indicators, etc. are extracted in a targeted manner, and the contextual information of the previous and next windows is taken into consideration to construct a multidimensional feature tensor. This tensor can describe the comprehensive characteristics of the data from the time domain, frequency domain, and even spatial dimensions.

[0056] Based on the multidimensional feature tensor, the rule engine is used to identify the semantic features of the data stream. This step introduces an analysis method based on the rule engine. As a specific method during implementation, it can match and analyze the features in the tensor according to pre-set rules combined with clinical knowledge and experience, thereby automatically identifying potential semantic features in the data stream, such as abnormal waveforms, trend changes, emergencies, etc. The rule engine provides a transparent and explainable way to convert complex feature data into clinically meaningful semantic information.

[0057] This optimization solution, through the organic combination of adaptive time windows, multimodal feature extraction and rule engine recognition, can more accurately and comprehensively capture the potential semantic features in medical monitoring data, effectively improving data analysis accuracy and real-time warning capabilities.

[0058] As a preferred embodiment of the above, Figure 3 As shown in the figure, based on the multi-dimensional feature tensor, the rule engine is used to identify the semantic features of the data flow, including:

[0059] Use the parsing results as dynamic input for semantic reasoning in the rule engine;

[0060] Use predefined rules as static input for semantic reasoning of the rule engine;

[0061] The rule engine performs structured analysis on the data stream based on multi-dimensional feature tensors to obtain analysis results, and matches dynamic input and static input based on the analysis results to identify semantic features. During the matching process, the semantic features are identified by comparing real-time data with preset rules, making the description easier to understand.

[0062] In the above preferred solution, the dynamic input only contains the key parameters obtained by analysis, and the data volume is small, which helps the system to quickly process and respond to changes, ensuring that abnormal events are captured in time. Combined with the structured analysis results, the rule engine can quickly match predefined rules, reduce unnecessary computing burden, and improve overall processing efficiency. By extracting only key parameters, the system will focus on the most clinically significant information, avoid interference caused by too many signal details, reduce data redundancy, and make the rule matching and semantic reasoning process clearer, easier to maintain and upgrade.

[0063] During implementation, the comprehensive judgment basis provided by structured analysis enabled the system to operate robustly and accurately identify abnormalities in key parameters, even in the presence of data noise or large short-term fluctuations. The system can flexibly adapt to different clinical scenarios or device characteristics by adjusting predefined rules, eliminating the need to redesign the data parsing component. The predefined rules in the static input provide a clear basis for system judgments, making it easier for clinical staff to understand and trust the system output. The structured analysis and rule matching process ensures that each abnormality judgment has a basis, enhancing the system's verifiability and clinical practicality.

[0064] This optimization solution uses the key parameters obtained from real-time analysis as dynamic input and combines them with predefined static rules to achieve structured analysis and matching of multi-dimensional feature tensors by the rule engine. This solution focuses on the extraction and analysis of core information, which not only simplifies the data processing process, but also improves real-time performance and accuracy, while also having good robustness, adaptability and interpretability.

[0065] As a preferred embodiment of the above, the lightweight network model performs the following tasks:

[0066] Receive data streams, extract local temporal features from the data streams through convolution operations, model temporal dependencies through gated recurrent units, and capture long-term temporal dependencies through temporal convolutional networks, and output temporal features; compress the temporal features into fixed-length vectors to obtain pooled features; map the pooled features to output parameters to generate structured key parameters;

[0067] The convolution kernel size and step size of the convolution operation are optimized for key waveform features in the data stream, and / or, when compressing the timing features, the neurons or channels that contribute most to the prediction of key parameters are preferentially retained.

[0068] In the above optimization scheme, by optimizing the convolution kernel size and step size according to key waveform features, the convolution operation can more accurately capture the local timing information in the data stream, ensuring that important details are not missed; compressing the timing features into a vector of fixed length not only reduces the data dimension but also retains the key timing information, making the subsequent mapping of output parameters more efficient and stable. In the feature compression process, the neurons or channels that contribute most to the prediction of key parameters are retained first, effectively filtering out redundant information, and improving the accuracy and robustness of the model in extracting key indicators.

[0069] By using the above-mentioned lightweight network model, we can achieve accurate extraction of local timing features, comprehensive modeling of timing dependencies, efficient compression of key features, and retention of important information. This not only ensures real-time performance and low computational burden, but also significantly improves the prediction accuracy and robustness of key parameters.

[0070] As a preferred embodiment of the above, Figure 4 As shown, the kernel size and stride of the convolution operation are optimized for key waveform features in the data stream, including:

[0071] Identify key waveform features in data streams through data visualization tools;

[0072] Calculate the initial value of the convolution kernel based on the width and sampling rate of the key waveform features;

[0073] Calculate the initial value of the step size based on the interval and sampling rate of key waveform features;

[0074] A grid search method is used to automatically search for the optimal convolution kernel size and step size based on the initial value within the preset parameter range.

[0075] In the above optimization scheme, key waveform features are identified through data visualization, so that parameter calculation is based on actual data conditions, ensuring that the convolution kernel and step size can accurately cover and slide in the key waveform area, thereby improving the extraction quality of local timing features; the grid search method is used to automatically find the optimal parameters within the preset range, which improves the adaptability of the system and can be flexibly adjusted under different devices or data modes to enhance the robustness of the model.

[0076] After implementation, through reasonable convolution kernel size and step size, the amount of calculation can be reduced while ensuring the accuracy of feature capture, thereby reducing the overall computational burden of the network. This helps to achieve real-time monitoring and rapid response, and meet the real-time requirements of the medical monitoring system.

[0077] As a preferred embodiment of the above, dynamically generating temporary parsing rules includes:

[0078] Initialize the basic parsing rule template according to the device type;

[0079] Modify the field mapping relationship in the basic parsing rule template according to the recognition results;

[0080] The revised parameter calculation logic is optimized based on the analysis results, and temporary analysis rules are generated.

[0081] Since the data formats, data structures, and signal characteristics generated by different devices may differ, we pre-select a rule template with strong adaptability based on the device type to ensure a reasonable starting point for subsequent parsing work. We also provide a customized rule framework for different devices, enabling the parsing work to adapt to diverse data inputs and reduce errors or deviations that may occur when general rules process data from special devices.

[0082] During implementation, the recognition results are used to correct the field mapping relationship in the basic parsing rule template, adjust the correspondence between the data fields and the actual signal characteristics, and ensure that key indicators can be accurately extracted during data parsing. Dynamic correction and optimization of field mapping relationships can improve parsing accuracy, making the meaning of each field in the data more consistent with the actual measurement value. After correcting the field mapping, based on the latest parsing results, the parameter calculation logic is further optimized. Specifically, this may include adjusting the calculation formula, weight distribution, or logical judgment conditions in the algorithm, and ultimately generating a set of temporary parsing rules that adapt to the current data stream. The optimized parameter calculation logic can better adapt to actual data fluctuations and reflect changes in data characteristics in real time. The generated temporary parsing rules are more flexible and accurate, and can quickly respond to changes in device status and data anomalies.

[0083] In order to ensure better implementation results, during the establishment of the communication link, the device type is automatically identified based on the device's unique identification code and / or communication characteristics, and authentication and permission management are completed.

[0084] In specific implementation, when the device initiates a connection request, the system first automatically extracts the device's unique identification code, such as device ID, MAC address, etc., and / or related communication characteristics, such as connection protocol, signal strength, firmware version, etc.; to achieve the above technical purposes, the system can pre-maintain a set of device type databases or rule bases, and automatically identify by comparing the extracted information to ensure that subsequent processing can be customized based on the device characteristics.

[0085] After confirming the device type, the system authenticates the device using its identification code and / or other authentication credentials, such as a digital certificate, preset password, or token. This authentication mechanism allows only legitimate, authorized devices to access the communication link, preventing unauthorized devices from accessing the system. Upon successful authentication, the system automatically assigns the appropriate access rights to the device based on the device type and predefined permission policies. Specifically, different device types can be assigned different permission levels, such as read-only, write, or administrative, to ensure secure access to data and resources.

[0086] As a preferred embodiment of the above, the medical monitoring data transmission method further comprises calculating a confidence score for each parsing result when executing the temporary parsing rule; triggering manual confirmation and feedback when the confidence score is lower than a set threshold.

[0087] By triggering the manual confirmation mechanism, false decisions or false alarms can be avoided in low confidence scenarios, effectively reducing the safety hazards caused by automated parsing errors. When the score is lower than the pre-set threshold, it indicates that the current automatic parsing has a high degree of uncertainty or may deviate from the expectation. In the implementation process, once low confidence is detected, the system can automatically suspend the current parsing process and present the parsing results, related data and current rule information to the human operator through the man-machine cooperation interface.

[0088] The professional staff confirms, supplements or corrects the parsing results with low confidence, and updates the adjusted information to the temporary parsing rule through the system feedback mechanism. This process can be immediate intervention on a single parsing result, or improvement on the rule template, thereby improving the accuracy of subsequent parsing.

[0089] Embodiment two

[0090] The medical monitoring method uses the medical monitoring data transmission method as described in embodiment one to transmit monitoring data.

[0091] In this embodiment, the use of the above transmission method ensures the safety and integrity of the data transmission process, and significantly improves the real-time performance and adaptive ability of the system, thereby providing accurate and timely monitoring data support for clinical decision-making, reducing the risk of misdiagnosis and optimizing the use of medical resources.

[0092] Embodiment three

[0093] The application method of the medical monitoring data transmission method as described in embodiment one synchronously transmits monitoring data from at least two of an electrocardiogram monitor, a ventilator, a blood oxygen monitor, a blood pressure monitor, an electroencephalogram monitor, a blood glucose monitor, a body temperature monitor, an infusion pump and an anesthetic machine to the same target system.

[0094] Through the embodiment, the monitoring data collected by multiple devices at the same time point can be integrated and presented in real time, and the synchronous transmission enables the data from multiple devices such as electrocardiogram, respiration, blood oxygen, and blood pressure to be gathered in real time, provides all-around monitoring of the physiological state of a patient, forms a global and dynamic physiological state system of the patient, and various monitoring devices can have differences in design, data format, and communication protocol, and in the application of the method, the data collected by different devices is converted into a unified format and kept consistent in time through the adaptation and synchronization mechanism of the unified platform, so that the comparability and integration of the data are ensured.

[0095] The fusion of multiple types of data helps clinicians grasp the health status of a patient as a whole, discover the correlation changes between various indicators in time, improve the accuracy and timeliness of diagnosis, the unified data platform enables different departments or medical institutions to share real-time monitoring data, promotes collaborative diagnosis and treatment across departments and institutions, reduces the risk of misdiagnosis, and improves the overall level of medical services.

[0096] The above shows and describes the basic principles, main features, and advantages of the present application. It should be understood by those skilled in the art that the present application is not limited to the above embodiments, and the above embodiments and descriptions in the specification are only to illustrate the principles of the present application, and various changes and improvements can be made to the present application without departing from the spirit and scope of the present application, and these changes and improvements all fall within the scope of the present application. The scope of protection of the present application is defined by the appended claims and their equivalents.

Claims

1. A method for transmitting medical monitoring data, characterized in that: Standardized conversion is performed during data transmission, including: Adapt the connection methods of different devices through physical interfaces or wireless communication protocols, and establish communication links for data stream transmission; parse key parameters in the data stream in real time using a lightweight neural network model to obtain parsing results, automatically identify potential semantic features of the data stream through multimodal signal analysis to obtain recognition results, and dynamically generate temporary parsing rules based on the parsing and recognition results to decompose the data stream into independent parameters; Reorganize the independent parameters into a unified standard format and push them to the target system through a standardized interface; Automatically identify the potential semantic features of data streams through multimodal signal analysis, including: Cutting the data stream into adaptive time windows; Distinguish the data mode of the current time window, extract corresponding features based on the differentiation results, and combine them with the context to obtain a multi-dimensional feature tensor; Based on the multidimensional feature tensor, a rule engine is used to identify semantic features of the data stream.

2. The medical monitoring data transmission method according to claim 1, characterized in that: Based on the multidimensional feature tensor, using a rule engine to identify semantic features of the data stream includes: Using the parsing result as dynamic input for semantic reasoning of the rule engine; Using predefined rules as static input for semantic reasoning by the rule engine; The rule engine performs a structured analysis on the data stream based on the multidimensional feature tensor to obtain an analysis result, and matches the dynamic input with the static input based on the analysis result to identify the semantic feature.

3. The medical monitoring data transmission method according to claim 1 or 2, characterized in that: The lightweight neural network model performs the following tasks: Receive the data stream, extract local temporal features in the data stream through a convolution operation, model temporal dependencies through a gated recurrent unit, and capture long temporal dependencies through a temporal convolutional network, and output temporal features; compress the temporal features into a vector of fixed length to obtain pooled features; map the pooled features to output parameters to generate structured key parameters; The convolution kernel size and step size of the convolution operation are optimized for key waveform features in the data stream, and / or, when compressing the timing features, the neurons or channels that contribute most to the prediction of key parameters are preferentially retained.

4. The medical monitoring data transmission method according to claim 3, characterized in that: The convolution kernel size and step size of the convolution operation are optimized for key waveform features in the data stream, including: Identify key waveform features in data streams through data visualization tools; Calculate the initial value of the convolution kernel based on the width and sampling rate of the key waveform features; Calculate the initial value of the step size based on the interval and sampling rate of the key waveform features; A grid search method is used to automatically search for the optimal convolution kernel size and step size based on the initial value within the preset parameter range.

5. The medical monitoring data transmission method according to claim 1, characterized in that: Dynamically generate temporary parsing rules, including: Initialize the basic parsing rule template according to the device type; Modify the field mapping relationship in the basic parsing rule template according to the recognition result; The modified parameter calculation logic is optimized according to the analysis result, and the temporary analysis rule is generated.

6. The medical monitoring data transmission method according to claim 1, characterized in that: During the process of establishing a communication link, the device type is automatically identified based on the device's unique identification code and / or communication characteristics, and authentication and permission management are completed.

7. The medical monitoring data transmission method according to claim 1, characterized in that: The method further includes calculating a confidence score for each parsing result when executing the temporary parsing rule; When the confidence score is lower than a set threshold, manual confirmation and feedback is triggered.

8. A medical monitoring method, characterized in that: The monitoring data is transmitted using the medical monitoring data transmission method according to any one of claims 1 to 7.

9. The application method of the medical monitoring data transmission method according to any one of claims 1 to 7, characterized in that: For at least two of the electrocardiogram monitor, ventilator, blood oxygen monitor, blood pressure monitor, electroencephalogram monitor, blood glucose monitor, temperature monitor, infusion pump, and anesthesia machine, monitoring data are synchronously transmitted to the same target system.

Images