Breathing machine parameter adjusting method and system based on end-expiratory carbon dioxide monitoring
The method and system improve ventilator parameter adjustments by synchronizing and aligning respiratory and electrocardiogram data to dynamically adjust parameters based on end-tidal carbon dioxide monitoring, addressing inefficiencies and inaccuracies in manual methods.
Patent Information
- Application Number
- CN202411199113.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-29
- Publication Date
- 2024-12-03
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Existing ventilator parameter adjustment methods are inefficient and lack accuracy due to manual adjustments based on invasive blood gas analysis, failing to account for individual respiratory support needs.
A method and system that utilizes end-tidal carbon dioxide monitoring to synchronize and align respiratory and electrocardiogram data, extract features, evaluate support and physical state information, and adjust ventilator parameters dynamically through a neural network, eliminating the need for manual intervention.
Enhances the accuracy and timeliness of ventilator parameter adjustments by analyzing respiratory support and physical state in real-time, ensuring the adjustments align with individual user needs.
Smart Images

Figure CN119055898A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of artificial intelligence and parameter adjustment technology, and in particular to a ventilator parameter adjustment method and system based on end-tidal carbon dioxide monitoring. Background Art
[0002] Monitoring of end-tidal carbon dioxide is crucial for user airway positioning, respiratory monitoring, circulation monitoring, auxiliary diagnosis and disease assessment. Especially in the field of ventilator parameter adjustment, medical staff will set the ventilator mode and parameters, such as oxygen concentration, tidal volume, respiratory rate and minute ventilation, according to the user's end-tidal carbon dioxide data to ensure effective ventilation of the user. However, due to the low efficiency and slow timeliness of manual adjustment, how to intelligently adjust the parameters of the ventilator is the current research focus.
[0003] The traditional method of adjusting ventilator parameters relies on the results of blood gas analysis, but arterial blood gas analysis requires arterial blood to be collected. This process is invasive and intermittent. Some medical institutions with conditions connect end-tidal carbon dioxide monitoring instruments to collect users' end-tidal carbon dioxide data in real time, and when the end-tidal carbon dioxide data meets the parameter adjustment conditions, they warn the staff and manually adjust the ventilator parameters. However, this method is still inefficient, and different users have different respiratory support needs, which makes the real-time adjustment of ventilator parameters less accurate. Summary of the invention
[0004] The main purpose of the present invention is to provide a ventilator parameter adjustment method and system based on end-tidal carbon dioxide monitoring, aiming to solve the problem that the existing technology is still inefficient and the respiratory support needs of different users are different, resulting in low accuracy in real-time adjustment of ventilator parameters.
[0005] To achieve the above object, the present invention provides a method for adjusting ventilator parameters based on end-tidal carbon dioxide monitoring, the method comprising:
[0006] Acquire the user's current respiratory monitoring data, the user's electrocardiogram monitoring data, and the user's current condition information, and perform synchronization and alignment processing on the user's respiratory monitoring data and the user's electrocardiogram monitoring data to obtain the user's comprehensive monitoring data;
[0007] Extracting each comprehensive monitoring feature in the comprehensive monitoring data through a data extraction strategy, and evaluating the user's current respiratory support demand information and the user's current physical state information through a feature evaluation model based on each monitoring feature information;
[0008] Based on the current breathing support demand information of the user and the current physical condition information of the user, generating the current breathing data adjustment range of the user through the breathing adjustment network, and based on the current condition information of the user and the current breathing data adjustment range of the user, identifying the target breathing adjustment amount of the user;
[0009] A target ventilator adjustment parameter of the ventilator corresponding to the target respiratory adjustment amount is identified through a ventilator adjustment database.
[0010] Optionally, the synchronous alignment processing of the user's respiratory monitoring data and the user's electrocardiogram monitoring data to obtain the user's comprehensive monitoring data includes:
[0011] Splitting the user's respiration monitoring data into first data sets of each respiration monitoring type, and splitting the user's electrocardiogram monitoring data into second data sets of each electrocardiogram monitoring type;
[0012] The first data sets of each respiratory monitoring type and the second data sets of each electrocardiogram monitoring type are respectively distributed and sorted in time order to obtain first data distribution information and second data distribution information, and the first data distribution information and the second data distribution information at the same time are processed to obtain the target first data distribution information of each respiratory monitoring type and the target second data distribution information of each electrocardiogram monitoring type;
[0013] The target first data distribution information of all respiratory monitoring types and the target second data distribution information of all electrocardiogram monitoring types are used as the comprehensive monitoring data of the user.
[0014] Optionally, extracting each comprehensive monitoring feature in the comprehensive monitoring data through a data extraction strategy includes:
[0015] In the monitoring database, query the first feature extraction strategy for each respiratory monitoring type, and query the second feature extraction strategy for each electrocardiogram monitoring type in the monitoring database;
[0016] Extracting the first monitoring features in the target first data distribution information of each respiratory monitoring type respectively through the first feature extraction strategy of each respiratory monitoring type, and extracting the second monitoring features in the target second data distribution information of each electrocardiogram monitoring type respectively through the second feature extraction strategy of each electrocardiogram monitoring type;
[0017] All the first monitoring features and all the second monitoring features are used as comprehensive monitoring features in the comprehensive monitoring data.
[0018] Optionally, the evaluating the user's current respiratory support requirement information and the user's current physical state information through a feature evaluation model based on each of the monitoring feature information includes:
[0019] Based on the evaluation database, in each respiratory monitoring type, a first respiratory monitoring type related to respiratory support and a second respiratory monitoring type related to a physical state are screened, and based on the evaluation database, in each electrocardiogram monitoring type, a first electrocardiogram monitoring type related to the respiratory support and a second electrocardiogram monitoring type related to a physical state are screened;
[0020] Splitting the feature assessment model into a respiratory support demand assessment model and a physical state assessment model;
[0021] Based on the first monitoring feature of each of the first respiratory monitoring types and the second monitoring feature of each of the first ECG monitoring types, the user's current respiratory support requirement information is evaluated through the respiratory support requirement evaluation model, and based on the first monitoring feature of each of the second respiratory monitoring types and the second monitoring feature of each of the second ECG monitoring types, the user's current physical state information is evaluated through the physical state evaluation model.
[0022] Optionally, the generating the current breathing data adjustment range of the user through a breathing adjustment network based on the current breathing support requirement information of the user and the current physical state information of the user includes:
[0023] Based on the current respiratory support requirement information of the user, query the respiratory support requirement level of the user, and based on the current physical condition information of the user, query the physical condition type of the user;
[0024] Using the user's respiratory support requirement level and the user's physical condition type, through the respiratory adjustment network, to identify the user's current target respiratory data range;
[0025] The current breathing data of the ventilator is collected, and based on the current target breathing data range and the current breathing data, an adjustment range of the current breathing data of the user is calculated.
[0026] Optionally, the identifying the target breathing adjustment amount of the user based on the current condition information of the user and the current breathing data adjustment range of the user includes:
[0027] Based on the current condition information of the user, querying the respiratory data limit corresponding to the current condition information of the user in a condition database;
[0028] A target breathing adjustment amount of the user is calculated based on the current breathing data adjustment range of the user and the user breathing data limit.
[0029] Optionally, the method further includes:
[0030] Adjusting the ventilator based on the target ventilator adjustment parameter to obtain respiratory monitoring feedback data of the user, and evaluating the current physiological state of the user through a physiological evaluation strategy based on the respiratory monitoring feedback data;
[0031] When the current physiological state of the user does not conform to the physiological state range corresponding to the current condition information of the user, reacquire the current respiratory monitoring data of the user and the electrocardiogram monitoring data of the user, and return to the step of performing synchronous alignment processing on the respiratory monitoring data of the user and the electrocardiogram monitoring data of the user to obtain the comprehensive monitoring data of the user;
[0032] Until the current physiological state of the user meets the physiological state range corresponding to the current condition information of the user, the preset user breathing state monitoring process is executed.
[0033] In addition, to achieve the above-mentioned purpose, the present invention also provides a ventilator parameter adjustment system based on end-tidal carbon dioxide, the ventilator parameter adjustment system based on end-tidal carbon dioxide comprising:
[0034] An acquisition module, used to acquire the user's current respiratory monitoring data, the user's ECG monitoring data, and the user's current condition information, and perform synchronization and alignment processing on the user's respiratory monitoring data and the user's ECG monitoring data to obtain the user's comprehensive monitoring data;
[0035] An evaluation module, configured to extract each comprehensive monitoring feature in the comprehensive monitoring data through a data extraction strategy, and based on each monitoring feature information, evaluate the user's current respiratory support demand information and the user's current physical state information through a feature evaluation model;
[0036] A generating module, configured to generate a current breathing data adjustment range of the user through a breathing adjustment network based on the current breathing support demand information of the user and the current physical condition information of the user, and to identify a target breathing adjustment amount of the user based on the current condition information of the user and the current breathing data adjustment range of the user;
[0037] The identification module is used to identify the target ventilator adjustment parameter of the ventilator corresponding to the target breathing adjustment amount through the ventilator adjustment database.
[0038] Optionally, the acquisition module is specifically used to:
[0039] Splitting the user's respiration monitoring data into first data sets of each respiration monitoring type, and splitting the user's electrocardiogram monitoring data into second data sets of each electrocardiogram monitoring type;
[0040] The first data sets of each respiratory monitoring type and the second data sets of each electrocardiogram monitoring type are respectively distributed and sorted in time order to obtain first data distribution information and second data distribution information, and the first data distribution information and the second data distribution information at the same time are processed to obtain the target first data distribution information of each respiratory monitoring type and the target second data distribution information of each electrocardiogram monitoring type;
[0041] The target first data distribution information of all respiratory monitoring types and the target second data distribution information of all electrocardiogram monitoring types are used as the comprehensive monitoring data of the user.
[0042] Optionally, the evaluation module is specifically used to:
[0043] In the monitoring database, query the first feature extraction strategy for each respiratory monitoring type, and query the second feature extraction strategy for each electrocardiogram monitoring type in the monitoring database;
[0044] Extracting the first monitoring features in the target first data distribution information of each respiratory monitoring type respectively through the first feature extraction strategy of each respiratory monitoring type, and extracting the second monitoring features in the target second data distribution information of each electrocardiogram monitoring type respectively through the second feature extraction strategy of each electrocardiogram monitoring type;
[0045] All the first monitoring features and all the second monitoring features are used as comprehensive monitoring features in the comprehensive monitoring data.
[0046] Optionally, the evaluation module is specifically used to:
[0047] Based on the evaluation database, in each respiratory monitoring type, a first respiratory monitoring type related to respiratory support and a second respiratory monitoring type related to a physical state are screened, and based on the evaluation database, in each electrocardiogram monitoring type, a first electrocardiogram monitoring type related to the respiratory support and a second electrocardiogram monitoring type related to a physical state are screened;
[0048] Splitting the feature assessment model into a respiratory support demand assessment model and a physical state assessment model;
[0049] Based on the first monitoring feature of each of the first respiratory monitoring types and the second monitoring feature of each of the first ECG monitoring types, the user's current respiratory support requirement information is evaluated through the respiratory support requirement evaluation model, and based on the first monitoring feature of each of the second respiratory monitoring types and the second monitoring feature of each of the second ECG monitoring types, the user's current physical state information is evaluated through the physical state evaluation model.
[0050] Optionally, the generating module is specifically used for:
[0051] Based on the current respiratory support requirement information of the user, query the respiratory support requirement level of the user, and based on the current physical condition information of the user, query the physical condition type of the user;
[0052] Using the user's respiratory support requirement level and the user's physical condition type, through the respiratory adjustment network, to identify the user's current target respiratory data range;
[0053] The current breathing data of the ventilator is collected, and based on the current target breathing data range and the current breathing data, an adjustment range of the current breathing data of the user is calculated.
[0054] Optionally, the generating module is specifically used for:
[0055] Based on the current condition information of the user, querying the respiratory data limit corresponding to the current condition information of the user in a condition database;
[0056] A target breathing adjustment amount of the user is calculated based on the current breathing data adjustment range of the user and the user breathing data limit.
[0057] Optionally, the system further includes:
[0058] An evaluation module, configured to adjust the ventilator based on the target ventilator adjustment parameters, obtain the user's respiratory monitoring feedback data, and evaluate the user's current physiological state through a physiological evaluation strategy based on the respiratory monitoring feedback data;
[0059] an iteration module, configured to reacquire the current respiratory monitoring data of the user and the electrocardiogram monitoring data of the user when the current physiological state of the user does not conform to the physiological state range corresponding to the current condition information of the user, and return to execute the step of performing synchronous alignment processing on the respiratory monitoring data of the user and the electrocardiogram monitoring data of the user to obtain the comprehensive monitoring data of the user;
[0060] The execution module is used to execute a preset user respiratory state monitoring process until the current physiological state of the user meets the physiological state range corresponding to the current condition information of the user.
[0061] In a third aspect, the present application provides a computer device, wherein the computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of any one of the methods in the first aspect are implemented.
[0062] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.
[0063] The present invention provides a method and system for adjusting ventilator parameters based on end-tidal carbon dioxide monitoring, the method comprising: obtaining a user's current respiratory monitoring data, the user's electrocardiogram monitoring data, and the user's current condition information, and performing synchronous alignment processing on the user's respiratory monitoring data and the user's electrocardiogram monitoring data to obtain the user's comprehensive monitoring data; extracting each comprehensive monitoring feature in the comprehensive monitoring data through a data extraction strategy, and based on each of the monitoring feature information, evaluating the user's current respiratory support demand information and the user's current physical state information through a feature evaluation model; based on the user's current respiratory support demand information and the user's current physical state information, generating the user's current respiratory data adjustment range through a respiratory adjustment network, and identifying the user's target respiratory adjustment amount based on the user's current condition information and the user's current respiratory data adjustment range; identifying the target ventilator adjustment parameter of the ventilator corresponding to the target respiratory adjustment amount through a ventilator adjustment database. This solution obtains monitoring data corresponding to the user's physiological parameters from multiple angles such as respiratory monitoring data and electrocardiogram monitoring data, thereby analyzing the user's current respiratory support demand information and current physical condition information from multiple angles, thereby improving the accuracy and practicality of identifying respiratory support needs and physical conditions. Then, this solution combines the respiratory support needs, physical condition, and the user's current medical condition information to comprehensively analyze the user's target respiratory adjustment amount through the respiratory adjustment network, which can not only effectively ensure the accuracy of the respiratory adjustment, but also ensure that the adjusted target respiratory adjustment amount is closer to the respiratory adjustment amount actually required by the user. Finally, this solution does not require manual adjustment, but instead realizes a dynamic respiratory parameter adjustment process through real-time monitoring and real-time adjustment to improve the timeliness and practicality of adjusting the user's respiratory needs. Thereby comprehensively improving the accuracy of real-time adjustment of ventilator parameters. BRIEF DESCRIPTION OF THE DRAWINGS
[0064] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0065] Figure 1 is a flow chart of a ventilator parameter adjustment method based on end-tidal carbon dioxide monitoring provided by an embodiment of the present invention;
[0066] Figure 2 It is a structural schematic diagram of a ventilator parameter adjustment system based on end-tidal carbon dioxide monitoring provided by an embodiment of the present invention;
[0067] Figure 3 An internal structure diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0068] The ventilator parameter adjustment method based on end-tidal carbon dioxide monitoring provided by an embodiment of the present invention is applied to a ventilator parameter adjustment system based on end-tidal carbon dioxide monitoring. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" in the specification and claims of this application and the above-mentioned figure descriptions and any variations thereof are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of this application or the above-mentioned figures are used to distinguish different objects, not to describe a specific order.
[0069] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.
[0070] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.
[0071] The ventilator parameter adjustment method based on end-tidal carbon dioxide monitoring provided by the embodiment of the present application can be applied to the application environment of ventilator parameter adjustment. The method can be applied to a terminal, a server, or a system including a terminal and a server, and is realized by the interaction of the terminal and the server. Among them, the terminal can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, etc. Among them, the terminal obtains the monitoring data corresponding to the physiological parameters of the user from multiple angles such as respiratory monitoring data and electrocardiogram monitoring data, thereby analyzing the current respiratory support demand information and the current physical state information of the user from multiple angles, thereby improving the accuracy and practicality of identifying the respiratory support demand and the physical state. Then, this scheme combines the respiratory support demand, the physical state, and the current condition information of the user, and comprehensively analyzes the target respiratory adjustment amount of the user through the respiratory adjustment network, which can not only effectively ensure the accuracy of the respiratory adjustment, but also ensure that the adjusted target respiratory adjustment amount is closer to the respiratory adjustment amount of the actual demand of the user. Finally, this scheme does not need manual adjustment, but realizes the dynamic respiratory parameter adjustment process by real-time monitoring and real-time adjustment, so as to improve the adjustment timeliness and practicality of the user's respiratory demand. Thereby comprehensively improving the accuracy of real-time adjustment of ventilator parameters.
[0072] In one embodiment, Figure 1 As shown, a method for adjusting ventilator parameters based on end-tidal carbon dioxide monitoring is provided, which is described by taking the method applied to a terminal as an example, and includes the following steps:
[0073] Step S101, obtaining the user's current respiratory monitoring data, the user's electrocardiogram monitoring data, and the user's current condition information, and performing synchronization and alignment processing on the user's respiratory monitoring data and the user's electrocardiogram monitoring data to obtain the user's comprehensive monitoring data.
[0074] In this embodiment, the terminal obtains the current respiratory monitoring data of multiple respiratory monitoring types through a pre-set integrated high-precision sensor array, wherein the respiratory monitoring type includes but is not limited to an end-tidal carbon dioxide sensor type, an oxygen sensor type, etc. Then the terminal obtains each ECG monitoring data through the multiple sensors of the above array, wherein the ECG monitoring type of the ECG monitoring data includes but is not limited to the ECG monitoring type corresponding to the respiratory rate sensor, the ECG monitoring type corresponding to the heart rate monitor, the ECG monitoring type corresponding to the sphygmomanometer, the ECG monitoring type corresponding to the blood oxygen saturation sensor, etc. Then, the terminal synchronizes and aligns each respiratory monitoring data and each ECG monitoring data through a time synchronization strategy and a space synchronization strategy to obtain the comprehensive monitoring data of the user. Among them, the comprehensive monitoring data includes the target first data distribution information of each respiratory monitoring type and the target second data distribution information of each ECG monitoring type. The specific determination process will be described in detail later.
[0075] Step S102, extracting various comprehensive monitoring features in the comprehensive monitoring data through a data extraction strategy, and based on each monitoring feature information, evaluating the user's current respiratory support demand information and the user's current physical state information through a feature evaluation model.
[0076] In this embodiment, the terminal extracts each comprehensive monitoring feature in the comprehensive monitoring data through a data extraction strategy, and based on each monitoring feature information, evaluates the user's current respiratory support demand information and the user's current physical state information through a feature evaluation model. Wherein, the data extraction strategy includes a first feature extraction strategy for each respiratory monitoring type, and a second feature extraction strategy for each electrocardiogram monitoring type. Wherein, different monitoring types and different monitoring types have different extraction strategies, which are stored in the monitoring database and the corresponding relationship between the extraction strategy and type in the monitoring database. For example, the extraction strategy of the carbon dioxide monitoring type is to extract feature data such as the carbon dioxide concentration value, the carbon dioxide percentage value, and the change value of carbon dioxide in the carbon dioxide monitoring data. Then, based on each monitoring feature information, the terminal evaluates the user's current respiratory support demand information and the user's current physical state information through a feature evaluation model. Wherein, the feature evaluation model includes a respiratory support demand evaluation model and a physical state evaluation model. The evaluation database includes the association information between respiratory support and each respiratory monitoring type and ECG monitoring type, and includes the association information between the physical state and each respiratory monitoring type and ECG monitoring type. The terminal identifies the evaluation respiratory support requirement information, the first monitoring feature of the respiratory monitoring type corresponding to the physical state information, and the second monitoring feature of the ECG monitoring type by querying each association information. The specific identification process will be described in detail later.
[0077] Step S103, based on the user's current breathing support demand information and the user's current physical condition information, generate the user's current breathing data adjustment range through the breathing adjustment network, and identify the user's target breathing adjustment amount based on the user's current condition information and the user's current breathing data adjustment range.
[0078] In this embodiment, the terminal generates the user's current breathing data adjustment range through the breathing adjustment network based on the user's current breathing support demand information and the user's current physical condition information, and identifies the user's target breathing adjustment amount based on the user's current condition information and the user's current breathing data adjustment range. Wherein, the breathing adjustment network is a classifier network based on a reinforcement learning neural network, and the terminal identifies the user's current breathing support demand information and the current breathing data adjustment range corresponding to the user's current physical condition information through the breathing adjustment network. Wherein, the target breathing adjustment amount includes sub-adjustments of each breathing adjustment type, and the breathing adjustment type includes but is not limited to oxygen concentration output type per unit time, gas output rate value type, gas output frequency value type, etc. The unit time is a time value preset by the staff at the terminal, which can change with the adjustment of the staff.
[0079] Step S104, identifying the target ventilator adjustment parameter of the ventilator corresponding to the target respiratory adjustment amount through the ventilator adjustment database.
[0080] In this embodiment, the terminal identifies the target ventilator adjustment parameter of the ventilator corresponding to the target respiratory adjustment amount through the ventilator adjustment database. The ventilator adjustment database includes the correspondence between each ventilator adjustment parameter and each respiratory adjustment amount, and the terminal identifies the target ventilator adjustment parameter of the ventilator corresponding to the target respiratory adjustment amount through the correspondence.
[0081] Based on the above scheme, by comprehensively acquiring the monitoring data corresponding to the user's physiological parameters from multiple angles such as respiratory monitoring data and electrocardiogram monitoring data, the user's current respiratory support demand information and current physical condition information are analyzed from multiple angles, thereby improving the accuracy and practicality of identifying respiratory support needs and physical conditions. Then, this scheme combines the respiratory support needs, physical condition, and the user's current medical condition information, and comprehensively analyzes the user's target respiratory adjustment amount through the respiratory adjustment network, which can not only effectively ensure the accuracy of the respiratory adjustment, but also ensure that the adjusted target respiratory adjustment amount is closer to the respiratory adjustment amount actually required by the user. Finally, this scheme does not require manual adjustment, but realizes the dynamic respiratory parameter adjustment process through real-time monitoring and real-time adjustment, so as to improve the timeliness and practicality of the adjustment of the user's respiratory needs. Thereby comprehensively improving the accuracy of real-time adjustment of ventilator parameters.
[0082] Optionally, the user's respiratory monitoring data and the user's ECG monitoring data are synchronously aligned to obtain the user's comprehensive monitoring data, including: splitting the user's respiratory monitoring data into a first data set of each respiratory monitoring type, and splitting the user's ECG monitoring data into a second data set of each ECG monitoring type; distributing and sorting each first data set of each respiratory monitoring type and each second data set of each ECG monitoring type in chronological order to obtain each first data distribution information and each second data distribution information; processing each first data distribution information at the same time and each second data distribution information at the same time to obtain target first data distribution information of each respiratory monitoring type and target second data distribution information of each ECG monitoring type; and using the target first data distribution information of all respiratory monitoring types and the target second data distribution information of all ECG monitoring types as the user's comprehensive monitoring data.
[0083] In this embodiment, the terminal splits the user's respiratory monitoring data into the first data set of each respiratory monitoring type, and splits the user's ECG monitoring data into the second data set of each ECG monitoring type. Then, the terminal performs distribution sorting processing on each first data set of each respiratory monitoring type and each second data set of each ECG monitoring type in chronological order to obtain each first data distribution information and each second data distribution information. Afterwards, the terminal processes each first data distribution information at the same time and each second data distribution information at the same time to obtain the target first data distribution information of each respiratory monitoring type and the target second data distribution information of each ECG monitoring type. During the distribution sorting processing, the terminal performs curve smoothing processing on the initial first data distribution information / initial second data distribution information obtained to obtain each first data distribution information / second data distribution information. Thereby reducing the influence of a single discrete value on the distribution information, and improving the accuracy of each data distribution information obtained.
[0084] Then, the terminal uses the target first data distribution information of all respiratory monitoring types and the target second data distribution information of all electrocardiogram monitoring types as the comprehensive monitoring data of the user.
[0085] Based on the above scheme, by arranging and distributing at different time points and then performing synchronous alignment processing, the problem of the accuracy of analyzing the user's respiratory support needs and physical condition being affected by time differences and data logic differences is avoided, thereby improving the accuracy and practicality of identifying the user's comprehensive monitoring data.
[0086] Optionally, various comprehensive monitoring features in the comprehensive monitoring data are extracted through a data extraction strategy, including: querying the first feature extraction strategy for each respiratory monitoring type in the monitoring database, and querying the second feature extraction strategy for each electrocardiogram monitoring type in the monitoring database; extracting the first monitoring feature in the target first data distribution information of each respiratory monitoring type through the first feature extraction strategy for each respiratory monitoring type, and extracting the second monitoring feature in the target second data distribution information of each electrocardiogram monitoring type through the second feature extraction strategy for each electrocardiogram monitoring type; all first monitoring features and all second monitoring features are used as various comprehensive monitoring features in the comprehensive monitoring data.
[0087] In this embodiment, the terminal queries the first feature extraction strategy of each respiratory monitoring type in the monitoring database, and queries the second feature extraction strategy of each ECG monitoring type in the monitoring database. Then, the terminal extracts the first monitoring feature in the target first data distribution information of each respiratory monitoring type respectively through the first feature extraction strategy of each respiratory monitoring type, and extracts the second monitoring feature in the target second data distribution information of each ECG monitoring type respectively through the second feature extraction strategy of each ECG monitoring type. Among them, the feature content of each monitoring feature / monitoring feature is different, and the monitoring feature type in each data distribution information is also different. For example, the monitoring features of the data distribution information include monitoring features / monitoring features such as distribution range features, distribution trend features, and specific data features.
[0088] Finally, the terminal uses all the first monitoring features and all the second monitoring features as comprehensive monitoring features in the comprehensive monitoring data.
[0089] Based on the above scheme, the accuracy and comprehensiveness of feature identification are improved by identifying each monitoring feature / monitoring feature according to monitoring type / monitoring type.
[0090] Optionally, based on each monitoring feature information, a feature evaluation model is used to evaluate the user's current respiratory support requirement information and the user's current physical state information, including: based on the evaluation database, in each respiratory monitoring type, a first respiratory monitoring type related to respiratory support and a second respiratory monitoring type related to physical state are screened, and based on the evaluation database, in each ECG monitoring type, a first ECG monitoring type related to respiratory support and a second ECG monitoring type related to physical state are screened; the feature evaluation model is split into a respiratory support requirement evaluation model and a physical state evaluation model; based on the first monitoring feature of each first respiratory monitoring type and the second monitoring feature of each first ECG monitoring type, the user's current respiratory support requirement information is evaluated through the respiratory support requirement evaluation model, and based on the first monitoring feature of each second respiratory monitoring type and the second monitoring feature of each second ECG monitoring type, the user's current physical state information is evaluated through the physical state evaluation model.
[0091] In this embodiment, the terminal screens the first respiratory monitoring type related to respiratory support and the second respiratory monitoring type related to the physical state in each respiratory monitoring type based on the evaluation database, and screens the first ECG monitoring type related to respiratory support and the second ECG monitoring type related to the physical state in each ECG monitoring type based on the evaluation database. For example, the respiratory monitoring type related to respiratory support is, the oxygen monitoring data type is the end-tidal carbon dioxide monitoring data type, and the respiratory monitoring type related to the physical state is the oxygen monitoring data type. Then, the terminal splits the feature evaluation model into a respiratory support demand evaluation model and a physical state evaluation model.
[0092] Then, the terminal evaluates the user's current respiratory support demand information through a respiratory support demand evaluation model based on the first monitoring feature of each first respiratory monitoring type and the second monitoring feature of each first ECG monitoring type, and evaluates the user's current physical state information through a physical state evaluation model based on the first monitoring feature of each second respiratory monitoring type and the second monitoring feature of each second ECG monitoring type. The respiratory support demand evaluation model is the same as the sample model of the physical state evaluation model, which is a deep learning neural network based on a self-attention mechanism. The terminal trains the sample model through each type of sample data related to respiratory support to obtain a respiratory support demand evaluation model, and trains the sample model through each type of sample data related to physical state to obtain a physical state evaluation model.
[0093] Based on the above scheme, the types corresponding to each respiratory support and the types corresponding to the physical condition are split and evaluated separately, thereby improving the accuracy and comprehensiveness of the evaluation.
[0094] Optionally, based on the user's current breathing support requirement information and the user's current physical condition information, a current breathing data adjustment range of the user is generated through a breathing adjustment network, including: querying the user's breathing support requirement level based on the user's current breathing support requirement information, and querying the user's physical condition type based on the user's current physical condition information; identifying the user's current target breathing data range through the breathing adjustment network based on the user's breathing support requirement level and the user's physical condition type; collecting the current breathing data of the ventilator, and calculating the user's current breathing data adjustment range based on the current target breathing data range and the current breathing data.
[0095] In this embodiment, the terminal queries the user's respiratory support requirement level based on the user's current respiratory support requirement information, and queries the user's physical state type based on the user's current physical state information. The respiratory support requirement level is divided into level one, level two, level three, level four, and level five from low to high, and the physical state type can be divided into weak type, normal type, excited type, emergency type, abnormal breathing type and other state types, wherein each level corresponds to a respiratory support requirement range, and each physical state type includes multiple physical state information. Then, the terminal queries the respiratory support requirement range to which the current respiratory support requirement information belongs, thereby determining the user's respiratory support requirement level, and queries the physical state type to which the current physical state information belongs, thereby determining the user's physical state type.
[0096] Then, the terminal uses the user's breathing support requirement level and the user's physical condition type to identify the user's current target breathing data range through the breathing adjustment network. The breathing adjustment network is used to identify the breathing data range of each breathing adjustment type for different physical condition types and different breathing support requirement levels.
[0097] Then, the terminal collects the current breathing data of the ventilator, and calculates the current breathing data adjustment range of the user based on the current target breathing data range and the current breathing data. The current breathing data includes the current breathing data amount of each breathing adjustment type, and then the terminal calculates the deviation value between each breathing data amount of each breathing adjustment type and the current breathing data amount of each breathing adjustment type in the breathing data range of each breathing adjustment type, and obtains the breathing adjustment amount range of each breathing adjustment type.
[0098] Based on the above scheme, by identifying the user's respiratory support requirement level and physical condition type, the respiratory data range of each respiratory adjustment type of the user is identified, and the current respiratory data amount of each respiratory adjustment type of the ventilator is calculated to obtain the respiratory adjustment amount range of each respiratory adjustment type, thereby improving the accuracy and comprehensiveness of the calculation.
[0099] Optionally, based on the user's current medical condition information and the user's current breathing data adjustment range, the user's target breathing adjustment amount is identified, including: based on the user's current medical condition information, querying the breathing data limit corresponding to the user's current medical condition information in a medical condition database; based on the user's current breathing data adjustment range and the user's breathing data limit, calculating the user's target breathing adjustment amount.
[0100] In this embodiment, the terminal queries the breathing data limit corresponding to the current condition information of the user in the condition database based on the current condition information of the user. The condition database includes breathing data limits of various breathing adjustment types corresponding to different condition degrees of different condition types, and then the terminal identifies the current condition degree of the current condition type of the user based on the current condition information of the user, and then queries the current breathing data limit of various breathing adjustment types corresponding to the current condition degree of the current condition type in the condition database. Finally, the terminal calculates the target breathing adjustment amount of the user based on the current breathing data adjustment range of the user and the breathing data limit of the user. Among them, the target breathing adjustment amount of each breathing adjustment type is to select the minimum breathing data adjustment amount that does not exceed the current breathing data limit of each breathing adjustment type, thereby reducing the adjustment range while ensuring the accuracy of the adjustment, so that the stability of the adjustment is better during dynamic adjustment, avoiding the influence of large-scale adjustment on the physiological state of the user, and further improving the energy-saving effect.
[0101] Based on the above scheme, by identifying the current breathing data limit of each breathing adjustment type corresponding to the current condition level of the user's current condition type, the minimum breathing data adjustment amount of each breathing adjustment type is screened, which not only ensures the accuracy of the adjustment, but also ensures the stability of the ventilator output during dynamic adjustment.
[0102] Optionally, the method also includes: adjusting the ventilator based on the target ventilator adjustment parameters, obtaining the user's respiratory monitoring feedback data, and evaluating the user's current physiological state through a physiological assessment strategy based on the respiratory monitoring feedback data; when the user's current physiological state does not conform to the physiological state range corresponding to the user's current condition information, re-acquiring the user's current respiratory monitoring data and the user's electrocardiogram monitoring data, and returning to perform synchronization and alignment processing on the user's respiratory monitoring data and the user's electrocardiogram monitoring data to obtain the user's comprehensive monitoring data step; until the user's current physiological state conforms to the physiological state range corresponding to the user's current condition information, executing the preset user respiratory state monitoring process.
[0103] In this embodiment, the terminal adjusts the ventilator based on the target ventilator adjustment parameters, obtains the user's respiratory monitoring feedback data, and evaluates the user's current physiological state through a physiological evaluation strategy based on the respiratory monitoring feedback data. The physiological state includes but is not limited to a suffocation physiological state, a mild suffocation physiological state, a normal physiological state, a sleep physiological state, a deep sleep physiological state, a pathological physiological state, a coma physiological state, and an emergency physiological state, etc., wherein different physiological states correspond to different respiratory frequency ranges, different respiratory rate ranges, different end-tidal carbon dioxide concentration ranges, different respiratory temperature ranges, etc. Then, the terminal identifies the user's current physiological state by querying the respiratory frequency range to which each respiratory frequency belongs in the respiratory monitoring feedback data, the respiratory rate range to which the respiratory rate belongs, the end-tidal carbon dioxide concentration range to which the end-tidal carbon dioxide concentration belongs, and the respiratory concentration range to which the respiratory concentration belongs.
[0104] Afterwards, when the user's current physiological state does not conform to the physiological state range corresponding to the user's current condition information, the terminal reacquires the user's current respiratory monitoring data and the user's ECG monitoring data, and returns to execute the synchronous alignment processing of the user's respiratory monitoring data and the user's ECG monitoring data to obtain the user's comprehensive monitoring data step. Among them, the physiological state range includes normal physiological state, sleep physiological state, deep sleep physiological state, etc. Finally, the terminal executes the preset user respiratory state monitoring process until the user's current physiological state conforms to the physiological state range corresponding to the user's current condition information. Among them, the respiratory state monitoring process is a process for monitoring the user's current respiratory monitoring data and the user's ECG monitoring data, and after each monitoring, the user's current physiological state is identified. When the current physiological state does not conform to the physiological state range corresponding to the user's current condition information, the terminal re-executes step S101.
[0105] Based on the above scheme, the ventilator parameters are dynamically adjusted through respiratory monitoring feedback to ensure the accuracy of real-time adjustment of the ventilator parameters. When the physiological state range is met, only the monitoring process is executed instead of the subsequent adjustment process, thereby reducing energy consumption and improving the energy-saving effect of the adjustment.
[0106] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.
[0107] Based on the same inventive concept, the embodiment of the present application also provides a ventilator parameter adjustment system based on end-tidal carbon dioxide monitoring for implementing the ventilator parameter adjustment method based on end-tidal carbon dioxide monitoring involved above. The implementation scheme for solving the problem provided by the system is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more embodiments of the ventilator parameter adjustment system based on end-tidal carbon dioxide provided below can refer to the limitations of the ventilator parameter adjustment method based on end-tidal carbon dioxide above, and will not be repeated here.
[0108] Further references Figure 2 , as a response to the above Figure 1 The implementation of the method shown in the present application provides an embodiment of a ventilator parameter adjustment system 200 based on end-tidal carbon dioxide, and the ventilator parameter adjustment system based on end-tidal carbon dioxide includes an acquisition module 210, an evaluation module 220, a generation module 230 and an identification module 240, wherein:
[0109] The acquisition module 210 is used to acquire the user's current respiratory monitoring data, the user's ECG monitoring data, and the user's current condition information, and synchronize and align the user's respiratory monitoring data and the user's ECG monitoring data to obtain the user's comprehensive monitoring data;
[0110] An evaluation module 220, configured to extract each comprehensive monitoring feature in the comprehensive monitoring data through a data extraction strategy, and evaluate the user's current respiratory support requirement information and the user's current physical state information through a feature evaluation model based on each monitoring feature information;
[0111] A generating module 230, configured to generate a current breathing data adjustment range of the user through a breathing adjustment network based on the current breathing support demand information of the user and the current physical condition information of the user, and to identify a target breathing adjustment amount of the user based on the current condition information of the user and the current breathing data adjustment range of the user;
[0112] The identification module 240 is used to identify the target ventilator adjustment parameter of the ventilator corresponding to the target respiratory adjustment amount through the ventilator adjustment database.
[0113] Optionally, the acquisition module 210 is specifically configured to:
[0114] Splitting the user's respiration monitoring data into first data sets of each respiration monitoring type, and splitting the user's electrocardiogram monitoring data into second data sets of each electrocardiogram monitoring type;
[0115] The first data sets of each respiratory monitoring type and the second data sets of each electrocardiogram monitoring type are respectively distributed and sorted in time order to obtain first data distribution information and second data distribution information, and the first data distribution information and the second data distribution information at the same time are processed to obtain the target first data distribution information of each respiratory monitoring type and the target second data distribution information of each electrocardiogram monitoring type;
[0116] The target first data distribution information of all respiratory monitoring types and the target second data distribution information of all electrocardiogram monitoring types are used as the comprehensive monitoring data of the user.
[0117] Optionally, the evaluation module 220 is specifically configured to:
[0118] In the monitoring database, query the first feature extraction strategy for each respiratory monitoring type, and query the second feature extraction strategy for each electrocardiogram monitoring type in the monitoring database;
[0119] Extracting the first monitoring features in the target first data distribution information of each respiratory monitoring type respectively through the first feature extraction strategy of each respiratory monitoring type, and extracting the second monitoring features in the target second data distribution information of each electrocardiogram monitoring type respectively through the second feature extraction strategy of each electrocardiogram monitoring type;
[0120] All the first monitoring features and all the second monitoring features are used as comprehensive monitoring features in the comprehensive monitoring data.
[0121] Optionally, the evaluation module 220 is specifically configured to:
[0122] Based on the evaluation database, in each respiratory monitoring type, a first respiratory monitoring type related to respiratory support and a second respiratory monitoring type related to a physical state are screened, and based on the evaluation database, in each electrocardiogram monitoring type, a first electrocardiogram monitoring type related to the respiratory support and a second electrocardiogram monitoring type related to a physical state are screened;
[0123] Splitting the feature assessment model into a respiratory support demand assessment model and a physical state assessment model;
[0124] Based on the first monitoring feature of each of the first respiratory monitoring types and the second monitoring feature of each of the first ECG monitoring types, the user's current respiratory support requirement information is evaluated through the respiratory support requirement evaluation model, and based on the first monitoring feature of each of the second respiratory monitoring types and the second monitoring feature of each of the second ECG monitoring types, the user's current physical state information is evaluated through the physical state evaluation model.
[0125] Optionally, the generating module 230 is specifically configured to:
[0126] Based on the current respiratory support requirement information of the user, query the respiratory support requirement level of the user, and based on the current physical condition information of the user, query the physical condition type of the user;
[0127] Using the user's respiratory support requirement level and the user's physical condition type, through the respiratory adjustment network, to identify the user's current target respiratory data range;
[0128] The current breathing data of the ventilator is collected, and based on the current target breathing data range and the current breathing data, an adjustment range of the current breathing data of the user is calculated.
[0129] Optionally, the generating module 230 is specifically configured to:
[0130] Based on the current condition information of the user, querying the respiratory data limit corresponding to the current condition information of the user in a condition database;
[0131] A target breathing adjustment amount of the user is calculated based on the current breathing data adjustment range of the user and the user breathing data limit.
[0132] Optionally, the system further includes:
[0133] An evaluation module, configured to adjust the ventilator based on the target ventilator adjustment parameters, obtain the user's respiratory monitoring feedback data, and evaluate the user's current physiological state through a physiological evaluation strategy based on the respiratory monitoring feedback data;
[0134] an iteration module, configured to reacquire the current respiratory monitoring data of the user and the electrocardiogram monitoring data of the user when the current physiological state of the user does not conform to the physiological state range corresponding to the current condition information of the user, and return to execute the step of performing synchronous alignment processing on the respiratory monitoring data of the user and the electrocardiogram monitoring data of the user to obtain the comprehensive monitoring data of the user;
[0135] The execution module is used to execute a preset user respiratory state monitoring process until the current physiological state of the user meets the physiological state range corresponding to the current condition information of the user.
[0136] Each module in the above-mentioned ventilator parameter adjustment system based on end-tidal carbon dioxide monitoring can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.
[0137] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 3 As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input system connected by a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a ventilator parameter adjustment method based on end-tidal carbon dioxide monitoring is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input system of the computer device can be a touch layer covered on the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse, etc.
[0138] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0139] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps of any one of the methods in the first aspect are implemented.
[0140] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of any one of the methods in the first aspect are implemented.
[0141] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.
[0142] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.
[0143] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0144] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.
Claims
1. A method for adjusting ventilator parameters based on end-tidal carbon dioxide monitoring, characterized in that: The method comprises: Acquire the user's current respiratory monitoring data, the user's electrocardiogram monitoring data, and the user's current condition information, and perform synchronization and alignment processing on the user's respiratory monitoring data and the user's electrocardiogram monitoring data to obtain the user's comprehensive monitoring data; Extracting each comprehensive monitoring feature in the comprehensive monitoring data through a data extraction strategy, and evaluating the user's current respiratory support demand information and the user's current physical state information through a feature evaluation model based on each monitoring feature information; Based on the current breathing support demand information of the user and the current physical condition information of the user, generating the current breathing data adjustment range of the user through the breathing adjustment network, and based on the current condition information of the user and the current breathing data adjustment range of the user, identifying the target breathing adjustment amount of the user; A target ventilator adjustment parameter of the ventilator corresponding to the target respiratory adjustment amount is identified through a ventilator adjustment database.
2. The method according to claim 1, characterized in that The synchronous alignment processing of the user's respiratory monitoring data and the user's electrocardiogram monitoring data to obtain the user's comprehensive monitoring data includes: Splitting the user's respiration monitoring data into first data sets of each respiration monitoring type, and splitting the user's electrocardiogram monitoring data into second data sets of each electrocardiogram monitoring type; The first data sets of each respiratory monitoring type and the second data sets of each electrocardiogram monitoring type are respectively distributed and sorted in time order to obtain first data distribution information and second data distribution information, and the first data distribution information and the second data distribution information at the same time are processed to obtain the target first data distribution information of each respiratory monitoring type and the target second data distribution information of each electrocardiogram monitoring type; The target first data distribution information of all respiratory monitoring types and the target second data distribution information of all electrocardiogram monitoring types are used as the comprehensive monitoring data of the user.
3. The method according to claim 2, characterized in that The method of extracting the comprehensive monitoring features from the comprehensive monitoring data through the data extraction strategy includes: In the monitoring database, query the first feature extraction strategy for each respiratory monitoring type, and query the second feature extraction strategy for each electrocardiogram monitoring type in the monitoring database; Extracting the first monitoring features in the target first data distribution information of each respiratory monitoring type respectively through the first feature extraction strategy of each respiratory monitoring type, and extracting the second monitoring features in the target second data distribution information of each electrocardiogram monitoring type respectively through the second feature extraction strategy of each electrocardiogram monitoring type; All the first monitoring features and all the second monitoring features are used as comprehensive monitoring features in the comprehensive monitoring data.
4. The method according to claim 3, characterized in that The step of evaluating the user's current respiratory support requirement information and the user's current physical condition information based on each of the monitoring feature information by means of a feature evaluation model includes: Based on the evaluation database, in each respiratory monitoring type, a first respiratory monitoring type related to respiratory support and a second respiratory monitoring type related to a physical state are screened, and based on the evaluation database, in each electrocardiogram monitoring type, a first electrocardiogram monitoring type related to the respiratory support and a second electrocardiogram monitoring type related to a physical state are screened; Splitting the feature assessment model into a respiratory support demand assessment model and a physical state assessment model; Based on the first monitoring feature of each of the first respiratory monitoring types and the second monitoring feature of each of the first ECG monitoring types, the user's current respiratory support requirement information is evaluated through the respiratory support requirement evaluation model, and based on the first monitoring feature of each of the second respiratory monitoring types and the second monitoring feature of each of the second ECG monitoring types, the user's current physical state information is evaluated through the physical state evaluation model.
5. The method according to claim 4, characterized in that The step of generating a current breathing data adjustment range of the user based on the current breathing support requirement information of the user and the current physical state information of the user through a breathing adjustment network includes: Based on the current respiratory support requirement information of the user, query the respiratory support requirement level of the user, and based on the current physical condition information of the user, query the physical condition type of the user; Using the user's respiratory support requirement level and the user's physical condition type, through the respiratory adjustment network, to identify the user's current target respiratory data range; The current breathing data of the ventilator is collected, and based on the current target breathing data range and the current breathing data, an adjustment range of the current breathing data of the user is calculated.
6. The method according to claim 4, characterized in that The step of identifying a target breathing adjustment amount of the user based on the current condition information of the user and the current breathing data adjustment range of the user includes: Based on the current condition information of the user, querying the respiratory data limit corresponding to the current condition information of the user in a condition database; A target breathing adjustment amount of the user is calculated based on the current breathing data adjustment range of the user and the user breathing data limit.
7. The method according to claim 1, characterized in that The method further comprises: Adjusting the ventilator based on the target ventilator adjustment parameter to obtain respiratory monitoring feedback data of the user, and evaluating the current physiological state of the user through a physiological evaluation strategy based on the respiratory monitoring feedback data; When the current physiological state of the user does not conform to the physiological state range corresponding to the current condition information of the user, reacquire the current respiratory monitoring data of the user and the electrocardiogram monitoring data of the user, and return to the step of performing synchronous alignment processing on the respiratory monitoring data of the user and the electrocardiogram monitoring data of the user to obtain the comprehensive monitoring data of the user; Until the current physiological state of the user meets the physiological state range corresponding to the current condition information of the user, the preset user breathing state monitoring process is executed.
8. A ventilator parameter adjustment system based on end-tidal carbon dioxide, characterized in that: The system comprises: An acquisition module, used to acquire the user's current respiratory monitoring data, the user's ECG monitoring data, and the user's current condition information, and perform synchronization and alignment processing on the user's respiratory monitoring data and the user's ECG monitoring data to obtain the user's comprehensive monitoring data; An evaluation module, configured to extract each comprehensive monitoring feature in the comprehensive monitoring data through a data extraction strategy, and based on each monitoring feature information, evaluate the user's current respiratory support demand information and the user's current physical state information through a feature evaluation model; A generating module, configured to generate a current breathing data adjustment range of the user through a breathing adjustment network based on the current breathing support demand information of the user and the current physical condition information of the user, and to identify a target breathing adjustment amount of the user based on the current condition information of the user and the current breathing data adjustment range of the user; The identification module is used to identify the target ventilator adjustment parameter of the ventilator corresponding to the target breathing adjustment amount through the ventilator adjustment database.
9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.
Citation Information
Patent Citations
Breathing parameter adjusting method and device of breathing support equipment, and breathing support equipment
CN109718437A
Respiration state prediction method based on cloud platform
CN110732068A
Cardiopulmonary function monitoring and breathing machine closed-loop control integrated device
CN115607123A
Remote noninvasive respiration parameter analysis and management system based on Internet
CN118001528A
Cited By
Breathing monitoring method based on big data analysis and breathing machine
CN119236245A
A respiratory monitoring method and ventilator based on big data analysis
CN119236245B
