Noninvasive blood lactic acid measuring method and system
By integrating ECG and PPG signals, the blood lactate prediction model is trained to solve the invasiveness and accuracy of the existing blood lactate measurement methods, and non-invasive and real-time blood lactate concentration monitoring is achieved, which improves user experience and accuracy, and is suitable for exercise science and health management.
Patent Information
- Application Number
- CN202510248135.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-04
- Publication Date
- 2025-07-18
Smart Images
Figure CN120323964A_ABST
Abstract
Description
Background Art
[0002] With the rapid development of health monitoring technology, non-invasive health monitoring has gradually become an important direction in daily health management. Especially in the field of sports science, it shows extensive application potential, especially in the monitoring of exercise load.
[0003] The disadvantages of existing blood lactate measurement methods are as follows:
[0004] I. Disadvantages of arterial blood sampling method:
[0005] 1. Pain and technical difficulty: Arterial blood sampling is more painful than venous blood sampling and requires higher technical skills. This increases the discomfort of athletes and also leads to complications during blood collection.
[0006] 2. Application limitations: Due to the complexity and pain of arterial blood sampling, its application in clinics is limited and it is more used for clinical research or detection in special situations.
[0007] II. Disadvantages of venous blood sampling method:
[0008] Although the venous blood sampling method is more commonly used and simpler, it also has some limitations:
[0009] 1. Relatively low accuracy: Although the venous blood lactate level can reflect the body's lactate metabolism, compared with arterial blood, its accuracy is slightly lower because venous blood more reflects the mixed metabolic state of various parts of the body.
[0010] 2. Affected by external factors: The measurement results of venous blood lactate are affected by various external factors, such as blood collection time, use of tourniquet, blood stasis time, etc. These factors cause changes in lactate content, thus affecting the accuracy of measurement results.
[0011] III. Disadvantages of laboratory detection methods:
[0012] 1. Complex operation: Laboratory detection methods such as lactate dehydrogenase method and lactate oxidase method, although accurate, are relatively complex in operation and require professional technical personnel and expensive equipment.
[0013] 2. Time-consuming: These laboratory detection methods usually take a long time to complete, from sample collection to result issuance, which takes several hours or even longer. This limits their application in emergency situations.
[0014] IV. Disadvantages of other methods:
[0015] 1. Acid-base titration method: Although this method can be used to determine the lactate content, when there are miscellaneous acids in the sample, it will cause the measured lactate content to be greater than its actual content, thus affecting the accuracy of the results.
[0016] 2. Enzyme electrode method: Although the enzyme electrode method is fast and sensitive, the stability and service life of the enzyme electrode may be affected by various factors, such as temperature, humidity, etc. In addition, the cost of the enzyme electrode is relatively high.
[0017] 3. Chromatography: Although gas chromatography and liquid chromatography can directly separate and determine lactic acid, the operation is relatively complex and requires expensive equipment. Gas chromatography also requires the derivatization esterification treatment of lactic acid, which increases the complexity of the operation and the possibility of errors. Summary of the Invention
[0018] This application provides a non-invasive blood lactic acid measurement method and system to improve the accuracy and robustness of blood lactic acid concentration prediction.
[0019] In the first aspect, a non-invasive blood lactic acid measurement method is provided, including the following steps:
[0020] Based on the ECG signal and PPG signal, train and construct a blood lactic acid prediction model;
[0021] Use the blood lactic acid prediction model to predict the blood lactic acid concentration and complete the measurement of the blood lactic acid value.
[0022] In the above technical solution, by training and constructing a blood lactic acid prediction model based on the ECG signal and PPG signal; using the blood lactic acid prediction model to predict the blood lactic acid concentration and complete the measurement of the blood lactic acid value; by fusing the ECG and PPG signals, non-invasive detection of the blood lactic acid concentration is realized, avoiding the pain of blood collection in traditional methods and having a better user experience; by combining the rich physiological, time-domain and space-domain features in the ECG and PPG signals, the physiological state of the cardiovascular system and hemodynamics can be comprehensively reflected, significantly improving the accuracy and robustness of blood lactic acid concentration prediction.
[0023] In a specific feasible implementation scheme, it further includes:
[0024] Obtain the ECG signal and PPG signal.
[0025] In a specific feasible implementation scheme, the step of training and constructing a blood lactic acid prediction model based on the ECG signal and PPG signal specifically includes:
[0026] Preprocess the ECG signal and PPG signal to obtain preprocessed ECG and PPG signals;
[0027] Extract and fuse features from the preprocessed ECG and PPG signals to obtain a training set and a test set;
[0028] Use the training set to train a prediction model for training;
[0029] Using the test set, the blood lactic acid prediction model is tested and obtained.
[0030] In a specific feasible embodiment, the method for preprocessing the ECG signal and PPG signal includes denoising processing, filtering processing, and baseline drift correction processing.
[0031] In a specific feasible embodiment, the features of the ECG signal include: time-domain features, frequency-domain features, and non-linear features.
[0032] In a specific feasible embodiment, the features of the PPG signal include: time-domain features, frequency-domain features, statistical features, and non-linear features related to blood volume changes.
[0033] In a specific feasible embodiment, the methods for feature fusion of the multi-dimensional features extracted from the ECG signal and the PPG signal include: correlation analysis method and principal component analysis PCA method.
[0034] In a specific feasible embodiment, the machine learning algorithms for constructing the blood lactic acid prediction model include random forest algorithm, support vector machine SVM algorithm, and regression neural network algorithm.
[0035] In a second aspect, a non-invasive blood lactic acid measurement system is provided, including:
[0036] A model module, configured to train and construct a blood lactic acid prediction model based on the ECG signal and PPG signal;
[0037] A prediction module, configured to use the blood lactic acid prediction model to predict the blood lactic acid concentration and complete the measurement of the blood lactic acid value.
[0038] In the above technical solution, by training and constructing a blood lactic acid prediction model based on the ECG signal and PPG signal; using the blood lactic acid prediction model to predict the blood lactic acid concentration and complete the measurement of the blood lactic acid value; by fusing the ECG and PPG signals, non-invasive detection of the blood lactic acid concentration is realized, avoiding the pain of blood collection in traditional methods and having a better user experience; by combining the rich physiological, time-domain, and spatial-domain features in the ECG and PPG signals, the physiological state of the cardiovascular system and hemodynamics can be comprehensively reflected, significantly improving the accuracy and robustness of blood lactic acid concentration prediction.
[0039] In a specific feasible embodiment, it further includes:
[0040] An acquisition module, configured to acquire the ECG signal and PPG signal. Description of the Drawings
[0041] Figure 1Flow chart of the non-invasive blood lactate measurement method provided by the embodiments of the present application;
[0042] Figure 2 Structural block diagram of the non-invasive blood lactate measurement system provided by the embodiments of the present application. Detailed implementation manners
[0043] The present application will be further described in detail below with reference to the accompanying drawings and embodiments. Through these descriptions, the features and advantages of the present application will become more clearly defined.
[0044] The special term "exemplary" herein means "serving as an example, embodiment, or illustration". Any embodiment described as "exemplary" here does not have to be construed as superior to or better than other embodiments. Although various aspects of the embodiments are shown in the drawings, the drawings do not have to be drawn to scale unless otherwise specified.
[0045] In addition, the technical features involved in different embodiments of the present application described below can be combined with each other as long as they do not conflict with each other.
[0046] To facilitate the understanding of the non-invasive blood lactate measurement method and system provided by the embodiments of the present application, the application scenario thereof will be described first. The non-invasive blood lactate measurement method and system provided by the embodiments of the present application are used to improve the accuracy and robustness of blood lactate concentration prediction. With the rapid development of health monitoring technology, non-invasive health monitoring has gradually become an important direction in daily health management, especially in the field of sports science, and has shown extensive application potential in sports load monitoring. The disadvantages of existing blood lactate measurement methods are as follows: First, the disadvantages of arterial blood sampling method: 1. Pain and technical difficulty: Arterial blood sampling is more painful than venous blood sampling and has higher technical requirements. This increases the discomfort of athletes and also leads to complications during blood sampling. 2. Application limitations: Due to the complexity and pain of arterial blood sampling, its application in clinics is limited and is more used for clinical research or detection in special situations. Second, the disadvantages of venous blood sampling method: Although the venous blood sampling method is more commonly used and simple, it also has some limitations: 1. Relatively low accuracy: Although the venous blood lactate level can reflect the body's lactate metabolism, compared with arterial blood, its accuracy is slightly lower because venous blood more reflects the mixed metabolic state of various parts of the body. 2. Affected by external factors: The measurement results of venous blood lactate are affected by various external factors, such as blood sampling time, use of tourniquet, blood stasis time, etc. These factors lead to changes in lactate content, thus affecting the accuracy of the measurement results. Third, the disadvantages of laboratory detection methods: 1. Complex operation: Laboratory detection methods such as lactate dehydrogenase method and lactate oxidase method are accurate but relatively complex in operation, requiring professional technical personnel and expensive equipment. 2. Time-consuming: These laboratory detection methods usually take a long time to complete, taking several hours or even longer from sample collection to result issuance. This limits their application in emergency situations. Fourth, the disadvantages of other methods: 1. Acid-base titration method: Although this method can be used to determine the lactate content, when there are miscellaneous acids in the sample, it will cause the measured lactate content to be greater than its actual content, thus affecting the accuracy of the result. 2. Enzyme electrode method: Although the enzyme electrode method is fast and sensitive, the stability and service life of the enzyme electrode may be affected by various factors, such as temperature, humidity, etc. In addition, the cost of the enzyme electrode is relatively high. 3. Chromatography method: Although gas chromatography and liquid chromatography can directly separate and determine lactate, the operation is relatively complex and requires expensive equipment. Gas chromatography also requires the derivatization esterification treatment of lactate, which increases the complexity of the operation and the possibility of errors. Therefore, the embodiments of the present application provide a non-invasive blood lactate measurement method and system to improve the accuracy and robustness of blood lactate concentration prediction. The following will be described in detail with specific drawings by way of examples.
[0047] Reference Figure 1 and Figure 2 , Figure 1Flow chart of the non-invasive blood lactate measurement method provided by the embodiments of the present application; Figure 2 Block diagram of the structure of the non-invasive blood lactate measurement system provided by the embodiments of the present application.
[0048] In Figure 1 the embodiments of the present application provide a non-invasive blood lactate measurement method, including the following steps:
[0049] Based on the ECG signal and PPG signal, train and construct a blood lactate prediction model;
[0050] Use the blood lactate prediction model to predict the blood lactate concentration and complete the measurement of the blood lactate value.
[0051] In the above technical solution, by training and constructing a blood lactate prediction model based on the ECG signal and PPG signal; using the blood lactate prediction model to predict the blood lactate concentration and complete the measurement of the blood lactate value; by fusing the ECG and PPG signals, non-invasive detection of the blood lactate concentration is realized, avoiding the pain of blood collection in traditional methods and having a better user experience; by combining the rich physiological, time-domain and space-domain features in the ECG and PPG signals, the physiological state of the cardiovascular system and hemodynamics can be comprehensively reflected, significantly improving the accuracy and robustness of blood lactate concentration prediction.
[0052] In a specific feasible implementation, it further includes:
[0053] Obtain the ECG signal and PPG signal.
[0054] In a specific feasible implementation, the step of training and constructing a blood lactate prediction model based on the ECG signal and PPG signal specifically includes:
[0055] Preprocess the ECG signal and PPG signal to obtain preprocessed ECG and PPG signals;
[0056] Extract and fuse features from the preprocessed ECG and PPG signals to obtain a training set and a test set;
[0057] Use the training set to train a prediction model for training;
[0058] Use the test set to test and obtain the blood lactate prediction model.
[0059] In a specific feasible implementation, the method for preprocessing the ECG signal and PPG signal includes denoising, filtering and baseline drift correction.
[0060] In a specific feasible implementation, the features of the ECG signal include: time-domain features, frequency-domain features and non-linear features.
[0061] In a specific feasible embodiment, the characteristics of the PPG signal include: time-domain characteristics, frequency-domain characteristics, statistical characteristics, and non-linear characteristics related to blood volume changes.
[0062] In a specific feasible embodiment, the methods for feature fusion of the multi-dimensional features extracted from the ECG signal and the PPG signal include: correlation analysis method and principal component analysis PCA method.
[0063] In a specific feasible embodiment, the machine learning algorithms for constructing the blood lactate prediction model include random forest algorithm, support vector machine SVM algorithm, and regression neural network algorithm.
[0064] Specifically, the non-invasive blood lactate measurement method proposes a non-invasive blood lactate measurement method that fuses the characteristics of ECG (Electrocardiogram) and PPG (Photoplethysmography), aiming to solve the problems of strong invasiveness, cumbersome detection process, poor real-time performance, and user inconvenience in traditional blood lactate measurement methods. It includes:
[0065] (1) Multi-signal acquisition and preprocessing
[0066] Simultaneously collect the ECG signal and the PPG signal through a wearable device. Preprocess the collected signals, including denoising, filtering, baseline drift correction, etc., to ensure the signal quality.
[0067] (2) Feature extraction and fusion
[0068] ECG signal: Extract time-domain characteristics (such as RMSSD, SDNN, SD1 / SD2, etc.), frequency-domain characteristics (such as LF, HF, LF / HF ratio), and non-linear characteristics (such as sample entropy, Kolmogorov entropy, fractal dimension, etc.).
[0069] PPG signal: Extract time-domain characteristics related to blood volume changes (such as pulse wave rise time, pulse wave amplitude), frequency-domain characteristics (such as heart rate spectral components), statistical characteristics (such as kurtosis, skewness), and non-linear characteristics (such as signal complexity, power spectral entropy).
[0070] Fuse the multi-dimensional features extracted from the ECG and PPG, and screen out the feature set highly correlated with blood lactate concentration through feature selection methods (such as correlation analysis or principal component analysis PCA, Principal Component Analysis).
[0071] (3) Machine learning model construction
[0072] Using the extracted fused features as input, a machine learning algorithm (such as random forest, support vector machine SVM, recurrent neural network, etc.) is adopted to construct a blood lactate concentration prediction model. In this embodiment, a random forest regression model is used to predict blood lactate values.
[0073] The model is trained and optimized using the training set and validation set, and finally the model performance is evaluated on the test set to ensure the accuracy and reliability of the prediction results.
[0074] In this embodiment, by adopting physiological, time-domain, and spatial-domain features in ECG and PPG signals and combining feature fusion with multi-model learning, real-time and non-invasive measurement of blood lactate concentration can be achieved. This method analyzes the physiological and time-domain features in ECG and PPG signals and uses a machine learning algorithm to construct a prediction model, thereby providing an accurate estimate of blood lactate concentration. It includes:
[0075] (1) Multi-signal fusion: By combining ECG and PPG signals and using the information such as physiological, time-domain, and spatial-domain features they contain, a new feature extraction and fusion method is proposed, effectively enhancing the accuracy of blood lactate concentration prediction.
[0076] (2) Non-invasive measurement: Avoids the collection of blood samples in traditional methods, reduces the discomfort of athletes, and improves the convenience and acceptability of measurement.
[0077] (3) Real-time monitoring: By dynamically analyzing physiological signals, provides real-time monitoring of blood lactate concentration, providing strong support for sports medicine, clinical monitoring, etc.
[0078] In the above technical solution, 1. Non-invasive monitoring is achieved: By fusing ECG and PPG signals, non-invasive detection of blood lactate concentration is realized, avoiding the pain of blood collection in traditional methods and having a better user experience. 2. Multi-signal fusion is adopted to improve the prediction accuracy: By combining the rich physiological, time-domain, and spatial-domain features in ECG and PPG signals, the physiological state of the cardiovascular system and hemodynamics can be comprehensively reflected, significantly improving the accuracy and robustness of blood lactate concentration prediction.
[0079] In Figure 2 this application embodiment provides a non-invasive blood lactate measurement system, including:
[0080] A model module, configured to train and construct a blood lactate prediction model based on ECG signals and PPG signals;
[0081] A prediction module, configured to use the blood lactate prediction model to predict the blood lactate concentration and complete the measurement of blood lactate values.
[0082] In the above technical solution, a blood lactate prediction model is trained and constructed based on the ECG signal and the PPG signal; the blood lactate concentration is predicted by using the blood lactate prediction model to complete the measurement of the blood lactate value; by fusing the ECG and PPG signals, non-invasive detection of the blood lactate concentration is achieved, avoiding the pain of blood collection in traditional methods and providing a better user experience; by combining the rich physiological, time-domain, and spatial-domain features in the ECG and PPG signals, the physiological state of the cardiovascular system and hemodynamics can be comprehensively reflected, significantly improving the accuracy and robustness of blood lactate concentration prediction.
[0083] In a specific feasible implementation, it further includes:
[0084] An acquisition module, configured to acquire the ECG signal and the PPG signal.
[0085] In this embodiment, by real-time monitoring of the blood lactate level, more accurate health data support is provided for athletes, which has great market prospects and application value. In the field of sports medicine, this application can be widely used in high-intensity sports or training processes. By real-time monitoring of the blood lactate level of athletes, it helps coaches and athletes adjust the training intensity and recovery plan, avoiding muscle fatigue, injury, or other health problems caused by excessive lactic acid. Through data-driven personalized training programs, not only can sports performance be improved, but also the risk of sports injuries can be effectively reduced. Finally, the wide application of wearable devices enables this technology to have the ability to monitor blood lactate in real time 24 / 7, especially suitable for sports tracking and health management. By integrating into wearable devices such as smart bracelets and smart watches, users can monitor their blood lactate levels at any time in daily life, providing data support for personal health management and promoting the cultivation of healthy behaviors. Generally speaking, the application of this application in the fields of sports science and health management not only has far-reaching market prospects, but also can provide more accurate and personalized health management solutions for users, helping to improve the overall health level and sports performance.
[0086] Those skilled in the art of the technical field to which this application pertains know that this application can be implemented as a system, a method, or a computer program product.
[0087] Therefore, the present disclosure can be specifically implemented in the following forms, that is: it can be completely hardware, can also be completely software (including firmware, resident software, microcode, etc.), or can also be a form combining hardware and software, generally referred to as "circuit", "module", or "system" in this article. In addition, in some embodiments, this application can also be implemented in the form of a computer program product in one or more computer-readable media, which contains computer-readable program code.
[0088] Any combination of one or more computer-readable media may be employed. The computer-readable media may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example — but not limited to — an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium include: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present document, the computer-readable storage medium may be any tangible medium that contains or stores a program which can be used by or in connection with an instruction execution system, apparatus, or device.
[0089] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limitations on the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application. On this basis, various substitutions and improvements can be made to the present application, and all of these fall within the protection scope of the present application.
Claims
1. A non-invasive blood lactic acid measurement method, characterized in that, It includes the following steps: Based on the ECG signal and the PPG signal, train and construct a blood lactic acid prediction model; Use the blood lactic acid prediction model to predict the blood lactic acid concentration and complete the measurement of the blood lactic acid value.
2. The non-invasive blood lactic acid measurement method according to claim 1, characterized in that It also includes: Obtain the ECG signal and the PPG signal.
3. The non-invasive blood lactic acid measurement method according to claim 2, characterized in that, The step of training and constructing a blood lactic acid prediction model based on the ECG signal and the PPG signal specifically includes: Preprocess the ECG signal and the PPG signal to obtain preprocessed ECG and PPG signals; Extract and fuse features from the preprocessed ECG and PPG signals to obtain a training set and a test set; Use the training set to train a prediction model for training; Use the test set to test and obtain the blood lactic acid prediction model.
4. The non-invasive blood lactate measurement method according to claim 3, wherein The method for preprocessing the ECG signal and the PPG signal includes denoising processing, filtering processing, and baseline drift correction processing.
5. The non-invasive blood lactate measurement method according to claim 4, characterized in that, The features of the ECG signal include: time-domain features, frequency-domain features, and non-linear features.
6. The non-invasive blood lactate measurement method according to claim 5, wherein The features of the PPG signal include: time-domain features, frequency-domain features, statistical features, and non-linear features related to blood volume changes.
7. The non-invasive blood lactate measurement method according to claim 6, characterized in that The method for fusing the multi-dimensional features extracted from the ECG signal and the PPG signal includes: correlation analysis method and principal component analysis PCA method.
8. The non-invasive blood lactic acid measurement method according to claim 7, characterized in that, The machine learning algorithms for constructing the blood lactic acid prediction model include random forest algorithm, support vector machine SVM algorithm, and regression neural network algorithm.
9. A non-invasive blood lactic acid measurement system, characterized in that, It includes: A model module for training and constructing a blood lactic acid prediction model based on the ECG signal and the PPG signal; A prediction module for using the blood lactic acid prediction model to predict the blood lactic acid concentration and complete the measurement of the blood lactic acid value.
10. The non-invasive blood lactate measurement system according to claim 9, characterized in that, It also includes: An acquisition module for obtaining the ECG signal and the PPG signal.