Brain efficacy evaluation method based on exhaled gas omics
Through exhaled gasomics analysis and PTR-TOF-MS technology, volatile organic compounds related to brain fatigue are identified, and the problem of poor timeliness assessment of brain fatigue in the prior art is solved, and rapid, non-invasive and efficient diagnosis is achieved.
Patent Information
- Application Number
- CN202411198216.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-29
- Publication Date
- 2024-12-06
AI Technical Summary
The existing brain fatigue assessment methods have poor timeliness and strong lag, making it difficult to conduct high-time observation and evaluation, and lack fast and non-invasive detection methods.
Exhaust gasomics analysis was used to detect volatile organic compounds by proton transfer time-of-flight mass spectrometry (PTR-TOF-MS) technology, and predicted by combining principal component analysis (PCA) and orthogonal partial least squares discrimination method (OPLS-DA) Model, identify compounds such as butene, pentene, ethyl formate, etc. to distinguish brain fatigue states.
It realizes rapid and non-invasive brain fatigue diagnosis, with high diagnostic efficacy, sensitivity and specificity, and can instantly detect changes in volatile organic matter in exhaled gas, providing a non-invasive and efficient brain efficacy evaluation method.
Smart Images

Figure CN119086892A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the field of biomedical technology, and in particular, relates to a brain performance evaluation method based on exhaled gasomics. Background Art
[0002] Mental fatigue is usually defined as a biological psychological state, which is manifested as a decrease in alertness, attention, memory and cognitive ability after continuous cognitive activities. Social processes have made mental fatigue common in many occupational fields, which has a significant impact on personal productivity, work safety and daily activities. Solving the problems caused by mental fatigue is crucial to maintaining a healthy and efficient working environment and improving personal work ability. However, due to the difficulty of conducting high-time observation and evaluation in existing evaluation methods (mainly using instrument assistance or compiling experimental procedures, such as ERP, EEG, behavioral experiments, eye movement experiments, etc., and analyzing objective data fed back by equipment), there are generally practical problems such as poor timeliness, strong lag and invasiveness. Therefore, there is an urgent need to establish an objective and systematic evaluation method in this field. Exhaled gas can reflect the state of the human body and is rich in a large amount of compound information. It is a potential non-invasive disease monitoring medium. Due to its simple sampling, rapid and non-invasive, and rich information, exhaled gas analysis has important advantages and significance in medical diagnosis and application. Therefore, in order to solve the above-mentioned technical problems faced by the prior art, the present application hopes to use a rapid and non-invasive detection method, namely breath analysis, which can quickly detect changes in volatile organic compounds in exhaled gas. This non-invasive and convenient method can instantly diagnose certain diseases and conditions.
[0003] Breathing is a basic characteristic of human life and a necessary condition for human existence. As an important product of respiratory movement, respiratory gases not only maintain normal physiological metabolism, but also can reflect the overall functioning of human body functions. When the body's metabolism is disordered or the body suffers from a disease, certain biochemical reactions in the body's metabolism will be enhanced, causing the concentration of some volatile organic compounds (VOCs) in the exhaled gas to increase. Therefore, the state of organ function can be judged by the changes in the concentration of these characteristic gases. In clinical practice, examples of the analysis of exhaled volatile organic compounds include the carbon 13 breath test for Helicobacter pylori, the exhaled nitric oxide test for asthma, and the methane hydrogen test for small intestinal bacterial overgrowth. In recent studies, the importance of volatile organic compounds in many diseases has also been found, including that the levels of multiple volatile organic compounds in patients with major depression were significantly reduced compared with healthy people, and 24 volatile organic compounds were found to be significantly increased in the exhaled breath of Alzheimer's patients, and a total of 253 volatile organic compounds were reported to be associated with cancer diagnosis. In most cases, these volatile organic compounds are hydrocarbons (aromatic and aliphatic) and oxygenated compounds (i.e., alcohols, aldehydes, phenols, carboxylic acids, ethers and furans), as well as less nitrogen-containing, sulfur-containing and halogen-containing compounds. Exhaled gas omics analysis, as a non-invasive and rapid diagnostic method, has been applied clinically and in many aspects. Therefore, the present invention selects the study of mental fatigue by exhaled gas omics analysis. Summary of the invention
[0004] In view of this, an object of the present invention is to provide a method for evaluating brain performance based on exhaled gasomics.
[0005] In the study of the present invention, the inventors selected a number of healthy subjects as research objects, induced brain fatigue state by continuous cognitive operation task for 120 minutes, evaluated the degree of brain fatigue state by multidimensional fatigue inventory (MFI-20), collected exhaled gas from the subjects before and after the continuous cognitive operation task, and then analyzed the exhaled gas metabolites of subjects with different brain loads by proton transfer reaction time of flight mass spectrometry (PTR-TOF-MS), compared the properties and contents of volatile organic compounds (VOCs), and the degree of difference between them in samples before and after brain fatigue by principal component analysis (PCA) and orthogonal partial least squares discriminant analysis (OPLS-DA), thereby establishing a prediction model, and verifying the effect of the constructed prediction model by area under the curve (AUC) and receiver operating characteristic (ROC) curve.
[0006] The present invention adopts the following technical solutions to achieve the above-mentioned invention objectives:
[0007] The first aspect of the present invention provides the use of volatile organic compounds as brain fatigue biomarkers in the development of products for diagnosing or assisting in the diagnosis of brain fatigue, wherein the volatile organic compounds include butene, pentene, 1,3-butadiene, ethyl formate, butanol, n-butane, acrolein, acrylonitrile, propionitrile, furan, methyl octanoate and / or ethyl sulfide.
[0008] Further, the volatile organic compound is any one of butene, pentene, 1,3-butadiene, ethyl formate, butanol, n-butane, acrolein, acrylonitrile, propionitrile, furan, methyl octanoate, and ethyl sulfide;
[0009] Optionally, the volatile organic compound is a combination of ethyl sulfide, ethyl formate, butene, n-butane and pentene.
[0010] In the present invention, the present invention has found through detailed experimental verification that the volatile organic compounds butene, pentene, 1,3-butadiene, ethyl formate, butanol, n-butane, acrolein, acrylonitrile, propionitrile, furan, methyl octanoate and / or ethyl sulfide have high diagnostic efficacy (AUC values are all greater than 0.750) in distinguishing brain fatigue subjects from non-brain fatigue subjects, and have high sensitivity and specificity, and can be used for effective diagnosis of brain fatigue. Among them, the combined diagnostic efficacy of five markers of ethyl sulfide, ethyl formate, butene, n-butane and pentene is the best (AUC value is as high as 0.888).
[0011] In some embodiments, the volatile organic compounds are derived from a subject. In some embodiments, the subject includes mammals and non-mammals. Examples of mammals include, but are not limited to, any member of the class Mammalia: humans, non-human primates such as chimpanzees and other apes and monkeys; farm animals such as cattle, horses, sheep, goats, pigs; domestic animals such as rabbits, dogs and cats; laboratory animals, including rodents such as rats, mice and guinea pigs, etc. Examples of non-mammals include, but are not limited to, birds, fish, etc. In one embodiment of the present invention, the subject is a human.
[0012] The second aspect of the present invention provides the use of a reagent for detecting the content or concentration of volatile organic compounds in a sample in the preparation of a product for diagnosing or assisting in the diagnosis of brain fatigue, wherein the volatile organic compounds are the volatile organic compounds described in the first aspect of the present invention.
[0013] Further, the reagent includes a reagent for detecting the content or concentration of the volatile organic compound in the sample by mass spectrometry, gas chromatography, spectroscopy, nuclear magnetic resonance or any combination thereof;
[0014] Optionally, the sample is exhaled breath from a subject.
[0015] In some embodiments, the method for detecting the content or concentration of volatile organic compounds includes mass spectrometry (MS), gas chromatography (GC), spectroscopy (SPA), nuclear magnetic resonance (NMR), laser spectroscopy, proton transfer time-of-flight mass spectrometry (PTR-TOF-MS), selected ion flow tube mass spectrometry (SIFT-MS), ion mobility spectrometry (IMS), electronic nose (E-nose), nanomaterial-based VOC / gas sensor (NMVS) or any combination thereof.
[0016] In some embodiments, the present invention has no particular limitations on the method for detecting the content or concentration of the volatile organic compounds or the reagent for detecting the content or concentration of the volatile organic compounds. Any method or reagent that can be used for quantitative analysis or qualitative analysis of the volatile organic compounds of the present invention in a sample to be tested from a subject is within the protection scope of the present invention.
[0017] In some embodiments, the method for detecting the content or concentration of the volatile organic compound is proton transfer time-of-flight mass spectrometry (PTR-TOF-MS), wherein the PTR-TOF-MS analyzes the analyte according to its mass-to-charge ratio (m / z), and the TOF analyzer separates the ions according to the change in their velocity after being accelerated at a constant potential. The PTR-TOF MS includes an ion source, a drift tube, and a mass spectrometer detector. At the top of the drift tube, the flowing air sample is mixed with the H generated by the ion source. 3 O + Mixing and proton transfer occur as the gas sample passes through the drift tube. PTR-MS is faster and more accurate than gas chromatography-mass spectrometry (GC-MS) in measuring VOC concentrations (ppt and ppb levels) and does not require a time-consuming pre-concentration stage.
[0018] In a specific embodiment, the present invention uses PTR-TOF-MS (model: KORE PTR 2E), and uses PAMS standard gas, TO5 standard gas, aldehyde and ketone standard gas, etc. as standard products. The specific experimental parameters and experimental steps are as follows: enter the standard gas distribution interface on the left side of the instrument, and enter "Set total outlet flow" 1000mL / min in the "Gas Distribution Ratio" page; enter the "Standard Gas MFC2" interface, enter "Standard Gas Concentration" 1ppm, "Gas Distribution Ratio Concentration" 0.005ppm; enter the "Dilution Gas MFC1" page, and select "Dilution Gas Component". Connect the standard gas dilution gas outlet to the instrument sample inlet solenoid valve inlet. Open the koretof.ini shortcut to modify the path and sample count of the sample data file, save and close. Open the "PTRMS" software, click "Autoacquire" to pop up the autorun TDC window, enter the number of run samples "NO.of Runs" and the run interval "Runinterval", and start collecting data. After data collection is completed, open the "PTR-TOF-MS Data Analysis Software", select the "Test Spectrum Address" of the standard / sample, and click "Continuous Sampling Analysis" to obtain the particle counts of different species and water isotope particle counts.
[0019] A third aspect of the present invention provides a diagnostic product for diagnosing or assisting in the diagnosis of brain fatigue.
[0020] Furthermore, the diagnostic product includes the reagent for detecting the content or concentration of volatile organic compounds in a sample as described in the second aspect of the present invention.
[0021] Furthermore, the diagnostic products include diagnostic kits and diagnostic chips.
[0022] In some embodiments, the kit may include a solid substrate such as a chip, a slide, an array, etc., which has reagents capable of detecting and / or quantifying one or more of the volatile organic compounds fixed at predetermined locations on the substrate. As an illustrative example, the chip may be provided with reagents fixed at discrete predetermined locations for detecting and quantifying the volatile organic compounds in a sample to be tested from a subject.
[0023] In some embodiments, the chip has reagents capable of detecting and / or quantifying one or more of the volatile organic compounds fixed at predetermined locations on the substrate. As an illustrative example, the chip can be provided with reagents fixed at discrete predetermined locations for detecting and quantifying the content or concentration of the volatile organic compounds in a sample to be tested from a subject.
[0024] A fourth aspect of the present invention provides a method for predicting brain fatigue state of a subject based on exhaled gasomics, the method comprising:
[0025] Acquiring data, obtaining content or concentration data of volatile organic compounds in the sample to be tested;
[0026] Analyzing data, inputting the content or concentration data of the volatile organic compounds into a constructed prediction model, wherein the prediction model predicts the brain fatigue state of the subject based on the content or concentration data of the volatile organic compounds;
[0027] Outputting a prediction result, and predicting whether the subject is in a brain fatigue state based on the output result of the prediction model;
[0028] The volatile organic compounds include butene, pentene, 1,3-butadiene, ethyl formate, butanol, n-butane, acrolein, acrylonitrile, propionitrile, furan, methyl octanoate and / or ethyl sulfide;
[0029] Optionally, the content or concentration data of the volatile organic compounds is obtained by testing the sample to be tested by mass spectrometry, gas chromatography, spectroscopy, nuclear magnetic resonance or any combination thereof;
[0030] Optionally, the construction of the prediction model includes:
[0031] Obtaining content or concentration data of volatile organic compounds, wherein the volatile organic compounds include butene, pentene, 1,3-butadiene, ethyl formate, butanol, n-butane, acrolein, acrylonitrile, propionitrile, furan, methyl octanoate and / or ethyl sulfide, and the content or concentration data of the volatile organic compounds are from a normal population and a brain fatigue population;
[0032] Constructing a prediction model and evaluating the effectiveness of the prediction model, dividing the content or concentration data of the volatile organic compounds into a training set and a test set, extracting the content or concentration data of the volatile organic compounds in the training set and inputting it into a machine learning model to construct a prediction model, and verifying it through the test set to evaluate the effectiveness of the prediction model;
[0033] Optionally, the machine learning model includes a linear regression model, a logistic regression model, a Lasso regression model, a Ridge regression model, a linear discriminant analysis model, a nearest neighbor model, a decision tree model, a perceptron model, a neural network model, a support vector machine model, a naive Bayes model, an AdaBoost model, a GBDT model, an XGBoost model, a LightGBM model, a CatBoost model and / or a random forest model;
[0034] Optionally, the sample to be tested is exhaled gas from a subject.
[0035] A fifth aspect of the present invention provides a system for predicting brain fatigue state of a subject based on exhaled gasomics, the system comprising:
[0036] A data acquisition unit is used to acquire the content or concentration data of volatile organic compounds in the sample to be tested;
[0037] A data analysis unit, used for inputting the content or concentration data of the volatile organic compounds into a constructed prediction model, wherein the prediction model predicts the brain fatigue state of the subject based on the content or concentration data of the volatile organic compounds;
[0038] A prediction result output unit, used for predicting whether the subject is in a brain fatigue state based on the output result of the prediction model;
[0039] The volatile organic compounds include butene, pentene, 1,3-butadiene, ethyl formate, butanol, n-butane, acrolein, acrylonitrile, propionitrile, furan, methyl octanoate and / or ethyl sulfide;
[0040] Optionally, the content or concentration data of the volatile organic compounds is obtained by testing the sample to be tested by mass spectrometry, gas chromatography, spectroscopy, nuclear magnetic resonance or any combination thereof;
[0041] Optionally, the construction of the prediction model includes:
[0042] Obtaining content or concentration data of volatile organic compounds, wherein the volatile organic compounds include butene, pentene, 1,3-butadiene, ethyl formate, butanol, n-butane, acrolein, acrylonitrile, propionitrile, furan, methyl octanoate and / or ethyl sulfide, and the content or concentration data of the volatile organic compounds are from a normal population and a brain fatigue population;
[0043] Constructing a prediction model and evaluating the effectiveness of the prediction model, dividing the content or concentration data of the volatile organic compounds into a training set and a test set, extracting the content or concentration data of the volatile organic compounds in the training set and inputting it into a machine learning model to construct a prediction model, and verifying it through the test set to evaluate the effectiveness of the prediction model;
[0044] Optionally, the machine learning model includes a linear regression model, a logistic regression model, a Lasso regression model, a Ridge regression model, a linear discriminant analysis model, a nearest neighbor model, a decision tree model, a perceptron model, a neural network model, a support vector machine model, a naive Bayes model, an AdaBoost model, a GBDT model, an XGBoost model, a LightGBM model, a CatBoost model and / or a random forest model;
[0045] Optionally, the sample to be tested is exhaled gas from a subject.
[0046] A sixth aspect of the present invention provides a device for predicting the brain fatigue state of a subject based on exhaled gasomics, the device comprising:
[0047] A memory and a processor, wherein the memory is used to store program instructions; the processor is used to call the program instructions, and when the program instructions are executed, the method for predicting the brain fatigue state of a subject based on exhaled gas omics described in the fourth aspect of the present invention is implemented.
[0048] The seventh aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for predicting the brain fatigue state of a subject based on exhaled gas omics as described in the fourth aspect of the present invention is implemented.
[0049] Compared with the prior art, the present invention has the following beneficial effects:
[0050] The present invention finds for the first time that by detecting volatile organic compounds such as butene, pentene, 1,3-butadiene, ethyl formate, butanol, n-butane, acrolein, acrylonitrile, propionitrile, furan, methyl octanoate and / or ethyl sulfide in exhaled breath, it is possible to effectively identify subjects with brain fatigue, and the method has good diagnostic efficacy, and is high in accuracy, sensitivity and specificity. Based on this, the present invention establishes a non-invasive and efficient brain performance assessment method based on exhaled breath omics, and the method can quickly detect changes in volatile organic compounds in exhaled breath. The brain fatigue state can be instantly diagnosed in this non-invasive and convenient manner. The present invention provides a rapid and non-invasive diagnostic method for the technical field of brain fatigue identification, and has broad application prospects. BRIEF DESCRIPTION OF THE DRAWINGS
[0051] Figure 1 : Statistical diagram of fatigue-inducing task results, including: (A) subjects’ accuracy rate during reaction, P<0.0001; (B) subjects’ reaction time during reaction, P<0.001; (C) subjects’ self-assessed fatigue level during reaction, P<0.0001; (D) MFI-20 scale score difference analysis before (Con group) and after (Tired group) fatigue, P<0.0001 (ns, P>0.05; *, P<0.05; **, P<0.01; ***, P<0.001; ****, P<0.0001) (n=20);
[0052] Figure 2 : Multivariate analysis and differences of VOCs, including (A) PCA score diagram of Con group and Tired group; (B) VOCs screening between Con group and Tired group based on OPLS-DA analysis; (C) Cluster analysis diagram of Con group and Tired group; Con group is the healthy control group, and Tired group is the group of people with brain fatigue (n=20);
[0053] Figure 3 : Bar graph distinguishing different volatile organic compounds in Con group and Tired group, among which, (A) butadiene; (B) propionitrile; (C) acrylonitrile; (D) acrolein; (E) butanol; (F) butene; (G) furan; (H) ethyl formate; (I) pentene; (J) methyl octanoate; (K) ethyl sulfide; (L) n-butane (n=20);
[0054] Figure 4 :ROC curve, 1,3-Butadiene, propionitrile, acrolein, furan, 1-Butanol, acrylonitrile, diethylsulfide, butene, methyl octanoate, n-butane, amylene, ethyl formate, conjunction curve;
[0055] Figure 5 A schematic flow chart of a method for predicting brain fatigue state of a subject based on exhaled gasomics provided in an embodiment of the present invention;
[0056] Figure 6 A schematic diagram of a system for predicting brain fatigue status of a subject based on exhaled gasomics provided in an embodiment of the present invention;
[0057] Figure 7 A schematic diagram of a device for predicting the brain fatigue state of a subject based on exhaled gasomics provided in an embodiment of the present invention. DETAILED DESCRIPTION
[0058] The present invention is further described below in conjunction with specific embodiments, which are only used to explain the present invention and cannot be understood as limiting the present invention. It can be understood by those skilled in the art that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and purpose of the present invention, and the scope of the present invention is defined by the claims and their equivalents.
[0059] The reagents and raw materials used in the present invention are easily obtained by those of ordinary skill in the art, and can be obtained from commercial sources unless otherwise specified. The experimental methods for which specific conditions are not specified in the present invention are usually tested under conventional conditions or under conditions recommended by the manufacturer. In particular, the following examples are only used to illustrate the present invention and should not limit the scope of the present invention in any way. It should be noted that the experimental conditions and results described in the following examples are only used to illustrate the present invention, and should not and will not limit the present invention described in detail in the claims.
[0060] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.
[0061] In some of the processes described in the specification and claims of the present invention and the above-mentioned drawings, multiple operations appearing in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this document or may be executed in parallel. The serial numbers of the operations, such as S101, S102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel.
[0062] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.
[0063] Figure 5 1 is a flow chart of a method for predicting brain fatigue state of a subject based on exhaled gasomics provided by an embodiment of the present invention. Specifically, the method comprises the following steps:
[0064] S101: Obtaining content or concentration data of volatile organic compounds in a sample to be tested;
[0065] In one embodiment, the volatile organic compound is any one or a combination of any two or more of butene, pentene, 1,3-butadiene, ethyl formate, butanol, n-butane, acrolein, acrylonitrile, propionitrile, furan, methyl octanoate, and ethyl sulfide.
[0066] In one embodiment, the sample to be tested is exhaled gas from a subject.
[0067] In one embodiment, the subject includes mammals and non-mammals. Examples of mammals include, but are not limited to, any member of the class Mammalia: humans, non-human primates such as chimpanzees and other apes and monkeys; farm animals such as cattle, horses, sheep, goats, pigs; domestic animals such as rabbits, dogs and cats; laboratory animals, including rodents such as rats, mice and guinea pigs, etc. Examples of non-mammals include, but are not limited to, birds, fish or other non-mammals, etc.
[0068] In one embodiment, the subject is a human.
[0069] In one embodiment, the content or concentration data of the volatile organic compounds can be obtained by detecting the sample to be tested using the following methods: mass spectrometry (MS), gas chromatography (GC), optical spectroscopy (SPA), nuclear magnetic resonance (NMR), laser spectroscopy, proton transfer time-of-flight mass spectrometry (PTR-TOF-MS), selected ion flow tube mass spectrometry (SIFT-MS), ion mobility spectrometry (IMS), electronic nose (E-nose), nanomaterial-based VOC / gas sensor (NMVS) or any combination thereof.
[0070] In one embodiment, proton transfer time-of-flight mass spectrometry (PTR-TOF-MS) is used to detect the content or concentration of volatile organic compounds in the sample to be tested.
[0071] In one embodiment, PTR-TOF-MS (model: KORE PTR 2E) is used, and PAMS standard gas, TO5 standard gas, aldehyde and ketone standard gas, etc. are used as standard products. Taking PAMS as an example, a standard gas test is performed. Before the test, it is necessary to confirm that the instrument has entered the standby state. Enter the standard gas distribution interface on the left side of the instrument, and enter "Set total outlet flow" 1000mL / min in the "Gas Distribution Ratio" page; enter the "Standard Gas MFC2" interface, enter "Standard Gas Concentration" 1ppm, "Gas Distribution Ratio Concentration" 0.005ppm; enter the "Dilution Gas MFC1" page, and select "Dilution Gas Component". Connect the standard gas dilution gas outlet to the instrument sample inlet solenoid valve inlet. Open the koretof.ini shortcut to modify the path and sample count of the sample data file, save and close. Open the "PTRMS" software, click "Auto acquire" to pop up the autorun TDC window, enter the number of run samples "NO.of Runs" and the run interval "Run interval", and start collecting data. After data collection is completed, open the "PTR-TOF-MS Data Analysis Software", select the "Test Spectrum Address" of the standard / sample, and click "Continuous Sampling Analysis" to obtain the particle counts of different species and water isotope particle counts.
[0072] In one embodiment, the inventors conducted PTR-TOF-MS (model: KORE PTR 2E) detection on the exhaled breath of 20 subjects before and after fatigue, and identified a total of 97 compounds based on the comparison results of the spectral library components. After the compounds were subjected to pre-processing steps such as characteristic peak extraction and normalization, they were analyzed using PTR-TOF-MS data analysis software to obtain the number of particles of different species and the number of water isotope particles. The PCA analysis results are shown in Figure 2 As shown in A, there was a certain degree of differentiation between the Con and Tired groups, indicating that there were significant metabolic differences between the subjects before and after fatigue. Figure 2 The cluster analysis diagram of C also confirmed the metabolic differences between the Con group and the Tired group. In order to further explore the differential metabolic markers related to brain performance, orthogonal partial least squares discriminant analysis (OPLS-DA) was used to analyze the differential metabolic markers between the Con group and the Tired group. Figure 2 The OPLS-DA analysis score diagram between the Con group and the Tired group shown in B clearly shows that the differential metabolite markers can effectively distinguish the two groups of subjects. Compounds with VIP value>1, |p(corr)|≥0.5, and P<0.05 were selected as candidate molecules, and specific metabolite markers with potential correlation with brain fatigue status were screened out. These markers may be of great significance for understanding the association between brain performance and fatigue. The results are shown in Table 1.
[0073] S102: inputting the content or concentration data of the volatile organic compound into a constructed prediction model, wherein the prediction model predicts the brain fatigue state of the subject based on the content or concentration data of the volatile organic compound;
[0074] In one embodiment, the construction of the prediction model includes:
[0075] Obtaining content or concentration data of volatile organic compounds, wherein the volatile organic compounds include butene, pentene, 1,3-butadiene, ethyl formate, butanol, n-butane, acrolein, acrylonitrile, propionitrile, furan, methyl octanoate and / or ethyl sulfide, and the content or concentration data of the volatile organic compounds are from a normal population and a brain fatigue population;
[0076] Construct a prediction model and evaluate the effectiveness of the prediction model, divide the content or concentration data of the volatile organic compounds into a training set and a test set, extract the content or concentration data of the volatile organic compounds in the training set and input it into a machine learning model to construct a prediction model, and verify it through the test set to evaluate the effectiveness of the prediction model, so as to obtain the constructed prediction model.
[0077] In one embodiment, the machine learning model includes a linear regression model, a logistic regression model, a Lasso regression model, a Ridge regression model, a linear discriminant analysis model, a nearest neighbor model, a decision tree model, a perceptron model, a neural network model, a support vector machine model, a naive Bayes model, an AdaBoost model, a GBDT model, an XGBoost model, a LightGBM model, a CatBoost model and / or a random forest model;
[0078] In one embodiment, the machine learning models are all machine learning models for constructing prediction models that are well known to those skilled in the art. Those skilled in the art understand that a prediction model for predicting a specific disease or state (brain fatigue) can be obtained by inputting a training set (comprising the content or concentration data of the volatile organic compounds in the exhaled gas of non-brain fatigue controls, and the content or concentration data of the volatile organic compounds in the exhaled gas of brain fatigue subjects) and a test set (comprising the content or concentration data of the volatile organic compounds in the exhaled gas of non-brain fatigue controls, and the content or concentration data of the volatile organic compounds in the exhaled gas of brain fatigue subjects) into the machine learning models for constructing prediction models that are well known to those skilled in the art.
[0079] In one embodiment, the training set is used to construct a prediction model, and the validation set is used to evaluate relevant performance indicators of the constructed prediction model, such as accuracy, sensitivity, specificity, etc.
[0080] In one embodiment, the prediction performance of the constructed prediction model is evaluated using the area under the curve (AUC) of the receiver operating characteristic (ROC) curve.
[0081] The AUC measurement is useful for comparing the accuracy of the classifier across the entire data range. A classifier with a higher AUC has a higher ability to correctly classify unknowns between two target groups (e.g., the content or concentration data of the volatile organic compounds in the exhaled breath of non-brain fatigue controls and the content or concentration data of the volatile organic compounds in the exhaled breath of brain fatigue subjects).
[0082] ROC curves are useful for describing the performance of specific features (e.g., volatile organic compounds described in the present invention) when distinguishing between two populations (e.g., non-brain fatigue individuals and brain fatigue individuals). Typically, feature data is selected in ascending order across the entire population (e.g., cases and controls) based on the value of a single feature. Then, for each value of the feature, the true positive and false positive rates of the data are calculated. The true positive rate is determined by counting the number of cases with values higher than the feature and dividing by the total number of cases. The false positive rate is determined by counting the number of controls with values higher than the feature and dividing by the total number of controls. Although this definition refers to the case where the feature is increased compared to the control, the definition is also applied to the case where the feature is lower compared to the control (in this case, samples with values lower than the feature will be counted).
[0083] ROC curves can be generated with respect to individual features, and can be generated with respect to other individual outputs, for example, a combination of two or more features can be mathematically combined (e.g., added, subtracted, multiplied, etc.) to provide a single sum value, and the single sum value can be plotted in the ROC curve. In addition, any combination of multiple features in which the combination is derived from a single output value can be plotted in the ROC curve. These combinations of features can include tests. The ROC curve is a plot of the true positive rate (sensitivity) of a test against the false positive rate (1-specificity) of the test.
[0084] Those skilled in the art can skillfully use the area under the curve (AUC) of the receiver operating characteristic (ROC) curve to evaluate the predictive efficacy of the constructed prediction model.
[0085] In one embodiment, the inventors compared the metabolites of the Con and Tired groups to explore molecular compounds that may be used as brain efficacy detection. Further analysis of the 12 compounds (P<0.01) showed that Figure 3 In order to evaluate the classification performance of the model, we performed ROC curve analysis and calculated the AUC value. The ROC curve is shown in the figure below. Figure 4As shown, the AUC results are shown in Table 2, and the ROC curve is close to the upper left corner, indicating that the model has a high diagnostic accuracy. The results show that ethyl sulfide has the highest specificity of 85.7%, sensitivity of 85.7%, the best separation value of 0.714, and AUC of 0.796 (95% confidence interval 0.609-0.983). The five markers of ethyl sulfide, ethyl formate, butene, n-butane and pentene are combined, and the AUC of the combined curve obtained is 0.888 (95% confidence interval 0.764-1.000), the best separation value is 0.643, and the sensitivity and specificity are 78.6% and 85.7%, respectively. The ROC curve of ethyl sulfide shows that the samples of the Con group and the Tired group are well separated, and ethyl sulfide has the strongest predictive ability.
[0086] In one embodiment, the inventors collected another part of the subjects and divided them into the Con group and the Tired group according to the above method. Further verification in the subjects found that the above 12 compounds had significant differential expression between the Con group and the Tired group. The ROC curve analysis results showed that the above 12 compounds and the above five markers of ethyl sulfide, ethyl formate, butene, n-butane and pentene combined had high diagnostic accuracy, and the AUC value, sensitivity and specificity were all high. This verification result further shows that the above 12 compounds and the above five markers of ethyl sulfide, ethyl formate, butene, n-butane and pentene combined have high diagnostic efficacy for the diagnosis of brain fatigue state.
[0087] S103: predicting whether the subject is in a state of brain fatigue based on the output result of the prediction model;
[0088] In one embodiment, whether the subject is in a state of brain fatigue can be determined based on the output result of the prediction model, and the corresponding prediction result can be output.
[0089] Figure 6 : is a schematic diagram of a system for predicting brain fatigue state of a subject based on exhaled gasomics provided by an embodiment of the present invention. Specifically, the system includes:
[0090] A data acquisition unit is used to acquire the content or concentration data of volatile organic compounds in the sample to be tested;
[0091] A data analysis unit, used for inputting the content or concentration data of the volatile organic compounds into a constructed prediction model, wherein the prediction model predicts the brain fatigue state of the subject based on the content or concentration data of the volatile organic compounds;
[0092] The prediction result output unit is used to predict whether the subject is in a brain fatigue state based on the output result of the prediction model.
[0093] In one embodiment, the volatile organic compounds include butene, pentene, 1,3-butadiene, ethyl formate, butanol, n-butane, acrolein, acrylonitrile, propionitrile, furan, methyl octanoate and / or ethyl sulfide.
[0094] In one embodiment, the content or concentration data of the volatile organic compounds is obtained by detecting the sample to be tested by mass spectrometry, gas chromatography, spectroscopy, nuclear magnetic resonance or any combination thereof.
[0095] In one embodiment, the construction of the prediction model includes:
[0096] Obtaining content or concentration data of volatile organic compounds, wherein the volatile organic compounds include butene, pentene, 1,3-butadiene, ethyl formate, butanol, n-butane, acrolein, acrylonitrile, propionitrile, furan, methyl octanoate and / or ethyl sulfide, and the content or concentration data of the volatile organic compounds are from a normal population and a brain fatigue population;
[0097] Construct a prediction model and evaluate the effectiveness of the prediction model, divide the content or concentration data of the volatile organic compounds into a training set and a test set, extract the content or concentration data of the volatile organic compounds in the training set and input it into a machine learning model to construct a prediction model, and verify it through the test set to evaluate the effectiveness of the prediction model.
[0098] In one embodiment, the machine learning model includes a linear regression model, a logistic regression model, a Lasso regression model, a Ridge regression model, a linear discriminant analysis model, a nearest neighbor model, a decision tree model, a perceptron model, a neural network model, a support vector machine model, a naive Bayes model, an AdaBoost model, a GBDT model, an XGBoost model, a LightGBM model, a CatBoost model and / or a random forest model.
[0099] In one embodiment, the sample to be tested is exhaled gas from a subject.
[0100] Figure 7 : is a schematic diagram of a device for predicting the brain fatigue state of a subject based on exhaled gasomics provided by an embodiment of the present invention. Specifically, the device includes:
[0101] A memory and a processor, wherein the memory is used to store program instructions; the processor is used to call the program instructions, and when the program instructions are executed, the method for predicting the brain fatigue state of a subject based on exhaled gas omics as described above is implemented.
[0102] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for predicting the brain fatigue state of a subject based on exhaled gas omics as described above is implemented.
[0103] The validation results of this validation example show that assigning intrinsic weights to indications can moderately improve the performance of the method relative to the default setting.
[0104] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0105] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely exemplary. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.
[0106] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0107] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0108] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium may include: a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc.
[0109] A person skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. The above-mentioned storage medium can be a read-only memory, a disk or an optical disk, etc.
[0110] The above is a detailed introduction to a computer device provided by the present invention. For a person skilled in the art, according to the concept of the embodiments of the present invention, there may be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as limiting the present invention.
[0111] Example Evaluation of brain performance based on exhaled gasomics and verification of its diagnostic efficacy
[0112] 1. Experimental methods
[0113] (1) Collection and storage of exhaled air
[0114] Before the experiment, all subjects kept a resting state in the same environment for 20 minutes to collect exhaled air and fill in the MFI-20 (Multidimensional Fatigue Inventory), and then began to perform the designated task. The entire task process lasted 2 hours. After completing the task, exhaled air was collected and the MFI-20 was filled. All participants were required to fast for at least 8 hours before the breath sample was collected to exclude the influence of nutrition or food. It is important to note that all individuals were required not to consume spicy food, alcohol, coffee, or smoke before collecting samples; exhaled air was collected in a disposable 1L sampling bag, and the collection room remained unchanged throughout the study; participants rinsed their mouths with pure water, then took a deep nasal breath, then expelled the dead space air in the mouth, slowly exhaled into the air for 2 seconds, and collected the remaining alveolar air into the sampling bag. Due to individual differences, the cycle may be different, and the sampling bag must be filled in the end; at least 1L of exhaled air was collected from each participant, and ambient air was collected before and after the sample was collected; all collected samples were stored and transformed at room temperature and away from light. The exhaled breath samples were processed by subtracting the background air data before further analysis; all samples were stored in a refrigerator at 4°C away from light and tested within 6 hours.
[0115] (2) Analysis of exhaled breath components before and after fatigue
[0116] Use PTR-TOF-MS (model: KORE PTR 2E), and use PAMS standard gas, TO5 standard gas, aldehyde and ketone standard gas, etc. as standard products. Take PAMS as an example to perform standard gas test. Before testing, you need to confirm that the instrument has entered the standby state. Enter the standard gas distribution interface on the left side of the instrument, and enter "Set total outlet flow" 1000mL / min on the "Gas distribution ratio" page; enter the "Standard Gas MFC2" interface, enter "Standard Gas Concentration" 1ppm, "Gas Distribution Ratio Concentration" 0.005ppm; enter the "Dilution Gas MFC1" page, and select "Dilution Gas Component". Connect the standard gas dilution gas outlet to the instrument sample inlet solenoid valve inlet. Open the koretof.ini shortcut to modify the path and sample count of the sample data file, save and close it. Open the "PTRMS" software, click "Autoacquire" to pop up the autorun TDC window, enter the number of run samples "NO.of Runs" and the run interval "Runinterval", and start collecting data. After data collection is completed, open the "PTR-TOF-MS Data Analysis Software", select the "Test Spectrum Address" of the standard / sample, and click "Continuous Sampling Analysis" to obtain the particle counts of different species and water isotope particle counts.
[0117] 2. Experimental results
[0118] (1) Establishment of mental workload model
[0119] The subjects' accuracy, reaction time, self-ratings in task execution, and multi-dimensional fatigue scale scores before and after the task were analyzed. These indicators were divided into different levels, namely task measurement method indicators and subjective measurement method indicators. Figure 1 A) Reaction time ( Figure 1 B) Self-assessed fatigue level ( Figure 1 C), a paired sample t-test was performed on the first block and the twelfth block, and the results showed significant differences between the two blocks (P>0.0001; P<0.001; P<0.0001); in the multidimensional fatigue scale scores of the subjects before and after fatigue ( Figure 1 D), compared with before fatigue, the subjects' scores after fatigue were significantly higher, and there was a significant difference between the two groups, which was statistically significant (P<0.0001); by comparing and analyzing the differences at different levels, it was verified that the 120-min continuous work task successfully induced the state of mental fatigue in the subjects.
[0120] (2) Multivariate analysis and differences of exhaled volatile organic compounds
[0121] PTR-TOF-MS (model: KORE PTR 2E) was used to detect the exhaled breath of 20 subjects before and after fatigue. A total of 97 compounds were identified based on the comparison results of the spectral library components. After the compounds were pre-processed by characteristic peak extraction and normalization, they were analyzed using PTR-TOF-MS data analysis software to obtain the number of particles of different species and the number of water isotope particles. The PCA analysis results are shown in Figure 2 As shown in A, there was a certain degree of differentiation between the Con and Tired groups, indicating that there were significant metabolic differences between the subjects before and after fatigue. Figure 2 The cluster analysis diagram of C also confirmed the metabolic differences between the Con group and the Tired group. In order to further explore the differential metabolic markers related to brain performance, orthogonal partial least squares discriminant analysis (OPLS-DA) was used to analyze the differential metabolic markers between the Con group and the Tired group. Figure 2 The OPLS-DA analysis score diagram between the Con group and the Tired group shown in B clearly shows that the differential metabolite markers can effectively distinguish the two groups of subjects. Compounds with VIP value>1, |p(corr)|≥0.5, and P<0.05 were selected as candidate molecules, and specific metabolite markers with potential correlation with brain fatigue status were screened out. These markers may be of great significance for understanding the association between brain performance and fatigue. The results are shown in Table 1.
[0122] Table 1 Differential metabolites between Con and Tired groups
[0123]
[0124]
[0125] (3) ROC analysis
[0126] The metabolites of Con and Tired groups were compared to explore the molecular compounds that may be used as brain efficacy detection. Further analysis of 12 compounds (P < 0.01) showed that Figure 3 In order to evaluate the classification performance of the model, we performed ROC curve analysis and calculated the AUC value. The ROC curve is shown in the figure below. Figure 4As shown, the AUC results are shown in Table 2, and the ROC curve is close to the upper left corner, indicating that the model has a high diagnostic accuracy. The results show that ethyl sulfide has the highest specificity of 85.7%, sensitivity of 85.7%, the best separation value of 0.714, and AUC of 0.796 (95% confidence interval 0.609-0.983). The five markers of ethyl sulfide, ethyl formate, butene, n-butane and pentene are combined, and the AUC of the combined curve obtained is 0.888 (95% confidence interval 0.764-1.000), the best separation value is 0.643, and the sensitivity and specificity are 78.6% and 85.7%, respectively. The ROC curve of ethyl sulfide shows that the samples of the Con group and the Tired group are well separated, and ethyl sulfide has the strongest predictive ability.
[0127] In addition, the present invention collected some subjects and divided them into Con group and Tired group according to the above method. It was further verified in the subjects that the above 12 compounds were significantly differentially expressed between the Con group and the Tired group. The ROC curve analysis results showed that the above 12 compounds and the above five markers of ethyl sulfide, ethyl formate, butene, n-butane and pentene combined had high diagnostic accuracy, and the AUC value, sensitivity and specificity were all high. This verification result further shows that the above 12 compounds and the above five markers of ethyl sulfide, ethyl formate, butene, n-butane and pentene combined have high diagnostic efficacy for the diagnosis of brain fatigue state.
[0128] Table 2 AUC of different volatile organic compounds for distinguishing Con and Tired groups
[0129]
[0130]
Claims
1. Application of volatile organic compounds as biomarkers of brain fatigue in the development of products for diagnosing or assisting in the diagnosis of brain fatigue, wherein the volatile organic compounds include butene, pentene, 1,3-butadiene, ethyl formate, butanol, n-butane, acrolein, acrylonitrile, propionitrile, furan, methyl octanoate and / or ethyl sulfide.
2. The use according to claim 1, characterized in that: The volatile organic compound is any one of butene, pentene, 1,3-butadiene, ethyl formate, butanol, n-butane, acrolein, acrylonitrile, propionitrile, furan, methyl octanoate, and ethyl sulfide; Optionally, the volatile organic compound is a combination of ethyl sulfide, ethyl formate, butene, n-butane and pentene.
3. Use of a reagent for detecting the content or concentration of volatile organic compounds in a sample in the preparation of a product for diagnosing or assisting in the diagnosis of brain fatigue, wherein the volatile organic compounds are the volatile organic compounds described in claim 1 or 2.
4. The use according to claim 3, characterized in that: The reagents include reagents for detecting the content or concentration of the volatile organic compounds in a sample by mass spectrometry, gas chromatography, spectroscopy, nuclear magnetic resonance or any combination thereof; Optionally, the sample is exhaled breath from a subject.
5. A diagnostic product for diagnosing or assisting in the diagnosis of brain fatigue, characterized in that: The diagnostic product comprises the reagent for detecting the content or concentration of volatile organic compounds in a sample as described in claim 3 or 4.
6. The diagnostic product according to claim 5, characterized in that The diagnostic products include diagnostic kits and diagnostic chips.
7. A method for predicting brain fatigue state of a subject based on exhaled gasomics, characterized in that: The method comprises: Acquiring data, obtaining content or concentration data of volatile organic compounds in the sample to be tested; Analyzing data, inputting the content or concentration data of the volatile organic compounds into a constructed prediction model, wherein the prediction model predicts the brain fatigue state of the subject based on the content or concentration data of the volatile organic compounds; Outputting a prediction result, and predicting whether the subject is in a brain fatigue state based on the output result of the prediction model; The volatile organic compounds include butene, pentene, 1,3-butadiene, ethyl formate, butanol, n-butane, acrolein, acrylonitrile, propionitrile, furan, methyl octanoate and / or ethyl sulfide; Optionally, the content or concentration data of the volatile organic compounds is obtained by testing the sample to be tested by mass spectrometry, gas chromatography, spectroscopy, nuclear magnetic resonance or any combination thereof; Optionally, the construction of the prediction model includes: Obtaining content or concentration data of volatile organic compounds, wherein the volatile organic compounds include butene, pentene, 1,3-butadiene, ethyl formate, butanol, n-butane, acrolein, acrylonitrile, propionitrile, furan, methyl octanoate and / or ethyl sulfide, and the content or concentration data of the volatile organic compounds are from a normal population and a brain fatigue population; Constructing a prediction model and evaluating the effectiveness of the prediction model, dividing the content or concentration data of the volatile organic compounds into a training set and a test set, extracting the content or concentration data of the volatile organic compounds in the training set and inputting it into a machine learning model to construct a prediction model, and verifying it through the test set to evaluate the effectiveness of the prediction model; Optionally, the machine learning model includes a linear regression model, a logistic regression model, a Lasso regression model, a Ridge regression model, a linear discriminant analysis model, a nearest neighbor model, a decision tree model, a perceptron model, a neural network model, a support vector machine model, a naive Bayes model, an AdaBoost model, a GBDT model, an XGBoost model, a LightGBM model, a CatBoost model and / or a random forest model; Optionally, the sample to be tested is exhaled gas from a subject.
8. A system for predicting brain fatigue status of subjects based on exhaled gas omics, characterized in that: The system comprises: A data acquisition unit is used to acquire the content or concentration data of volatile organic compounds in the sample to be tested; A data analysis unit, used for inputting the content or concentration data of the volatile organic compounds into a constructed prediction model, wherein the prediction model predicts the brain fatigue state of the subject based on the content or concentration data of the volatile organic compounds; A prediction result output unit, used for predicting whether the subject is in a brain fatigue state based on the output result of the prediction model; The volatile organic compounds include butene, pentene, 1,3-butadiene, ethyl formate, butanol, n-butane, acrolein, acrylonitrile, propionitrile, furan, methyl octanoate and / or ethyl sulfide; Optionally, the content or concentration data of the volatile organic compounds is obtained by testing the sample to be tested by mass spectrometry, gas chromatography, spectroscopy, nuclear magnetic resonance or any combination thereof; Optionally, the construction of the prediction model includes: Obtaining content or concentration data of volatile organic compounds, wherein the volatile organic compounds include butene, pentene, 1,3-butadiene, ethyl formate, butanol, n-butane, acrolein, acrylonitrile, propionitrile, furan, methyl octanoate and / or ethyl sulfide, and the content or concentration data of the volatile organic compounds are from a normal population and a brain fatigue population; Constructing a prediction model and evaluating the effectiveness of the prediction model, dividing the content or concentration data of the volatile organic compounds into a training set and a test set, extracting the content or concentration data of the volatile organic compounds in the training set and inputting it into a machine learning model to construct a prediction model, and verifying it through the test set to evaluate the effectiveness of the prediction model; Optionally, the machine learning model includes a linear regression model, a logistic regression model, a Lasso regression model, a Ridge regression model, a linear discriminant analysis model, a nearest neighbor model, a decision tree model, a perceptron model, a neural network model, a support vector machine model, a naive Bayes model, an AdaBoost model, a GBDT model, an XGBoost model, a LightGBM model, a CatBoost model and / or a random forest model; Optionally, the sample to be tested is exhaled gas from a subject.
9. A device for predicting the brain fatigue state of a subject based on exhaled gasomics, characterized in that: The device comprises: A memory and a processor, wherein the memory is used to store program instructions; the processor is used to call the program instructions, and when the program instructions are executed, the method for predicting the brain fatigue state of a subject based on exhaled gas omics as described in claim 7 is implemented.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for predicting the brain fatigue state of a subject based on exhaled gas omics as described in claim 7 is implemented.
Citation Information
Cited By
Expiratory gas marker for evaluating mental fatigue state and method and device for identifying mental fatigue state
CN121445379A
