Human body exhaled air compound disease detection system

Abstract

The invention provides a human body exhaled air compound disease detection system, and relates to the technical field of disease detection, the system can comprise a spectrometer device and a gas sensing array device, through the dual-channel design of the spectrometer device and the gas sensing array device, the spectrometer carries out pre-separation and ion peak detection on complex exhaled air, and the complex exhaled air is detected through the gas sensing array device. Non-target gas interference caused by cross sensitivity is eliminated, and gas sensing array equipment is used for detecting the concentration of various nitrogen-containing markers to form a multi-dimensional characteristic data set; and the results of the two are jointly input into a disease detection model subjected to deep learning training, so that comprehensive detection of diseases such as asthma and chronic kidney diseases can be realized. The method overcomes the misjudgment caused by cross sensitivity of a single sensor, breaks through the limitation of insufficient information amount of a single marker, can remarkably improve the detection accuracy, and meets the requirements of noninvasive, rapid and accurate clinical diagnosis.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of disease detection, and in particular to a human exhaled air composite disease detection system. BACKGROUND

[0002] Human exhaled air is rich in biomarker information. Current medical research has found that in the early stages of some diseases, human cells will appear abnormal in the process of metabolism and energy exchange, causing changes in the composition and content of human exhaled air.

[0003] For example, the concentration of nitrogen-containing disease marker gases such as nitrogen oxides (NOx), ammonia (NH3), and trimethylamine (TMA) in the exhaled air of patients with asthma and chronic kidney disease is significantly increased. By using this characteristic, early diagnosis of chronic kidney disease patients can be achieved by detecting these characteristic trace gases with high precision.

[0004] Currently, a single gas sensor can achieve low-concentration accurate detection of a specific target gas, but for the complex atmosphere in human exhaled air, it has the problem of cross-sensitivity, that is, it also responds to non-target detection gases, which leads to low detection accuracy.

[0005] In addition, the concentration information of a single nitrogen-containing marker is not sufficient to judge the progression of asthma or chronic kidney disease. The concentration information of multiple nitrogen-containing markers needs to be integrated to have clinical value. SUMMARY

[0006] The present application provides a human exhaled air composite disease detection system to overcome the limitations of misjudgment caused by cross-sensitivity of a single sensor and insufficient amount of single marker information, thereby improving detection accuracy and meeting the needs of non-invasive, rapid, and accurate clinical diagnosis. To achieve the above purpose, the present application adopts the following technical solutions:

[0007] In a first aspect, the present application provides a human exhaled air composite disease detection system, which can include:

[0008] A mass spectrometer device and a gas sensing array device;

[0009] The mass spectrometer device is used for pre-separation of mixed gas and ion peak inspection of the gas after pre-separation;

[0010] The gas sensing array device is used to collect the patient's exhaled gas and identify the concentration of characteristic trace gas corresponding to the disease to be detected in the patient's exhaled gas, so that the computing control device inputs the ion peak signal set output by the mass spectrometer device and the signal data set output by the gas sensing array device into a pre-trained disease detection model to obtain a disease detection result, which is one of health, asthma, pneumonia and chronic kidney disease.

[0011] Optionally, the system further comprises a carbon dioxide sensor.

[0012] The carbon dioxide sensor is used to detect the gas exhaled by the patient, and when the carbon dioxide concentration in the gas reaches a concentration threshold, a valve guide signal is sent to the computing control device.

[0013] Optionally, the gas sensing array device comprises a NOx gas sensor, an NH3 gas sensor, a TMA gas sensor and a CRE gas sensor.

[0014] The valve assembly, the sampling pump and the gas sensing array device constitute a controllable first gas pipeline along the gas flow direction.

[0015] Optionally, the mass spectrometer device comprises a gas chromatograph and an ion migration device.

[0016] The gas chromatograph is used to separate the components in the patient's exhaled gas into single or simplified component clusters in time sequence according to the adsorption or desorption ability difference of different gases on the chromatographic column.

[0017] The ion migration device is used to ionize the separated gas to form an ion peak signal set.

[0018] Optionally, the quantitative ring, the valve assembly, the gas source bottle, the gas chromatograph and the ion migration device constitute a controllable second gas pipeline.

[0019] Optionally, the first gas pipeline and the second gas pipeline are connected by the valve assembly and the quantitative ring.

[0020] Optionally, the system further comprises a computing control device, which is used to control the opening and closing of the valve assembly in the first gas pipeline and the valve assembly in the second gas pipeline, so as to control the conduction or closing of the first gas pipeline and the second gas pipeline.

[0021] Optionally, the first gas circuit comprises a plurality of sampling pumps, wherein the first sampling pump is arranged at the gas inlet end of the gas sensing array device, the second sampling pump is arranged at the outlet end of the gas sensing array device, and the third sampling pump is arranged at the gas outlet end of the quantitative ring.

[0022] The computing control device is also configured to control each sampling pump in the second loop to work to accelerate the flow direction of the patient's exhaled gas and the waste gas.

[0023] Optionally, the first gas passage further comprises a solenoid valve connected with the gas sensing array device.

[0024] The computing control device is also configured to control the solenoid valve to start to draw air into the gas sensing array device and discharge the patient's exhaled gas.

[0025] Optionally, the computing control device is specifically configured to take the softmax function as an output layer activation function of the disease detection model, and take an output result with the maximum probability of the output layer activation function as the disease detection result.

[0026] In a second aspect, the embodiments of the present application further provide a computing control device, which can comprise a processor and a memory: the memory is configured to store one or more computer programs; the one or more computer programs comprise instructions, when executed by the processor, cause the computing control device to input the ion peak signal set output by the mass spectrometer device and the signal data set output by the gas sensing array device into a pre-trained disease detection model, and obtain a disease detection result, the disease detection result being one of health, asthma, pneumonia and chronic kidney disease.

[0027] In a third aspect, the embodiments of the present application further provide a computer storage medium comprising computer instructions, the computer instructions running on the computing control device of the second aspect.

[0028] The human exhaled gas composite disease detection system provided by the present application can overcome the misjudgment caused by the cross-sensitivity of a single sensor and the limitation of insufficient information amount of a single marker, and further improve the detection accuracy to meet the needs of non-invasive, rapid and accurate clinical diagnosis. In order to achieve the above-mentioned purpose, the present application adopts the following technical solutions:

[0029] In a first aspect, the present application provides a human exhaled gas composite disease detection system, which can comprise:

[0030] A mass spectrometer device and a gas sensing array device;

[0031] The mass spectrometer device is configured to pre-separate the mixed gas and perform ion peak detection on the gas after pre-separation.

[0032] The gas sensing array device is used to collect the patient's exhaled gas and identify the concentration of characteristic trace gas corresponding to the disease to be detected in the patient's exhaled gas, so that the computing control device inputs the ion peak signal set output by the mass spectrometer device and the signal data set output by the gas sensing array device into a pre-trained disease detection model to obtain a disease detection result, which is one of health, asthma, pneumonia and chronic kidney disease.

[0033] Optionally, the system further comprises a carbon dioxide sensor.

[0034] The carbon dioxide sensor is used to detect the gas exhaled by the patient, and when the carbon dioxide concentration in the gas reaches a concentration threshold, a valve guide signal is sent to the computing control device.

[0035] Optionally, the gas sensing array device comprises a NOx gas sensor, an NH3 gas sensor, a TMA gas sensor and a CRE gas sensor.

[0036] The valve assembly, the sampling pump and the gas sensing array device constitute a controllable first gas pipeline along the gas flow direction.

[0037] Optionally, the mass spectrometer device comprises a gas chromatograph and an ion migration device.

[0038] The gas chromatograph is used to separate the components in the patient's exhaled gas into single or simplified component clusters in time sequence according to the adsorption or desorption ability difference of different gases on the chromatographic column.

[0039] The ion migration device is used to ionize the separated gas to form an ion peak signal set.

[0040] Optionally, the quantitative ring, the valve assembly, the gas source bottle, the gas chromatograph and the ion migration device constitute a controllable second gas pipeline.

[0041] Optionally, the first gas pipeline and the second gas pipeline are connected by the valve assembly and the quantitative ring.

[0042] Optionally, the system further comprises a computing control device, which is used to control the opening and closing of the valve assembly in the first gas pipeline and the valve assembly in the second gas pipeline, so as to control the conduction or closing of the first gas pipeline and the second gas pipeline.

[0043] Optionally, the first gas circuit comprises a plurality of sampling pumps, wherein the first sampling pump is arranged at the gas inlet end of the gas sensing array device, the second sampling pump is arranged at the outlet end of the gas sensing array device, and the third sampling pump is arranged at the gas outlet end of the quantitative ring.

[0044] The computing control device is further configured to control each sampling pump in the second loop to work to accelerate the flow direction of the patient's exhaled gas and the waste gas.

[0045] Optionally, the first gas passage further comprises a solenoid valve connected with the gas sensing array device.

[0046] The computing control device is further configured to control the solenoid valve to start to draw air into the gas sensing array device and discharge the patient's exhaled gas.

[0047] Optionally, the computing control device is specifically configured to take the softmax function as an output layer activation function of the disease detection model, and take an output result with the maximum probability of the output layer activation function as the disease detection result.

[0048] In a second aspect, the embodiments of the present application further provide a computing control device, which can include a processor and a memory: the memory is configured to store one or more computer programs; the one or more computer programs include instructions, when executed by the processor, cause the computing control device to input the ion peak signal set output by the mass spectrometer device and the signal data set output by the gas sensing array device into a pre-trained disease detection model, and obtain a disease detection result, the disease detection result being one of health, asthma, pneumonia and chronic kidney disease.

[0049] In a third aspect, the embodiments of the present application further provide a computer storage medium, including computer instructions, the computer instructions running on the computing control device in the second aspect. BRIEF DESCRIPTION OF DRAWINGS

[0050] Figure 1 A structural schematic diagram of a human exhaled gas composite disease detection system provided by the embodiments of the present application;

[0051] Figure 2 A structural schematic diagram of another human exhaled gas composite disease detection system provided by the embodiments of the present application;

[0052] Figure 3 A flowchart of a disease testing method provided by the embodiments of the present application;

[0053] Figure 4 A flowchart of another disease testing method provided by the embodiments of the present application. DETAILED DESCRIPTION

[0054] The terms "first", "second" and "third" and the like in the specification and claims of the present application and the description of the drawings are used to distinguish different objects, and are not used to limit a specific order.

[0055] In the embodiments of the present application, the word "exemplary" or "for example" is used to mean serving as an example, instance, or illustration, at 99 least with respect to the matters described at that point in the detailed description. The use of any of these terms in the detailed description is not to the exclusion of the other embodiments or use of terms. For the purposes of the present application, the term "or" is used in the inclusive sense (i.e., and / or) unless the context clearly indicates otherwise.

[0056] Human exhaled breath is rich in biomarker information. Now medical research has found that in the early stages of some diseases, human cells will appear abnormal in the process of metabolism and energy exchange, causing changes in the composition and content of human exhaled breath.

[0057] For example, the concentration of nitrogen oxide (NOx), ammonia (NH3), trimethylamine (TMA) and creatinine, etc. in the exhaled breath of patients with asthma and chronic kidney disease is significantly increased. By using this feature, the early diagnosis of chronic kidney disease patients can be achieved by high-precision detection of these characteristic trace gases.

[0058] At present, a single gas sensor can achieve low-concentration accurate detection of a specific target gas, but for the complex components in human exhaled breath, it has the problem of cross-sensitivity, that is, it also responds to non-target detection gases, which further leads to low detection accuracy. In addition, the concentration information of a single nitrogen-containing marker is not sufficient for the judgment of the progress of asthma or chronic kidney disease, and the concentration information of the above-mentioned multiple nitrogen-containing markers needs to be integrated to have clinical value.

[0059] In view of this, the present application provides a human exhaled breath composite disease detection system, comprising: a mass spectrometer device and a gas sensing array device;

[0060] The spectrometer device is used for pre-separation of mixed gas and ion peak inspection of the gas after pre-separation, the gas sensing array device is used for collecting patient exhaled gas and identifying the concentration of characteristic trace gas corresponding to the disease to be detected in the patient exhaled gas, so that the computing control device inputs the ion peak signal set output by the spectrometer device and the signal data set output by the gas sensing array device into the pre-trained disease detection model to obtain a disease detection result, and the disease detection result is one of health, asthma, pneumonia and chronic kidney disease. In this way, through the dual-channel design of "spectrometer device + gas sensing array device", the spectrometer is used for pre-separation and ion peak inspection of complex exhaled gas, and the non-target gas interference caused by cross-sensitivity is eliminated, the gas sensing array device is used for synchronously quantifying the concentration of multiple nitrogen-containing markers (NOx, NH3 and TMA), and a multi-dimensional feature data set is formed; the results of the two are jointly input into the disease detection model trained by deep learning, so that comprehensive discrimination of diseases such as asthma and chronic kidney disease can be realized. Therefore, the misjudgment caused by the cross-sensitivity of a single sensor is overcome, the limitation of insufficient information quantity of a single marker is broken through, the detection accuracy is significantly improved, and the needs of non-invasive, rapid and accurate clinical diagnosis are met.

[0061] In order to make the technical solutions of the present application clearer and easier to understand, the human exhaled gas composite disease detection system provided by the embodiments of the present application will be introduced below in combination with the above-mentioned embodiments and corresponding drawings. Here, it can be called Embodiment One, and an example is shown in Figure 1 The human exhaled gas composite disease detection system provided by Embodiment One of the present application can include a spectrometer device 101 and a gas sensing array device 102.

[0062] The spectrometer device 101 is used for pre-separation of mixed gas and ion peak inspection of the gas after pre-separation;

[0063] The gas sensing array device 102 is used for collecting patient exhaled gas and identifying the concentration of characteristic trace gas corresponding to the disease to be detected in the patient exhaled gas, so that the computing control device inputs the ion peak signal set output by the spectrometer device and the sensor array response signal data set output by the gas sensing array device into the pre-trained disease detection model to obtain a disease detection result, and the disease detection result is one of health, asthma, pneumonia and chronic kidney disease.

[0064] In some possible implementation manners, the system provided by the embodiment can further include a carbon dioxide CO2 sensor 1, the carbon dioxide sensor is used for detecting the gas exhaled by the patient, and when the carbon dioxide concentration in the gas reaches a concentration threshold, a valve guide signal is sent to the computing control device. In this way, through the pre-concentration control of the human exhaled CO2 sensor, it is ensured that the patient exhaled gas collected is alveolar gas, and the interference of impurity gas in the oral cavity is excluded.

[0065] In some possible implementations, the gas sensor array device 102 may include a NOx gas sensor, an NH3 gas sensor, a TMA gas sensor, and a CRE gas sensor. Of course, this is just an example, and the gas sensor array device 102 may also include some of the sensors mentioned above. The specific configuration can be set according to actual needs, and is not limited here.

[0066] This allows for the detection of NOx, NH3, TMA, and CRE in exhaled air. Exhaled air at an appropriate flow rate enters the gas sensing array device to undergo oxidation-reduction reactions, and the concentration of the target gas can be obtained by detecting changes in resistance. The sensor responds specifically to the oxidation / reduction reactions of NOx, NH3, TMA, and CRE, with minimal cross-interference. The reaction products directly change the resistance of the sensing layer, which is a single-valued function of the concentration, eliminating the need for complex separation or compensation algorithms, thus resulting in high detection accuracy. Furthermore, the gas undergoes oxidation-reduction instantaneously on the sensing membrane surface, reaching steady state within <1 second of resistance change, eliminating the long path delays of chromatographic columns and optical cavities, resulting in fast response time. In addition, multiple sensors are integrated into a single unit, eliminating the need for pumps, valves, and other components, making the device relatively small in size.

[0067] The valve assembly, sampling pump, and gas sensor array device form a controllable on / off first gas pipeline along the gas flow direction.

[0068] For example, such as Figure 2 As shown, the valve assembly here can be an electromagnetic three-way valve 11, and the sampling pump can include sampling pump 13 (also called the first sampling pump), sampling pump 10 (the second sampling pump), and sampling pump 9 (the third sampling pump). The first sampling pump can be set at the air inlet end of the gas sensing array device 102 to draw alveolar gas into the gas sensing array device 102. The second sampling pump can be set at the outlet end of the gas sensing array device to draw out the exhaust gas after it has been detected by the gas sensing array device. The third sampling pump can be set at the air outlet end of the metering loop to draw alveolar gas into the metering loop 8.

[0069] Sampling pump 9, sampling pump 10, sampling pump 13, electromagnetic three-way valve 11, and gas sensing array device 102 form a controllable on / off first gas pipeline along the gas flow direction.

[0070] In some possible implementations, the first gas pipeline in this embodiment may further include a solenoid valve 13, which is connected to the gas sensing array device 102.

[0071] In some possible implementations, the spectrometer device in this application embodiment may include a gas chromatograph device 5 (corresponding to...) Figure 2The gas chromatograph device 5 can include a chromatograph thermostat, a chromatograph column, and a corresponding carrier gas flow control device, and the GC chromatograph column can be a DB-5 capillary chromatograph column with an inner diameter of 0.53 mm, a length of 15 m, and a film thickness of 1.5 μm. The ion mobility device 6 can include a drift tube, a power supply, a heating device, and a circuit, and the drift tube can be stacked by a stainless steel ring and a polytetrafluoroethylene ring.

[0072] The gas chromatograph device 5 is used to separate the components of the patient's exhaled gas into single or simplified component clusters in time sequence according to the adsorption or desorption ability difference of different gases on the chromatograph column, and the ion mobility device 6 is used to ionize the separated gas to form an ion peak signal set.

[0073] The second gas pipeline is composed of the quantifying ring 8, the valve assembly, the gas source bottle 2, the gas chromatograph device 5, and the ion mobility device 6.

[0074] For example, the valve assembly can include the six-way valve 7, the electrically controlled gas valve 3, and the electrically controlled gas valve 4. The six-way valve 7 is used to control the target flow of the sample gas (patient's exhaled gas) to be left in the quantifying ring. The electrically controlled gas valve 3 is used to control the drift gas provided by the gas source 2 to the IMS, and the electrically controlled gas valve 4 is used to control the carrier gas provided by the gas source 2 to the GC.

[0075] In some possible implementation manners, the first gas pipeline and the second gas pipeline are connected by the six-way valve and the quantifying ring.

[0076] After the patient's exhaled alveolar gas is collected, the alveolar gas can be divided into two paths, one of which enters the gas sensing array device through the electrically controlled valve 11, and the other of which enters the spectrum separation device through the six-way valve 7.

[0077] In some possible implementation manners, the system provided by the embodiment of the present application can further include a computing control device 103, which is used to control the opening and closing of the valve assembly (which can include the electromagnetic three-way valve 11) in the first gas pipeline and the valve assembly (which can include the six-way valve 7, the electrically controlled gas valve 3, and the electrically controlled gas valve 4) in the second gas pipeline, so as to control the conduction or closing of the first gas pipeline and the second gas pipeline.

[0078] In some possible implementation manners, the computing control device 103 can also be used to control the operation of each sampling pump in the second loop, so as to accelerate the flow direction of the patient's exhaled gas and the waste gas.

[0079] The computing control device can also be used to control the electromagnetic valve to start, so as to draw air into the gas sensing array device and discharge the patient's exhaled gas.

[0080] In some possible implementation manners, the computing control device 103 can be specifically used for storing ion peak signal sets output by the mass spectrometer device and signal data output by the gas sensing array device, and then pre-processing the stored data.

[0081] Specifically, data pre-processing can be performed on a chromatogram output by the mass spectrometer, noise can be filtered out, signal peaks can be detected, and a baseline can be corrected, and overlapping peaks can be cut. By analyzing and comparing the chromatographic information, concentration information of NO2, NO, TMA, NH3, and CRE in the exhaled gas of the test patient is obtained, and an exhaled gas chromatographic signal data set of the patient is constructed. The R-t response curve group data output by the gas sensing array device can be pre-processed, and the amplitude limiting filtering algorithm and the Kalman filtering can be used respectively to remove data outliers and smooth the data. The abnormal data in the data set is removed, the response value of each sensor is calculated, the response information of the sensor array is obtained, and a sensor array response signal data set of the exhaled gas of the patient is constructed. The gas chromatographic signal data set and the sensor array response signal data are input into a pre-trained disease detection model to obtain a disease detection result.

[0082] In some possible implementation manners, the number of nodes in the hidden layer of the neural network in the disease detection model can be 10, 9, and 8, respectively, and the computing control device is specifically used for using Leaky ReLU as an activation function, which is defined as follows:

[0083]

[0084] Wherein, x is the input of the activation function, and a is the slope in the negative region, which can be 0.01, for example.

[0085] The softmax function is used as the output layer activation function of the disease detection model, so that the output satisfies 0≤label[i]≤1 and The output result with the maximum probability output by the output layer activation function (N=max(Label[i]) i=0, 1, 2, 3) is selected as the final predicted disease result.

[0086] In some possible implementation manners, the computing control device can also be used for using a cross-entropy loss function as a loss function for model training, and training the disease detection model. The cross-entropy loss function is as follows:

[0087] L(p,q)=-∑ x (p(x)logq(x)+(1-p(x))log(1-q(x)))

[0088] Wherein, P is the one-hot label of the actual disease, and q represents the disease detection result output by the model.

[0089] The application provides a human exhaled air composite disease detection system, comprising: a mass spectrometer device and a gas sensing array device;

[0090] The mass spectrometer device is used for pre-separating mixed gas and performing ion peak inspection on the gas after pre-separation, the gas sensing array device is used for collecting patient exhaled gas and identifying the concentration of characteristic trace gas corresponding to a disease to be detected in the patient exhaled gas, so that the computing control device inputs an ion peak signal set output by the mass spectrometer device and a signal data set output by the gas sensing array device into a pre-trained disease detection model to obtain a disease detection result, and the disease detection result is one of health, asthma, pneumonia and chronic kidney disease. In this way, through the dual-channel design of the "mass spectrometer device + gas sensing array device", the mass spectrometer is used for pre-separating and ion peak inspection on complex exhaled gas, non-target gas interference caused by cross-sensitivity is eliminated, the gas sensing array device is used for synchronously quantifying the concentration of multiple nitrogen-containing markers (NOx, NH3, TMA and CRE), and a multi-dimensional feature data set is formed; the results of the two are jointly input into a disease detection model trained by deep learning, so that comprehensive discrimination of diseases such as asthma and chronic kidney disease can be realized. The application overcomes the misjudgment caused by cross-sensitivity of a single sensor, breaks through the limitation of insufficient information quantity of a single marker, can significantly improve the detection accuracy, and meets the needs of non-invasive, rapid and accurate clinical diagnosis.

[0091] In addition, the application also provides a disease testing method, which corresponds to the human exhaled air composite disease detection system described above. In order to make the technical solutions of the application clearer and easier to understand, the disease testing method provided by the embodiments of the application will be introduced below in combination with the above-mentioned embodiments and corresponding drawings. The above-mentioned embodiment can be referred to as embodiment one, and the present embodiment can be referred to as embodiment two. The method provided in embodiment two can be implemented in the human exhaled air composite disease detection system shown in the structure of Figure 1 , as shown in Figure 3 , the disease testing method can include but is not limited to the following contents:

[0092] S301: The mass spectrometer device receives mixed gas, pre-separates the mixed gas, and performs ion peak inspection on the gas after pre-separation.

[0093] S302: The gas sensing array device collects patient exhaled gas and identifies the concentration of characteristic trace gas corresponding to a disease to be detected in the patient exhaled gas.

[0094] S303: The computing control device inputs an ion peak signal set output by the mass spectrometer device and a signal data set output by the gas sensing array device into a pre-trained disease detection model to obtain a disease detection result, and the disease detection result is one of health, asthma, pneumonia and chronic kidney disease.

[0095] The embodiment is similar to the specific implementation principle of the computing control device in Embodiment One, and thus is not described herein.

[0096] The application also provides another disease testing method, which corresponds to the human exhaled air composite disease detection system as described above, and can be referred to as Embodiment Three. The method provided in Embodiment Three can be implemented in the human exhaled air composite disease detection system with the structure as shown in Figure 2 Figure 4 The disease testing method can include but is not limited to the following contents:

[0097] S401: The carbon dioxide sensor detects the gas exhaled by the patient.

[0098] The carbon dioxide sensor obtains the gas exhaled by the patient. If the carbon dioxide concentration in the gas exhaled by the patient reaches a concentration threshold, a valve conduction signal is sent to the computing control device, so that the computing control device controls the first gas pipeline and the second gas pipeline to be conducted according to the valve conduction signal. The concentration threshold can be set according to requirements. In this way, through the pre-concentration control of the human exhaled CO2 sensor, it is ensured that the collected patient exhaled air is alveolar air, and the interference of impurity gas in the oral cavity is excluded.

[0099] If the carbon dioxide concentration in the gas exhaled by the patient does not reach the concentration threshold, the detection is performed again.

[0100] S402: The computing control device controls the sampling pump 9 to start.

[0101] The computing control device can control the sampling pump 9 to start according to the valve conduction signal, so that the alveolar air (gas exhaled by the patient) is drawn into the six-way valve, and the target flow of alveolar air is left in the quantitative ring 8, so as to ensure that the collected is pure alveolar air, avoiding the dilution and pollution of the respiratory tract dead space gas (anatomical ineffective space gas), thereby improving the accuracy of subsequent analysis. Control the excess gas to be discharged.

[0102] S403: The computing control device controls the electrically controlled gas valve 3 to open.

[0103] The computing control device can control the electrically controlled gas valve 3 to open according to the valve conduction signal, so as to provide ion mobility spectrometry (IMS) drift gas.

[0104] S404: The computing control device controls the electrically controlled gas valve 4 to open.

[0105] The computing control device can control the electrically controlled gas valve 4 to open according to the valve conduction signal, so as to provide gas chromatography (GC) carrier gas. ​

[0106] S405: The gas chromatograph device pre-separates the mixed gas.

[0107] The gas chromatograph device pre-separates the received alveolar air (i.e. the mixed gas).

[0108] S406: The ion mobility device performs ion peak inspection on the pre-separated gas.

[0109] The ion mobility device performs ion peak inspection on the pre-separated gas.

[0110] S407: The computing control device controls the electrically controlled three-way valve 11 to open.

[0111] The computing control device can control the electrically controlled three-way valve 11 to open according to the valve guide communication signal, and it should be noted that at this time, the computing control device needs to control the end of the electrically controlled three-way valve 11 close to the sampling pump 11 and the end close to the gas sensing array device to open, and control the end close to the sampling pump 10 to close, so as to ensure that the alveolar air enters the gas sampling device.

[0112] S408: The computing control device controls the electrically controlled three-way valve 13 to open.

[0113] S409: The computing control device controls the sampling pump 14 to start.

[0114] The computing control device can control the sampling pump 14 to start according to the valve guide communication signal, and the alveolar air is sucked into the gas sampling device.

[0115] S410: The computing control device controls the electromagnetic valve 13 and the sampling pump 14 to close.

[0116] S411: The computing control device stores the ion peak signal set output by the mass spectrometer device and the signal data output by the gas sensing array device.

[0117] S412: The computing control device controls the electromagnetic valve 13 to open and the sampling pump 10 to start.

[0118] The computing control device controls the electromagnetic valve 13 to open and the sampling pump 10 to start, and clean air is sucked into the gas sensing array device to discharge the alveolar air.

[0119] S413: The computing control device controls the gas source to input clean air.

[0120] S414: The computing control device pre-processes the stored data.

[0121] S415: The computing control device inputs the data after pre-processing to the disease detection model to obtain a disease detection result.

[0122] Step S414 and step S415 are similar to the implementation principle in Embodiment 1, and thus are not described again. For details, refer to the relevant description in Embodiment 1.

[0123] In some embodiments, the computing control device can be a desktop, a laptop, a notebook computer, an Ultra-mobile Personal Computer (UMPC), a handheld computer, a netbook, a Personal Digital Assistant (PDA), or the like, and the specific form of the computing control device is not specially limited in the present application.

[0124] It can be understood that the interface connection relationship between the modules in the embodiment is only illustrative and does not constitute a structural limitation on the human exhaled air composite disease detection system. In some other embodiments of the present application, the human exhaled air composite disease detection system can also use different interface connection modes or combinations of multiple interface connection modes in the above embodiments.

[0125] The technical solutions of the embodiment can be embodied in the form of a software product, and the computer software product is stored in a storage medium and includes instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the method described in the embodiments. The storage medium includes a flash memory, a mobile hard disk, a read-only memory, a random access memory, a magnetic disk or an optical disk, and various media that can store program codes.

[0126] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or replacements within the technical scope disclosed in the present application should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A human exhaled breath multi-disease detection system, characterized in that, The system comprises a mass spectrometer device and a gas sensing array device. The mass spectrometer device is configured to pre-separate mixed gas and perform ion peak inspection on the pre-separated gas. The gas sensing array device is configured to collect patient exhaled gas and identify the concentration of characteristic trace gas corresponding to the disease to be detected in the patient exhaled gas, so that the computing control device inputs the ion peak signal set output by the mass spectrometer device and the signal data set output by the gas sensing array device into a pre-trained disease detection model to obtain a disease detection result, which is one of health, asthma, pneumonia and chronic kidney disease.

2. The system of claim 1, wherein, The system further comprises a carbon dioxide sensor. The carbon dioxide sensor is configured to detect the patient exhaled gas and send a valve guide signal to the computing control device when the carbon dioxide concentration in the gas reaches a concentration threshold.

3. The system of claim 2, wherein, The gas sensing array device comprises a NOx gas sensor, an NH3 gas sensor, a trimethylamine TMA gas sensor and a creatinine CRE gas sensor. The valve assembly, the sampling pump and the gas sensing array device constitute a controllable first gas pipeline along the gas flow direction.

4. The system of claim 3, wherein, The mass spectrometer device comprises a gas chromatograph and an ion migration device. The gas chromatograph is configured to separate the components in the patient exhaled gas into single or simplified component clusters in time sequence according to the adsorption or desorption capacity difference of different gases on the chromatographic column. The ion migration device is configured to ionize the separated gas to form an ion peak signal set.

5. The system of claim 3, wherein, The quantitative ring, the valve assembly, the gas source bottle, the gas chromatograph and the ion migration device constitute a controllable second gas pipeline.

6. The system of claim 5, wherein, The first gas pipeline and the second gas pipeline are connected by the valve assembly and the quantitative ring.

7. The system of claim 6, wherein, The system further comprises a computing control device configured to control the opening and closing of the valve assembly in the first gas pipeline and the valve assembly in the second gas pipeline to control the conduction or closing of the first gas pipeline and the second gas pipeline.

8. The system of claim 7, wherein, The first gas circuit comprises a plurality of sampling pumps, wherein a first sampling pump is arranged at the gas inlet end of the gas sensing array device, a second sampling pump is arranged at the outlet end of the gas sensing array device, and a third sampling pump is arranged at the gas outlet end of the quantitative ring. The computing control device is further configured to control the operation of each sampling pump in the second circuit to accelerate the flow direction of the patient exhaled gas and the waste gas.

9. The system of claim 7, wherein, The first gas pipeline further comprises a solenoid valve connected to the gas sensing array device. The computing control device is further configured to control the solenoid valve to start to draw air into the gas sensing array device and discharge patient exhaled gas.

10. The system of claim 7, wherein, The computing control device is specifically configured to use a normalized exponential softmax function as the output layer activation function of the disease detection model and select the output result with the maximum probability of the output layer activation function as the disease detection result.

Images