Index detection system

Abstract

The invention discloses an index detection system. An index detection system comprises a first processor, a second processor and an index processing device. The first processor is in wireless communication connection with the second processor, and the second processor is in network connection with the index processing equipment; the first processor is connected with the blood pressure detection sensor, obtains detection data of the blood pressure detection sensor for a target object, performs validity detection on the detection data to obtain a validity detection result, and sets a validity label of the detection data based on the validity detection result; transmitting the detection data carrying the validity label to a second processor in a wireless communication mode; the second processor transmits the detection data carrying the validity label to the index processing equipment in a network communication mode; and the index processing equipment receives the detection data carrying the validity label, identifies the valid detection data, determines the vascular function index based on the valid detection data, and realizes non-invasive measurement, invasive measurement and validity detection of the index.

Description

Technical Field

[0001] The present invention relates to the field of medical technology, and in particular to an indicator detection system. Background Art

[0002] Coronary artery and microvascular function measurements mainly include coronary artery functional measurement and microvascular functional measurement. Among them, coronary artery functional measurement mainly refers to the measurement of blood flow reserve fraction, and microvascular functional measurement mainly refers to the measurement of microcirculatory resistance coefficient.

[0003] The traditional way to obtain the blood flow reserve fraction is to use a pressure guide wire to be sent from the radial artery or femoral artery to the coronary artery of the heart, and then to the vascular lesion to measure the FFR. The process of delivering the pressure guide wire is cumbersome and is restricted by factors such as the thickness and shape of the blood vessels. It often requires the operator to have more operating experience. In addition, the pressure guide wire is expensive and has high manufacturing costs. During the measurement process, adenosine drugs need to be injected to induce maximum congestion. Most of the subjects will feel chest tightness and other discomfort due to the influence of the drugs.

[0004] The traditional microcirculatory resistance coefficient is measured by the thermodilution method, which uses a pressure guidewire with a temperature sensor to be placed in the blood vessel. After three injections of normal saline, the temperature changes at the catheter port and the guidewire are recorded to calculate the average blood flow time, and then the distal coronary artery pressure measured by the pressure guidewire is used to calculate the microcirculatory resistance coefficient. Similar to the blood flow reserve fraction, the microcirculatory resistance coefficient measured by the guidewire is limited in application due to the complex operation, high price, and increased risk. Summary of the invention

[0005] The present invention provides an index detection system to solve the problems of complex and high-risk wired connection wiring.

[0006] According to one aspect of the present invention, there is provided an indicator detection system, comprising: a first processor, a second processor and an indicator processing device; the first processor is wirelessly connected to the second processor, and the second processor is network-connected to the indicator processing device;

[0007] The first processor is connected to the blood pressure detection sensor, obtains detection data of the blood pressure detection sensor for the target object, performs validity detection on the detection data to obtain a validity detection result, sets a validity tag for the detection data based on the validity detection result, and transmits the detection data carrying the validity tag to the second processor in a wireless communication manner;

[0008] The second processor transmits the detection data carrying the validity tag to the indicator processing device in a network communication manner;

[0009] The index processing device receives the detection data carrying the validity tag, identifies the valid detection data, and determines the vascular function index of the target object based on the valid detection data.

[0010] Optionally, the first processor includes a first processing module, and the first processing module includes a storage space;

[0011] The first processing module is used to: store the detected data into a storage space; identify the waveform feature data in the detection data in the storage space, and determine the detection data within the neighborhood of the waveform feature data;

[0012] Based on the detection waveform, the validity of the waveform to be detected formed by the detection data within the neighborhood range is judged to obtain a validity detection result.

[0013] Optionally, the first processing module is further used to: determine a detection threshold based on the detection data in the storage space;

[0014] When it is detected that the detection data in the storage space is greater than the detection threshold, waveform feature recognition is performed.

[0015] Optionally, the first processor is configured with a first interface and / or a second interface;

[0016] The blood pressure detection sensor connected to the first interface is an invasive blood pressure sensor;

[0017] The blood pressure detection sensor connected to the second interface is a non-invasive blood pressure sensor.

[0018] Optionally, the detection data corresponding to the non-invasive blood pressure sensor is pulse wave data;

[0019] The first processor is specifically used to: obtain first original data of the non-invasive blood pressure sensor for the target object, convert the first original data into pulse wave data; perform validity determination on a pulse wave waveform formed by pulse wave data in a neighborhood corresponding to the pulse wave data and a pulse wave detection waveform to obtain a validity detection result;

[0020] And / or, the detection data corresponding to the invasive blood pressure sensor is blood pressure data;

[0021] The first processor is specifically used to: obtain the second original data of the invasive blood pressure sensor for the target object, and convert the second original data into blood pressure data; perform validity judgment on the blood pressure waveform formed by the blood pressure data in the neighborhood corresponding to the blood pressure data and the blood pressure detection waveform to obtain a validity detection result.

[0022] Optionally, the first processor is further used to: determine the heartbeat cycle of the target object based on the valid pulse wave data; transmit the heartbeat cycle to the indicator processing device;

[0023] The index processing device is also used to: determine the initial blood pressure waveform based on the heart cycle, determine the target blood pressure waveform based on the initial blood pressure waveform and the pulse wave data corresponding to the heart cycle, determine the mean arterial pressure based on the target blood pressure waveform; determine the vascular function index of the target object based on the mean arterial pressure.

[0024] Optionally, the second processor is further used to perform anomaly detection on the detection data carrying the validity tag to obtain anomaly detection results, set an anomaly detection tag for the detection data according to the anomaly detection results, and send the detection data carrying the validity tag and the anomaly detection tag to the indicator processing device;

[0025] The index processing device determines non-abnormal valid detection data based on the validity label and the abnormal detection label, and determines the vascular function index of the target object based on the non-abnormal valid detection data.

[0026] Optionally, the vascular function index includes one or more of the blood flow reserve fraction and the microcirculatory resistance coefficient.

[0027] Optionally, the index processing device further includes a display module, which is used to display one or more items of the target object's vascular function index, test data, and a validity label of the test data.

[0028] Optionally, the indicator processing device is connected to a plurality of second processor networks, and obtains detection data carrying validity tags transmitted by the plurality of second processors respectively, and processes the detection data transmitted by the plurality of second processors in parallel to obtain vascular function indicators of a plurality of target objects.

[0029] The technical solution of the embodiment of the present invention is an indicator detection system, including a first processor, a second processor and an indicator processing device; the first processor is wirelessly connected to the second processor, and the second processor is network-connected to the indicator processing device, which solves the problem of complex wired connection wiring and reduces the complexity of the connection of the indicator detection system; the first processor is connected to the blood pressure detection sensor, obtains the detection data of the blood pressure detection sensor for the target object, and performs validity detection on the detection data to obtain the validity detection result, sets the validity tag of the detection data based on the validity detection result, and transmits the detection data carrying the validity tag to the second processor by wireless communication, providing accurate data support for subsequent analysis and processing; the second processor transmits the detection data carrying the validity tag to the indicator processing device by network communication; the indicator processing device receives the detection data carrying the validity tag, identifies the valid detection data, and determines the vascular function index of the target object based on the valid detection data, which solves the problem of complex wired connection wiring and realizes the measurement and validity detection of the vascular function index of the target object.

[0030] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0032] Figure 1 It is a structural schematic diagram of an indicator detection system provided by Embodiment 1 of the present invention;

[0033] Figure 2 It is a structural schematic diagram of an indicator detection system provided by an embodiment of the present invention;

[0034] Figure 3 is a schematic diagram of a structure between a plurality of second processors and an indicator processing device provided by an embodiment of the present invention;

[0035] Figure 4 is a structural schematic diagram of an indicator detection system provided by Embodiment 2 of the present invention;

[0036] Figure 5 It is a structural diagram of an indicator detection system provided in Example 3 of the present invention. DETAILED DESCRIPTION

[0037] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0038] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0039] Embodiment 1

[0040] Figure 1 Schematic diagram of the structure of an indicator detection system provided by the first embodiment of the present invention. This embodiment is applicable to the situation of measuring and detecting the effectiveness of the vascular function indicators of the target object. Figure 1 As shown, the index detection system includes: a first processor 110, a second processor 120 and an index processing device 130; the first processor 110 is wirelessly connected to the second processor 120, and the second processor 120 is network-connected to the index processing device 130; the first processor 110 is connected to the blood pressure detection sensor, obtains the detection data of the blood pressure detection sensor for the target object, and performs validity detection on the detection data to obtain the validity detection result, sets the validity tag of the detection data based on the validity detection result, and transmits the detection data carrying the validity tag to the second processor 120 by wireless communication; the second processor 120 transmits the detection data carrying the validity tag to the index processing device 130 by network communication; the index processing device 130 receives the detection data carrying the validity tag, identifies the valid detection data, and determines the vascular function index of the target object based on the valid detection data.

[0041] In this embodiment, the first processor 110 is connected to the second processor 120 by wireless communication, including but not limited to WIFI communication, Bluetooth communication, Zigbee communication, 4G / 5G communication and LoRaWAN communication. The first processor 110 and the second processor 120 are connected by wireless communication, which reduces the complexity of the wiring of the indicator detection system and improves the efficiency of the detection data transmission.

[0042] The first processor 110 can be understood as a device for obtaining detection data of the blood pressure detection sensor for the target object and performing validity detection on the detection data, for example, the first processor 110 includes a collector. Among them, the detection data can be understood as data detected by the blood pressure detection sensor for the target object, for example, it can include blood pressure data and pulse data of the target object. The first processor 110 is connected to the blood pressure detection sensor, for example, the first processor 110 can be connected to the blood pressure detection sensor through an interface. The first processor 110 is configured with at least one interface. Optionally, the first processor 110 is configured with a first interface and a second interface, and the first interface and the second interface are used to connect different types of blood pressure detection sensors. For example, the blood pressure detection sensor connected to the first interface is an invasive blood pressure sensor, and the blood pressure detection sensor connected to the second interface is a non-invasive blood pressure sensor. The first interface and the second interface can be connected to the blood pressure detection sensor at the same time, and the blood pressure detection sensor can also be connected to any interface. In the process of the blood pressure detection sensor detecting the target object, due to the insufficient connection between the blood pressure detection sensor and the target object, the detection data of the target object collected by the blood pressure detection sensor is inaccurate, making the detection data of the target object invalid, and then affecting the subsequent data analysis and processing, so the detection data can be tested for validity to obtain a validity test result. For example, a validity test can be performed based on the waveform of the detection data, and the waveform of the detection data is compared with a preset waveform to obtain a validity test result, wherein the validity test result can be understood as data used to characterize whether the detection data is valid, and can be obtained by performing a validity test on the detection data. For example, the validity test result may include that the detection data is valid and that the detection data is invalid. A validity label can be set for the detection data according to the validity test result. Different marks can be set for the validity label, for example, different numbers or letters can be set to represent the validity label to distinguish whether the detection data is valid. For example, the waveform of the detection data can be compared with a reference waveform. When the waveform of the detection data is consistent with (or matches) the reference waveform, the validity test result is that the detection data is valid, and the validity label can be set to 1; when the waveform of the detection data is inconsistent with (or does not match) the reference waveform, the validity test result is that the detection data is invalid, and the validity label can be set to 0.

[0043] In some embodiments, the first processor 110 may also include a first processing module, which includes a storage space. Exemplarily, the storage space may be a cache queue; the first processing module is used to: store the detection data in the storage space; identify waveform feature data in the detection data in the storage space, and determine the detection data within the neighborhood where the waveform feature data is located; and perform validity judgment on the waveform to be detected formed by the detection data within the neighborhood based on the detection waveform to obtain a validity detection result.

[0044] Among them, the first processing module can be understood as a module that performs processing such as storage, identification and validity determination on the detection data. The storage space can be understood as a cache queue that temporarily stores the detection data of the target object acquired by the first processor 110. The waveform feature data can be understood as feature data that characterizes the waveform formed by the detection data. For example, the waveform feature data may include peak data, and the peak data is the maximum detection data in each fluctuation cycle during the fluctuation of the detection data. It can be obtained through a pattern recognition model. For example, the detection data in the storage space can be input into a pre-trained pattern recognition model for processing, and the waveform feature data in the detection data in the storage space can be obtained. The pattern recognition model includes but is not limited to a neural network model, for example, it can include a convolutional neural network model and a support vector machine model.

[0045] The waveform feature data is marked to distinguish other data in the detection data. It is understandable that the detection data all correspond to a timestamp, which can be an acquisition timestamp of the detection data, and the detection data in the storage space are sorted based on the timestamp. The detection data in the neighborhood range where the waveform feature data is located is determined by a preset time range or a data volume range. For example, the preset time range includes a first time period before the timestamp of the waveform feature data and a second time period after the timestamp of the waveform feature data. The data volume range may include a first number of detection data located before the waveform feature data and a second number of detection data located before the waveform feature data, and the first number and the second number may be the same or different. Exemplarily, the detection data in the neighborhood range where the waveform feature data is located can select 10 detection data before the waveform feature data to 20 detection data after the waveform feature data. The detection data in the neighborhood range where the above-mentioned waveform feature data is located forms a waveform to be detected, for example, the detection data in the above-mentioned range can be fitted to obtain the waveform to be detected. The neighborhood range where the waveform feature data is located can be set according to demand, and there is no limitation here.

[0046] The waveform to be detected can be understood as a waveform formed by the detection data within the neighborhood range where the waveform feature data is located. For the same waveform feature data, the waveform to be detected can be different. The detection waveform can be understood as a reference waveform within the neighborhood range where the waveform feature data is located, which can be pre-stored in the first processor 110, and is used to determine the validity of the waveform to be detected corresponding to each waveform feature data. The first processing module determines the validity of the waveform to be detected according to the detection waveform. Specifically, the validity of the waveform to be detected formed by the detection data within the neighborhood range can be determined by waveform similarity. For example, the similarity between the waveform to be detected and the detection waveform can be calculated. When the similarity is greater than or equal to the first preset similarity threshold, it indicates that the detection data corresponding to the waveform to be detected is valid. For example, the similarity between the waveform to be detected and the detection waveform is 0.85, and the first preset similarity threshold is 0.8. Since the similarity between the waveform to be detected and the detection waveform is greater than the first preset similarity threshold, it means that the detection data is valid, and the validity test result is that the detection data is valid.

[0047] In order to shorten the time of waveform feature recognition and improve the efficiency of waveform feature recognition, preset conditions can be set, and waveform feature recognition is performed when the detection data in the storage space meets the preset conditions.

[0048] Optionally, the first processing module is further used to: determine a detection threshold based on the detection data in the storage space; and perform waveform feature recognition when it is detected that the detection data in the storage space is greater than the detection threshold.

[0049] Specifically, the detection threshold can be understood as a condition for whether the detection data in the storage space is subjected to waveform feature recognition, which can be obtained by calculating at least one of the maximum value, minimum value and average value of the detection data in the storage space. For example, the average value of the detection data in the storage space can be calculated, and the detection threshold is dynamically determined based on the average value. It is understandable that the detection data in the storage space changes in real time, and the detection data that completes the validity detection is transmitted to the second processor 120. Optionally, a preset ratio value of the average value is determined as the detection threshold, for example, three quarters of the average value is determined as the detection threshold. It is understandable that the detection threshold can also be determined according to different ratios or multiples of the maximum value or the minimum value, which is not limited here. When it is detected that the detection data in the storage space is greater than the detection threshold, the detection data is subjected to waveform feature recognition, which reduces the amount of calculation and thereby improves the detection efficiency of the indicator.

[0050] The second processor 120 can be understood as being used to receive the detection data of the validity tag transmitted by the first processor 110, and the second processor 120 can include a receiver. The second processor 120 can transmit the detection data carrying the validity tag to the indicator processing device 130 in a network communication manner, and the network communication includes but is not limited to Ethernet communication. The second processor 120 transmits the detection data carrying the validity tag to the indicator processing device 130 in a network communication manner, thereby improving the transmission efficiency of the detection data carrying the validity tag.

[0051] Since the second processor 120 has data anomalies in the process of receiving the detection data carrying the validity tag transmitted by the first processor 110, for example, the detection data carrying the validity tag exceeds the preset range and is missing. In order to reduce the impact of the data anomaly on subsequent tasks, the second processor 120 can perform anomaly detection on the detection data carrying the validity tag.

[0052] Optionally, the second processor 120 is also used to perform anomaly detection on the detection data carrying the validity label to obtain anomaly detection results, set anomaly detection labels for the detection data according to the anomaly detection results, and send the detection data carrying the validity label and the anomaly detection label to the indicator processing device 130.

[0053] Specifically, the second processor 120 performs anomaly detection on the detection data carrying the validity tag, which can be implemented by the anomaly detection module in the second processor 120. For example, the detection data carrying the validity tag is input into the anomaly detection module for anomaly detection to obtain an anomaly detection result. Among them, the anomaly detection result can be understood as a result that characterizes whether the detection data has an anomaly, and the anomaly detection result can include whether the detection data has an anomaly and the anomaly type. According to the anomaly detection result, a corresponding anomaly detection tag is set for the detection data.

[0054] For example, the detection data carrying the validity label is input into the pre-trained anomaly detection module in the second processor 120 for anomaly detection. The anomaly detection module includes but is not limited to a neural network model. The anomaly detection module obtains an anomaly detection result of the detection data and sets a corresponding anomaly detection label for the detection data according to the anomaly detection result of the detection data.

[0055] For example, different detection rules are set for each anomaly detection item, and anomaly detection is performed on the detection data based on the detection rules of different detection items. For example, anomaly detection items may include but are not limited to outlier detection and missing value detection. For example, the detection rule corresponding to the outlier detection includes the numerical range of the detection data, and the detection data is compared with the numerical range. If the detection data is within the data range, it is determined that it does not belong to an outlier. If the detection data is outside the data range, it is determined that it belongs to an outlier. For example, the detection rule corresponding to the missing value detection includes a time interval threshold of adjacent detection data. If the interval time of adjacent detection data is less than or equal to the time interval threshold, it is determined that there is no data missing. If the interval time of adjacent detection data is greater than the time interval threshold, it is determined that there is data missing.

[0056] Different abnormality detection labels are set for abnormal detection data. For example, a non-abnormality label is set for detection data without abnormality, which may be 1, and a corresponding abnormality label is set for detection data with abnormality according to the abnormality type. For example, the abnormality detection label of detection data exceeding a preset range is 2, and the abnormality detection label of detection data with missing data is 3. The detection data carrying the validity label and the abnormality detection label are sent to the indicator processing device 130 for processing.

[0057] Optionally, the index processing device 130 is used to: determine non-abnormal valid detection data based on the validity label and the abnormal detection label, and determine the vascular function index of the target object based on the non-abnormal valid detection data.

[0058] Specifically, the indicator processing device 130 can be understood as a device that processes detection data carrying validity tags and anomaly detection tags, including but not limited to computers, mobile phones, and tablet computers, etc. Non-abnormal valid detection data can be understood as detection data carrying validity tags and no anomaly tags.

[0059] The vascular function index can be understood as the index data used to characterize the vascular function state of the target object. Optionally, the vascular function index includes but is not limited to one or more of the blood flow reserve fraction and the microcirculatory resistance coefficient. The index processing device 130 is configured with a plurality of calculation algorithms for vascular function indexes. For example, the index processing device 130 includes a plurality of vascular function index calculation modules, each of which is configured with a corresponding calculation algorithm for calculating the vascular function index.

[0060] Among them, the Fractional Flow Reserve (FFR) can be understood as the ratio of the maximum blood flow obtained by the myocardial area supplied by the blood vessel to the maximum blood flow that can be obtained in the same area under normal conditions in theory when there is a stenotic lesion in the coronary artery. It can be simplified as the ratio of the pressure at the distal end of the coronary artery stenosis to the pressure at the proximal end of the stenosis. The calculation formula of FFR is as follows:

[0061]

[0062] Among them, Pd represents the average pressure at the distal end of coronary artery stenosis, and Pa represents the average pressure at the proximal and distal ends of coronary artery stenosis.

[0063] The microcirculatory resistance coefficient (Index of Microcirculatory Resistance, IMR) can be understood as the resistance of microvessels to blood flow. It can be obtained by calculating the product of distal coronary artery pressure and mean blood flow time. The calculation formula of IMR is as follows:

[0064] IMR = Pd × Tmn;

[0065] in, Pd represents the mean pressure distal to the coronary artery stenosis, Tmn Represents mean blood transit time.

[0066] Optionally, the indicator processing device 130 is connected to a plurality of second processors 120 through a network, such as a wired network connection or a wireless network connection. The indicator processing device 130 respectively obtains detection data carrying validity tags transmitted by the plurality of second processors 120, and processes the detection data transmitted by the plurality of second processors 120 in parallel to obtain vascular function indicators of a plurality of target objects.

[0067] Specifically, the index processing device 130 can be connected to a plurality of second processors 120 through a network, and the plurality of second processors 120 transmit the detection data carrying the validity tag to the index processing device 130, and the index processing device 130 can process the detection data transmitted by the plurality of second processors 120 in parallel to obtain the vascular function indexes of the plurality of target objects, thereby improving the processing efficiency and speed of the index processing device 130. For example, see Figure 2 , Figure 21 is a schematic diagram of a connection between a plurality of second processors and an index processing device provided by an embodiment of the present invention. Each second processor 120 corresponds to a first processor 110, the first processor 110 and the corresponding second processor 120 are connected via wireless communication, the index processing device 130 can be connected to the plurality of second processors 120 via a network, and the index processing device 130 can process the detection data transmitted by the plurality of second processors 120 in parallel to obtain the vascular function indexes of the plurality of target objects.

[0068] Optionally, the index processing device 130 further includes a display module, which is used to display one or more items of the target object's vascular function index, test data, and a validity label of the test data.

[0069] During the process of index collection and processing, the data generated during the index detection process can be displayed to deal with abnormal situations and provide visual comparison for operators. The display module in the index processing device 130 can display the vascular function index. For example, the display module can display the numerical information of the vascular function index, the range of the vascular function index under normal conditions, and the comparison result of the vascular function index with the vascular function index under normal conditions. Exemplarily, the display module can display FFR, the range of FFR under normal conditions, and the comparison result of FFR with FFR under normal conditions. For example, FFR can be marked in the form of arrows. When FFR is lower than the range of FFR under normal conditions, FFR is marked with a downward arrow. When FFR is within the range of FFR under normal conditions, FFR is marked with a horizontal line segment. The display module can display IMR, the range of IMR under normal conditions, and the comparison result of IMR with IMR under normal conditions. For example, IMR can be marked in the form of arrows. When IMR is higher than the range of IMR under normal conditions, IMR is marked with an upward arrow. When IMR is within the range of IMR under normal conditions, IMR is marked with a horizontal line segment. The display module can also display the detection data and the validity label of the detection data. For example, the display module can display the waveform of the detection data, the corresponding numerical information and the validity label.

[0070] On the basis of the above embodiment, the display module is also used to display diastolic pressure, systolic pressure, heart rate and an analysis report formed based on one or more of the vascular function index, diastolic pressure, systolic pressure and heart rate, etc. The analysis includes but is not limited to color code diagrams, suggestions and conclusions, etc. Among them, diastolic pressure, systolic pressure and heart rate can be determined based on the waveform data formed by the detection data. The color code diagram can be understood as a vascular marking image drawn by the vascular function index. In the color code diagram, different colors are set for different sub-segments of the target blood pressure segment (the vascular segment detected in this embodiment) based on the vascular function index to distinguish the functional status of the target vascular segment. It can be understood that the vascular function index includes the vascular function index of multiple vascular points in the target vascular segment (for example, it can be obtained by uniform sampling). The above-mentioned color code diagram is formed by the vascular function index of multiple vascular points, which can intuitively display the vascular function status of the target vascular segment.

[0071] On the basis of determining the vascular function indexes of multiple vascular points of the target vascular segment, the abnormal vascular points among the vascular function indexes of the multiple vascular points are identified. Accordingly, the analysis report may include the vascular function indexes of the abnormal vascular points, for example, the abnormal vascular points may include vascular points with abnormal stenosis. Optionally, based on the index threshold corresponding to the abnormal type, the vascular function indexes of the multiple vascular points are determined to determine the abnormal vascular points. Different abnormal types can be determined for different vascular function indexes, and different abnormal types may correspond to different index thresholds.

[0072] According to the vascular function index of the abnormal vascular point and the abnormal type of the abnormal vascular point, the suggestions and conclusions are determined. Optionally, each abnormal type may correspond to at least one index threshold, and accordingly, each abnormal type may correspond to at least one abnormal level. For example, the suggestions and conclusions corresponding to the abnormal type are pre-set, or the suggestions and conclusions corresponding to each abnormal level in the abnormal type are set. According to one or more of the abnormal type and abnormal level corresponding to the abnormal vascular point, the corresponding conclusions and suggestions are matched to form an analysis report.

[0073] For example, see Figure 3 , Figure 31 is a schematic diagram of the structure of an indicator detection system provided by an embodiment of the present invention. 1 represents the first interface of the first processor 110, 2 represents the second interface of the first processor 110, 3 represents the first processor 110, 4 represents the second processor 120, 5 represents the indicator processing device 130, 6 represents the wireless communication connection between the first processor 110 and the second processor 120, and 7 represents the network connection between the second processor 120 and the indicator processing device 130. The first processor 110 includes a sensor interface module 31, a signal conditioning module 32, an ADC conversion module 33, a data processing module 34 (the first processing module in the above embodiment) and a wireless transmission module 35. Among them, the sensor interface module 31 includes a first interface and a second interface, the first interface is used to connect an invasive blood pressure sensor, and the second interface is used to connect a non-invasive blood pressure sensor; the signal conditioning module 32 can condition and amplify the detection data to facilitate the subsequent analysis and processing of the detection data; the ADC conversion module 33 can convert the detection data into a discrete digital signal; the first processing module 34 includes a storage space, the first processing module 34 can store the detection data in the storage space, identify the waveform feature data in the detection data in the storage space, determine the detection data within the neighborhood of the waveform feature data, and perform validity judgment on the waveform to be detected formed by the detection data within the neighborhood based on the detection waveform to obtain the validity detection result; the wireless transmission module 35 can transmit the detection data carrying the validity tag to the second processor 120 by wireless transmission. The second processor 120 includes a wireless transmission module 41, a data processing module 42 and a network communication module 43. The wireless transmission module 41 is used to receive the detection data with validity tags transmitted by the first processor 110; the data processing module 42 can perform abnormality detection on the detection data with validity tags to obtain abnormality detection results, and set abnormality detection tags for the detection data according to the abnormality detection results; the network communication module 43 can transmit the detection data with validity tags and abnormality detection tags to the indicator processing device 130 through Ethernet communication. The indicator processing device 130 includes a display module 51, an FFR calculation module 52, an IMR calculation module 53 and a network communication module 54. The network communication module 54 is used to receive the detection data with validity tags and abnormality detection tags; the IMR calculation module 53 is used to calculate the IMR in the vascular function index; the FFR calculation module 52 is used to calculate the FFR in the vascular function index; the display module 51 is used to display the IMR, FFR, detection data and the validity tags of the detection data.

[0074] The technical solution of this embodiment is to set up a first processor, a second processor and an indicator processing device; the first processor is wirelessly connected to the second processor, and the second processor is network-connected to the indicator processing device, thereby solving the problem of complex wired connection wiring and reducing the complexity of the connection of the indicator detection system; the first processor is connected to the blood pressure detection sensor to obtain the detection data of the blood pressure detection sensor for the target object, and performs validity detection on the detection data to obtain the validity detection result, and sets a validity tag for the detection data based on the validity detection result, and transmits the detection data carrying the validity tag to the second processor by wireless communication, thereby providing accurate data support for subsequent analysis and processing; the second processor transmits the detection data carrying the validity tag to the indicator processing device by network communication; the indicator processing device receives the detection data carrying the validity tag, identifies the valid detection data, and determines the vascular function index of the target object based on the valid detection data, thereby improving the accuracy of the vascular function index of the target object, solving the problem of complex and high-risk invasive measurement wiring, and realizing the measurement and validity detection of the vascular function index of the target object.

[0075] Embodiment 2

[0076] Figure 4 1 is a schematic diagram of the structure of an indicator detection system provided by the second embodiment of the present invention. This embodiment is an optimization of the above embodiment. This embodiment is applicable to the situation of non-invasive measurement and effectiveness detection of the vascular function indicators of the target object. Figure 4 As shown, the index detection system includes: a first processor 210, a second processor 220 and an index processing device 230; the first processor 210 is wirelessly connected to the second processor 220, and the second processor 220 is network-connected to the index processing device 230; the first processor 210 is configured with a second interface 211, and the second interface 211 is connected to the non-invasive blood pressure sensor to obtain the pulse wave data of the non-invasive blood pressure sensor for the target object, and perform validity detection on the pulse wave data to obtain the validity detection result, set the validity tag of the pulse wave data based on the validity detection result, and transmit the pulse wave data carrying the validity tag to the second processor 220 in a wireless communication manner; the second processor 220 transmits the pulse wave data carrying the validity tag to the index processing device 230 in a network communication manner; the index processing device 230 receives the pulse wave data carrying the validity tag, identifies the valid detection data, and determines the vascular function index of the target object based on the valid detection data.

[0077] In this embodiment, the first processor 210 and the second processor 220 can be located in the same physical space. The first processor 210 and the second processor 220 are connected via wireless communication, which reduces the complexity of the wiring of the index detection system and improves the efficiency of the detection data transmission. The second interface 211 can be understood as an interface for connecting a non-invasive blood pressure sensor, and the pulse wave data can be understood as data characterizing the pulse pulsation of the target object, which can be converted from data collected by the non-invasive blood pressure sensor. The non-invasive blood pressure sensor includes but is not limited to a non-invasive photoplethysmogram (PPG) sensor and other physiological parameter acquisition sensors. By connecting the non-invasive blood pressure sensor via the second interface 211, the first processor 210 can obtain the pulse wave data of the non-invasive blood pressure sensor for the target object.

[0078] Optionally, the first processor 210 can be used to: obtain first original data of the non-invasive blood pressure sensor for the target object, and convert the first original data into pulse wave data; perform validity judgment on the pulse wave waveform formed by the pulse wave data in the neighborhood corresponding to the pulse wave data and the pulse wave detection waveform to obtain a validity detection result.

[0079] Specifically, the first raw data can be understood as data of the target object collected by the non-invasive blood pressure sensor, for example, it can include arterial absorbance. The pulse wave waveform can be understood as a waveform formed by fitting multiple pulse wave data. Multiple continuous pulse wave data can be fitted to obtain a pulse wave waveform. For example, 10 continuous pulse wave data can be fitted to obtain a pulse wave waveform. It can be obtained through a pulse wave waveform fitting model. For example, the pulse wave data in the neighborhood corresponding to the pulse wave data can be input into a pre-trained pulse wave waveform fitting model for processing to obtain a pulse wave waveform. The pulse wave waveform fitting model includes but is not limited to a neural network model. The pulse wave detection waveform can be understood as a reference waveform corresponding to the neighborhood range where the waveform feature data is located. It can be pre-stored in the first processor 210. When the first processor 210 detects the pulse wave waveform, the pulse wave waveform formed by the pulse wave data in the neighborhood range is judged to be effective according to the pulse wave detection waveform. The pulse wave waveform can be judged to be effective by waveform similarity judgment. For example, the waveform similarity between the pulse wave waveform and the pulse wave detection waveform can be calculated, and when the similarity is greater than or equal to the second preset similarity threshold, it indicates that the pulse wave data is valid. For example, the waveform similarity between the pulse wave waveform and the pulse wave detection waveform is 0.7, and the second preset similarity threshold is 0.5. Since the waveform similarity between the pulse wave waveform and the pulse wave detection waveform is greater than the second preset similarity threshold, it indicates that the pulse wave data is valid, and the validity detection result is that the pulse wave data is valid.

[0080] Exemplarily, the first processor 110 obtains the first raw data of the non-invasive blood pressure sensor for the target object by filtering the detection data. The first raw data is the arterial absorbance of the target object. The absorbance when the artery is filled is A1, and the absorbance when the artery is contracted is A2. When the incident light intensity is I0, the light intensity when the artery is filled collected by the non-invasive blood pressure sensor is I min , the light intensity collected by the non-invasive blood pressure sensor during arterial contraction is I max , then the difference between the absorbance when the artery is filled and the absorbance when the artery is contracted is:

[0081]

[0082] The ratio of light absorption in the two wavelengths is:

[0083]

[0084] in, λ1 The wavelength is the wavelength of light absorbed when the artery is filled. λ2 The wavelength is the wavelength of light absorbed when the artery contracts. By transforming it, we can get:

[0085]

[0086] right Using the Maclaurin expansion, we can get:

[0087]

[0088] The above formula can be approximated as The light absorption ratio Q at the two wavelengths is used as pulse wave data.

[0089] In some embodiments, the pulse wave data of the target object collected by the non-invasive blood pressure sensor is weak, and the first processor 210 can condition and amplify the pulse wave data of the target object. For example, the first processor 210 is configured with a conditioning module and an operational amplifier module, and the pulse wave data of the target object can be sequentially input into the conditioning module and the operational amplifier module to condition and amplify the pulse wave data of the target object, so as to facilitate subsequent analysis and processing. The pulse wave data of the target object collected by the non-invasive blood pressure sensor is a continuous analog signal. The first processor 210 can convert the pulse wave data of the target object into a discrete digital signal, for example, the analog signal can be converted into a digital signal through an analog-to-digital converter. There is interference in the process of collecting the pulse wave data of the target object, for example, electromyographic signals can interfere with the pulse wave data of the target object, so that the collected pulse wave data of the target object is inaccurate, so the pulse wave data of the target object processed by the analog-to-digital converter can be filtered by the first processor 210, for example, a digital filter can be selected for filtering. The system function expression of the digital filter is:

[0090]

[0091] Where z represents the complex variable of the digital filter, b k represents the coefficient of the forward channel, a k represents the coefficient of the feedback channel, M and N represent the number of forward channels and feedback channels respectively.

[0092] In the process of the non-invasive blood pressure sensor detecting the target object, due to the insufficient connection between the non-invasive blood pressure sensor and the target object, or the inaccurate wearing method of the non-invasive blood pressure sensor, the pulse wave data of the target object collected by the non-invasive blood pressure sensor is invalid data, which in turn affects the subsequent data analysis and processing. Therefore, the pulse wave data can be tested for validity to obtain a validity test result. For example, the validity test can be performed based on the waveform of the pulse wave data, and the waveform of the pulse wave data is compared with the preset waveform to obtain the validity test result, wherein the validity test result can be understood as data used to characterize whether the pulse wave data is valid, for example, the validity test result can include the pulse wave data being valid and the pulse wave data being invalid. The preset waveform here can be understood as the pulse wave reference waveform.

[0093] A validity label can be set for the pulse wave data according to the validity test result. The validity label can be set with different marks, for example, different numbers or letters can be set to represent the validity label to distinguish whether the pulse wave data is valid. For example, the waveform of the pulse wave data can be compared with the reference waveform. When the waveform of the pulse wave data is consistent with or matches the reference waveform, the validity test result is that the pulse wave data is valid, and the validity label can be set to Y; when the waveform of the pulse wave data is inconsistent with or does not match the reference waveform, the validity test result is that the pulse wave data is invalid, and the validity label can be set to N.

[0094] Optionally, the first processor 210 may also include a first processing module, which includes a storage space; the first processing module is used to: store the pulse wave data in the storage space; identify the waveform feature data in the pulse wave data in the storage space, and determine the pulse wave data within the neighborhood where the waveform feature data is located; based on the detection waveform, perform validity judgment on the waveform to be detected formed by the pulse wave data within the neighborhood, and obtain a validity detection result.

[0095] Specifically, the pulse wave data acquired by the first processor 210 is stored in the storage space, and the waveform feature data in the pulse wave data in the storage space is identified to determine the pulse wave data within the neighborhood of the waveform feature data, and the validity of the detected waveform is determined based on the detected waveform.

[0096] The waveform feature data is marked to distinguish other data in the pulse wave data. It is understandable that the pulse wave data all correspond to a timestamp, which can be the acquisition timestamp of the pulse wave data, and the pulse wave data in the storage space is sorted based on the timestamp. The pulse wave data in the neighborhood range where the waveform feature data is located is determined by a preset time range or a data volume range. For example, the preset time range includes a third time period before the timestamp of the waveform feature data and a fourth time period after the timestamp of the waveform feature data. The data volume range may include a third number of pulse wave data located before the waveform feature data and a fourth number of pulse wave data located before the waveform feature data. Exemplarily, the pulse wave data in the neighborhood range where the waveform feature data is located can select 10 pulse wave data before the waveform feature data to 20 pulse wave data after the waveform feature data. The pulse wave data in the neighborhood range where the above-mentioned waveform feature data is located forms a waveform to be detected. For example, the pulse wave data in the above-mentioned range can be fitted to obtain the waveform to be detected. The neighborhood range where the waveform feature data is located can be set according to demand, and there is no limitation here.

[0097] In order to shorten the time of waveform feature recognition and improve the efficiency of waveform feature recognition, preset conditions can be set, and waveform feature recognition is performed when the pulse wave data in the storage space meets the preset conditions.

[0098] Optionally, the first processing module is further used to: determine a detection threshold based on the pulse wave data in the storage space; and perform waveform feature recognition when it is detected that the pulse wave data in the storage space is greater than the detection threshold.

[0099] Specifically, the detection threshold can be obtained by calculating at least one of the maximum value, minimum value and average value of the pulse wave data in the storage space. For example, the average value of the pulse wave data in the storage space can be calculated, and the detection threshold is dynamically determined based on the average value. It can be understood that the pulse wave data in the storage space changes in real time, and the pulse wave data that completes the effectiveness detection is transmitted to the second processor 220. Optionally, a preset ratio value of the average value is determined as the detection threshold, for example, three quarters of the average value is determined as the detection threshold. The detection threshold can also be determined according to different ratios or multiples of the maximum value or the minimum value, which is not limited here. When it is detected that the pulse wave data in the storage space is greater than the detection threshold, the waveform feature recognition is performed on the pulse wave data, which reduces the amount of calculation and thereby improves the detection efficiency of the indicator.

[0100] A non-invasive blood pressure sensor is connected via a second interface to obtain first raw data of the non-invasive blood pressure sensor for a target object, and the first raw data is converted into pulse wave data; the validity of a pulse wave waveform formed by pulse wave data in a neighborhood corresponding to the pulse wave data and a pulse wave detection waveform are judged to obtain a validity test result, thereby realizing non-invasive collection and validity judgment of pulse wave data, providing accurate data support for subsequent determination of vascular function indicators, and thereby improving the accuracy of calculation of vascular function indicators.

[0101] Optionally, the first processor 210 is further used to: determine the heartbeat cycle of the target object based on valid pulse wave data; and transmit the heartbeat cycle to the indicator processing device 230.

[0102] Specifically, the target object's heartbeat cycle can be calculated based on the valid pulse wave data within a preset time period. For example, within one minute, the target object's valid pulse wave data includes 60 peaks and 60 troughs, and the calculated target object's heartbeat cycle is 1 second.

[0103] The second processor 220 can transmit the pulse wave data carrying the validity tag to the indicator processing device 230 in a network communication manner, and the network communication includes but is not limited to Ethernet communication. The second processor 220 transmits the pulse wave data carrying the validity tag to the indicator processing device 230 in a network communication manner, thereby improving the transmission efficiency of the pulse wave data carrying the validity tag.

[0104] Since the second processor 220 has data anomalies in the process of receiving the pulse wave data with validity tags transmitted by the first processor 210, for example, the pulse wave data with validity tags may exceed a preset range or be missing, etc. In order to reduce the impact of data anomalies on subsequent tasks, the second processor 220 may perform anomaly detection on the pulse wave data with validity tags.

[0105] Optionally, the second processor 220 is also used to: perform anomaly detection on pulse wave data carrying a validity tag to obtain anomaly detection results, set an anomaly detection tag for the pulse wave data according to the anomaly detection results, and send the pulse wave data carrying the validity tag and the anomaly detection tag to the indicator processing device 230.

[0106] Specifically, the second processor 220 performs anomaly detection on the pulse wave data carrying a validity label, which can be implemented through the anomaly detection module in the second processor 220. For example, the pulse wave data carrying the validity label is input into the anomaly detection module for anomaly detection to obtain anomaly detection results. Among them, the anomaly detection result can be understood as a result that characterizes whether the pulse wave data has an anomaly, and the anomaly detection result may include whether the pulse wave data has an anomaly, and the anomaly type. A corresponding anomaly detection label is set for the pulse wave data according to the anomaly detection result. For example, the pulse wave data carrying the validity label is input into a pre-trained anomaly detection module in the second processor 220 for anomaly detection. The anomaly detection module includes but is not limited to a neural network model. The anomaly detection module obtains an anomaly detection result of the pulse wave data, and a corresponding anomaly detection label is set for the pulse wave data according to the anomaly detection result of the pulse wave data.

[0107] Different detection rules are set for each abnormal detection item, and the pulse wave data is subjected to abnormal detection based on the detection rules of different detection items. For example, the abnormal detection items may include but are not limited to abnormal value detection and missing value detection. For example, the detection rule corresponding to the abnormal value detection includes the numerical range of the pulse wave data, and the pulse wave data is compared with the numerical range. If the pulse wave data is within the data range, it is determined that it is not an abnormal value. If the pulse wave data is outside the data range, it is determined that it is an abnormal value. For example, the detection rule corresponding to the missing value detection includes the time interval threshold of adjacent pulse wave data. If the interval time of adjacent pulse wave data is less than or equal to the time interval threshold, it is determined that there is no data missing. If the interval time of adjacent pulse wave data is greater than the time interval threshold, it is determined that there is data missing.

[0108] Different abnormality detection tags are set for abnormal pulse wave data, for example, a non-abnormality tag is set for detection data without abnormality, for example, it can be 1; the detection data with abnormality is set with a corresponding abnormality tag according to the abnormality type, for example, the abnormality detection tag of pulse wave data exceeding the preset range is 4, and the abnormality detection tag of pulse wave data with missing is 5. The pulse wave data carrying the validity tag and the abnormality detection tag are sent to the indicator processing device 230 for processing.

[0109] The index processing device 230 may receive the pulse wave data carrying the validity tag and the abnormality detection tag transmitted by the second processor 220. Optionally, the index processing device 230 is used to: determine the non-abnormal valid detection data based on the validity tag and the abnormality detection tag, and determine the vascular function index of the target object based on the non-abnormal valid detection data.

[0110] Optionally, the indicator processing device 230 is also used to: determine the initial blood pressure waveform based on the cardiac cycle, determine the target blood pressure waveform based on the initial blood pressure waveform and the pulse wave data corresponding to the cardiac cycle, determine the mean arterial pressure based on the target blood pressure waveform; determine the vascular function indicator of the target object based on the mean arterial pressure.

[0111] Specifically, the cardiac cycle includes a systolic period and a diastolic period. During the systolic period, the blood pressure rises, and during the diastolic period, the blood pressure falls. For example, in any cardiac cycle, the initial blood pressure waveform may present a process of gradually rising and then gradually falling. Vascular function indicators include one or more of the blood flow reserve fraction and the microcirculatory resistance coefficient. The initial blood pressure waveform can be understood as a blood pressure waveform determined according to the cardiac cycle. The initial blood pressure waveform can be obtained according to a blood pressure waveform conversion model. For example, the cardiac cycle can be input into a pre-trained blood pressure waveform conversion model to obtain the initial blood pressure waveform corresponding to the cardiac cycle. The blood pressure waveform conversion model includes but is not limited to a neural network model. The target blood pressure waveform can be understood as a blood pressure waveform used to determine the vascular function indicators of the target object, which can be determined based on the initial blood pressure waveform and the pulse wave data corresponding to the cardiac cycle.

[0112] Taking the blood flow reserve score as an example of the vascular function indicator, the blood flow reserve score is calculated as follows: the indicator processing device 230 stores historical coronary artery medical images of multiple target objects, matches them according to the unique identifier of the target object, and uses the matched historical coronary artery medical images as the coronary artery medical images of the target object. A three-dimensional coronary artery model of the target object is constructed according to the coronary artery medical images of the target object. The pulse wave data is divided into calibrated pulse wave data and calculated pulse wave data, the calculation cycle includes multiple heartbeat cycles, the calibrated pulse wave data includes multiple heartbeat cycle calibrated pulse wave data, the calculated pulse wave data includes multiple heartbeat cycle calculated pulse wave data, the calibration features of each heartbeat cycle calibrated pulse wave data are extracted and the average features between each calibration feature are calculated, the calculation features of each heartbeat cycle calculated pulse wave data are extracted, the calculated pressure value corresponding to the heartbeat cycle calculated pulse wave data is calculated according to the average feature and the calculated feature, and the target blood pressure waveform is obtained according to the initial blood pressure waveform and the calculated pressure value. According to Kirchhoff's law, the relationship between flow resistance, blood flow and blood pressure is obtained, and then the pressure field of the three-dimensional coronary artery model is solved. The first vascular pressure at the target vascular position is determined based on the pressure field of the three-dimensional coronary artery model. The mean arterial pressure can be determined based on the target blood pressure waveform. For example, the mean arterial pressure corresponding to the target blood pressure waveform can be obtained by integrating the target blood pressure waveform. Based on the mean arterial pressure, the vascular pressure of the three-dimensional coronary artery model is corrected for congestion using the congestion correction formula to obtain the second vascular pressure, and the ratio between the second vascular pressure and the first vascular pressure is calculated, and the ratio between the second vascular pressure and the first vascular pressure is used as the blood flow reserve fraction of the target object.

[0113] In this embodiment, when the mean arterial pressure is determined based on the target blood pressure waveform, the diastolic pressure, systolic pressure and heart rate are also determined based on the target blood pressure waveform. The maximum value in the target blood pressure waveform is the systolic pressure, the minimum value in the target blood pressure waveform is the diastolic pressure, and the average of multiple blood pressure values ​​in the target blood pressure waveform is the mean arterial pressure. The heartbeat cycle is determined based on the target blood pressure waveform, and the heart rate can be determined based on the heartbeat cycle. The heart rate, that is, the number of heart beats in 1 minute, can be determined based on the ratio of 1 minute to the duration of the heartbeat cycle.

[0114] Optionally, the index processing device 230 is used to: determine non-abnormal valid detection data based on the validity label and the abnormal detection label, and determine the vascular function index of the target object based on the non-abnormal valid detection data.

[0115] Specifically, non-abnormal valid detection data may include pulse wave data carrying validity labels and non-abnormal labels. The pulse wave data carrying validity labels and abnormal detection labels can be classified and processed by an effective detection data classification model. For example, the pulse wave data carrying validity labels and abnormal detection labels can be input into a pre-trained effective detection data classification model for classification processing to obtain non-abnormal valid detection data. The effective detection data classification model includes but is not limited to a neural network model.

[0116] Optionally, the index processing device 230 further includes a display module, which is used to display one or more of the target object's vascular function index, pulse wave data, and a validity label of the pulse wave data.

[0117] Specifically, the display module of the index processing device 230 can display the vascular function index, for example, the display module can display the numerical information of the vascular function index, the range of the vascular function index under normal conditions, and the comparison result between the vascular function index and the vascular function index under normal conditions. The display module can also display the pulse wave data and the validity label corresponding to the pulse wave data.

[0118] Optionally, the indicator processing device 230 is connected to a network of multiple second processors 220, obtains pulse wave data carrying validity tags transmitted by the multiple second processors 220, processes the pulse wave data transmitted by the multiple second processors 220 in parallel, and obtains vascular function indicators of multiple target objects.

[0119] The technical solution of this embodiment is to set up a first processor, a second processor and an indicator processing device; the first processor is wirelessly connected to the second processor, and the second processor is network-connected to the indicator processing device, thereby solving the problem of complex wired wiring and reducing the complexity of the indicator detection system connection; the first processor is configured with a second interface, the second interface is connected to the non-invasive blood pressure sensor, obtains the pulse wave data of the non-invasive blood pressure sensor for the target object, and performs validity detection on the pulse wave data to obtain the validity detection result, sets the validity tag of the pulse wave data based on the validity detection result, and transmits the pulse wave data carrying the validity tag to the second processor by wireless communication, thereby providing accurate data support for subsequent analysis and processing; the second processor transmits the pulse wave data carrying the validity tag to the indicator processing device by network communication; the indicator processing device receives the pulse wave data carrying the validity tag, identifies the valid detection data, and determines the vascular function index of the target object based on the valid detection data, thereby improving the accuracy of the vascular function index of the target object and realizing the non-invasive measurement and validity detection of the vascular function index of the target object.

[0120] Embodiment 3

[0121] Figure 5 1 is a schematic diagram of the structure of an indicator detection system provided by the third embodiment of the present invention. This embodiment is an optimization of the first embodiment. This embodiment is applicable to the case of invasive measurement and effectiveness detection of the vascular function indicators of the target object. Figure 5 As shown, the index detection system includes: a first processor 310, a second processor 320 and an index processing device 330; the first processor 310 is wirelessly connected to the second processor 320, and the second processor 320 is network-connected to the index processing device 330; the first processor 310 is configured with a first interface 311, the first interface 311 is connected to the invasive blood pressure sensor, obtains the blood pressure data of the target object from the invasive blood pressure sensor, and performs validity detection on the blood pressure data to obtain the validity detection result, sets the validity tag of the blood pressure data based on the validity detection result, and transmits the blood pressure data carrying the validity tag to the second processor 320 by wireless communication; the second processor 320 transmits the blood pressure data carrying the validity tag to the index processing device 330 by network communication; the index processing device 330 receives the blood pressure data carrying the validity tag, identifies the valid detection data, and determines the vascular function index of the target object based on the valid detection data.

[0122] In some embodiments, the first processor 310 and the second processor 320 may be located in the same physical space. For example, the first processor 310 and the second processor 320 may be located in the same acquisition room, which may be an operating room in some embodiments. In some embodiments, the first processor 310 and the second processor 320 may be located in different physical spaces, and one second processor 320 may be communicatively connected to at least one first processor 310.

[0123] The first processor 310 is connected to the second processor 320 via wireless communication, which reduces the complexity of the wiring of the index detection system and improves the efficiency of the detection data transmission. The first interface 311 can be understood as an interface for connecting an invasive blood pressure sensor. By connecting the invasive blood pressure sensor through the first interface 311, the first processor 310 can obtain the blood pressure data of the invasive blood pressure sensor for the target object.

[0124] Optionally, the first processor 310 can be used to: obtain second original data of the invasive blood pressure sensor for the target object, and convert the second original data into blood pressure data; perform validity judgment on the blood pressure waveform formed by the blood pressure data in the neighborhood corresponding to the blood pressure data and the blood pressure detection waveform to obtain a validity detection result.

[0125] Specifically, the blood pressure data may include one or more of systolic pressure, diastolic pressure and mean arterial pressure. The second raw data may be understood as the raw data collected by the invasive blood pressure sensor, for example, may include an analog signal. The second raw data may be converted into blood pressure data after processing. For example, the first processor 310 is provided with a conditioning module and an operational amplifier module, and the second raw data may be sequentially input into the conditioning module and the operational amplifier module, and the second raw data may be conditioned and amplified to facilitate subsequent analysis and processing. The conditioned and amplified second raw data is a continuous analog signal, and the first processor 310 may convert the second raw data into a discrete digital signal, for example, the analog signal may be converted into a digital signal through an analog-to-digital converter, and the converted second raw data is the blood pressure data.

[0126] In some embodiments, the blood pressure data of the target object collected by the invasive blood pressure sensor is weak, and the first processor 310 can condition and amplify the blood pressure data of the target object. For example, the first processor 310 is configured with a conditioning module and an operational amplifier module, and the blood pressure data of the target object can be input into the conditioning module and the operational amplifier module in sequence, and the blood pressure data of the target object is conditioned and amplified to facilitate subsequent analysis and processing. The blood pressure data of the target object collected by the invasive blood pressure sensor is a continuous analog signal. The first processor 310 can convert the blood pressure data of the target object into a discrete digital signal, for example, the analog signal can be converted into a digital signal through an analog-to-digital converter. There is interference in the process of collecting the blood pressure data of the target object, which makes the collected blood pressure data of the target object inaccurate, so the blood pressure data of the target object processed by the analog-to-digital converter can be filtered by the first processor 310.

[0127] In the process of detecting the target object by the invasive blood pressure sensor, due to the insufficient connection between the invasive blood pressure sensor and the target object, the blood pressure data of the target object collected by the invasive blood pressure sensor is invalid data, which in turn affects the subsequent data analysis and processing. Therefore, the blood pressure data can be tested for validity to obtain a validity test result. For example, the validity test can be performed based on the waveform of the blood pressure data, and the waveform of the blood pressure data is compared with the preset waveform to obtain a validity test result, wherein the validity test result can be understood as data used to characterize whether the blood pressure data is valid, for example, the validity test result can include valid blood pressure data and invalid blood pressure data. The preset waveform here can be understood as a blood pressure reference waveform.

[0128] A validity label can be set for the blood pressure data according to the validity test result. The validity label can be set with different marks, for example, different numbers or letters can be set to represent the validity label to distinguish whether the blood pressure data is valid. For example, the waveform of the blood pressure data can be compared with the reference waveform. When the waveform of the blood pressure data is consistent or matches the reference waveform, the validity test result is that the blood pressure data is valid, and the validity label can be set to 1; when the waveform of the blood pressure data is inconsistent or does not match the reference waveform, the validity test result is that the blood pressure data is invalid, and the validity label can be set to 0.

[0129] Optionally, the first processor 310 may also include a first processing module, which includes a storage space; the first processing module is used to: store the blood pressure data in the storage space; identify the waveform feature data in the detection data in the storage space, and determine the blood pressure data within the neighborhood range where the waveform feature data is located; and perform validity judgment on the waveform to be detected formed by the blood pressure data within the neighborhood range based on the detection waveform to obtain a validity test result.

[0130] Specifically, the blood pressure data acquired by the first processor 310 is stored in the storage space, and the blood pressure data within the neighborhood of the waveform characteristic data is determined by identifying the waveform characteristic data in the blood pressure data in the storage space, and the validity of the waveform to be detected is determined based on the detected waveform.

[0131] The waveform characteristic data is marked to distinguish other data in the blood pressure data. It is understandable that the blood pressure data all correspond to a timestamp, which can be the acquisition timestamp of the blood pressure data, and the blood pressure data in the storage space are sorted based on the timestamp. The blood pressure data within the neighborhood range where the waveform characteristic data is located is determined by a preset time range or a data volume range. For example, the preset time range includes the fifth time period before the timestamp of the waveform characteristic data and the sixth time period after the timestamp of the waveform characteristic data. The data volume range may include the fifth number of blood pressure data located before the waveform characteristic data and the sixth number of blood pressure data located before the waveform characteristic data. Exemplarily, the blood pressure data within the neighborhood range where the waveform characteristic data is located can select 10 blood pressure data before the waveform characteristic data to 20 blood pressure data after the waveform characteristic data. The detection data within the neighborhood range where the above-mentioned waveform characteristic data is located forms a waveform to be detected. For example, the blood pressure data within the above-mentioned range can be fitted to obtain the waveform to be detected. The neighborhood range where the waveform characteristic data is located can be set according to demand, and there is no limitation here.

[0132] The first processing module determines the validity of the waveform to be detected based on the detection waveform. Specifically, the validity of the waveform to be detected formed by the blood pressure data within the neighborhood range can be determined by waveform similarity. For example, the waveform similarity between the blood pressure waveform and the blood pressure detection waveform can be calculated. When the similarity is greater than or equal to the third preset similarity threshold, it indicates that the blood pressure data is valid. For example, the waveform similarity between the blood pressure waveform and the blood pressure detection waveform is 0.8, and the third preset similarity threshold is 0.75. Since the waveform similarity between the blood pressure waveform and the blood pressure detection waveform is greater than the third preset similarity threshold, it means that the blood pressure data is valid, and the validity test result is that the blood pressure data is valid.

[0133] In order to shorten the time of waveform feature recognition and improve the efficiency of waveform feature recognition, preset conditions can be set, and waveform feature recognition is performed when the blood pressure data in the storage space meets the preset conditions.

[0134] Optionally, the first processing module is further used to: determine a detection threshold based on the blood pressure data in the storage space; and perform waveform feature recognition when it is detected that the blood pressure data in the storage space is greater than the detection threshold.

[0135] Specifically, the detection threshold can be obtained by calculating at least one of the maximum value, minimum value and average value of the blood pressure data in the storage space. For example, the average value of the blood pressure data in the storage space can be calculated, and the detection threshold is dynamically determined based on the average value. It is understandable that the blood pressure data in the storage space changes in real time, and the blood pressure data that completes the effectiveness detection is transmitted to the second processor 120. Optionally, a preset ratio value of the average value is determined as the detection threshold, for example, three quarters of the average value is determined as the detection threshold. It is understandable that the detection threshold can also be determined according to different ratios or multiples of the maximum or minimum value, which is not limited here. When it is detected that the blood pressure data in the storage space is greater than the detection threshold, the waveform feature recognition is performed on the blood pressure data, which reduces the amount of calculation and thereby improves the detection efficiency of the indicator.

[0136] The second processor 320 can transmit the blood pressure data carrying the validity tag to the indicator processing device 330 via network communication, and the network communication includes but is not limited to Ethernet communication. The second processor 320 transmits the blood pressure data carrying the validity tag to the indicator processing device 330 via network communication, thereby improving the transmission efficiency of the blood pressure data carrying the validity tag.

[0137] Since the second processor 320 has data anomalies when receiving the blood pressure data with validity tags transmitted by the first processor 310, for example, the blood pressure data with validity tags may exceed a preset range or be missing, etc. In order to reduce the impact of data anomalies on subsequent tasks, the second processor 320 may perform anomaly detection on the blood pressure data with validity tags.

[0138] Optionally, the second processor 320 is also used to perform abnormality detection on the blood pressure data carrying the validity tag to obtain the abnormality detection result, set the abnormality detection tag for the blood pressure data according to the abnormality detection result, and send the blood pressure data carrying the validity tag and the abnormality detection tag to the indicator processing device 330.

[0139] Specifically, the second processor 320 performs abnormality detection on the blood pressure data carrying the validity label, which can be implemented through the abnormality detection module in the second processor 320. For example, the blood pressure data carrying the validity label is input into the abnormality detection module for abnormality detection to obtain an abnormality detection result. Among them, the abnormality detection result can be understood as a result that characterizes whether the blood pressure data has an abnormality, and the abnormality detection result may include whether the blood pressure data has an abnormality, and the type of abnormality. According to the abnormality detection result, a corresponding abnormality detection label is set for the blood pressure data. For example, the blood pressure data carrying the validity label is input into the pre-trained abnormality detection module in the second processor 320 for abnormality detection. The abnormality detection module includes but is not limited to a neural network model. The abnormality detection module obtains the abnormality detection result of the blood pressure data, and sets the corresponding abnormality detection label for the blood pressure data according to the abnormality detection result of the blood pressure data.

[0140] For example, for each abnormal detection item, different detection rules are set, and the blood pressure data is detected for abnormalities based on the detection rules of different detection items. For example, the abnormal detection items may include but are not limited to abnormal value detection and missing value detection. For example, the detection rule corresponding to the abnormal value detection includes the numerical range of the blood pressure data, and the blood pressure data is compared with the numerical range. If the blood pressure data is within the data range, it is determined that it is not an abnormal value. If the blood pressure data is outside the data range, it is determined that it is an abnormal value. For example, the detection rule corresponding to the missing value detection includes the time interval threshold of adjacent blood pressure data. If the interval time of adjacent blood pressure data is less than or equal to the time interval threshold, it is determined that there is no missing data. If the interval time of adjacent blood pressure data is greater than the time interval threshold, it is determined that there is missing data.

[0141] Different abnormality detection labels are set for abnormal blood pressure data. For example, a non-abnormality label is set for detection data without abnormality, which may be 0. The detection data with abnormality is set with a corresponding abnormality label according to the abnormality type. For example, the abnormality detection label of blood pressure data exceeding a preset range is 6, and the abnormality detection label of missing blood pressure data is 7. The blood pressure data carrying the validity label and the abnormality detection label are sent to the indicator processing device 330 for processing.

[0142] The index processing device 330 may receive the blood pressure data carrying the validity tag and the abnormality detection tag transmitted by the second processor 320. Optionally, the index processing device 330 is used to: determine the non-abnormal valid detection data based on the validity tag and the abnormality detection tag, and determine the vascular function index of the target object based on the non-abnormal valid detection data.

[0143] Specifically, non-abnormal valid detection data may include blood pressure data carrying validity labels and non-abnormal labels. The blood pressure data carrying validity labels and abnormal detection labels can be classified and processed by an effective detection data classification model. For example, the blood pressure data carrying validity labels and abnormal detection labels can be input into a pre-trained effective detection data classification model for classification processing to obtain non-abnormal valid detection data. The effective detection data classification model includes but is not limited to a neural network model.

[0144] Optionally, the index processing device 330 further includes a display module, which is used to display one or more of the target object's vascular function index, blood pressure data, and a validity label of the blood pressure data.

[0145] Specifically, the display module of the index processing device 330 can display the vascular function index, for example, the display module can display the numerical information of the vascular function index, the range of the vascular function index under normal conditions, and the comparison result between the vascular function index and the vascular function index under normal conditions. The display module can also display blood pressure data and the validity label corresponding to the blood pressure data.

[0146] Optionally, the indicator processing device 330 is connected to a network of multiple second processors 320, obtains blood pressure data carrying validity tags transmitted by the multiple second processors 320, processes the blood pressure data transmitted by the multiple second processors 320 in parallel, and obtains vascular function indicators of multiple target objects.

[0147] The technical solution of this embodiment is to set up a first processor, a second processor and an indicator processing device; the first processor is wirelessly connected to the second processor, and the second processor is network-connected to the indicator processing device, thereby solving the problem of complex wired wiring and reducing the complexity of the indicator detection system connection; the first processor is configured with a first interface, the first interface is connected to the invasive blood pressure sensor, obtains the blood pressure data of the target object from the invasive blood pressure sensor, and performs validity detection on the blood pressure data to obtain the validity detection result, sets a validity tag for the blood pressure data based on the validity detection result, and transmits the blood pressure data carrying the validity tag to the second processor by wireless communication, thereby providing accurate data support for subsequent analysis and processing; the second processor transmits the blood pressure data carrying the validity tag to the indicator processing device by network communication; the indicator processing device receives the blood pressure data carrying the validity tag, identifies the valid detection data, determines the vascular function index of the target object based on the valid detection data, thereby improving the accuracy of the vascular function index of the target object and realizing the measurement and validity detection of the vascular function index of the target object.

[0148] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0149] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. An index detection system, characterized in that: include: A first processor, a second processor and an indicator processing device; the first processor is wirelessly connected to the second processor, and the second processor is network-connected to the indicator processing device; The first processor is connected to the blood pressure detection sensor, obtains detection data of the blood pressure detection sensor for the target object, performs validity detection on the detection data to obtain a validity detection result, sets a validity tag of the detection data based on the validity detection result, and transmits the detection data carrying the validity tag to the second processor in a wireless communication manner; The second processor transmits the detection data carrying the validity tag to the indicator processing device in a network communication manner; The index processing device receives the detection data carrying the validity tag, identifies the valid detection data, and determines the vascular function index of the target object based on the valid detection data.

2. The index detection system according to claim 1, characterized in that: The first processor includes a first processing module, and the first processing module includes a storage space; The first processing module is used for: storing the detection data in the storage space; identifying waveform feature data in the detection data in the storage space, and determining detection data within a neighborhood of the waveform feature data; The validity of the waveform to be detected formed by the detection data within the neighborhood range is determined based on the detection waveform to obtain the validity detection result.

3. The index detection system according to claim 2, characterized in that: The first processing module is also used for: determining a detection threshold based on the detection data in the storage space; When it is detected that the detection data in the storage space is greater than the detection threshold, waveform feature recognition is performed.

4. The index detection system according to any one of claims 1 to 3, characterized in that: The first processor is configured with a first interface and / or a second interface; The blood pressure detection sensor connected to the first interface is an invasive blood pressure sensor; The blood pressure detection sensor connected to the second interface is a non-invasive blood pressure sensor.

5. The index detection system according to claim 4, characterized in that: The detection data corresponding to the non-invasive blood pressure sensor is pulse wave data; The first processor is specifically used to: obtain the first original data of the non-invasive blood pressure sensor for the target object, convert the first original data into the pulse wave data; perform validity judgment on the pulse wave waveform formed by the pulse wave data in the neighborhood corresponding to the pulse wave data and the pulse wave detection waveform to obtain a validity detection result; And / or, the detection data corresponding to the invasive blood pressure sensor is blood pressure data; The first processor is specifically used to: obtain the second original data of the invasive blood pressure sensor for the target object, and convert the second original data into the blood pressure data; perform validity judgment on the blood pressure waveform formed by the blood pressure data in the neighborhood corresponding to the blood pressure data and the blood pressure detection waveform to obtain a validity detection result.

6. The index detection system according to claim 5, characterized in that: The first processor is further used to: determine the heartbeat cycle of the target object based on valid pulse wave data; and transmit the heartbeat cycle to the indicator processing device; The index processing device is also used to: determine an initial blood pressure waveform based on the heart cycle, determine a target blood pressure waveform based on the initial blood pressure waveform and pulse wave data corresponding to the heart cycle, determine a mean arterial pressure based on the target blood pressure waveform; and determine a vascular function index of the target object based on the mean arterial pressure.

7. The index detection system according to claim 1, characterized in that: The second processor is further used to perform anomaly detection on the detection data carrying the validity tag to obtain anomaly detection results, set an anomaly detection tag for the detection data according to the anomaly detection results, and send the detection data carrying the validity tag and the anomaly detection tag to the indicator processing device; The index processing device determines non-abnormal valid detection data based on the validity tag and the abnormal detection tag, and determines the vascular function index of the target object based on the non-abnormal valid detection data.

8. The index detection system according to claim 1, characterized in that: The vascular function index includes one or more of the blood flow reserve fraction and the microcirculatory resistance coefficient.

9. The index detection system according to claim 1, characterized in that: The index processing device further includes a display module, which is used to display one or more of the vascular function index of the target object, the test data, and a validity label of the test data.

10. The index detection system according to claim 1, characterized in that: The indicator processing device is connected to a plurality of second processor networks, and respectively obtains the detection data carrying the validity tags transmitted by the plurality of second processors, and processes the detection data transmitted by the plurality of second processors in parallel to obtain vascular function indicators of the plurality of target objects.

Images