A blood sedimentation measurement system, a blood sedimentation measurement apparatus, and a blood sedimentation measurement method

Abstract

The application discloses a blood sedimentation measuring system, a blood sedimentation measuring device and a blood sedimentation measuring method. The blood sedimentation measuring system comprises a sampling distribution device, a blood sedimentation detection device, a blood cell detection device and a data processing device. The sampling distribution device is configured to collect a blood sample to be measured, and at least partially distribute the blood sample to be measured to the blood sedimentation detection device and the blood cell detection device respectively. The blood sedimentation detection device is configured to obtain a parameter related to red blood cell aggregation of the blood sample to be measured through a red blood cell aggregation curve. The blood cell detection device is configured to obtain blood cell data of the blood sample to be measured, at least including red blood cell data. The data processing device is configured to acquire the parameter related to red blood cell aggregation and the blood cell data, and input the parameter related to red blood cell aggregation and the blood cell data into a neural network model to calculate a first blood sedimentation measurement result. The application can obtain a blood sedimentation measurement result with better consistency with a blood sedimentation measurement result measured by a Westergren method.

Description

Technical Field

[0001] This invention relates to the field of medical device technology, and in particular to an erythrocyte sedimentation rate (ESR) measurement system, ESR measurement device, and ESR measurement method. Background Technology

[0002] Within the body's bloodstream, red blood cells remain dispersed and suspended due to blood flow and the repulsion of negative charges on their surfaces. However, when blood is left to stand outside the body, red blood cells settle due to gravity. In pathological conditions, changes in the types and amounts of proteins in the plasma alter the blood's charge balance, reducing the negative charge on the surface of red blood cells and causing them to form rouleaux, thus accelerating sedimentation. Therefore, the rate of red blood cell sedimentation over one hour, known as the erythrocyte sedimentation rate (ESR), can be used to aid in disease assessment.

[0003] The commonly used method for measuring erythrocyte sedimentation rate (ESR) is the Widmanstätten method. According to this method, the sedimentation rate of erythrocytes in a sedimentation tube is observed and recorded; that is, timing begins after blood sample injection, and the distance the interface between aggregated cells and plasma moves downward relative to the top of the blood sample (the height of the suspension medium) is observed after one hour. However, with the increase in hospital patients, the one-hour measurement efficiency cannot meet daily testing needs. Therefore, a rapid method for measuring ESR is required.

[0004] To quickly measure erythrocyte sedimentation rate (ESR), among the relevant technologies known to the inventor, there is a rapid measurement method based on erythrocyte aggregation, referred to as the erythrocyte aggregation method. However, the correlation between the ESR measured by the erythrocyte aggregation method and the ESR measured by the Widmanstätten method is poor.

[0005] It should be noted that the statements in this background section only provide background information related to the present invention and do not necessarily constitute prior art. Summary of the Invention

[0006] This invention provides an erythrocyte sedimentation rate (ESR) measurement system, ESR measurement device, and ESR measurement method, which can quickly and accurately obtain corrected ESR test results, and these ESR test results have good consistency with the ESR test results obtained by the Widmanstätten method.

[0007] The first aspect of this invention provides an erythrocyte sedimentation rate (ESR) measurement system, comprising a sampling and dispensing device, an ESR detection device, a blood cell detection device, and a data processing device.

[0008] The sampling and dispensing device is configured to collect a blood sample to be tested and to distribute at least a portion of the blood sample to be tested to the erythrocyte sedimentation rate (ESR) detection device and the blood cell detection device, respectively.

[0009] The erythrocyte sedimentation rate (ESR) detection device is configured to detect a portion of the allocated blood sample to obtain a red blood cell aggregation curve showing the change in light intensity over time of transmitted light or scattered light scattering from the allocated blood sample portion.

[0010] The blood cell detection device is configured to detect a portion of a distributed blood sample to obtain blood cell data of the blood sample to be tested, the blood cell data including at least red blood cell data;

[0011] The data processing device is configured to extract parameters related to erythrocyte aggregation and the blood cell data from the erythrocyte aggregation curve, and input the parameters related to erythrocyte aggregation and the blood cell data into a neural network model to calculate the first erythrocyte sedimentation rate (ESR) measurement result.

[0012] In some embodiments, the parameters associated with erythrocyte aggregation include at least two feature parameters extracted from the erythrocyte aggregation curve.

[0013] In some embodiments, the erythrocyte sedimentation rate (ESR) detection device is further configured to deagglomerate the red blood cells in the allocated blood sample portion by causing the allocated blood sample portion to flow back and forth in the detection area of ​​the ESR detection device before detecting the allocated blood sample portion.

[0014] In some embodiments, the parameters related to erythrocyte aggregation are selected from the group consisting of:

[0015] The area enclosed by the red blood cell aggregation curve and the time axis during the time period from the start time of the measurement to the end time of the measurement;

[0016] The second erythrocyte sedimentation rate (ESR) measurement result is calculated based on the area and the preset calibration curve;

[0017] The minimum transmitted light intensity during the time period between the start and end of the measurement;

[0018] The difference between the transmitted light intensity at the start time point and the transmitted light intensity at the end time point; and

[0019] The time point corresponding to half of the transmitted light intensity at the end of the measurement.

[0020] In some embodiments, the data processing device is further configured to output at least one of the first erythrocyte sedimentation rate (ESR) measurement result and the second ESR measurement result.

[0021] In some embodiments, the blood cell data may also include one or more of platelet data, white blood cell data, and hemoglobin data.

[0022] In some embodiments, the blood cell detection device includes an impedance detection unit, which includes a detection orifice and a detection circuit configured to detect impedance changes in cells in a portion of a blood sample allocated to the impedance detection unit as they pass through the detection orifice.

[0023] The blood cell data includes red blood cell data, platelet data, and / or white blood cell data obtained based on the impedance change signal.

[0024] In some embodiments, the red blood cell data obtained based on the impedance change signal includes one or more of the following: red blood cell pulse signal, red blood cell count, hematocrit value, mean erythrocyte volume, red blood cell volume coefficient of variation, red blood cell distribution width standard deviation, red blood cell volume histogram, and red blood cell scatter plot; and / or

[0025] Platelet data obtained from impedance change signals include platelet counts obtained from impedance change signals; and / or

[0026] White blood cell data obtained from impedance change signals include white blood cell counts obtained from said impedance change signals.

[0027] In some embodiments, the blood cell detection device includes an optical detection unit having a light source, a flow chamber, and a photodetector. The light source is configured to emit a light beam to illuminate a detection area of ​​the flow chamber, and the photodetector is configured to detect optical signals generated by cells in a portion of a blood sample allocated to the optical detection unit after being illuminated by light as they pass through the detection area.

[0028] The blood cell data includes red blood cell data and / or platelet data and / or white blood cell data obtained based on the optical signal.

[0029] In some embodiments, the red blood cell data obtained from the optical signal includes red blood cell pulse signals and / or red blood cell scatter plots; and / or

[0030] Platelet data obtained from optical signals include platelet counts obtained from optical signals; and / or

[0031] White blood cell data obtained from optical signals include white blood cell counts obtained from optical signals.

[0032] In some embodiments, the blood cell detection device includes a hemoglobin detection unit configured to detect the hemoglobin concentration in a portion of a blood sample allocated to the hemoglobin detection unit;

[0033] The blood cell data include hemoglobin concentration and / or mean hemoglobin content and / or mean hemoglobin concentration obtained based on hemoglobin concentration.

[0034] A second aspect of the present invention provides an erythrocyte sedimentation rate (ESR) measuring device, comprising an ESR detection device and a data processing device;

[0035] The erythrocyte sedimentation rate (ESR) detection device is configured to detect the blood sample to be tested, so as to obtain the red blood cell aggregation curve of the intensity of transmitted light or scattered light that is transmitted through the distributed blood sample portion over time.

[0036] The data processing device is configured to: extract parameters related to erythrocyte aggregation from the erythrocyte aggregation curve, obtain blood cell data of the blood sample to be tested detected by a blood cell analyzer, wherein the blood cell data includes at least erythrocyte data, and input the parameters related to erythrocyte aggregation and the blood cell data into a neural network model to calculate the erythrocyte sedimentation rate (ESR) measurement result.

[0037] In some embodiments, the erythrocyte sedimentation rate (ESR) detection device is further configured to deaggregate the red blood cells in the blood sample to be tested by allowing the blood sample to be tested to flow back and forth in the detection area of ​​the ESR detection device before detecting the red blood cell aggregation curve, and to detect the red blood cell aggregation curve as a function of time the intensity of transmitted light transmitted through the deaggregated blood sample to be tested or the scattered light scattered by the blood sample to be tested.

[0038] In some embodiments, the parameters associated with erythrocyte aggregation include at least two feature parameters extracted from the erythrocyte aggregation curve.

[0039] A third aspect of the present invention provides a method for measuring erythrocyte sedimentation rate (ESR), comprising the following steps:

[0040] Obtain the erythrocyte aggregation curve of the blood sample to be tested, and obtain the parameters related to erythrocyte aggregation of the blood sample to be tested from the erythrocyte aggregation curve, wherein the erythrocyte aggregation curve is the curve of the change of light intensity of transmitted light or scattered light scattered by the blood sample to be tested over time.

[0041] Obtain blood cell data from the blood sample to be tested, wherein the blood cell data includes at least red blood cell data; and

[0042] The parameters related to erythrocyte aggregation and the blood cell data are input into a neural network model to calculate the first erythrocyte sedimentation rate (ESR) measurement result.

[0043] In some embodiments, the parameters associated with erythrocyte aggregation include at least two feature parameters extracted from the erythrocyte aggregation curve.

[0044] In some embodiments, the parameters related to erythrocyte aggregation are selected from the group consisting of:

[0045] The area enclosed by the red blood cell aggregation curve and the time axis during the time period from the start time of the measurement to the end time of the measurement;

[0046] The second erythrocyte sedimentation rate (ESR) measurement result is calculated based on the area and the preset calibration curve;

[0047] The minimum transmitted light intensity during the time period between the start and end of the measurement;

[0048] The difference between the transmitted light intensity at the start time point and the transmitted light intensity at the end time point; and

[0049] The time point corresponding to half of the transmitted light intensity at the end of the measurement.

[0050] In some embodiments, the method further includes outputting at least one of the first erythrocyte sedimentation rate (ESR) measurement result and the second ESR measurement result.

[0051] In some embodiments, the blood cell data may also include one or more of platelet data, white blood cell data, and hemoglobin data.

[0052] In some embodiments, the blood cell data includes red blood cell data and / or platelet data and / or white blood cell data obtained by flow cytometry and / or the Coulter method.

[0053] In some embodiments, the red blood cell data includes one or more of the following: red blood cell pulse signal, red blood cell count, hematocrit, mean corpuscular volume, coefficient of variation of red blood cell volume, standard deviation of red blood cell distribution width, red blood cell volume distribution histogram, and red blood cell scatter plot, measured by the Coulter method; and / or, the platelet data includes platelet count measured by the Coulter method; and / or, the white blood cell data includes white blood cell count measured by flow cytometry or the Coulter method; and / or the hemoglobin data includes hemoglobin concentration and / or mean corpuscular hemoglobin content and / or mean corpuscular hemoglobin concentration obtained based on the hemoglobin concentration.

[0054] In some embodiments, the red blood cell data includes red blood cell pulse signals and / or red blood cell scatter plots measured by flow cytometry.

[0055] A fourth aspect of the present invention provides a method for measuring erythrocyte sedimentation rate (ESR), comprising the following steps:

[0056] A portion of the blood sample to be tested is transported to the optical detection tube, and the portion of the blood sample to be tested is circulated back and forth in the optical detection tube in order to deaggregate the red blood cells in the portion of the blood sample to be tested.

[0057] After the deagglomeration process, the portion of the blood sample to be tested is placed still in the optical detection tube and illuminated with light to obtain the red blood cell aggregation curve of the intensity of transmitted light through the portion of the blood sample to be tested changing over time.

[0058] The analyzed data is input into a deep learning algorithm with a neural network structure. The analyzed data includes parameters related to erythrocyte aggregation obtained from the erythrocyte aggregation curve and includes blood cell data of the blood sample to be tested, measured by flow cytometry and / or the Coulter method, wherein the blood cell data includes at least erythrocyte data; and

[0059] The erythrocyte sedimentation rate (ESR) of the blood sample to be tested is calculated using the deep learning algorithm.

[0060] Based on the aspects provided by this invention, a corrected erythrocyte sedimentation rate (ESR) measurement result is obtained by using parameters related to erythrocyte aggregation and blood cell data as input parameters to a neural network model. Compared with existing erythrocyte aggregation methods, it can obtain ESR measurement results with better consistency with those obtained by the Widmanstätten method. Attached Figure Description

[0061] Other features and advantages of the invention will become clear from the following detailed description of exemplary embodiments of the invention with reference to the accompanying drawings.

[0062] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0063] Figure 1 This is a schematic block diagram of an erythrocyte sedimentation rate (ESR) measurement system according to some embodiments of the present invention.

[0064] Figure 2 This is a schematic flowchart illustrating the erythrocyte sedimentation rate (ESR) measurement method according to some embodiments of the present invention.

[0065] Figure 3 This is a schematic diagram of the erythrocyte sedimentation rate (ESR) measurement system according to some embodiments of the present invention.

[0066] Figure 4 The images show erythrocyte aggregation curves of blood samples to be tested, as shown in some embodiments of the present invention.

[0067] Figure 5The calibration curves used in some embodiments of the present invention to obtain the erythrocyte sedimentation rate (ESR) measurement results before correction are shown.

[0068] Figure 6 This demonstrates the correlation between the uncorrected erythrocyte sedimentation rate (ESR) measurement results obtained by the present invention and the ESR measurement results obtained by the prior art reference erythrocyte aggregation method.

[0069] Figure 7 This shows the impedance change signal of red blood cells in a blood sample obtained by impedance method as they pass through a detection orifice.

[0070] Figure 8 This is a histogram of red blood cell volume distribution in a blood sample obtained by impedance method.

[0071] Figure 9 This is a scatter plot of red blood cells in a blood sample obtained by impedance method.

[0072] Figure 10 This shows the optical changes in red blood cells of a blood sample obtained by optical methods as they pass through the detection area and are illuminated by light.

[0073] Figure 11 This is a scatter plot of red blood cells in a blood sample obtained using optical methods.

[0074] Figure 12 This is a schematic diagram of the structure of a neural network model according to some embodiments of the present invention.

[0075] Figure 13 The correlation between the erythrocyte sedimentation rate (ESR) measurement results modified according to the present invention and the Widmanstätten method ESR measurement results is shown.

[0076] Figure 14 This is a schematic block diagram of an erythrocyte sedimentation rate (ESR) measuring device according to some embodiments of the present invention.

[0077] Figure 15 This is a schematic flowchart illustrating the erythrocyte sedimentation rate (ESR) measurement method according to other embodiments of the present invention. Detailed Implementation

[0078] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0079] Currently, ESR values ​​from blood samples are increasingly used in clinical practice to aid in disease diagnosis. The inventors of this invention have noted that there is poor consistency between ESR values ​​obtained using the erythrocyte aggregation method and those obtained using a reference method, namely the Widmanstätten method. In other words, ESR values ​​obtained using the erythrocyte aggregation method do not accurately reflect the natural sedimentation rate of erythrocytes.

[0080] Based on this, in order to quickly obtain ESR values ​​that can more accurately reflect the natural sedimentation rate of erythrocytes, a technical solution is proposed to obtain the corrected erythrocyte sedimentation rate measurement results based on parameters related to erythrocyte aggregation and blood cell data using a neural network model.

[0081] refer to Figure 1 This invention provides an erythrocyte sedimentation rate (ESR) measurement system. The ESR measurement system includes a sampling and dispensing device 10, an ESR detection device 20, a blood cell detection device 30, and a data processing device 40.

[0082] The sampling and dispensing device 10 is configured to collect the blood sample to be tested and to distribute at least a portion of the blood sample to the erythrocyte sedimentation rate (ESR) detection device 20 and the blood cell detection device 30, respectively.

[0083] The erythrocyte sedimentation rate (ESR) detection device 20 is configured to detect a portion of the allocated blood sample to obtain a red blood cell aggregation curve showing the change in light intensity over time of transmitted light or scattered light scattering from the allocated blood sample portion.

[0084] The blood cell detection device 30 is configured to detect a portion of a distributed blood sample to obtain blood cell data of the blood sample to be tested, the blood cell data including at least red blood cell data.

[0085] The data processing device 40 is configured to extract parameters and blood cell data related to erythrocyte aggregation from the erythrocyte aggregation curve, and input the parameters and blood cell data related to erythrocyte aggregation into a neural network model to calculate the first erythrocyte sedimentation rate (ESR1).

[0086] Accordingly, refer to Figure 2 This invention also provides a method for measuring erythrocyte sedimentation rate (ESR), comprising the following steps:

[0087] S501, Obtain the red blood cell aggregation curve of the blood sample to be tested, and extract the parameters related to red blood cell aggregation of the blood sample to be tested from the red blood cell aggregation curve. The red blood cell aggregation curve is the curve of the change in light intensity of transmitted light or scattered light scattered by the blood sample to be tested over time.

[0088] S502, acquire blood cell data of the blood sample to be tested, wherein the blood cell data includes at least red blood cell data; and

[0089] S503 inputs parameters related to erythrocyte aggregation and blood cell data into a neural network model to calculate the first erythrocyte sedimentation rate (ESR1).

[0090] The erythrocyte sedimentation rate (ESR) measurement method provided in this embodiment of the invention is implemented, in particular, by the ESR measurement system provided in this embodiment of the invention.

[0091] In this invention, a first erythrocyte sedimentation rate (ESR) measurement result is obtained by using parameters related to erythrocyte aggregation and blood cell data, including at least erythrocyte data, as input parameters to a neural network model. Compared with existing rapid erythrocyte aggregation methods, this method yields ESR measurement results that are in better agreement with those obtained using the Widmanstätten method.

[0092] In some embodiments, the parameters associated with erythrocyte aggregation include at least two feature parameters extracted from the erythrocyte aggregation curve.

[0093] In some embodiments, reference Figure 3 The sampling dispensing device 10 may include a sampling needle 11 and a driving device (not shown in the figure). The driving device is used to drive the sampling needle 11 to move so that the sampling needle 11 collects the blood sample to be tested and distributes at least a portion of the blood sample to be tested to the erythrocyte sedimentation rate (ESR) detection device 20 and at least a portion of the blood sample to be tested to the blood cell detection device 30.

[0094] The erythrocyte sedimentation rate (ESR) detection device 20 may include an ESR detection line 21 and an ESR optical detection component 22. The ESR detection line 21 provides a detection site for the dispensed portion of the blood sample to be tested. The ESR optical detection component 22 irradiates the portion of the blood sample dispensed into the ESR detection line 21 with light and detects the degree of light absorption or scattering by the portion of the blood sample dispensed into the ESR detection line 21 to obtain parameters related to erythrocyte aggregation of the blood sample. During the detection by the ESR optical detection component 22, the portion of the blood sample dispensed into the ESR detection line 21 does not shift, i.e., it remains stationary.

[0095] refer to Figure 3In some embodiments, the first end 211 of the erythrocyte sedimentation rate (ESR) detection line 21 is connected to the end 112 of the sampling needle 11 furthest from the needle tip 111. The second end 212 of the ESR detection line 21 is connected to the power assembly 24. The power assembly 24 is used to drive the blood sample to be tested to flow in the ESR detection line 21 and to stop the blood sample after it flows into the detection area within the ESR detection line 21 and remains stationary so that the ESR optical detection assembly 22 can detect the blood sample. That is, the power assembly 24 is not only used to drive the blood sample to be tested into the ESR detection line 21, but also to ensure that the blood sample in the ESR detection line 21 remains stationary during ESR detection.

[0096] In a specific example, the operation of the erythrocyte sedimentation rate (ESR) detection device 20 provided in this embodiment of the invention is as follows: The power component 24 drives a portion of the blood sample to be tested to flow into the ESR detection pipeline 21. When this portion of the blood sample reaches the detection area of ​​the ESR detection pipeline 21, the power component 24 suddenly stops and momentarily interrupts the flow of the portion of the blood sample in the ESR detection pipeline 21, causing the portion of the blood sample to suddenly decelerate (or stop flowing), subsequently leading to the aggregation and precipitation of red blood cells. During the aggregation and precipitation of red blood cells, a change in the signal detected by the ESR optical detection component 21 will occur. Here, the optical detection component specifically performs ESR detection on the blood sample using a turbidimetric method.

[0097] In some embodiments, please refer to Figure 3 The erythrocyte sedimentation rate (ESR) detection device includes a light emitter 221 and a light receiver 222. The light emitter 221 and the light receiver 222 are located on opposite sides of the detection area of ​​the ESR detection conduit 21. The light emitter 221 is used to illuminate the blood sample to be tested within the detection area. The light receiver 222 is used to measure the change in light intensity over time after the light emitted by the light emitter 221 passes through the blood sample to be tested, for example, to obtain a red blood cell aggregation curve.

[0098] In other embodiments, the light receiver 222 can also be used to measure the change in light intensity over time of light scattered by the blood sample to be tested, for example, to obtain a red blood cell aggregation curve.

[0099] In some embodiments, the erythrocyte sedimentation rate (ESR) detection device 20 is further configured to deaggregate the red blood cells in the allocated blood sample portion by allowing the allocated blood sample portion to flow back and forth within the detection area of ​​the ESR detection device before detection. This ensures that the red blood cells in the blood sample within the detection area are as dispersed as possible before the ESR optical detection component detects the degree of red blood cell aggregation, thereby enabling more accurate measurement of the degree of red blood cell aggregation. The red blood cell aggregation curve is a curve showing the change in light intensity transmitted through the deaggregated blood sample over time.

[0100] Therefore, in Figure 3 In the illustrated embodiment, a power unit 24 can be used to drive the blood sample in the erythrocyte sedimentation rate (ESR) detection tubing 21 to flow back and forth. Especially when the power unit 24 is constructed as a syringe, the speed and direction of the syringe's movement can be flexibly set, allowing for flexible deagglomeration of the blood sample and saving blood volume.

[0101] After the power component 24 drives the blood sample in the erythrocyte sedimentation rate (ESR) detection tube 21 to flow back and forth a predetermined number of times, the power component 24 immediately stops driving, causing the blood sample in the ESR detection tube 21 to stop flowing. The red blood cells in the blood sample in the ESR detection tube 21 aggregate, causing a change in light transmittance.

[0102] In some embodiments, the erythrocyte sedimentation rate (ESR) detection device 20 may be configured to acquire a red blood cell aggregation curve showing the change in light intensity of transmitted light through a portion of the dispensed blood sample over time.

[0103] Figure 4 The diagram shows erythrocyte aggregation curves of blood samples from some embodiments of the present invention. Figure 4 In this context, t1 refers to the start time of the measurement, t2 refers to the end time of the measurement, and the erythrocyte aggregation curve is the curve showing the change in transmitted light intensity (i.e., transmittance) over time from the start time t1 to the end time t2. Parameters related to erythrocyte aggregation can be obtained from this erythrocyte aggregation curve; that is, parameters related to erythrocyte aggregation can include curve features extracted from the erythrocyte aggregation curve.

[0104] In some specific embodiments, reference is made to Figure 4 Transmittance (also known as transmittance) is the relative light intensity, which is equal to the ratio of transmitted light intensity to background light intensity. Parameters related to erythrocyte aggregation are selected from a group including the following parameters:

[0105] The area under the time axis (AUC) between the erythrocyte aggregation curve and the time axis during the time interval from the measurement start time t1 to the measurement end time t2.

[0106] The second erythrocyte sedimentation rate (ESR2) is calculated based on the area AUC and a preset calibration curve (which is stored, for example, in the data processing device 40).

[0107] The minimum transmitted light intensity during the time period from the start time point t1 to the end time point t2 of the measurement;

[0108] The difference between the transmitted light intensity at the start time point t1 and the transmitted light intensity at the end time point t2; and

[0109] The time point t3 corresponds to half of the transmitted light intensity at the end of the measurement at time point t2. In other words, the transmitted light intensity at time point t3 is half of the transmitted light intensity at the end of the measurement at time point t2.

[0110] Parameters related to erythrocyte aggregation can be selected from the above parameters, all of which are obtained through [method / process]. Figure 4 The parameters are obtained from the erythrocyte aggregation curve shown, therefore, the above parameters can also be referred to as the curve characteristics of the erythrocyte aggregation curve.

[0111] The second erythrocyte sedimentation rate (ESR2) was calculated based on the area AUC and a pre-set calibration curve. The calibration curve is shown below. Figure 5 As shown, in Figure 5 In the figure, the horizontal axis represents the area AUC, and the vertical axis represents the second erythrocyte sedimentation rate (ESR2). Therefore, as long as the erythrocyte aggregation curve of the blood sample to be tested is obtained, and the area AUC enclosed by the erythrocyte aggregation curve and the time axis during the time period from the measurement start time point t1 to the measurement end time point t2 is obtained through the erythrocyte aggregation curve, the second erythrocyte sedimentation rate (ESR2) can be obtained through this calibration curve.

[0112] Research has shown a correlation between the area under the red blood cell aggregation curve (AUC) and the Widmanstätten ESR (ESR) of blood samples. Therefore, the calibration curve can be statistically fitted using the AUC of the red blood cell aggregation curves from a large number of blood samples and the Widmanstätten ESR. For each sample, the red blood cell aggregation curve is obtained using the aggregation method, and the area under the curve (AUC) is calculated. The Widmanstätten ESR measurement result is then obtained using the Widmanstätten method. Finally, the data from multiple samples are fitted together to obtain the calibration curve.

[0113] In some embodiments, the calibration curve is stored in the data processing device 40 as a series of discrete points, and therefore the second erythrocyte sedimentation rate (ESR2) is obtained on the calibration curve based on the ACU by means of table lookup and interpolation.

[0114] Of course, in other embodiments, a function can also be fitted using the large amount of sample data described above, and the second erythrocyte sedimentation rate (ESR2) can be calculated using the function. The ordinate value of each discrete point on the calibration curve is the Widmanstätten erythrocyte sedimentation rate measurement result. That is to say, the calibration curve is obtained by combining the aggregation method and the Widmanstätten method. Therefore, the second erythrocyte sedimentation rate measurement result obtained by the calibration curve will be closer to the Widmanstätten erythrocyte sedimentation rate measurement result than the erythrocyte sedimentation rate measurement result obtained by using only the aggregation method in the prior art.

[0115] The second erythrocyte sedimentation rate (ESR) measurement results obtained using the embodiments of the present invention show a good correlation with the reference values ​​obtained by the erythrocyte aggregation method detected by ALIFAX instruments in the prior art, such as... Figure 6As shown. Figure 6 As shown, the correlation between the second erythrocyte sedimentation rate (ESR) measurement results and the reference aggregation method measurement results exceeded 0.9, indicating that the second ESR measurement results and the reference aggregation method measurement results have good consistency.

[0116] Refer again Figure 3 The blood cell detection device 30 may include a blood cell reaction chamber 31 and a blood cell detection component (not shown in the figure). The blood cell reaction chamber 31 provides a place for mixing reagents with the dispensed portion of the blood sample to be tested, and the blood cell detection component is used to perform blood cell detection on the portion of the blood sample to be tested in the blood cell reaction chamber 31 to obtain blood cell data of the blood sample to be tested.

[0117] Those skilled in the art will understand that the blood cell detection component of the blood cell detection device 30 may include at least one of an optical detection unit, an impedance detection unit, and a hemoglobin detection unit. Correspondingly, the reaction cell may include at least one of an optical detection reaction cell, an impedance detection reaction cell, and a hemoglobin detection reaction cell. When the blood cell detection device 30 performs a routine blood test on a blood sample, the blood sample and corresponding reagents (e.g., diluent and / or hemolysin and / or staining agent, etc.) can be added to the reaction cell 31. The blood cell detection component measures the blood sample in the reaction cell 31 to obtain at least one blood cell data. The blood cell data may include one or more of red blood cell data, platelet data, white blood cell data, and hemoglobin data. Specifically, it may be at least one or more combinations of WBC (White blood cell) classification parameters, WBC count and morphological parameters, HGB (Hemoglobin) parameters, RBC (Red blood cell) and PLT (blood platelet) count and morphological parameters.

[0118] In some embodiments, the blood cell data used in this invention include red blood cell data and / or platelet data and / or white blood cell data obtained by flow cytometry and / or the Coulter method (also known as impedance cytometry).

[0119] In one specific embodiment, the impedance detection unit of the blood cell detection device 30, based on the Coulter method, includes a detection orifice and a detection circuit. The detection circuit is configured to detect impedance changes (or pulse signals) in cells within a blood sample portion allocated to the impedance detection unit as they pass through the detection orifice. Figure 7 As shown. The blood cell data used in this invention may include red blood cell data, platelet data, or white blood cell data obtained based on impedance change signals.

[0120] Furthermore, the red blood cell data used in this invention may include one or more of the following: red blood cell count, hematocrit, mean corpuscular volume, coefficient of variation of red blood cell volume, and standard deviation of red blood cell distribution width, measured by the Coulter method (i.e., obtained from impedance change signals). And / or, the platelet data used in this invention may be platelet counts measured by the Coulter method (i.e., obtained from impedance change signals). And / or, the white blood cell data used in this invention may be white blood cell counts measured by the Coulter method (i.e., obtained from impedance change signals).

[0121] In other embodiments, the red blood cell data used in this invention may also include a red blood cell volume distribution histogram obtained based on impedance change signals, such as... Figure 8 As shown.

[0122] Alternatively or additionally, the red blood cell data used in this invention may also include a scatter plot of red blood cells obtained based on impedance change signals. The data used to generate this scatter plot includes the red blood cell volume signal, i.e., the impedance change signal, and other signals related to the passage of red blood cells through the detection orifice, such as the time it takes for the red blood cells to pass through the orifice or the time it takes for the red blood cells to reach the center of the orifice. Figure 9 As shown in the scatter plot of red blood cells, the horizontal axis represents the time it takes for a red blood cell to pass through the detection orifice, and the vertical axis represents the impedance signal.

[0123] In other embodiments, the red blood cell data used in this invention may also include the impedance change signal itself measured by the impedance detection unit.

[0124] In another specific embodiment, the optical detection unit of the blood cell detection device 30 operates based on the principle of flow cytometry. The optical detection unit has a light source, a flow chamber, and a photodetector. The light source is configured to emit a light beam to illuminate the detection area of ​​the flow chamber, and the photodetector is configured to detect the optical signal (or pulse signal) generated when cells in a portion of the blood sample allocated to the optical detection unit are illuminated as they pass through the detection area. Figure 10 As shown. The blood cell data used in this invention may include red blood cell data obtained based on optical signals. Here, the sample to be tested is not hemolyzed when the optical detection unit detects red blood cells. For example, the blood cell data used in this invention may include a red blood cell scatter plot obtained based on the optical signals detected by the optical detection unit. Preferably, the red blood cell scatter plot obtained by flow cytometry includes at least the forward scattered light signal (FSC) of red blood cells, while other signals forming the red blood cell scatter plot may be the lateral scattered light signal (SSC) and / or the lateral fluorescence signal (SFL) of red blood cells. Figure 11 As shown in the scatter plot of erythrocytes, the horizontal axis represents the lateral fluorescence signal (SFL) of erythrocytes, and the vertical axis represents the forward scattered light signal (FSC) of erythrocytes.

[0125] Of course, in other embodiments, the blood cell data used in this invention may also include optical signals measured by the optical detection unit, especially the forward-scattered light signal itself.

[0126] In other embodiments, the blood cell data used in this invention may also include platelet data and / or white blood cell data obtained from optical signals.

[0127] Specifically, platelet data obtained from optical signals includes platelet counts obtained from optical signals. White blood cell data obtained from optical signals includes white blood cell counts obtained from optical signals.

[0128] In some embodiments, the blood cell data used in this invention includes hemoglobin concentration detected by a hemoglobin detection unit and / or average hemoglobin content and / or average hemoglobin concentration obtained based on the hemoglobin concentration. The hemoglobin detection unit is used to detect the hemoglobin concentration in a portion of the blood sample allocated to the hemoglobin detection unit.

[0129] In some embodiments, the neural network model used for blood cell data includes, for example, a back propagation (BP) neural network model or a convolutional neural network model. Preferably, the neural network model is pre-trained and stored in the data processing device 40. For example, the neural network model is pre-trained using test data from a large number of clinical samples.

[0130] In some embodiments, one of the parameters related to erythrocyte aggregation is the second erythrocyte sedimentation rate (ESR) measurement result, while the other parameter related to erythrocyte aggregation is selected from other parameters related to erythrocyte aggregation, such as the curve characteristic values ​​mentioned above. In other words, the second ESR measurement result is the object of correction, and the other parameter related to erythrocyte aggregation is the parameter used to correct the second ESR measurement result. Here, the second ESR measurement result is corrected using both the parameter related to erythrocyte aggregation and blood cell data, resulting in the corrected first ESR measurement result.

[0131] Furthermore, the second erythrocyte sedimentation rate (ESR) measurement result, blood cell data, and one or more erythrocyte aggregation curve features can be input into a pre-trained neural network model to output the first ESR measurement result. For example, the second ESR measurement result, the erythrocyte volume distribution histogram obtained by impedance analysis, and one or more erythrocyte aggregation curve features can be input into a pre-trained neural network model to output the first ESR measurement result. As another example, the second ESR measurement result, the erythrocyte scatter plot obtained by impedance analysis, and one or more erythrocyte aggregation curve features can be input into a pre-trained neural network model to output the first ESR measurement result. Yet another example, the second ESR measurement result, the erythrocyte scatter plot obtained by optical analysis, and one or more erythrocyte aggregation curve features can be input into a pre-trained neural network model to output the first ESR measurement result. And yet another example, the second ESR measurement result, the impedance change signal of erythrocytes passing through the detection orifice, and one or more erythrocyte aggregation curve features can be input into a pre-trained neural network model to output the first ESR measurement result. In addition, the second erythrocyte sedimentation rate (ESR) measurement result, the optical signal generated by red blood cells after being illuminated when passing through the detection area, and one or more red blood cell aggregation curve features can be input into a pre-trained neural network model to output the first ESR measurement result.

[0132] Figure 12 A trained neural network model is shown, which has three input parameters: the second erythrocyte sedimentation rate (ESR2), the hematocrit (HCT), and the time point t3 corresponding to half the transmitted light intensity at the measurement end time t2. The model then performs calculations over K nodes to obtain the first ESR measurement result, ensuring that the first ESR result, ESR1, is consistent with the ESR result obtained using the Widmanstätten method. Specifically, the neural network model here is a backpropagation (BP) neural network model.

[0133] The results of the second erythrocyte sedimentation rate (ESR2), hematocrit (HCT), time point t3 corresponding to half the transmitted light intensity at the end of the measurement (t2), and the Widmanstätten method measurement were collected from a large number of blood samples and then analyzed according to... Figure 11 The neural network model shown is trained to obtain its parameters. Next, the erythrocyte sedimentation rate (ESR) measurement system according to the present invention is used, and the Widmanstätten method is employed to detect the blood sample to be tested, obtaining the corresponding first ESR measurement result (ESR1) and the Widmanstätten measurement result. Based on the first ESR measurement result and the Widmanstätten measurement result of the blood sample to be tested, the following is obtained: Figure 13 The correlation is shown. (As shown in the image) Figure 13 As shown, the correlation between the first erythrocyte sedimentation rate (ESR1) measurement result and the Widmanstätten method measurement result exceeded 0.9268, indicating that the first ESR measurement result and the Widmanstätten method measurement result have good consistency.

[0134] In some embodiments, the data processing device 40 may also be configured to output at least one of a first erythrocyte sedimentation rate (ESR) measurement result and a second ESR measurement result. Specifically, either the first ESR measurement result or the second ESR measurement result may be selected and reported to the user, or both may be reported to the user for reference.

[0135] In some embodiments, the data processing device 40 may include a processor and a memory. The processor may be a CPU, GPU, or other chip with computing capabilities. The memory stores various computer programs, such as computational models, for the processor to execute, as well as the data required to execute the computer programs. The computational models used in this invention are, for example, stored in the memory.

[0136] like Figure 14 As shown, this embodiment of the invention also provides an erythrocyte sedimentation rate (ESR) measuring device, including an ESR detection device 20 and a data processing device 40.

[0137] The erythrocyte sedimentation rate (ESR) detection device 20 is configured to detect the blood sample to be tested, in order to obtain the red blood cell aggregation curve showing the change in light intensity over time of transmitted light transmitted through or scattered light scattered by the distributed portion of the blood sample.

[0138] The data processing device 40 is configured to: extract parameters related to erythrocyte aggregation from the erythrocyte aggregation curve, acquire blood cell data of the blood sample to be tested by a blood cell analyzer, wherein the blood cell data includes at least erythrocyte data, and input the parameters related to erythrocyte aggregation and the blood cell data into a neural network model to calculate the erythrocyte sedimentation rate (ESR) measurement result.

[0139] Here, the blood cell analyzer is located outside the erythrocyte sedimentation rate (ESR) measuring device and is communicatively connected to the data processing unit 40 so that the data processing unit can acquire the blood cell data detected by the blood cell analyzer.

[0140] In some embodiments, the erythrocyte sedimentation rate (ESR) detection device is further configured to deaggregate the red blood cells in the blood sample to be tested by allowing the blood sample to be tested to flow back and forth in the detection area of ​​the ESR detection device before detecting the red blood cell aggregation curve, and to detect the red blood cell aggregation curve as a function of time the intensity of transmitted light transmitted through the deaggregated blood sample or the scattered light scattered by the blood sample to be tested.

[0141] Other features and advantages of the erythrocyte sedimentation rate (ESR) measuring device provided in the embodiments of the present invention can be found in the above description of the ESR measuring system and ESR measuring method provided in the embodiments of the present invention.

[0142] refer to Figure 15 This invention provides a method for measuring erythrocyte sedimentation rate (ESR), comprising the following steps:

[0143] S601, a portion of the blood sample to be tested is transported to the optical detection tube, and the portion of the blood sample to be tested is allowed to flow back and forth in the optical detection tube in order to deaggregate the red blood cells in the portion of the blood sample to be tested.

[0144] S602, after deagglomeration treatment, a portion of the blood sample to be tested is placed still in the optical detection tube and illuminated with light to obtain the red blood cell aggregation curve of the intensity of transmitted light through a portion of the blood sample to be tested changing over time.

[0145] S603, the parsed data is input into a deep learning algorithm with a neural network structure. The parsed data includes parameters related to erythrocyte aggregation obtained from erythrocyte aggregation curves and includes blood cell data of the blood sample to be tested, measured by flow cytometry and / or the Coulter method, wherein the blood cell data includes at least erythrocyte data; and

[0146] S604 calculates the erythrocyte sedimentation rate (ESR) test results of the blood sample to be tested using a deep learning algorithm.

[0147] For example, the sampling needle of the erythrocyte sedimentation rate (ESR) measurement system draws up the blood sample to be tested, mixes it thoroughly to allow the red blood cells in the blood sample to fully deaggregate, and measures the change curve of the light intensity transmitted through the deaggregated blood sample over time, which is the red blood cell aggregation curve.

[0148] In the erythrocyte sedimentation rate (ESR) measurement method of this invention, the red blood cells in the blood sample to be tested are first deagglomerated, and then an ESR aggregation curve is obtained after the deagglomeration process. Based on this ESR aggregation curve, parameters related to ESR aggregation are obtained. These parameters, along with blood cell data, are used as input parameters for a deep learning algorithm to calculate the ESR detection result of the blood sample. This allows for the rapid acquisition of ESR measurement results that are more consistent with those obtained using the Widmanstätten method.

[0149] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them; although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications can still be made to the specific implementation of the present invention or equivalent substitutions can be made to some technical features without departing from the spirit of the technical solutions of the present invention, and all such modifications and substitutions should be covered within the scope of the technical solutions claimed in the present invention.

Claims

1. A system for measuring erythrocyte sedimentation rate (ESR), characterized in that, It includes a sampling and dispensing device, an erythrocyte sedimentation rate (ESR) detection device, a blood cell detection device, and a data processing device. The sampling and dispensing device is configured to collect a blood sample to be tested and to distribute at least a portion of the blood sample to be tested to the erythrocyte sedimentation rate (ESR) detection device and the blood cell detection device, respectively. The erythrocyte sedimentation rate (ESR) detection device is configured to detect a portion of the allocated blood sample to obtain a red blood cell aggregation curve showing the change in light intensity over time of transmitted light or scattered light scattering from the allocated blood sample portion. The blood cell detection device is configured to detect a portion of a distributed blood sample to obtain blood cell data of the blood sample to be tested, the blood cell data including at least red blood cell data; The data processing device is configured to extract parameters related to erythrocyte aggregation from the erythrocyte aggregation curve and acquire the blood cell data, input the parameters related to erythrocyte aggregation and the blood cell data into a neural network model to calculate a first erythrocyte sedimentation rate (ESR) measurement result. The parameters related to erythrocyte aggregation include at least two feature parameters extracted from the erythrocyte aggregation curve, and the at least two feature parameters include a second ESR measurement result. The second ESR measurement result is calculated based on the area enclosed by the erythrocyte aggregation curve and the time axis during the time period from the measurement start time point to the measurement end time point and a preset calibration curve. The blood cell data includes hematocrit and mean erythrocyte volume. The calibration curve is configured to fit the area enclosed by the erythrocyte aggregation curve and the time axis of multiple blood samples and the erythrocyte sedimentation rate data obtained by Widmanstätten method.

2. The erythrocyte sedimentation rate (ESR) measurement system according to claim 1, characterized in that, The erythrocyte sedimentation rate (ESR) detection device is further configured to deagglomerate the red blood cells in the allocated blood sample portion by causing the allocated blood sample portion to flow back and forth in the detection area of ​​the ESR detection device before detecting the allocated blood sample portion. The red blood cell aggregation curve is the curve showing the change in light intensity transmitted through the deaggregated blood sample over time.

3. The erythrocyte sedimentation rate (ESR) measurement system according to claim 1 or 2, characterized in that, The parameters related to erythrocyte aggregation are selected from the group consisting of: The area enclosed by the red blood cell aggregation curve and the time axis during the time period from the start time of the measurement to the end time of the measurement; The minimum transmitted light intensity during the time period between the start and end of the measurement; The difference between the transmitted light intensity at the start time point and the transmitted light intensity at the end time point of the measurement; as well as The time point corresponding to half of the transmitted light intensity at the end of the measurement.

4. The erythrocyte sedimentation rate (ESR) measurement system according to any one of claims 1 to 3, characterized in that, The data processing device is further configured to output at least one of the first erythrocyte sedimentation rate (ESR) measurement result and the second ESR measurement result.

5. The erythrocyte sedimentation rate (ESR) measurement system according to any one of claims 1 to 4, characterized in that, The blood cell data also includes one or more of platelet data, white blood cell data, and hemoglobin data.

6. The erythrocyte sedimentation rate (ESR) measurement system according to any one of claims 1 to 5, characterized in that, The blood cell detection device includes an impedance detection unit, which includes a detection orifice and a detection circuit. The detection circuit is configured to detect the impedance change signal of cells in a portion of the blood sample allocated to the impedance detection unit as they pass through the detection orifice. The blood cell data includes red blood cell data, platelet data, and / or white blood cell data obtained based on the impedance change signal.

7. The erythrocyte sedimentation rate (ESR) measurement system according to claim 6, characterized in that, The red blood cell data obtained based on the impedance change signal includes one or more of the following: red blood cell pulse signal, red blood cell count, hematocrit value, mean erythrocyte volume, coefficient of variation of red blood cell volume, standard deviation of red blood cell distribution width, red blood cell volume histogram, and red blood cell scatter plot; and / or Platelet data obtained from the impedance change signal includes platelet counts obtained from the impedance change signal; and / or White blood cell data obtained from impedance change signals include white blood cell counts obtained from said impedance change signals.

8. The erythrocyte sedimentation rate (ESR) measurement system according to any one of claims 1 to 7, characterized in that, The blood cell detection device includes an optical detection unit, which has a light source, a flow chamber, and a photodetector. The light source is configured to emit a light beam to illuminate the detection area of ​​the flow chamber, and the photodetector is configured to detect the optical signal generated by cells in a blood sample portion allocated to the optical detection unit after being illuminated by light as they pass through the detection area. The blood cell data includes red blood cell data and / or platelet data and / or white blood cell data obtained based on the optical signal.

9. The erythrocyte sedimentation rate (ESR) measurement system according to claim 8, characterized in that, The red blood cell data obtained from the optical signals include red blood cell pulse signals and / or red blood cell scatter plots; and / or Platelet data obtained based on the optical signal includes platelet counts obtained based on the optical signal; and / or The white blood cell data obtained from the optical signal includes the white blood cell count obtained from the optical signal.

10. The erythrocyte sedimentation rate (ESR) measurement system according to any one of claims 1 to 9, characterized in that, The blood cell detection device includes a hemoglobin detection unit, which is configured to detect the hemoglobin concentration in a portion of a blood sample allocated to the hemoglobin detection unit. The blood cell data includes the hemoglobin concentration and / or the average hemoglobin content and / or average hemoglobin concentration obtained based on the hemoglobin concentration.

11. An erythrocyte sedimentation rate (ESR) measuring device, comprising an ESR detection device and a data processing device; The erythrocyte sedimentation rate (ESR) detection device is configured to detect the blood sample to be tested, so as to obtain the red blood cell aggregation curve of the intensity of transmitted light or scattered light that is transmitted through the distributed blood sample portion over time. The data processing device is configured to: extract parameters related to erythrocyte aggregation from the erythrocyte aggregation curve, acquire blood cell data of the blood sample to be tested detected by a blood cell analyzer, the blood cell data including at least erythrocyte data, and input the parameters related to erythrocyte aggregation and the blood cell data into a neural network model to calculate the erythrocyte sedimentation rate (ESR) measurement result. The parameters related to erythrocyte aggregation include at least two feature parameters extracted from the erythrocyte aggregation curve, the at least two feature parameters including a second ESR measurement result. The second ESR measurement result is calculated based on the area enclosed by the erythrocyte aggregation curve and the time axis during the time period from the measurement start time point to the measurement end time point and a preset calibration curve. The blood cell data includes hematocrit and mean erythrocyte volume. The calibration curve is configured to fit the area enclosed by the erythrocyte aggregation curve and the time axis of multiple blood samples and the erythrocyte sedimentation rate data obtained by Widmanstätten method.

12. The erythrocyte sedimentation rate (ESR) measuring device according to claim 11, characterized in that, The erythrocyte sedimentation rate (ESR) detection device is further configured to deaggregate the red blood cells in the blood sample to be tested by allowing the blood sample to be tested to flow back and forth in the detection area of ​​the ESR detection device before detecting the red blood cell aggregation curve, and to detect the red blood cell aggregation curve as a function of time the intensity of transmitted light transmitted through the deaggregated blood sample to be tested or the scattered light scattered by the blood sample to be tested.

13. A method for measuring erythrocyte sedimentation rate (ESR), characterized in that, Includes the following steps: Obtain the red blood cell aggregation curve of the blood sample to be tested, and extract the parameters related to red blood cell aggregation of the blood sample to be tested from the red blood cell aggregation curve, wherein the red blood cell aggregation curve is the curve of the change of light intensity of transmitted light or scattered light scattered by the blood sample to be tested over time. Obtain blood cell data from the blood sample to be tested, wherein the blood cell data includes at least red blood cell data; and The parameters related to erythrocyte aggregation and the blood cell data are input into a neural network model to calculate a first erythrocyte sedimentation rate (ESR) measurement result. The parameters related to erythrocyte aggregation include at least two feature parameters extracted from the erythrocyte aggregation curve. The at least two feature parameters include a second ESR measurement result. The second ESR measurement result is calculated based on the area enclosed by the erythrocyte aggregation curve and the time axis during the time period from the measurement start time point to the measurement end time point and a preset calibration curve. The blood cell data includes hematocrit and mean erythrocyte volume. The calibration curve is configured to fit the area enclosed by the erythrocyte aggregation curve and the time axis of multiple blood samples and the erythrocyte sedimentation rate data obtained by Widmanstätten method.

14. The erythrocyte sedimentation rate (ESR) measurement method according to claim 13, characterized in that, The parameters related to erythrocyte aggregation are selected from the group consisting of: The area enclosed by the red blood cell aggregation curve and the time axis during the time period from the start time of the measurement to the end time of the measurement; The minimum transmitted light intensity during the time period between the start and end of the measurement; The difference between the transmitted light intensity at the start time point and the transmitted light intensity at the end time point of the measurement; as well as The time point corresponding to half of the transmitted light intensity at the end of the measurement.

15. The erythrocyte sedimentation rate (ESR) measurement method according to claim 14, characterized in that, It also includes outputting at least one of the first erythrocyte sedimentation rate (ESR) measurement result and the second ESR measurement result.

16. The method for measuring erythrocyte sedimentation rate according to any one of claims 13 to 15, characterized in that, The blood cell data also includes one or more of platelet data, white blood cell data, and hemoglobin data.

17. The erythrocyte sedimentation rate (ESR) measurement method according to claim 16, characterized in that, The blood cell data includes red blood cell data and / or platelet data and / or white blood cell data obtained by flow cytometry and / or Coulter method.

18. The erythrocyte sedimentation rate (ESR) measurement method according to claim 17, characterized in that, The red blood cell data includes one or more of the following: red blood cell pulse signal, red blood cell count, hematocrit, mean corpuscular volume, coefficient of variation of red blood cell volume, standard deviation of red blood cell distribution width, red blood cell volume distribution histogram, and red blood cell scatter plot, measured by the Coulter method; and / or, the platelet data includes platelet count measured by flow cytometry or the Coulter method; and / or, the white blood cell data includes white blood cell count measured by flow cytometry or the Coulter method; and / or the hemoglobin data includes hemoglobin concentration and / or mean corpuscular hemoglobin content and / or mean corpuscular hemoglobin concentration obtained based on the hemoglobin concentration.

19. The erythrocyte sedimentation rate (ESR) measurement method according to claim 17 or 18, characterized in that, The red blood cell data includes red blood cell pulse signals and / or red blood cell scatter plots measured by flow cytometry.

20. A method for measuring erythrocyte sedimentation rate (ESR), characterized in that, Includes the following steps: A portion of the blood sample to be tested is transported to the optical detection tube, and the portion of the blood sample to be tested is circulated back and forth in the optical detection tube in order to deaggregate the red blood cells in the portion of the blood sample to be tested. After the deagglomeration process, the portion of the blood sample to be tested is placed still in the optical detection tube and illuminated with light to obtain the red blood cell aggregation curve of the intensity of transmitted light through the portion of the blood sample to be tested changing over time. The analytical data is input into a deep learning algorithm with a neural network structure. The analytical data includes parameters related to erythrocyte aggregation obtained from the erythrocyte aggregation curve and blood cell data of the blood sample to be tested measured by flow cytometry and / or Coulter method. The parameters related to erythrocyte aggregation include at least two feature parameters extracted from the erythrocyte aggregation curve. The at least two feature parameters include a second erythrocyte sedimentation rate (ESR) measurement result. The second ESR measurement result is calculated based on the area enclosed by the erythrocyte aggregation curve and the time axis during the time period from the measurement start time point to the measurement end time point and a preset calibration curve. The blood cell data includes hematocrit and mean erythrocyte volume. The calibration curve is configured to fit the area enclosed by the erythrocyte aggregation curve and the time axis of multiple blood samples and the erythrocyte sedimentation rate data obtained by Widmanstätten method. as well as The erythrocyte sedimentation rate (ESR) of the blood sample to be tested is calculated using the deep learning algorithm.

Images