Blood cell analysis device and blood cell analysis method

Abstract

The invention discloses blood cell analysis equipment and a blood cell analysis method. The equipment comprises a sample injection module, a sample adding module, a detection module, a processor and a display, the sample introduction module is used for acquiring a blood sample; the sample adding module is connected with the sample introduction module and is used for mixing a reagent with a blood sample to obtain a to-be-detected sample solution; the detection module is connected with the sample adding module and is used for detecting the to-be-detected sample liquid to obtain detection data; the processor is connected with the detection module and is used for receiving the detection data and predicting a prediction score of the detection data; the display is connected with the processor and used for displaying an analysis interface which is at least used for displaying the predicted score. Therefore, the predicted score can be directly displayed on the analysis interface of the display, so that medical staff can intuitively obtain the predicted score of the disease risk predicted according to the detection data, the information interpretation efficiency of a user is improved, and the use experience of the user is improved.

Description

Technical Field

[0001] This application relates to the field of blood cell analysis technology, and in particular to blood cell analysis equipment and methods. Background Technology

[0002] Blood cell analysis equipment is typically used to measure the content of cells or various substances in blood samples, providing a series of parameters as a basis for clinical disease screening, auxiliary diagnosis, or treatment monitoring. For certain diseases, due to the multi-factor nature of disease risk design, blood cell analysis equipment cannot output predicted disease risk based on the results of routine tests. Medical personnel cannot intuitively obtain relevant disease risk information from the test data; they must rely on their own experience to interpret and judge the data using multiple parameters, resulting in low information analysis efficiency and a poor user experience. Summary of the Invention

[0003] To address the aforementioned technical problems, this application provides a blood cell analysis device and a blood cell analysis method.

[0004] To address the aforementioned problems, this application provides a blood cell analysis device, including a sample injection module, a sample dispensing module, a detection module, a processor, and a display. The sample injection module is used to acquire a blood sample. The sample dispensing module is connected to the sample injection module and is used to mix reagents with the blood sample to obtain a test sample solution. The detection module is connected to the sample dispensing module and is used to detect the test sample solution to obtain detection data. The processor is connected to the detection module and is used to receive the detection data and predict the predicted score of the detection data. The display is connected to the processor and is used to display an analysis interface, which at least displays the predicted score.

[0005] Optionally, the processor is configured to generate an alarm text based on the predicted score, and display the alarm text on the analysis interface; and / or, the processor is configured to generate an alarm score graph based on the predicted score, and display the alarm score graph on the analysis interface.

[0006] Optionally, when generating the alarm score map based on the predicted score, the processor is used to obtain a pre-stored alarm threshold, and the processor is also used to generate the alarm score map based on the predicted score and the alarm threshold.

[0007] Optionally, the detection data includes multiple parameter data, the processor is used to calculate the contribution value of each of the parameter data, and the processor is also used to generate a feature contribution map based on the contribution value, so as to display the feature contribution map on the analysis interface.

[0008] Optionally, the contribution value is the contribution of the parameter data to the sample prediction; the feature contribution map includes a bar chart corresponding to each of the parameter data, the feature contribution map includes a first bar chart that increases the alarm probability of the sample detection and a second bar chart that decreases the alarm probability of the sample detection, and at least one of the color and arrow direction of the first bar chart is different from the second bar chart.

[0009] Optionally, after obtaining the predicted score, the processor is used to obtain corresponding prompt information based on the predicted score, and the processor is also used to display the prompt information and the predicted score on the analysis interface; wherein, the prompt information includes disease risk warnings and / or treatment suggestions for the blood sample.

[0010] Optionally, the processor is used to input the detection data into the prediction model to obtain the prediction score output by the prediction model; the processor is also used to display at least a portion of the detection data used by the prediction model on the analysis interface.

[0011] Optionally, the processor is used to determine whether the detection data is abnormal; the processor is also used to respond to at least one abnormality of the detection data by displaying all the detection data on the analysis interface and adjusting the display mode of the abnormal detection data so that at least one of the colors and display positions of the abnormal detection data is different from that of the normal detection data; and / or, the detection data includes multiple parameter data, and the processor is used to: calculate the contribution value of each parameter data; based on the contribution values ​​of all the parameter data, obtain the parameter data whose contribution values ​​satisfy a first preset condition; display all the detection data on the analysis interface and mark the parameter data that satisfy the first preset condition.

[0012] Optionally, the processor is used to determine whether the detection data is abnormal, and the processor is also used to respond to at least one abnormality in the detection data by displaying the abnormal detection data on the analysis interface; or, the detection data includes multiple parameter data, and the processor is used to calculate the contribution value of all the parameter data to obtain the parameter data whose contribution value satisfies a first preset condition; the processor is also used to display the parameter data that satisfies the first preset condition on the analysis interface.

[0013] To address the aforementioned problems, this application provides a blood cell analysis method, comprising: acquiring a blood sample; mixing a reagent with the blood sample to obtain a test sample solution; detecting the test sample solution to obtain detection data; predicting a predicted score of the detection data; and displaying the predicted score on an analysis interface.

[0014] Optionally, after the step of predicting the predicted score of the test data and displaying the predicted score on the analysis interface, the blood cell analysis method further includes: generating an alarm text based on the predicted score to display the alarm text on the analysis interface, and / or generating an alarm score graph based on the predicted score to display the alarm score graph on the analysis interface.

[0015] Optionally, generating an alarm score map based on the predicted score includes: obtaining a pre-stored alarm threshold; and generating an alarm score map based on the predicted score and the alarm threshold.

[0016] Optionally, after the steps of the detection data including multiple parameter data and predicting the predicted score of the detection data and displaying the predicted score on the analysis interface, the blood cell analysis method further includes: calculating the contribution value of each parameter data; generating a feature contribution map based on the contribution value, and displaying the feature contribution map on the analysis interface.

[0017] This application provides a blood cell analysis device and a blood cell analysis method. The device includes a sample injection module, a sample loading module, a detection module, a processor, and a display. The sample injection module is used to acquire blood samples. The sample loading module is connected to the sample injection module and is used to mix reagents with the blood sample to obtain a test sample solution. The detection module is connected to the sample loading module and is used to detect the test sample solution to obtain detection data. The processor is connected to the detection module and is used to receive the detection data and predict the predicted score of the detection data. The display is connected to the processor and is used to display the analysis interface, which is used to display at least the predicted score. Therefore, by directly displaying the predicted score on the analysis interface of the display, medical personnel can intuitively obtain the predicted score of disease risk based on the test data, thereby improving the efficiency of information interpretation and enhancing the user experience. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein: Figure 1 This is a schematic diagram of the structure of an embodiment of the blood cell analyzer provided in this application; Figure 2 This is a schematic diagram of the structure of one embodiment of the alarm score diagram provided in this application; Figure 3 This is a schematic diagram of the structure of one embodiment of the feature contribution map provided in this application; Figure 4 This is a schematic flowchart of an embodiment of the blood cell analysis method provided in this application.

[0019] Among them, 10 is the sample injection module; 20 is the sample dispensing module; 30 is the detection module; 40 is the processor; and 50 is the display. Detailed Implementation

[0020] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0021] It should be noted that if the embodiments of this application involve directional indicators (such as up, down, left, right, front, back, etc.), the directional indicators are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indicators will also change accordingly.

[0022] Furthermore, if the embodiments of this application involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed in this application.

[0023] Please see Figure 1 , Figure 1 This is a schematic diagram of an embodiment of the blood cell analyzer provided in this application. Figure 1 As shown, this application embodiment first provides a blood cell analysis device, which includes a sample injection module 10, a sample loading module 20, a detection module 30, a processor 40, and a display 50.

[0024] The sample injection module 10 is used to acquire blood samples. The sample dispensing module 20 is connected to the sample injection module 10 and is used to mix reagents with the blood sample to obtain a test sample solution. The detection module 30 is connected to the sample dispensing module 20 and is used to detect the test sample solution to obtain detection data. The processor 40 is connected to the detection module 30 and is used to receive the detection data and predict the predicted scores of the detection data. The display 50 is connected to the processor 40 and is used to display the analysis interface, which is used to display at least the predicted scores.

[0025] Specifically, the sample introduction module 10 may include an injector assembly and a sampling assembly. The injector assembly is used to acquire a sample tube containing a blood sample, and the sampling assembly is used to collect the blood sample from the sample tube to transfer the blood sample to the sample application module 20. The sample application module 20 is used to mix the reagents required for detection with the blood sample to obtain a test sample solution and transfer the test sample solution to the detection module 30. The detection module 30 is used to detect the test sample solution. The detection module 30 may, but is not limited to, use electrochemical methods, impedance detection, sheath current detection, optical detection, etc., to detect the test sample solution to obtain detection data.

[0026] The detection data includes, but is not limited to, data related to the detection items obtained by the detection module 30 in the routine blood test mode. For example, the detection items may include at least one of the following: Complete Blood Count (CBC), Differential Count (DIFF), Reticulocyte Count (RET), and Platelet Count – Fluorescent Method (PLT-F); the detection data may include red blood cell parameters, such as the number of red blood cells (RBC), mean corpuscular volume (MCV), hemoglobin concentration (HGB), hematocrit (HCT), standard deviation of red blood cell distribution width (RDW-SD), coefficient of variation of red blood cell distribution width (RDW-CV), mean corpuscular hemoglobin content (MCH), mean corpuscular hemoglobin concentration (MCHC), number of small red blood cells, percentage of small red blood cells, number of large red blood cells, percentage of large red blood cells, mean volume of small red blood cells, mean volume of large red blood cells, and peak position of the red blood cell histogram (R-MFV).

[0027] Furthermore, the processor 40 is used to acquire detection data from the detection module 30 and perform disease risk prediction based on the detection data to obtain a prediction score. The prediction score is used to indicate the likelihood of a disease risk in the blood sample. In a possible manner, a prediction model is deployed in the processor 40, which is used to input the detection data into the prediction model. The prediction model processes the detection data according to the constructed model structure to output a prediction score. The prediction score can, but is not limited to, predict the risk of anemia in the blood sample and is represented by digital parameters so that the user can intuitively assess the disease risk of the blood sample through the prediction score displayed on the display 50.

[0028] The analysis interface displayed on monitor 50 is used to visualize the predicted scores. The analysis interface can visually represent the predicted scores through a combination of text parameters, charts, colors, and symbols, among other display methods; specific limitations are not specified here.

[0029] In this embodiment, the device includes a sample injection module 10, a sample dispensing module 20, a detection module 30, a processor 40, and a display 50. The sample injection module 10 is used to acquire blood samples. The sample dispensing module 20 is connected to the sample injection module 10 and is used to mix reagents with the blood sample to obtain a test sample solution. The detection module 30 is connected to the sample dispensing module 20 and is used to detect the test sample solution to obtain detection data. The processor 40 is connected to the detection module 30 and is used to receive the detection data and predict the predicted score of the detection data. The display 50 is connected to the processor 40 and is used to display an analysis interface, which is at least used to display the predicted score. Therefore, by directly displaying the predicted score on the analysis interface of the display 50, medical personnel can intuitively obtain the predicted score of disease risk based on the detection data, thereby improving the efficiency of information interpretation and enhancing the user experience.

[0030] In one embodiment, please refer to Figure 2 , Figure 2 This is a schematic diagram of an embodiment of the alarm score graph provided in this application. The processor 40 is used to generate alarm text based on the predicted score, so as to display the alarm text on the analysis interface, and / or, the processor 40 is used to generate an alarm score graph based on the predicted score, so as to display the alarm score graph on the analysis interface.

[0031] Specifically, after acquiring the predicted score, the processor 40 generates an alarm text based on the predicted score. The alarm text directly reflects the disease risk level corresponding to the blood sample through text information. For example, the alarm text may be, but is not limited to, "Predicted score: 80" or "Patient A's disease risk predicted score is 80," etc. and / or, such as Figure 2 As shown, after obtaining the predicted score, the processor 40 generates an alarm score map based on the predicted score. The alarm score map directly reflects the disease risk level of the blood sample in a graphical manner.

[0032] In one possible manner, processor 40 is used to display alarm text on the analysis interface; or, processor 40 is used to display alarm text and alarm score graph on the analysis interface; or, processor 40 is used to display alarm score graph on the analysis interface.

[0033] Therefore, the processor 40 in this embodiment can generate alarm text and / or alarm score graphs to meet the user's display needs for disease risk prediction in different scenarios. For example, the analysis interface of the display 50 can provide an intuitive explanatory description through alarm text, and / or help users quickly determine the disease risk present in the blood sample through the visualization level of the alarm score graph, thereby improving the user's information interpretation efficiency and optimizing the human-computer interaction experience, making it easier for users to choose a display method that suits their reading habits.

[0034] Optionally, when generating an alarm score map based on the predicted score, the processor 40 is used to obtain a pre-stored alarm threshold, and the processor 40 is also used to generate an alarm score map based on the predicted score and the alarm threshold.

[0035] Specifically, after obtaining the predicted score, the processor 40 compares the predicted score with the alarm threshold. If the predicted score is greater than or equal to the alarm threshold, the blood sample is considered to have a higher risk of disease; if the predicted score is less than the alarm threshold, the blood sample is considered to have a lower risk of disease. The alarm score graph is used to illustrate the difference between the predicted score and the alarm threshold, allowing users to intuitively assess the disease risk of the blood sample through the difference between the predicted score and the alarm threshold in the alarm score graph.

[0036] For example, the alarm score chart can represent the difference between the predicted score and the alarm threshold using bar charts, scatter plots, bubble charts, etc. Or, as... Figure 2 As shown, the alarm score chart can also be presented by placing the predicted score and alarm threshold on the same scale and representing them with bars of different lengths, allowing users to directly judge the magnitude of the predicted score and alarm threshold using a single metric. Alternatively, the alarm score chart can use different color labels or symbols to indicate the degree to which the predicted score deviates from the alarm threshold; for example, if the alarm threshold is 50, the alarm score chart would show a yellow label when the predicted score is 60, an orange label when the predicted score is 70, and a red label when the predicted score is 80, and so on.

[0037] Therefore, by visually comparing the preset alarm threshold with the predicted score obtained by the processor 40, an alarm score graph is generated. When the alarm score graph is displayed on the analysis interface, it can intuitively reflect the predicted disease risk level of the blood sample, making it easy for users to quickly judge the disease risk and carry out subsequent processing based on the alarm score graph.

[0038] Furthermore, the aforementioned alarm threshold can be obtained by averaging the predicted scores corresponding to multiple detection data processed by the processor 40. Alternatively, a threshold that balances sensitivity and specificity can be found through a prediction model as the alarm threshold. Alternatively, the processor 40 can also display an adjustment interface on the display 50, allowing the user to input the desired alarm threshold for adjustment to meet the sensitivity and specificity requirements of disease risk prediction in different scenarios. The specific method for obtaining the alarm threshold is not limited here.

[0039] In one embodiment, please refer to Figure 3 , Figure 3 This is a schematic diagram of the structure of one embodiment of the feature contribution map provided in this application. For example... Figure 3 As shown, the detection data includes multiple parameter data. The processor 40 is used to calculate the contribution value of each parameter data. The processor 40 is also used to generate a feature contribution map based on the contribution value, so as to display the feature contribution map on the analysis interface.

[0040] Specifically, the detection data includes parameter data corresponding to multiple detection items. Processor 40 is used to input the detection data into the prediction model and obtain the prediction score output by the prediction model. Processor 40 is also used to calculate the prediction value of the prediction model under different combinations of parameter data, and to calculate the marginal contribution of each parameter data in the model prediction using multiple combinations of prediction values, i.e., to obtain the contribution value. Processor 40 is also used to generate a feature contribution map based on the contribution value, so as to display the feature contribution map on the analysis interface.

[0041] In possible ways, the contribution values ​​can be, but are not limited to, Shapley Additive Explanations (SHAP values). After the processor 40 inputs the detection data into the prediction model, it can calculate the contribution of each parameter data by introducing a SHAP interpreter. The feature contribution map described above can be, but is not limited to, a Shapley Additive Explanation map. The feature contribution map is used to visualize the contribution of each parameter data to the prediction model in predicting disease risk, so that users can understand the decision-making process for predicting the disease risk of blood samples and perform subsequent processing through the feature contribution map.

[0042] Therefore, the processor 40 in this embodiment can transform the contribution value of parameter data into a visualized feature contribution map to intuitively present the degree of influence of each detection indicator on the predicted score of disease risk, help users quickly identify key abnormal parameters, and enable users to quickly understand the decision-making ideas of the prediction model, thereby further improving the user experience and ease of operation.

[0043] Optionally, the contribution value is the contribution of the parameter data to the sample prediction. The feature contribution map includes a bar chart corresponding to each parameter data. The feature contribution map includes a first bar chart that increases the alarm probability of sample detection and a second bar chart that decreases the alarm probability of sample detection. At least one of the colors and arrow directions of the first bar chart is different from that of the second bar chart.

[0044] Specifically, such as Figure 3 As shown, when generating the feature contribution map, the processor 40 can divide the contribution values ​​of all parameter data into a first type of contribution value and a second type of contribution value. The first type of contribution value is the contribution value that increases the alarm probability of disease risk, and the second type of contribution value is the contribution value that decreases the alarm probability of disease risk. The processor 40 is used to generate a first bar chart corresponding to the contribution values ​​belonging to the first type and a second bar chart corresponding to the contribution values ​​belonging to the second type, so as to generate a feature contribution map based on the first bar chart and the second bar chart, which makes it easy for users to intuitively obtain the degree of influence of each detection indicator on the predicted score of disease risk.

[0045] At least one of the colors and arrow directions of the first bar chart is different from that of the second bar chart. For example, the color of the first bar chart is different from the color of the second bar chart, such as... Figure 3 As shown, the first bar chart is red, and the second bar chart is blue; and / or, the arrows in the first bar chart point in a different direction than the arrows in the second bar chart, such as... Figure 3 As shown, the first bar chart has an arrow pointing to the right, and the second bar chart has an arrow pointing to the left. For example, the feature contribution graph includes a horizontal axis representing the alarm probability of the prediction model, with the predicted alarm probability increasing along the direction indicated by the horizontal axis. The first bar chart includes connected bars and arrow shapes, with the arrow shape aligned with the direction indicated by the axis. The length of the first bar chart corresponds to the position of the contribution value of the parameter data on the horizontal axis, so that the first bar chart can be used to indicate that the parameter data increases the alarm probability of sample detection. The second bar chart includes connected bars and arrow shapes, with the arrow shape opposite to the direction indicated by the axis. The length of the second bar chart corresponds to the position of the contribution value of the parameter data on the horizontal axis, so that the second bar chart can be used to indicate that the parameter data decreases the alarm probability of sample detection.

[0046] In one possible approach, processor 40 can be used to display the contribution values ​​of all parameter data sequentially in descending order through corresponding bar charts to obtain a feature contribution map. For example, the parameter data can be sorted by their absolute contribution values, and the first or second bar chart can be generated sequentially in ascending order. Alternatively, to improve the aesthetics of the feature contribution map, several parameter data points with lower absolute contribution values ​​can be combined into a single bar chart for display, allowing users to directly observe the parameter data with higher contribution values. Further, such as... Figure 3 As shown, the horizontal axis of the feature contribution plot represents the predicted probability of a blood sample having a corresponding disease, as output by the prediction model. The percentage value of the predicted probability is the prediction score. The vertical axis of the feature contribution plot represents the parameter data and their corresponding parameter names, sorted from highest to lowest absolute value of the contribution value. Following the order from lowest to highest, the starting point of the bar with the lowest contribution value on the horizontal axis is the average positive probability of the training samples of the prediction model; the starting point of the bar with the second lowest contribution value is the ending point of the bar with the lowest contribution value; the starting point of the bar with the third lowest contribution value is the ending point of the bar with the second lowest contribution value; and so on, upwards until the bar with the highest contribution value is reached, with the ending point of the bar with the highest contribution value representing the predicted probability output by the prediction model.

[0047] Therefore, the processor 40 in this embodiment transforms the prediction logic of the abstract prediction model into a visual first bar chart or a second bar chart to intuitively present the degree of influence of each parameter data on the alarm prediction of the disease risk of the blood sample, helping users to quickly identify key abnormal parameters.

[0048] In one embodiment, after obtaining the predicted score, the processor 40 is used to obtain corresponding prompt information based on the predicted score. The processor 40 is also used to display the prompt information and the predicted score on the analysis interface. The prompt information includes disease risk warnings and / or treatment suggestions for the blood sample.

[0049] Specifically, the prompt information includes disease risk warnings and / or treatment suggestions for the blood sample. These prompts are used to provide the user with recommendations for subsequent testing or treatment of the blood sample. The disease risk warning indicates the degree of disease risk present in the blood sample and the corresponding predicted disease. For example, the processor 40 can generate a corresponding disease risk warning based on a comparison between the predicted score and an alarm threshold; for instance, it generates an alarm prompt indicating a suspected disease when the predicted score is greater than or equal to the alarm threshold, and generates an alarm prompt indicating no abnormality when the predicted score is less than the alarm threshold. And / or, the treatment suggestion prompt provides the user with interpretation suggestions for the suspected disease in the blood sample, the corresponding risk, and relevant recommendations for subsequent testing. For example, the processor 40 can generate a corresponding treatment suggestion prompt based on a comparison between the predicted score and the alarm threshold; for instance, it generates at least one prompt such as an explanation of the suspected disease, the degree of risk, and recommendations for subsequent testing when the predicted score is greater than or equal to the alarm threshold, and generates an interpretation text indicating no abnormality when the predicted score is less than the alarm threshold.

[0050] Therefore, the processor 40 in this embodiment can present a visual analysis interface by combining alarm scores with prompt information, which can help users quickly understand the specific reasons and risk levels of sample anomalies, handling suggestions, etc., improve the efficiency of users in checking and analyzing abnormal samples, reduce human interpretation errors, and improve the user experience.

[0051] In one embodiment, the processor 40 is configured to input detection data into a prediction model to obtain a prediction score output by the prediction model; the processor 40 is also configured to display at least a portion of the detection data used by the prediction model on an analysis interface.

[0052] Specifically, based on the parameter requirements of the prediction model for different diseases, the prediction model can use at least a portion of the detection data for prediction. The processor 40 is also used to display at least a portion of the detection data used by the prediction model on the analysis interface. For example, the processor 40 can display all the parameter data of the detection items used by the prediction model on the analysis interface; or, the processor 40 can display the parameter data of abnormal detection items on the analysis interface; or, the processor 40 can display the parameter data of detection items that contribute significantly to the prediction model on the analysis interface; or, the processor 40 can display the parameter data of multiple pre-configured detection items on the analysis interface.

[0053] Therefore, the processor 40 in this embodiment can improve the interpretability of the detection data by synchronously displaying the detection data of the input prediction model and the output prediction score on the analysis interface, thereby assisting users in judging the credibility of disease prediction alarms and helping users quickly locate key project parameters; at the same time, the display range of the detection data can be adjusted according to different reading needs to improve the user experience.

[0054] Optionally, the processor 40 is used to determine whether the detection data is abnormal; the processor 40 is also used to, in response to at least one abnormality in the detection data, display all the detection data on the analysis interface, and adjust the display method of the abnormal detection data so that at least one of the colors and display positions of the abnormal detection data is different from that of the normal detection data. And / or, the detection data includes multiple parameter data, and the processor 40 is used to: calculate the contribution value of each parameter data; based on the contribution values ​​of all parameter data, obtain the parameter data whose contribution values ​​satisfy a first preset condition; display all the detection data on the analysis interface, and mark the parameter data that satisfy the first preset condition.

[0055] Specifically, the detection data includes multiple parameter data, and the processor 40 is used to display all parameter data on the analysis interface. The processor 40 is also used to adjust the display method of abnormal detection data so that at least one of the colors and display positions of the abnormal detection data is different from that of the normal detection data; and / or, the processor 40 is also used to obtain parameter data whose contribution values ​​meet a first preset condition, and to mark the parameter data that meet the first preset condition in the parameter data of the analysis interface.

[0056] When adjusting the display method of abnormal detection data, the processor 40 compares the parameter data of each detection item with the standard parameter range of that item. It determines that the parameter data is abnormal when it exceeds the standard parameter range and normal when it is within the standard parameter range. The processor 40 also displays abnormal parameter data on the analysis interface in a first display mode and normal parameter data in a second display mode. At least one of the colors and display positions of the first and second display modes is different. For example, normal parameter data can be displayed in black font, and abnormal parameter data in red font; or, normal parameter data can be displayed in a table format in a first position on the analysis interface, and abnormal parameter data in a table format in a second position. Furthermore, when displaying the numerical values ​​of the detection data, a downward red arrow can be placed on the side of the value less than the standard parameter range, and an upward red arrow can be placed on the side of the value greater than the standard parameter range. No specific limitation is made on the display method of abnormal detection data here.

[0057] When marking parameter data that meets the first preset condition, the processor 40 calculates the contribution value of all parameter data and determines whether the contribution value of each parameter data meets the first preset condition to obtain parameter data that meets the first preset condition. The first preset condition can be data whose contribution value is greater than a preset contribution value, or it can be parameter data located in the first few positions of the sorted result, where the contribution values ​​of all parameter data are sorted from highest to lowest. The processor 40 also sets a marker bar next to the values ​​of all parameter data to mark parameter data that meets the first preset condition by adding emphasis symbols to the marker bar; or it can mark parameter data that meets the first preset condition by displaying it in blue font, bold font, diagonal font, etc.

[0058] Therefore, the processor 40 in this embodiment displays all detection data on the analysis interface and adjusts the display method of abnormal detection data or marks detection data with high contribution, so as to realize the centralized display of detection data and the differentiated display of abnormal data and / or key data, which significantly improves the user's efficiency in identifying abnormal data and / or key data and enhances the user experience.

[0059] Optionally, the processor 40 is used to determine whether the detection data is abnormal, and the processor 40 is also used to display the abnormal detection data on the analysis interface in response to at least one abnormality in the detection data.

[0060] Specifically, the processor 40 can display the parameters that are determined to be abnormal in the detection data on the analysis interface, so that users can intuitively obtain the abnormal detection data on the analysis interface, reduce the interference of redundant information, and improve the user experience.

[0061] Optionally, the detection data includes multiple parameter data. The processor 40 is used to calculate the contribution value of all parameter data to obtain parameter data whose contribution value satisfies the first preset condition. The processor 40 is also used to display the parameter data that satisfies the first preset condition on the analysis interface.

[0062] Specifically, the processor 40 can also display the parameters with higher contribution values ​​in the detection data on the analysis interface, so that users can intuitively obtain the key data and corresponding values ​​that the prediction model focuses on when making predictions, reduce redundant information interference, and improve the user experience.

[0063] In one embodiment, the processor 40 is used to display the alarm text, alarm score graph, feature contribution graph, detection data and prompt information on the analysis interface. Alternatively, the processor 40 is used to display the alarm text, alarm score graph, detection data and prompt information on the analysis interface to meet the personalized needs of different users for data focus and assist users in making judgments, thereby improving the user experience.

[0064] Please see Figure 4 , Figure 4 This is a schematic flowchart of an embodiment of the blood cell analysis method provided in this application. Figure 4 As shown in the embodiments of this application, a blood cell analysis method is also proposed, which includes the following steps: Step S11: Obtain a blood sample.

[0065] Obtain the blood sample to be tested. Specifically, the sample tube containing the blood sample can be obtained by controlling the injector assembly, and the blood sample in the sample tube can be drawn by the sampling assembly.

[0066] Step S12: Mix the reagent with the blood sample to obtain the test sample solution.

[0067] After obtaining a blood sample, the blood sample is mixed with the reagents required for the test to obtain the test sample solution.

[0068] Step S13: Detect the sample solution to obtain detection data.

[0069] After obtaining the sample solution to be tested, the sample solution is tested to obtain test data. The test data includes, but is not limited to, parameter data of relevant test items obtained in the routine blood test mode.

[0070] Step S14: Predict the predicted score of the detection data and display the predicted score on the analysis interface.

[0071] After acquiring the test data, the test data is input into the prediction model for prediction to obtain the prediction score corresponding to the test data. The prediction score is then displayed on the analysis interface of the display 50 to show the relevant test results of the blood sample through the analysis interface.

[0072] In this embodiment, the blood cell analysis method involves acquiring a blood sample, mixing reagents with the blood sample to obtain a test sample solution, testing the test sample solution to obtain test data, predicting the predicted score of the test data, and displaying the predicted score on the analysis interface. Therefore, medical personnel can intuitively obtain the predicted score of disease risk based on the test data from the analysis interface, thereby improving the efficiency of information interpretation and enhancing the user experience.

[0073] In one embodiment, after step S14, the blood cell analysis method of this embodiment further includes: generating alarm text based on the predicted score to display the alarm text on the analysis interface, and / or generating an alarm score graph based on the predicted score to display the alarm score graph on the analysis interface.

[0074] Optionally, the above step of generating an alarm score map based on the predicted score further includes: obtaining a pre-stored alarm threshold; and generating an alarm score map based on the predicted score and the alarm threshold.

[0075] In one embodiment, the detection data includes multiple parameter data. After step S14, the blood cell analysis method of this embodiment further includes: calculating the contribution value of each parameter data; generating a feature contribution map based on the contribution value, and displaying the feature contribution map on the analysis interface.

[0076] Optionally, the contribution value is the contribution of the parameter data to the sample prediction. The feature contribution map includes a bar chart corresponding to each parameter data. The feature contribution map includes a first bar chart that increases the alarm probability of sample detection and a second bar chart that decreases the alarm probability of sample detection. At least one of the colors and arrow directions of the first bar chart is different from that of the second bar chart.

[0077] In one embodiment, after step S14, the blood cell analysis method of this embodiment further includes: obtaining corresponding prompt information based on the predicted score; displaying the prompt information and the predicted score on the analysis interface; wherein the prompt information includes disease risk prompts and / or treatment suggestions for the blood sample.

[0078] In one embodiment, step S14 further includes: inputting detection data into a prediction model to obtain a prediction score output by the prediction model; and displaying at least a portion of the detection data used by the prediction model on an analysis interface.

[0079] The above description is merely an embodiment of this application and does not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A blood cell analysis apparatus characterized by comprising: include: The sample introduction module is used to acquire blood samples; A sample addition module, connected to the sample injection module, is used to mix reagents with the blood sample to obtain a test sample solution; A detection module, connected to the sample addition module, is used to detect the sample solution to be tested in order to obtain detection data; A processor, connected to the detection module, is used to receive the detection data and predict the predicted score of the detection data; A display, connected to the processor, is used to display an analysis interface, which is at least used to display the predicted score.

2. The blood cell analysis apparatus according to claim 1, characterized by The processor is configured to generate an alarm text based on the predicted score, and display the alarm text on the analysis interface; and / or, the processor is configured to generate an alarm score graph based on the predicted score, and display the alarm score graph on the analysis interface.

3. The blood cell analysis apparatus according to claim 2, characterized by When generating the alarm score map based on the predicted score, the processor is used to obtain a pre-stored alarm threshold, and the processor is also used to generate the alarm score map according to the predicted score and the alarm threshold.

4. The blood cell analysis apparatus according to claim 1, wherein The detection data includes multiple parameter data. The processor is used to calculate the contribution value of each parameter data. The processor is also used to generate a feature contribution map based on the contribution value, and to display the feature contribution map on the analysis interface.

5. The blood cell analysis device according to claim 4, characterized in that, The contribution value is the contribution of the parameter data to the sample prediction; the feature contribution map includes a bar chart corresponding to each parameter data, and the feature contribution map includes a first bar chart that increases the alarm probability of the sample detection and a second bar chart that decreases the alarm probability of the sample detection, wherein at least one of the color and arrow direction of the first bar chart is different from that of the second bar chart.

6. The blood cell analysis device according to claim 1, characterized in that, After obtaining the predicted score, the processor is used to obtain corresponding prompt information based on the predicted score, and the processor is also used to display the prompt information and the predicted score on the analysis interface; The notification information includes disease risk warnings and / or treatment suggestions for the blood sample.

7. The blood cell analysis device according to any one of claims 1-6, characterized in that, The processor is used to input the detection data into the prediction model to obtain the prediction score output by the prediction model; The processor is also configured to display at least a portion of the detection data used by the prediction model on the analysis interface.

8. The blood cell analysis device according to claim 7, characterized in that, The processor is used to determine whether the detection data is abnormal; the processor is also used to, in response to at least one abnormality in the detection data, display all the detection data on the analysis interface, and adjust the display method of the abnormal detection data so that at least one of the colors and display positions of the abnormal detection data is different from that of the normal detection data; and / or, The detection data includes multiple parameter data, and the processor is used for: Calculate the contribution value of each of the parameter data; Based on the contribution values ​​of all the parameter data, obtain the parameter data whose contribution values ​​satisfy the first preset condition; All the detected data are displayed on the analysis interface, and the parameter data that meet the first preset condition are marked.

9. The blood cell analysis device according to claim 7, characterized in that, The processor is used to determine whether the detection data is abnormal, and the processor is further used to, in response to at least one abnormality in the detection data, display the abnormal detection data on the analysis interface; or, The detection data includes multiple parameter data. The processor is used to calculate the contribution value of all the parameter data to obtain the parameter data whose contribution value satisfies a first preset condition. The processor is also used to display the parameter data that satisfies the first preset condition on the analysis interface.

10. A method for blood cell analysis, characterized in that, include: Obtain blood samples; The reagent is mixed with the blood sample to obtain the test sample solution; The sample solution to be tested is then analyzed to obtain test data; Predict the predicted score of the detected data and display the predicted score on the analysis interface.

11. The blood cell analysis method according to claim 10, characterized in that, Following the step of predicting the predicted score of the test data and displaying the predicted score on the analysis interface, the blood cell analysis method further includes: An alarm text is generated based on the predicted score and displayed on the analysis interface; and / or an alarm score graph is generated based on the predicted score and displayed on the analysis interface.

12. The blood cell analysis method according to claim 11, characterized in that, The process of generating an alarm score map based on the predicted score includes: Retrieve pre-stored alarm thresholds; The alarm score map is generated based on the predicted score and the alarm threshold.

13. The blood cell analysis method according to claim 10, characterized in that, The detection data includes multiple parameter data; after the step of predicting the prediction score of the detection data and displaying the prediction score on the analysis interface, the blood cell analysis method further includes: Calculate the contribution value of each of the parameter data; A feature contribution map is generated based on the contribution value, and the feature contribution map is displayed on the analysis interface.

Images