Method and system for identifying abnormity in blood coagulation process based on big data analysis

Abstract

The invention discloses a big data analysis-based abnormity identification method and system in a blood coagulation process, and the method comprises the steps: combining standard blood coagulation detection and thrombelastogram dynamic monitoring, achieving the spanning from a static index to function whole-course evaluation, combining the individualized features of a patient to screen historical similar cases, and precisely identifying a key blood coagulation index; according to the method, the accuracy and timeliness of blood coagulation state monitoring are remarkably improved, individualized early warning and intervention basis is provided for clinic, the risk of bleeding or thrombus is effectively prevented, and the clinical application prospect is wide. And intelligent and refined development of blood coagulation management is promoted.

Description

Technical Field

[0001] The present invention belongs to the technical field of data processing and relates to a method and system for identifying abnormalities in a coagulation process based on big data analysis. Background Art

[0002] The coagulation process is a critical link in maintaining a dynamic balance between normal hemostasis and preventing thrombosis. Abnormal coagulation function can lead to bleeding or thrombotic disorders, and in severe cases, can even be life-threatening. Therefore, identifying abnormalities in the coagulation process plays an important role in preventing and controlling bleeding disorders, reducing surgical risks, and preventing thrombosis.

[0003] The commonly used method for identifying abnormalities in the coagulation process is standard coagulation testing, which assesses a patient's coagulation function, bleeding risk, and thrombotic tendency through a series of laboratory tests (such as prothrombin time (PT), activated partial thromboplastin time (APTT), and thrombin time (TT)). Although this method is an important means of clinical coagulation assessment and plays a vital role in preoperative evaluation, bleeding disorder screening, and anticoagulant drug monitoring, the assessment of coagulation abnormalities relies on the physician's experience or a unified normal standard, and cannot provide objective and personalized assessment results for different patient conditions.

[0004] Taking into account the differences in medical history, age, physiological status, etc., the same coagulation index may have different meanings for different patients. Even under the unified standard, a patient's coagulation index exceeds the normal range, which does not necessarily mean that there is an abnormality, while another patient may have a coagulation dysfunction even if the index is within the normal range. Using a unified standard to identify abnormalities in the patient's coagulation process will often lead to inaccurate identification results. Summary of the Invention

[0005] The purpose of the present invention is to solve the problem in the prior art that the normal range of the same coagulation index is different for different patients due to the influence of different patients' ages, medical histories, etc., and the use of unified standards to identify abnormalities in the patient's coagulation process often leads to inaccurate identification results. A method and system for identifying abnormalities in the coagulation process based on big data analysis is provided.

[0006] To achieve the above-mentioned purpose, the present invention adopts the following technical solutions to achieve it: a method for identifying abnormalities in the coagulation process based on big data analysis, comprising: obtaining the coagulation index data of the current patient through standard coagulation testing, and obtaining the thromboelastogram of the current patient using a TEG device; obtaining the similarity between the age, disease background and drug use of the patient in the historical data and the characteristics of the current patient, and then screening out the target data reflecting the coagulation condition of the current patient; according to the correlation between each coagulation index data in the target data and the changes in the thromboelastogram, obtaining the reflection degree value of each coagulation index data on the normal state of the coagulation process of the current patient, and sorting all the reflection degree data, and selecting several coagulation indexes with the highest reflection degree. It is a coagulation index that has a significant impact on the patient's coagulation process; based on the obtained coagulation indexes with the highest degree of reflection, several coagulation indexes with the highest degree of reflection are regarded as target coagulation indexes, and a coordinate system is drawn according to the target coagulation index, all target historical patient data are placed in the coordinate system, the data of the coordinate system are clustered, and the clustered data with the highest density is obtained as normal patient data, and then the normal range of the target coagulation index is determined; it is judged whether the current patient's coagulation index data is within the normal range of the target coagulation index. If not, the degree of deviation of the current patient's coagulation index data from the normal range of the target coagulation index is obtained based on the maximum and minimum values of the current patient's coagulation index data and the normal range of the target coagulation index, and then the degree of coagulation abnormality of the current patient is obtained.

[0007] A further improvement of the present invention is that: further, the parameters included in the thromboelastogram are: R time, K time, α angle, MA value and Ly30; among which, R time is the time from liquid blood to fibrin formation; K time is the time from coagulation to reaching a certain strength; α angle is the fibrin generation rate; MA value is the final strength of the blood clot; Ly30 is the thrombus degradation rate within 30 minutes; the coagulation index data include prothrombin time PT, international normalized ratio INR, activated partial thromboplastin time APTT, thrombin time TT, fibrinogen FIB and D-dimer and platelet count PLT.

[0008] Furthermore, the age, disease background, and medication usage of the patients in the historical data are obtained to determine the similarity between the characteristics of the current patient. Specifically, the age similarity of the patients is obtained based on the age difference between the patients in the historical data and the current patient. Specifically, in, Indicates the age similarity between the i-th historical data patient and the current patient, represents the age of the i-th patient in the historical data, Indicates the age of the current patient, represents the absolute value of the age difference between the i-th patient in the historical data and the current patient; This means that the smaller the absolute value of the age difference is, the higher the age similarity is; Make sure the fraction is meaningful and The similarity of the patient's disease background is calculated based on the degree of disease overlap between the patient in the historical data and the current patient. If the patient in the historical data has the same disease as the current patient, the similarity is high; if the patient in the historical data has the corresponding disease but the current patient does not, the similarity is low. If the patient in the historical data and the current patient both have or do not have a certain disease, then it is counted; otherwise, it is not counted. Thus, the similarity of the disease background between the patient in the historical data and the current patient is calculated as follows: in, Indicates the degree of similarity between the disease of the i-th historical data patient and the current patient, Indicates the total number of diseases that affect coagulation indicators. = represents the count value of the dth disease corresponding to the i-th historical data patient; the similarity of the patient's drug use is calculated in the same way as the disease similarity; if the patient in the historical data takes or does not take a certain drug at the same time as the current patient, the count is 1; if the patient in the historical data takes a certain drug but the current patient does not take it, the count is 0. The similarity between the drug use of the patient in the historical data and the current patient is calculated as follows: in, Indicates the similarity between the medication usage of the i-th historical data patient and the current patient, Indicates the total number of drugs that affect coagulation indicators. Indicates the count value of the bth drug corresponding to the i-th historical data patient.

[0009] Furthermore, target data reflecting the coagulation condition of the current patient is screened out, specifically: combining the similarities between the patients in the historical data and the current patient in terms of age, disease, and medication, obtaining a similarity value between the patient in each historical data and the current patient; judging whether the obtained similarity value is greater than a set threshold; if so, it is considered that the patient corresponding to the historical data and the current patient have a high similarity, and the coagulation process of the patient corresponding to the historical data can reflect the abnormal coagulation process of the current patient, and all target data that can reflect the coagulation condition of the current patient are screened out; the obtaining of the similarity value between the patient in each historical data and the current patient is specifically: in, Indicates the similarity between the patient in the i-th historical data and the current patient.

[0010] Furthermore, the correlation between each coagulation index data in the target data and the thromboelastogram change is specifically as follows: Step 1: Select any coagulation index data in the target data and any parameter in the thromboelastogram, and normalize the selected coagulation index data and parameter respectively; Step 2: Use the normalized coagulation index data as the horizontal coordinate and the parameter as the vertical coordinate, and regard the values corresponding to all target data as data and put them into the coordinate; Step 3: Evenly divide the horizontal coordinate into several segments, use the coordinate value of the center point of each segment as the horizontal coordinate value, use the average value of all vertical coordinate data corresponding to the horizontal coordinate segment as the vertical coordinate value corresponding to the center point, and compare the horizontal coordinate data with the vertical coordinate. The data correspond one to one to obtain a coagulation index data-parameter coordinate diagram; Step 4: Use the least squares method to fit the data in the coordinate diagram to obtain a fitting curve; Step 5: According to the slope of the fitting curve, obtain the degree of influence of the coagulation index data on the parameter; Step 6: Repeat steps 1 to 5 to respectively obtain the degree of influence of the coagulation index data on other parameters in the thromboelastogram; Step 7: Based on the degree of influence of the coagulation index data on all parameters in the thromboelastogram, obtain the degree of reflection of the coagulation index data on the patient's coagulation process; Step 8: Repeat steps 1 to 7 to obtain the degree of reflection of all coagulation index data in the target data on the patient's coagulation process.

[0011] Furthermore, according to the slope of the fitting curve, the influence of the coagulation index data on the parameter is obtained. Specifically, taking the coagulation index data INR in the target data and the parameter R time in the thromboelastogram as an example, in, Indicates the influence of coagulation index data INR on R time, Indicates the number of selected points on the fitting curve, Indicates the slope value of the oth point on the "INR-R time" fitting curve, It represents the absolute value of the slope difference between two adjacent points on the fitting curve. The smaller the absolute value of the slope difference, the more consistent the slopes at different positions on the curve, and the higher the correlation between the INR coagulation index and the R time; The average slope of different points on the fitting curve represents the overall trend of the fitting curve. The larger the absolute value of the average slope, the greater the influence of INR on R time. The degree of reflection of the coagulation index data on the patient's coagulation process is obtained based on the influence of the coagulation index data on all parameters in the thromboelastogram. Specifically, the influence degrees of the coagulation index data on all parameters in the thromboelastogram are added and averaged, and the obtained average value is used as the reflection degree of the coagulation index data on the patient's coagulation process.

[0012] Furthermore, a coordinate system is drawn according to the target coagulation index, all target historical patient data are placed in the coordinate system, the data in the coordinate system are clustered, and the clustered data with the highest density is taken as normal patient data, and then the normal range of the target coagulation index is determined. Specifically, the obtained target coagulation index is regarded as the index most closely related to the patient's coagulation process, so the target coagulation index of patients with normal coagulation should be within the normal range; normal data are all concentrated in the same range, and abnormal coagulation data are usually due to different factors causing their abnormalities, and the abnormal manifestations are also quite different; so a coordinate system is drawn according to the target coagulation index, all target historical patient data are placed in the coordinate system, and the data of the target coagulation index are clustered. coordinate system; wherein, the target historical patient data is the data that is screened out and has a high similarity with the current patient's characteristics; the data with a high similarity refers to the target data that are similar in age, disease background and medication between the patients in the historical data and the current patient, and can reflect the current patient's coagulation condition; the DBSCAN clustering method is used to cluster the data in the coordinate system, and then multiple clusters and single-point data are obtained, and the single-point noise data is excluded to obtain the cluster data with the highest density in all clusters as the normal patient data; according to the maximum and minimum values of the corresponding target coagulation index in the normal coagulation patient data, the normal range of the target coagulation index corresponding to the patient is determined.

[0013] Furthermore, according to the maximum and minimum values of the current patient's coagulation index data and the target coagulation index normal range, the deviation degree of the current patient's coagulation index data from the target coagulation index normal range is obtained. Specifically, if the current patient's target coagulation index data is within the target coagulation index normal range, the abnormal degree of the coagulation index is recorded as Otherwise, the degree of abnormality is calculated based on the degree of deviation of the current patient data from the normal range: in, Indicates the abnormality of the u-th target coagulation index of the current patient, Indicates the corresponding value of the u-th target coagulation index of the current patient, Indicates the minimum value of the normal range of the u-th target coagulation index, represents the maximum value of the normal range of the u-th target coagulation index; represents the minimum function.

[0014] Furthermore, the abnormality of blood coagulation of the current patient is obtained, specifically: the abnormality of the patient under each target blood coagulation index is comprehensively calculated to calculate the abnormality of blood coagulation of the current patient. in, Indicates the current patient's coagulation abnormality level. Indicates the number of target coagulation indicators, Indicates the abnormality of the u-th target coagulation index of the current patient.

[0015] The abnormality identification system in the coagulation process based on big data analysis includes: a first acquisition module, which obtains the coagulation index data of the current patient through standard coagulation testing, and obtains the thromboelastogram of the current patient using TEG equipment; a second acquisition module, which obtains the similarity between the patient's age, disease background and drug use in historical data and the characteristics of the current patient, and then filters out target data reflecting the coagulation status of the current patient; a selection module, which obtains the reflection degree value of each coagulation index data on the normal state of the current patient's coagulation process based on the correlation between each coagulation index data in the target data and the thromboelastogram change, and sorts all the reflection degree data, and selects the coagulation indexes with the highest reflection degree as the target data. The coagulation index that has a significant impact on the coagulation process of the patient; a clustering module, which regards several coagulation indexes with the highest degree of reflection as target coagulation indexes based on the obtained data, and draws a coordinate system according to the target coagulation indexes, puts all target historical patient data into the coordinate system, clusters the data of the coordinate system, and takes the clustered data with the highest density as normal patient data, and then determines the normal range of the target coagulation index; a judgment module, which judges whether the coagulation index data of the current patient is within the normal range of the target coagulation index. If not, the deviation degree of the coagulation index data of the current patient from the normal range of the target coagulation index is obtained according to the maximum and minimum values of the coagulation index data of the current patient and the normal range of the target coagulation index, and then obtains the degree of coagulation abnormality of the current patient.

[0016] Compared with the existing technology, the present invention has the following beneficial effects: the present invention combines standard coagulation detection with dynamic monitoring of thromboelastography to achieve a leap from static indicators to full functional evaluation, and at the same time combines the patient's individual characteristics to screen historical similar cases and accurately identify key coagulation indicators; introduces correlation analysis to dynamically screen key indicators, and uses cluster analysis to establish an adaptive normal range, and finally evaluates abnormalities by quantifying the degree of deviation. The present invention significantly improves the accuracy and timeliness of coagulation status monitoring, provides individualized early warning and intervention basis for clinicians, effectively prevents bleeding or thrombosis risks, and promotes the development of coagulation management towards intelligence and refinement. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 Schematic diagram of the process of identifying abnormalities in the coagulation process based on big data analysis of the present invention; Figure 2Schematic diagram of the structure of the abnormality identification system in the coagulation process based on big data analysis of the present invention. DETAILED DESCRIPTION

[0019] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings herein can be arranged and designed in various different configurations.

[0020] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention as claimed, but rather merely represents selected embodiments of the present invention. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without creative effort shall fall within the scope of protection of the present invention.

[0021] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings.

[0022] In the description of the embodiments of the present invention, it should be noted that if the terms "upper," "lower," "horizontal," "inner," etc. appear, the orientation or positional relationship indicated is based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship in which the inventive product is typically placed when in use. These terms are merely for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or component referred to must have a specific orientation, be constructed, or operate in a specific orientation. Therefore, they should not be construed as limitations on the present invention. In addition, the terms "first," "second," etc. are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0023] In addition, if the term "horizontal" appears, it does not mean that the component must be absolutely horizontal, but can be slightly tilted. For example, "horizontal" only means that its direction is more horizontal than "vertical", and does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0024] In the description of the embodiments of the present invention, it should be noted that, unless otherwise expressly specified or limited, the terms "disposed," "installed," "connected," and "connected" should be understood in a broad sense. For example, they can refer to fixed connections, detachable connections, or integral connections; they can refer to mechanical connections or electrical connections; they can refer to direct connections or indirect connections through an intermediate medium; and they can refer to internal connections between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on specific circumstances.

[0025] The present invention will be described in further detail below with reference to the accompanying drawings: Figure 1 The present invention discloses a method for identifying abnormalities in the coagulation process based on big data analysis, including: S101, obtaining the coagulation index data of the current patient through standard coagulation testing, and using a TEG device to obtain the thromboelastogram of the current patient; the parameters contained in the thromboelastogram are: R time, K time, α angle, MA value and Ly30; among which, R time is the time from liquid blood to fibrin formation; K time is the time from coagulation to reaching a certain strength; α angle is the fibrin generation rate; MA value is the final strength of the blood clot; Ly30 is the thrombus degradation rate within 30 minutes; the coagulation index data include prothrombin time PT, international normalized ratio INR, activated partial thromboplastin time APTT, thrombin time TT, fibrinogen FIB and D-dimer and platelet count PLT.

[0026] S102: Obtain the similarity between the age, disease background, and medication usage of the patient in the historical data and the characteristics of the current patient, and then filter out target data reflecting the coagulation status of the current patient; the degree of similarity of the patient age is obtained based on the difference between the age of the patient in the historical data and the age of the current patient, specifically: in, Indicates the age similarity between the i-th historical data patient and the current patient, represents the age of the i-th patient in the historical data, Indicates the age of the current patient, represents the absolute value of the age difference between the i-th patient in the historical data and the current patient; This means that the smaller the absolute value of the age difference is, the higher the age similarity is; Make sure the fraction is meaningful and The similarity of the patient's disease background is calculated based on the degree of disease overlap between the patient in the historical data and the current patient. If the patient in the historical data has the same disease as the current patient, the similarity is high; if the patient in the historical data has the corresponding disease but the current patient does not, the similarity is low. If the patient in the historical data and the current patient both have or do not have a certain disease, then it is counted; otherwise, it is not counted. Thus, the similarity of the disease background between the patient in the historical data and the current patient is calculated as follows: in, Indicates the degree of similarity between the disease of the i-th historical data patient and the current patient, Indicates the total number of diseases that affect coagulation indicators. = represents the count value of the dth disease corresponding to the i-th historical data patient; the similarity of the patient's drug use is calculated in the same way as the disease similarity; if the patient in the historical data takes or does not take a certain drug at the same time as the current patient, the count is 1; if the patient in the historical data takes a certain drug but the current patient does not take it, the count is 0. The similarity between the drug use of the patient in the historical data and the current patient is calculated as follows: in, Indicates the similarity between the medication usage of the i-th historical data patient and the current patient, Indicates the total number of drugs that affect coagulation indicators. Indicates the count value of the bth drug corresponding to the i-th historical data patient.

[0027] Filtering out target data reflecting the coagulation condition of the current patient, specifically: combining the similarities between the patient in the historical data and the current patient in terms of age, disease, and medication, obtaining a similarity value between the patient in each historical data and the current patient; judging whether the obtained similarity value is greater than a set threshold; if so, it is considered that the patient corresponding to the historical data and the current patient have a high similarity, and the coagulation process of the patient corresponding to the historical data can reflect the abnormality of the coagulation process of the current patient, and filtering out all target data that can reflect the coagulation condition of the current patient; obtaining a similarity value between the patient in each historical data and the current patient, specifically: in, Indicates the similarity between the patient in the i-th historical data and the current patient.

[0028] S103, based on the correlation between each coagulation index data in the target data and the thromboelastogram changes, obtain the reflection degree value of each coagulation index data on the normal state of the current patient's coagulation process, and sort all the reflection degree data, and select several coagulation indexes with the highest reflection degree as the coagulation indexes that have a significant impact on the patient's coagulation process; the correlation between each coagulation index data in the target data and the thromboelastogram changes is specifically as follows: S103.1: select any coagulation index data in the target data and any parameter in the thromboelastogram, and normalize the selected coagulation index data and parameters respectively; S103.2: use the normalized coagulation index data as the horizontal coordinate and the parameter as the vertical coordinate, and regard the corresponding values of all target data as data and put them into the coordinates; S103.3: evenly divide the horizontal coordinate into several segments, and use the coordinate value of the center point of each segment as the horizontal coordinate value, The average value of all the corresponding ordinate data in the horizontal axis segment is used as the ordinate value corresponding to the center point, and the horizontal axis data and the vertical axis data are matched one by one to obtain the coagulation index data-parameter coordinate diagram; S103.4: Use the least squares method to fit the data in the coordinate diagram to obtain a fitting curve; S103.5: According to the slope of the fitting curve, obtain the degree of influence of the coagulation index data on the parameter; S103.6: Repeat S103.1 to S103.5 to obtain the degree of influence of the coagulation index data on other parameters in the thromboelastogram; S103.7: Based on the degree of influence of the coagulation index data on all parameters in the thromboelastogram, obtain the numerical value of the degree of reflection of the coagulation index data on the patient's coagulation process; S103.8: Repeat S103.1 to S103.7 to obtain the numerical value of the degree of reflection of all coagulation index data in the target data on the patient's coagulation process.

[0029] According to the slope of the fitting curve, the influence of the coagulation index data on the parameter is obtained. Specifically, taking the coagulation index data INR in the target data and the parameter R time in the thromboelastogram as an example, in, Indicates the influence of coagulation index data INR on R time, Indicates the number of selected points on the fitting curve, Indicates the slope value of the oth point on the "INR-R time" fitting curve, It represents the absolute value of the slope difference between two adjacent points on the fitting curve. The smaller the absolute value of the slope difference, the more consistent the slopes at different positions on the curve, and the higher the correlation between the INR coagulation index and the R time; The average slope of different points on the fitting curve represents the overall trend of the fitting curve. The larger the absolute value of the average slope, the greater the influence of INR on R time. The degree of reflection of the coagulation index data on the patient's coagulation process is obtained based on the influence of the coagulation index data on all parameters in the thromboelastogram. Specifically, the influence degrees of the coagulation index data on all parameters in the thromboelastogram are added and averaged, and the obtained average value is used as the reflection degree of the coagulation index data on the patient's coagulation process.

[0030] S104: The obtained coagulation indices with the highest degree of reflection are regarded as target coagulation indices, and a coordinate system is drawn based on the target coagulation indices. All target historical patient data are placed in the coordinate system, and the data in the coordinate system are clustered. The clustered data with the highest density are taken as normal patient data, and the normal range of the target coagulation indices is determined. The obtained target coagulation indices are regarded as the indices most closely related to the patient's coagulation process. Therefore, the target coagulation indices of patients with normal coagulation should all be within the normal range. Normal data are all concentrated in the same range, while abnormal coagulation data usually have different abnormal manifestations due to different influencing factors causing the abnormality. Therefore, a coordinate system is drawn based on the target coagulation indices, and all target historical patient data are placed in the coordinate system. The data in the coordinate system are clustered using the DBSCAN clustering method. The clustering will obtain multiple clusters and single point data. The single point noise data is excluded, and the cluster data with the highest density among all clusters is obtained as the normal patient data. The normal range of the target coagulation indices corresponding to the patient is determined based on the maximum and minimum values of the corresponding target coagulation indices in the normal coagulation patient data.

[0031] S105, determining whether the coagulation index data of the current patient is within the target coagulation index normal range; if not, obtaining the degree of deviation between the coagulation index data of the current patient and the target coagulation index normal range based on the maximum and minimum values of the coagulation index data of the current patient and the target coagulation index normal range, and then obtaining the degree of coagulation abnormality of the current patient.

[0032] If the target coagulation index data of the current patient is within the normal range of the target coagulation index, the abnormal degree of the coagulation index is recorded as Otherwise, the degree of abnormality is calculated based on the degree of deviation of the current patient data from the normal range: in, Indicates the abnormality of the u-th target coagulation index of the current patient, Indicates the corresponding value of the u-th target coagulation index of the current patient, Indicates the minimum value of the normal range of the u-th target coagulation index, represents the maximum value of the normal range of the u-th target coagulation index; represents the minimum function.

[0033] Obtain the current patient's abnormal coagulation level, specifically: comprehensively calculate the abnormality level of the patient under each target coagulation index, in, Indicates the current patient's coagulation abnormality level. Indicates the number of target coagulation indicators, Indicates the abnormality of the u-th target coagulation index of the current patient.

[0034] See also Figure 2 The present invention discloses a system for identifying abnormalities in the coagulation process based on big data analysis, comprising: a first acquisition module, which obtains the coagulation index data of the current patient through standard coagulation testing, and obtains the thromboelastogram of the current patient using a TEG device; a second acquisition module, which obtains the similarity between the age, disease background and drug use of the patient in the historical data and the characteristics of the current patient, and then filters out target data reflecting the coagulation status of the current patient; a selection module, which obtains the reflection degree value of each coagulation index data on the normal state of the coagulation process of the current patient based on the correlation between each coagulation index data in the target data and the thromboelastogram change, and sorts all the reflection degree data, and selects several coagulation index data with the highest reflection degree. The indicator is a coagulation indicator that has a significant impact on the patient's coagulation process; a clustering module, which regards several coagulation indicators with the highest degree of reflection as target coagulation indicators based on the obtained data, and draws a coordinate system based on the target coagulation indicator, puts all target historical patient data into the coordinate system, clusters the data of the coordinate system, and takes the clustered data with the highest density as normal patient data, thereby determining the normal range of the target coagulation indicator; a judgment module, which judges whether the coagulation indicator data of the current patient is within the normal range of the target coagulation indicator. If not, the degree of deviation of the coagulation indicator data of the current patient from the normal range of the target coagulation indicator is obtained based on the maximum and minimum values of the coagulation indicator data of the current patient and the normal range of the target coagulation indicator, thereby obtaining the degree of coagulation abnormality of the current patient.

[0035] Example: The present invention discloses a method for identifying abnormalities in the coagulation process based on big data analysis, comprising: S1, obtaining the patient's coagulation index data through a standard coagulation test, and obtaining the patient's thromboelastogram (TEG) using a TEG device.

[0036] Because assessing the likelihood of abnormalities in a patient's coagulation process primarily relies on coagulation parameter data obtained from standard coagulation testing, a blood sample is first collected from the patient via venous sampling. A minimum of 2 ml of blood is collected to ensure accurate coagulation factor concentrations, and 3.2% sodium citrate anticoagulant is added. Immediately after blood collection, gently invert the tube to mix thoroughly to avoid clot formation. The blood is then sent for analysis within 30 minutes to prevent coagulation factor degradation. After blood collection, the blood is analyzed in the laboratory using the ACL TOP automated coagulation analyzer. Data are recorded during the analysis, including prothrombin time (PT), international normalized ratio (INR), activated partial thromboplastin time (APTT), thrombin time (TT), fibrinogen ionization (FIB), D-dimer, and platelet count (PLT).

[0037] Because standard coagulation tests cannot reflect the dynamic changes in the coagulation process, thromboelastography (TEG) is required to analyze the correlation between coagulation parameters obtained through standard coagulation tests and abnormalities in the patient's coagulation process. Therefore, a portion of the collected blood sample (1-2ml) is used to draw a coagulation process curve through the TEG device. Based on the coagulation process curve, important parameters are recorded, including R time (from liquid blood to fibrin formation), K time (from coagulation to reaching a certain strength), α angle (fibrin formation rate (curve slope)), MA value (final clot strength), and Ly30 (thrombus degradation rate within 30 minutes).

[0038] S2. According to the similarity between historical patients and the current patient, and the degree to which different coagulation indicators reflect the patient's coagulation abnormality, the normal range of coagulation indicators for the current patient is obtained.

[0039] Because the coagulation process of a patient is greatly affected by the patient's own age, disease, medication, and other conditions, under the influence of these factors, a unified normal range standard for coagulation indicators may not be applicable to different patients. Therefore, based on the similarity between the patient in the historical data and the current patient in these characteristics, target data that can reflect the current patient's coagulation status is screened to reduce the impact of these influencing factors on the accuracy of the abnormal identification results of the patient's coagulation process. In addition, for different patients, each coagulation indicator has a different degree of reflection of its coagulation abnormality. For example, the patient's coagulation process may have a higher tolerance for certain coagulation indicators, that is, when these indicators undergo large changes, the patient's coagulation process remains normal. Therefore, based on the correlation between each coagulation indicator and the abnormal manifestation of the patient's coagulation process, the coagulation indicator that best reflects the current patient's coagulation abnormality is obtained to reduce the impact of changes in other indicators with smaller reactions on the final results.

[0040] S2.1. Based on the similarity between the characteristics of patients in historical data and the current patient, screen target data that can reflect the coagulation status of the current patient.

[0041] Because the coagulation process of different patients is affected by individual differences, disease status, age, and other factors, the normal ranges for the same coagulation indicators may vary for different patients. For example, in newborns, coagulation factors are immature, and PT and APTT are physiologically prolonged, but this does not indicate abnormality. In the elderly, physiological increases in fibrinogen and D-dimer may increase the risk of thrombosis, but PT / APTT may still be normal. In patients with DIC, PT, APTT, and D-dimer are all elevated. Therefore, only patient data with a higher similarity in historical data with the current patient's characteristics can accurately reflect the normal range of the current patient's coagulation indicators. Therefore, by calculating the similarity between the characteristics of patients in historical data and the current patient, target data that reflects the current patient's coagulation status can be screened.

[0042] The main factors affecting the normal range of a patient's coagulation indicators are the patient's age, disease background, and medication use. Therefore, the similarity between the patient in the historical data and the current patient is calculated based on these aspects.

[0043] The degree of similarity of patient age is obtained based on the difference between the patient age in historical data and the current patient age: in, Indicates the age similarity between the i-th historical data patient and the current patient, represents the age of the i-th patient in the historical data, Indicates the age of the current patient, Represents the absolute value of the age difference between the i-th patient in the historical data and the current patient. This means that the smaller the absolute value of the age difference is, the higher the age similarity is. Make sure the fraction is meaningful and .

[0044] The similarity of the patient's disease background is based on the degree of overlap between the disease of the patient in the historical data and the current patient. If the patient in the historical data has the same disease as the current patient, the similarity is high; if the patient in the historical data has the corresponding disease but the current patient does not, the similarity is low. The main diseases that affect the patient's coagulation indicators include liver disease, hemophilia, DIC (disseminated intravascular coagulation), APS (antiphospholipid syndrome), deep vein thrombosis (DVT), pulmonary embolism (PE) and pregnancy. Therefore, statistics are taken from this disease. If the patient in the historical data and the current patient both have or do not have a certain disease, it is counted, otherwise it is not counted. For example: if the patient in the historical data and the current patient both have or do not have hemophilia, then the disease is counted. ; If the patient in the historical data has DIC disease, but the current patient does not, then the count . Thus, the similarity of the disease background between the patients in the historical data and the current patient is calculated: in, Indicates the degree of similarity between the disease of the i-th historical data patient and the current patient, Indicates the total number of diseases that statistically affect coagulation indicators (here ), Represents the count value of the d-th disease corresponding to the i-th historical data patient.

[0045] The calculation process for drug usage similarity is the same as that for disease similarity. Since the main drugs that affect the coagulation process include warfarin, unfractionated heparin (UFH), low molecular weight heparin (LMWH), Xa inhibitors (rivaroxaban, apixaban), and direct thrombin inhibitors (dabigatran), the similarity between the drug usage of patients in historical data and the current patient is calculated: in, Indicates the similarity between the medication usage of the i-th historical data patient and the current patient, Indicates the total number of drugs that affect coagulation indicators. Indicates the count value of the bth drug corresponding to the i-th historical data patient.

[0046] Combined with the similarities between the patients in the historical data and the current patient in terms of age, disease, and medication, the degree of similarity between each patient in the historical data and the current patient is calculated. in, Indicates the similarity between the patient in the i-th historical data and the current patient, Indicates the age similarity between the i-th historical data patient and the current patient, Indicates the degree of similarity between the disease of the i-th historical data patient and the current patient, Indicates the similarity between the medication usage of the i-th historical data patient and the current patient. It represents the average similarity between the i-th historical data patient and the current patient in these aspects. When the historical data corresponds to the patient with a high similarity to the current patient, it is considered that the historical data can reflect the abnormal coagulation process of the current patient. Therefore, all target data that can reflect the coagulation condition of the current patient are screened out.

[0047] S2.2, obtaining a normal range of the coagulation index based on the relationship between the thromboelastogram and the coagulation index of the patient in the target data.

[0048] Because different coagulation indicators are influenced by individual patient characteristics, they may indicate different degrees of abnormal coagulation. This means that for some patients, even if a single coagulation indicator has significant deviations, the coagulation process may still be normal. For example, a neonatal INR of 1.5-2.0 is still normal and does not require intervention. Therefore, we first determine the degree to which each coagulation indicator reflects the normal state of the patient's coagulation process based on the correlation between each coagulation indicator in the target data and the thromboelastogram (TEL) changes. This allows us to identify coagulation indicators with a significant impact on the patient's coagulation process.

[0049] Because when a patient's coagulation process is normal, the patient's coagulation index data should be within the normal range. Therefore, the coagulation index data of patients with normal coagulation process should be relatively concentrated. However, there are many factors that lead to abnormal coagulation in patients and the impact is different. Therefore, the coagulation index data of patients with abnormal coagulation are relatively different. Therefore, by clustering the coagulation index data obtained through screening in the target data, a patient data set with normal coagulation process is obtained, and based on this, the normal range of coagulation index for the current patient is obtained.

[0050] First, based on the patient's thromboelastogram in the target data, record the R time, K time, α angle, MA value and Ly30 data on the curve. By analyzing the correlation between these data and coagulation indicators, calculate the degree of response of each coagulation indicator to the patient's coagulation process. The specific process is: (1) Draw the thromboelastogram parameters and coagulation indicator coordinate diagram. Here, the R time in the thromboelastogram and the INR in the coagulation indicator are taken as examples: a) Normalize the R time data and the INR data. Because the INR data itself is a standardized ratio data, no further processing is required here. Only the R time data needs to be normalized: in, Represents the normalized value of the i-th R time data, Indicates the original data value of R time, Indicates the maximum value of R time, Indicates the minimum R time.

[0051] b) Draw a coordinate graph with the INR value as the horizontal axis and the R time as the vertical axis, and place the corresponding values of all target data into the coordinates.

[0052] c) Unify the correspondence between the horizontal and vertical coordinate values in the coordinate graph. Because there may be certain differences between different patient data, there may be multiple vertical coordinate values corresponding to one horizontal coordinate. In order to avoid this situation affecting subsequent analysis, it is necessary to unify the correspondence between the horizontal and vertical coordinate values in the coordinate graph. Divide the horizontal coordinate into 100 segments evenly, use the coordinate value of the center point of each segment as the horizontal coordinate value, and use the average value of all the vertical coordinate data corresponding to the horizontal coordinate segment as the vertical coordinate value corresponding to the center point. In this way, the horizontal coordinate data and the vertical coordinate data correspond one-to-one, and the "INR-R time" coordinate graph is obtained.

[0053] (2) Use the least squares method to fit the data in the coordinate graph to obtain the fitting curve.

[0054] (3) Calculate the degree of influence of the INR coagulation index on the R time based on the slope of the fitting curve. First, if the INR coagulation index has a strong correlation with the R time, then the slope value of each point on the fitting curve should be relatively consistent. At the same time, the larger the absolute value of the overall slope of the fitting curve, the greater the influence of the change in the INR value on the R time, that is, a small change in the INR value can cause a significant change in the R time. Therefore, 20 points (empirical values) are evenly selected on the fitting curve, and the degree of influence of the INR coagulation index on the R time is calculated based on their slope characteristics: in, Indicates the degree of influence of INR coagulation index on R time, Indicates the number of selected points on the fitting curve, here , Indicates the slope value of the oth point on the "INR-R time" fitting curve, It represents the absolute value of the slope difference between two adjacent points on the fitting curve. The smaller the absolute value of the slope difference is, the more consistent the slopes are at different positions on the curve, and the higher the correlation between the INR coagulation index and the R time is. The average slope of different points on the fitting curve represents the overall trend of the fitting curve. The larger the absolute value of the average slope, the greater the impact of INR on R time.

[0055] (4) Repeat the above steps (1) to (3) to calculate the influence of INR coagulation index on K time, α angle, MA value and Ly30 value respectively. 、 、 、 .

[0056] (5) Calculate the degree to which INR reflects the patient's coagulation process. If INR has a significant effect on multiple parameters in the thromboelastogram (TEG), then the degree to which INR reflects the patient's coagulation process is stronger. The degree to which INR reflects the patient's coagulation process is calculated as follows: in, Indicates the degree to which INR responds to the patient's coagulation process. Indicates the degree of influence of INR coagulation index on R time, Indicates the degree of influence of INR coagulation index on K time, Indicates the degree of influence of INR coagulation index on α angle, Indicates the degree of influence of INR coagulation index on MA value, Indicates the degree of influence of INR coagulation index on Ly30 value. The average value of the corresponding influence degrees of all parameters in the thromboelastogram was used as the response degree of INR to the coagulation process of the patient.

[0057] (6) According to the above method, the degree of reflection of all coagulation indicators in the standard coagulation test on the patient's coagulation process is obtained respectively. According to the corresponding reflection degree, the three coagulation indicators with the highest reflection degree are considered to be the coagulation indicators that have a significant impact on the patient's coagulation process.

[0058] After screening through the above steps, the three coagulation indices obtained are the three most closely related to the patient's coagulation process and are considered the target coagulation indices. Therefore, the three coagulation index data for patients with normal coagulation should all be within the normal range. Normal data are all concentrated in the same range, while abnormal coagulation data usually have different abnormal manifestations due to different influencing factors. Therefore, the three target coagulation indices are used as the x-axis, y-axis, and z-axis, respectively, to draw a coordinate system, and all target historical patient data are placed in the coordinate system. The DBSCAN clustering method is used to cluster the data in the coordinate system. Clustering will obtain multiple clusters and single-point data. The single-point noise data is excluded, and the cluster data with the highest density among all clusters is obtained as the normal patient data.

[0059] The normal range of the target coagulation index corresponding to the patient is determined based on the maximum and minimum values of the target coagulation index corresponding to the patient in the data of the patient with normal coagulation.

[0060] S3, calculating the degree of abnormal coagulation of the current patient according to the normal range of the coagulation index of the current patient.

[0061] Use standard coagulation test to obtain the coagulation index data of the current patient. If the target coagulation index data of the current patient is within the normal range obtained in the above steps, the abnormality of the coagulation index is recorded as Otherwise, the degree of abnormality is calculated based on the degree of deviation of the current patient data from the normal range: in, Indicates the abnormality of the u-th target coagulation index of the current patient, Indicates the corresponding value of the u-th target coagulation index of the current patient, Indicates the minimum value of the normal range of the u-th target coagulation index, Indicates the maximum value of the normal range of the u-th target coagulation index. represents the minimum function.

[0062] The abnormal degree of the patient's coagulation under each target coagulation index is comprehensively calculated to calculate the current abnormal degree of the patient's coagulation: in, Indicates the current patient's coagulation abnormality level. Indicates the number of target coagulation indicators, here , Indicates the abnormality of the u-th target coagulation index of the current patient.

[0063] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A method for identifying abnormalities in the coagulation process based on big data analysis, characterized in that: include: Obtain the current patient's coagulation index data through standard coagulation testing, and use TEG equipment to obtain the current patient's thromboelastogram; obtain the similarity between the patient's age, disease background, and medication use in historical data and the characteristics of the current patient, and then filter out target data that reflects the current patient's coagulation status; According to the correlation between each coagulation index data and the thromboelastogram changes in the target data, the reflection degree value of each coagulation index data on the normal state of the current patient's coagulation process is obtained, and all the reflection degree data are sorted, and several coagulation indexes with the highest reflection degree are selected as coagulation indexes that have a significant impact on the patient's coagulation process; based on the several coagulation indexes with the highest reflection degree obtained, they are regarded as target coagulation indexes, and a coordinate system is drawn according to the target coagulation index, all target historical patient data are placed in the coordinate system, the data of the coordinate system are clustered, and the clustered data with the highest density is obtained as normal patient data, and then the normal range of the target coagulation index is determined; it is judged whether the coagulation index data of the current patient is within the normal range of the target coagulation index. If not, the deviation degree of the current patient's coagulation index data from the normal range of the target coagulation index is obtained based on the maximum and minimum values of the current patient's coagulation index data and the normal range of the target coagulation index, and then the degree of coagulation abnormality of the current patient is obtained.

2. The method for identifying abnormalities in the coagulation process based on big data analysis according to claim 1, characterized in that: The parameters included in the thromboelastogram are: R time, K time, α angle, MA value and Ly30; among them, R time is the time from liquid blood to fibrin formation; K time is the time from coagulation to reaching a certain strength; α angle is the fibrin generation rate; MA value is the final strength of the blood clot; Ly30 is the thrombus degradation rate within 30 minutes; the coagulation index data include prothrombin time PT, international normalized ratio INR, activated partial thromboplastin time APTT, thrombin time TT, fibrinogen FIB and D-dimer and platelet count PLT.

3. The method for identifying abnormalities in the coagulation process based on big data analysis according to claim 2, characterized in that: The acquisition of the similarity between the age, disease background, and medication use of the patient in the historical data and the characteristics of the current patient is specifically as follows: the degree of similarity of the patient age is obtained based on the difference between the age of the patient in the historical data and the age of the current patient, specifically as follows: in, Indicates the age similarity between the i-th historical data patient and the current patient, represents the age of the i-th patient in the historical data, Indicates the age of the current patient, represents the absolute value of the age difference between the i-th patient in the historical data and the current patient; This means that the smaller the absolute value of the age difference is, the higher the age similarity is; Make sure the fraction is meaningful and The similarity of the patient's disease background is calculated based on the degree of disease overlap between the patient in the historical data and the current patient. If the patient in the historical data has the same disease as the current patient, the similarity is high; if the patient in the historical data has the corresponding disease but the current patient does not, the similarity is low. If the patient in the historical data and the current patient both have or do not have a certain disease, then it is counted; otherwise, it is not counted. Thus, the similarity of the disease background between the patient in the historical data and the current patient is calculated as follows: in, Indicates the degree of similarity between the disease of the i-th historical data patient and the current patient, Indicates the total number of diseases that affect coagulation indicators. = represents the count value of the dth disease corresponding to the i-th historical data patient; the similarity of the patient's drug use is calculated in the same way as the disease similarity; if the patient in the historical data takes or does not take a certain drug at the same time as the current patient, the count is 1; if the patient in the historical data takes a certain drug but the current patient does not take it, the count is 0. The similarity between the drug use of the patient in the historical data and the current patient is calculated as follows: in, Indicates the similarity between the medication usage of the i-th historical data patient and the current patient, Indicates the total number of drugs that affect coagulation indicators. Indicates the count value of the bth drug corresponding to the i-th historical data patient.

4. The method for identifying abnormalities in the coagulation process based on big data analysis according to claim 3, characterized in that: The target data reflecting the coagulation condition of the current patient is screened out as follows: combining the similarities between the patients in the historical data and the current patient in terms of age, disease, and medication, obtaining a similarity value between the patient in each historical data and the current patient; judging whether the obtained similarity value is greater than a set threshold; if so, it is considered that the patient corresponding to the historical data and the current patient have a high similarity, and the abnormal coagulation process of the current patient can be reflected through the coagulation process of the patient corresponding to the historical data, and all target data that can reflect the coagulation condition of the current patient are screened out; obtaining a similarity value between the patient in each historical data and the current patient is specifically as follows: in, Indicates the similarity between the patient in the i-th historical data and the current patient.

5. The method for identifying abnormalities in the coagulation process based on big data analysis according to claim 4, characterized in that: The correlation between each coagulation index data in the target data and the change of the thromboelastogram is specifically as follows: Step 1: Select any coagulation index data in the target data and any parameter in the thromboelastogram, and normalize the selected coagulation index data and parameter respectively; Step 2: Use the normalized coagulation index data as the horizontal coordinate and the parameter as the vertical coordinate, and regard the values corresponding to all target data as data and put them into the coordinate; Step 3: Evenly divide the horizontal coordinate into several segments, use the coordinate value of the center point of each segment as the horizontal coordinate value, use the average value of all vertical coordinate data corresponding to the horizontal coordinate segment as the vertical coordinate value corresponding to the center point, and compare the horizontal coordinate data with the vertical coordinate data. According to the one-to-one correspondence, a coagulation index data-parameter coordinate diagram is obtained; Step 4: The data in the coordinate diagram is fitted using the least squares method to obtain a fitting curve; Step 5: According to the slope of the fitting curve, the degree of influence of the coagulation index data on the parameter is obtained; Step 6: Repeat steps 1 to 5 to respectively obtain the degree of influence of the coagulation index data on other parameters in the thromboelastogram; Step 7: Based on the degree of influence of the coagulation index data on all parameters in the thromboelastogram, the degree of reflection of the coagulation index data on the patient's coagulation process is obtained; Step 8: Repeat steps 1 to 7 to obtain the degree of reflection of all coagulation index data in the target data on the patient's coagulation process.

6. The method for identifying abnormalities in the coagulation process based on big data analysis according to claim 5, characterized in that: The influence of the coagulation index data on the parameter is obtained according to the slope of the fitting curve. Specifically, taking the coagulation index data INR in the target data and the parameter R time in the thromboelastogram as an example, in, Indicates the influence of coagulation index data INR on R time, Indicates the number of selected points on the fitting curve, Indicates the slope value of the oth point on the "INR-R time" fitting curve, It represents the absolute value of the slope difference between two adjacent points on the fitting curve. The smaller the absolute value of the slope difference, the more consistent the slopes at different positions on the curve, and the higher the correlation between the INR coagulation index and the R time; The average slope of different points on the fitting curve represents the overall trend of the fitting curve. The larger the absolute value of the average slope, the greater the influence of INR on R time. The degree of reflection of the coagulation index data on the patient's coagulation process is obtained based on the influence of the coagulation index data on all parameters in the thromboelastogram. Specifically, the influence degrees of the coagulation index data on all parameters in the thromboelastogram are added and averaged, and the obtained average value is used as the reflection degree of the coagulation index data on the patient's coagulation process.

7. The method for identifying abnormalities in the coagulation process based on big data analysis according to claim 6, characterized in that: The coordinate system is drawn according to the target coagulation index, all target historical patient data are placed in the coordinate system, the data of the coordinate system are clustered, and the clustered data with the highest density are taken as normal patient data, and then the normal range of the target coagulation index is determined. Specifically, the obtained target coagulation index is regarded as the index most closely related to the patient's coagulation process, so the target coagulation index of patients with normal coagulation should be within the normal range; normal data are all concentrated in the same range, and abnormal coagulation data are usually due to different factors causing their abnormalities, and the abnormal manifestations are also quite different; so the coordinate system is drawn according to the target coagulation index, all target historical patient data are placed in the coordinate system, and the clustered data with the highest density are taken as normal patient data, and then the normal range of the target coagulation index is determined. coordinate system; wherein, the target historical patient data is the data that is screened out and has a high similarity with the current patient's characteristics; the data with a high similarity refers to the data that are similar in age, disease background and medication between the patients in the historical data and the current patient, and can reflect the coagulation status of the current patient; the DBSCAN clustering method is used to cluster the data in the coordinate system, and then multiple clusters and single-point data are obtained, and the single-point noise data is excluded to obtain the cluster data with the highest density in all clusters as the normal patient data; according to the maximum and minimum values of the corresponding target coagulation index in the normal coagulation patient data, the normal range of the target coagulation index corresponding to the patient is determined.

8. The method for identifying abnormalities in the coagulation process based on big data analysis according to claim 7, characterized in that: According to the maximum and minimum values of the current patient's coagulation index data and the target coagulation index normal range, the deviation degree of the current patient's coagulation index data from the target coagulation index normal range is obtained. Specifically, if the current patient's target coagulation index data is within the target coagulation index normal range, the abnormal degree of the coagulation index is recorded as Otherwise, the degree of abnormality is calculated based on the degree of deviation of the current patient data from the normal range: in, Indicates the abnormality of the u-th target coagulation index of the current patient, Indicates the corresponding value of the u-th target coagulation index of the current patient, Indicates the minimum value of the normal range of the u-th target coagulation index, represents the maximum value of the normal range of the u-th target coagulation index; represents the minimum function.

9. The method for identifying abnormalities in the coagulation process based on big data analysis according to claim 8, characterized in that: The method of obtaining the abnormal coagulation degree of the current patient is as follows: comprehensively analyzing the abnormality degree of each target coagulation index of the patient and calculating the abnormal coagulation degree of the current patient. in, Indicates the current patient's coagulation abnormality level. Indicates the number of target coagulation indicators, Indicates the abnormality of the u-th target coagulation index of the current patient.

10. The abnormality identification system in the coagulation process based on big data analysis is characterized by: include: a first acquisition module, wherein the first acquisition module obtains the coagulation index data of the current patient through a standard coagulation test and obtains the thromboelastogram of the current patient using a TEG device; a second acquisition module, which obtains the similarity between the age, disease background, and medication use of the patient in the historical data and the characteristics of the current patient, and then filters out target data reflecting the coagulation status of the current patient; a selection module, wherein the selection module obtains a numerical value of the degree of reflection of each coagulation index data on the normal state of the current patient's coagulation process based on the correlation between each coagulation index data in the target data and the thromboelastogram change, and sorts all the reflection degree data to select several coagulation indexes with the highest reflection degree as coagulation indexes that have a significant impact on the patient's coagulation process; a clustering module, wherein the clustering module regards the several coagulation indexes with the highest reflection degree as target coagulation indexes based on the obtained coagulation indexes, draws a coordinate system according to the target coagulation index, puts all target historical patient data into the coordinate system, clusters the data of the coordinate system, and obtains the cluster data with the highest density as normal patient data, thereby determining the normal range of the target coagulation index; a judgment module, wherein the judgment module determines whether the coagulation index data of the current patient is within the normal range of the target coagulation index. If not, the judgment module obtains the degree of deviation of the coagulation index data of the current patient from the normal range of the target coagulation index based on the maximum and minimum values of the coagulation index data of the current patient and the normal range of the target coagulation index, thereby obtaining the degree of coagulation abnormality of the current patient.

Images