Acute Kidney Injury Detection Method and System Based on Missing Data

Abstract

The present invention relates to the field of medical diagnosis technology, and particularly to a method and system for detecting acute kidney injury based on missing data. The present invention obtains the preoperative creatinine abnormality degree according to the difference in serum creatinine data between the patient to be tested and similar patients during the preoperative analysis period, and obtains the initial postoperative creatinine abnormality degree according to the change rate and prominence of the serum creatinine data at each moment during the postoperative analysis period of the patient to be tested; based on the difference between the preoperative creatinine abnormality degree and the initial postoperative creatinine abnormality degree, and the difference between the blood loss and the blood transfusion volume, the final postoperative creatinine abnormality degree is obtained, and the acute kidney injury of the patient to be tested is detected by combining the preoperative creatinine abnormality degree and the total urine volume during the postoperative analysis period. The present invention reduces the influence of cardiopulmonary bypass on the postoperative serum creatinine abnormality degree according to the changes in the serum creatinine abnormality degree before and after surgery and the difference between the blood loss and the blood transfusion volume, and combines the preoperative creatinine abnormality degree and the urine volume to improve the accuracy of detecting acute kidney injury in the patient to be tested.

Description

Technical Field

[0001] The present invention relates to the technical field of medical diagnosis, and particularly to a method and system for detecting acute kidney injury based on missing data. Background Art

[0002] Acute Kidney Injury (AKI) refers to a clinical syndrome caused by a sudden decline in renal function within a short period of time. During cardiothoracic surgery, cardiopulmonary bypass (CPB) technology is often used to maintain the vital signs of patients when the heart stops beating. However, the hemodynamic changes, continuous blood anticoagulation, and reperfusion injury after tissue ischemia caused by CPB technology can induce various postoperative complications; acute kidney injury is a relatively common and serious complication after cardiothoracic surgery. Therefore, detecting acute kidney injury in patients after cardiothoracic surgery helps to ensure the life safety of patients.

[0003] Existing methods usually determine acute kidney injury based on changes in serum creatinine levels and urine output in patients after cardiothoracic surgery; however, due to the possible changes in blood volume in patients during CPB in cardiothoracic surgery, the postoperative serum creatinine concentration cannot accurately reflect the renal injury of patients, resulting in a low accuracy of detecting acute kidney injury. Summary of the Invention

[0004] In order to solve the technical problem that the serum creatinine concentration cannot accurately reflect the renal injury during surgery due to CPB, resulting in a low accuracy of detecting acute kidney injury, the purpose of the present invention is to provide a method and system for detecting acute kidney injury based on missing data, and the specific technical solutions adopted are as follows:

[0005] In a first aspect, an embodiment of the present invention provides a method for detecting acute kidney injury based on missing data, the method comprising:

[0006] Obtaining serum creatinine data of the patient to be tested and similar patients at each moment during the preoperative analysis period, as well as the blood loss, blood transfusion volume during surgery, total urine output during the postoperative analysis period, and serum creatinine data at each moment of the patient to be tested;

[0007] Obtaining the preoperative creatinine abnormality degree according to the difference in serum creatinine data of the patient to be tested and similar patients during the preoperative analysis period; obtaining the initial postoperative creatinine abnormality degree according to the change rate of the serum creatinine data at each moment during the postoperative analysis period of the patient to be tested, and the prominence of the position at each moment and the serum creatinine data;

[0008] Obtain the final postoperative creatinine abnormality degree based on the difference between the preoperative creatinine abnormality degree and the initial postoperative creatinine abnormality degree, as well as the difference between the intraoperative blood loss and blood transfusion volume of the patient to be tested.

[0009] Perform acute kidney injury detection on the patient to be tested based on the preoperative creatinine abnormality degree, the final postoperative creatinine abnormality degree, and the total urine volume of the patient to be tested during the postoperative analysis period.

[0010] Further, the obtaining of the preoperative creatinine abnormality degree includes:

[0011] Record the patient to be tested and similar patients as analysis patients, and respectively record the mean and variance of the serum creatinine data at all times during the preoperative analysis period of each analysis patient as the creatinine overall value and creatinine dispersion value of the corresponding analysis patient;

[0012] Obtain the creatinine overall difference value between the patient to be tested and each similar patient based on the difference in the creatinine overall value and the difference in the creatinine dispersion value between the patient to be tested and each similar patient;

[0013] Perform negative correlation and normalization processing on the sum of the creatinine overall difference values of the patient to be tested and all similar patients to obtain the preoperative creatinine abnormality degree.

[0014] Further, the obtaining of the initial postoperative creatinine abnormality degree includes:

[0015] Take the ratio of the result of normalizing the difference between the serum creatinine data of the patient to be tested at each moment and the previous adjacent moment during the postoperative analysis period to the time interval as the abnormality index of the serum creatinine data at each moment during the postoperative analysis period;

[0016] Obtain the creatinine weight at each moment during the postoperative analysis period based on the prominence of the serum creatinine data of the patient to be tested at each moment, the time interval between each moment and the previous adjacent moment, and the position of each moment during the postoperative analysis period;

[0017] Perform weighted summation on the abnormality indexes of the serum creatinine data at all times during the postoperative analysis period according to the creatinine weight, and perform normalization processing on the result of the weighted summation to obtain the initial postoperative creatinine abnormality degree.

[0018] Further, the obtaining of the creatinine weight at each moment during the postoperative analysis period includes:

[0019] Arrange the serum creatinine data at all times within the local preset time period at each moment during the postoperative analysis period of the patient to be tested in chronological order to obtain the local creatinine sequence at each moment during the postoperative analysis period; obtain the first-order difference sequence of the local creatinine sequence, and normalize the mean value of all elements in the first-order difference sequence to obtain the prominent index of the serum creatinine data at each moment during the postoperative analysis period;

[0020] Take the time interval between each moment during the postoperative analysis period and the previous adjacent moment as the time error index at each moment during the postoperative analysis period;

[0021] Take the time interval between the start moment of the postoperative analysis period and each moment as the postoperative duration at each moment during the postoperative analysis period;

[0022] According to the prominent index, the time error index and the postoperative duration, obtain the creatinine weight at each moment during the postoperative analysis period; the prominent index, the time error index and the postoperative duration are all positively correlated with the creatinine weight.

[0023] Further, the obtaining of the final postoperative creatinine abnormality degree includes:

[0024] Normalize the difference between the initial postoperative creatinine abnormality degree and the preoperative creatinine abnormality degree to obtain the change value of creatinine abnormality before and after;

[0025] Normalize the difference between the blood transfusion volume and the blood loss volume during the operation of the patient to be tested to obtain the extracorporeal circulation influence value;

[0026] According to the change value of creatinine abnormality before and after and the extracorporeal circulation influence value, obtain the final postoperative creatinine abnormality degree; the change value of creatinine abnormality before and after is positively correlated with the final postoperative creatinine abnormality degree, and the extracorporeal circulation influence value is negatively correlated with the final postoperative creatinine abnormality degree.

[0027] Further, the detecting of acute kidney injury for the patient to be tested according to the preoperative creatinine abnormality degree, the final postoperative creatinine abnormality degree and the total urine volume of the patient to be tested during the postoperative analysis period includes:

[0028] Perform a negative correlation mapping on the total urine volume during the postoperative analysis period of the patient to be tested, and normalize the product of the preoperative creatinine abnormality degree, the final postoperative creatinine abnormality degree and the mapping result to obtain the kidney injury risk index;

[0029] Based on the kidney injury risk index, perform acute kidney injury detection on the patient to be tested.

[0030] Further, obtaining the overall creatinine difference value between the patient to be tested and each similar patient according to the difference between the overall creatinine value and the discrete creatinine value of the patient to be tested and each similar patient includes:

[0031] Taking the product of the absolute value of the difference between the overall creatinine values of the patient to be tested and each similar patient and the absolute value of the difference between the discrete creatinine values as the overall creatinine difference value between the patient to be tested and each similar patient.

[0032] Further, the duration of the local preset time period is less than the duration of the postoperative analysis time period.

[0033] Further, the duration of the preoperative analysis time period is less than the duration of the postoperative analysis time period.

[0034] In a second aspect, another embodiment of the present invention provides an acute kidney injury detection system based on missing data, and the system includes:

[0035] A data acquisition module, configured to obtain the serum creatinine data of the patient to be tested and similar patients at each moment during the preoperative analysis time period, as well as the blood loss, blood transfusion volume of the patient to be tested during the operation, and the total urine volume and the serum creatinine data at each moment during the postoperative analysis time period;

[0036] A creatinine initial abnormality analysis module, configured to obtain the preoperative creatinine abnormality degree according to the difference in the serum creatinine data of the patient to be tested and similar patients during the preoperative analysis time period; and obtain the initial postoperative creatinine abnormality degree according to the change rate of the serum creatinine data of the patient to be tested at each moment during the postoperative analysis time period and the prominence of the position at each moment and the serum creatinine data;

[0037] A creatinine final abnormality analysis module, configured to obtain the final postoperative creatinine abnormality degree according to the difference between the preoperative creatinine abnormality degree and the initial postoperative creatinine abnormality degree, and the difference between the blood loss and blood transfusion volume of the patient to be tested during the operation;

[0038] A kidney injury detection module, configured to perform acute kidney injury detection on the patient to be tested according to the preoperative creatinine abnormality degree, the final postoperative creatinine abnormality degree, and the total urine volume of the patient to be tested during the postoperative analysis time period.

[0039] The present invention has the following beneficial effects:

[0040] In the embodiments of the present invention, the preoperative creatinine abnormality degree analyzes the risk of the patient to be tested suffering from acute kidney injury after surgery from the preoperative perspective; the change rate of the serum creatinine data at each moment during the postoperative analysis period reflects the abnormality degree of the serum creatinine data, and the position of each moment and the prominence degree of the serum creatinine data present the importance of the serum creatinine data at each moment for analyzing the abnormality degree of the postoperative serum creatinine data. By combining the above factors to analyze the overall abnormality degree of the postoperative serum creatinine data, the initial postoperative creatinine abnormality degree is obtained; compared with simply analyzing the abnormality degree based on the serum creatinine data of the patient to be tested after surgery, the difference between the preoperative creatinine abnormality degree and the initial postoperative creatinine abnormality degree can more prominently reflect the abnormality degree of the postoperative serum creatinine data. At the same time, by combining the difference between the blood loss and blood transfusion volume caused by cardiopulmonary bypass during the operation for analysis, the influence of the change in the patient's blood volume caused by cardiopulmonary bypass during the operation on the abnormality degree of the postoperative serum creatinine data is reduced, so that the final postoperative creatinine abnormality degree can more accurately reflect the risk of the patient to be tested suffering from acute kidney injury after surgery. This solution analyzes the abnormality degree of the serum creatinine data of the patient to be tested from two perspectives of before and after surgery, considers the risk of the patient to be tested suffering from acute kidney injury after surgery, and the final postoperative creatinine abnormality degree reduces the influence of cardiopulmonary bypass on the abnormality analysis. At the same time, by combining the total urine volume reflecting acute kidney injury, the accuracy of detecting acute kidney injury in the patient to be tested is greatly improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required to be used in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0042] Figure 1 It is a flowchart of the steps of a method for detecting acute kidney injury based on missing data provided by an embodiment of the present invention;

[0043] Figure 2 It is a flowchart of the steps of a method for obtaining the initial postoperative creatinine abnormality degree provided by an embodiment of the present invention;

[0044] Figure 3 It is a system structure diagram of a system for detecting acute kidney injury based on missing data provided by an embodiment of the present invention;

[0045] Figure 4 It is a schematic diagram of a computer device of a device for detecting acute kidney injury based on missing data provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0046] To further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following specifically describes, in conjunction with the accompanying drawings and preferred embodiments, the method and system for detecting acute kidney injury based on missing data proposed according to the present invention, its specific implementation manner, structure, features, and effects. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0047] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which this invention belongs.

[0048] The following specifically describes, in conjunction with the accompanying drawings, the specific solutions of the method and system for detecting acute kidney injury based on missing data provided by the present invention.

[0049] Embodiment 1:

[0050] The present invention proposes a method for detecting acute kidney injury based on missing data. Please refer to Figure 1 , which shows the step flowchart of a method for detecting acute kidney injury based on missing data provided by an embodiment of the present invention. The method includes:

[0051] Step S1: Obtain the serum creatinine data of the patient to be tested and similar patients at each moment during the preoperative analysis period, as well as the blood loss, blood transfusion volume during the operation, and total urine volume during the postoperative analysis period of the patient to be tested and the serum creatinine data at each moment.

[0052] Before the patient to be tested undergoes cardiothoracic surgery, collect the basic information of the patient to be tested; select the basic information of patients who have undergone cardiothoracic surgery and developed acute kidney injury after the operation from the hospital's medical record database, and record these patients as candidate patients. Among them, the attributes of the basic information include: age, gender, smoking years, drinking years, disease, and type of surgery; age, smoking years, and drinking years are numerical data; gender, disease, and type of surgery are text data.

[0053] To analyze the risk of the patient to be tested developing acute kidney injury after cardiothoracic surgery, select candidate patients similar to the basic information of the patient to be tested as similar patients of the patient to be tested. The specific method for obtaining similar patients is as follows:

[0054] The patient to be tested and the candidate patient are denoted as target patients, and the difference degree of each attribute of the patient to be tested and the candidate patient is obtained; if the basic information of each attribute of the target patient is text data, the basic information of each attribute of the target patient is converted into word vectors, and the DTW value of the word vectors of each attribute of the patient to be tested and the candidate patient is calculated as the difference degree of the corresponding attribute; if the basic information of each attribute of the target patient is numerical data, the absolute value of the difference between the basic information of each attribute of the patient to be tested and the candidate patient is used as the difference degree of the corresponding attribute; the sum of the difference degrees of all attributes of the patient to be tested and the candidate patient is normalized to obtain the overall difference degree between the patient to be tested and the candidate patient. Among them, the Dynamic Time Warping (DTW) algorithm is a well-known technology to those skilled in the art and will not be elaborated here.

[0055] Since the smaller the overall difference degree is, the higher the similarity of the basic information between the patient to be tested and the candidate patient is, the candidate patient corresponding to the overall difference degree less than the preset similarity threshold is denoted as the similar patient of the patient to be tested.

[0056] It should be noted that in the embodiment of the present invention, the bag-of-words model is selected to convert the text data into word vectors, the normalization method is the Norm function, and the preset similarity threshold takes the empirical value of 0.3, and the implementer can set it according to the specific situation; in other embodiments, technologies such as TF-IDF and Word2Vec can also be selected for word vector conversion, and normalization methods such as function conversion and maximum-minimum normalization. Among them, the bag-of-words model is a well-known technology to those skilled in the art and will not be elaborated here.

[0057] Serum creatinine level is an important indicator to measure renal function. Creatinine is a metabolite produced by muscle metabolism and is mainly excreted through the kidneys. The creatinine level in plasma reflects the filtration function of the kidneys. The 24 hours before the patient undergoes cardiothoracic surgery and the 48 hours after the surgery are denoted as the preoperative analysis period and the postoperative analysis period respectively; the patient to be tested and its similar patient are denoted as the analysis patients. The serum creatinine concentration of the blood samples of the analysis patients is randomly collected N1 times during the preoperative analysis period using a colorimetric analyzer, and is denoted as the serum creatinine data of each moment of the analysis patients during the preoperative analysis period. The serum creatinine concentration of the blood samples of the patient to be tested is randomly collected N2 times during the postoperative analysis period using a colorimetric analyzer, and is denoted as the serum creatinine data of each moment during the postoperative analysis period.

[0058] It should be noted that since the serum creatinine data in the postoperative analysis period is more important for detecting acute kidney injury in the patient to be tested than that in the preoperative analysis period, the duration of the preoperative analysis period is less than that of the postoperative analysis period, and N1 is less than N2, where both N1 and N2 are positive integers. Among them, N1 takes the empirical value of 3, and N2 takes the empirical value of 50. The implementer can set it according to the specific situation. Because the serum creatinine data in the postoperative analysis period is randomly collected, there are differences in the time intervals between different adjacent moments in the postoperative analysis period.

[0059] During the cardiothoracic surgery of the patient to be tested, the amount of blood input into the patient to be tested during extracorporeal circulation is measured and recorded as the intraoperative blood transfusion volume, and the blood loss of the patient is measured and recorded as the intraoperative blood loss volume; the total urine volume of the patient to be tested in the postoperative analysis period is collected.

[0060] Step S2: Obtain the preoperative creatinine abnormality degree according to the difference in serum creatinine data between the patient to be tested and the similar patients in the preoperative analysis period; obtain the initial postoperative creatinine abnormality degree according to the change rate of the serum creatinine data at each moment in the postoperative analysis period of the patient to be tested, and the prominence of the serum creatinine data at each moment.

[0061] The similar patients of the patient to be tested have acute kidney injury after cardiothoracic surgery. The difference in serum creatinine data between the patient to be tested and the similar patients in the preoperative analysis period reflects the risk of the patient to be tested having acute kidney injury after surgery, thereby reflecting the abnormal degree of the serum creatinine data of the patient to be tested in the preoperative analysis period, and obtaining the preoperative creatinine abnormality degree.

[0062] Preferably, in some possible implementation manners of the embodiment of the present invention, the method for obtaining the preoperative creatinine abnormality degree includes: recording the patient to be tested and the similar patients as analysis patients, and respectively recording the mean value and variance of the serum creatinine data at all moments in the preoperative analysis period of each analysis patient as the creatinine overall value and creatinine discrete value of the corresponding analysis patient; obtaining the creatinine overall difference value between the patient to be tested and each similar patient according to the difference in the creatinine overall value and the difference in the creatinine discrete value between the patient to be tested and each similar patient; performing negative correlation and normalization processing on the sum of the creatinine overall difference values between the patient to be tested and all similar patients to obtain the preoperative creatinine abnormality degree.

[0063] The creatinine overall value reflects the overall level of the serum creatinine data of the analysis patient in the preoperative analysis period, and the creatinine discrete value reflects the discrete degree of the serum creatinine data of the analysis patient in the preoperative analysis period. In this embodiment, the difference in the serum creatinine data between the patient to be tested and the similar patients is measured by the creatinine overall value and the creatinine discrete value. The calculation method of the specific difference situation is: taking the product of the absolute value of the difference between the creatinine overall values of the patient to be tested and each similar patient and the absolute value of the difference between the creatinine discrete values as the creatinine overall difference value between the patient to be tested and each similar patient.

[0064] If the overall difference value of creatinine between the patient to be tested and all similar patients is smaller, it indicates that the preoperative serum creatinine level of the patient to be tested is closer to the preoperative serum creatinine level of similar patients with acute kidney injury after surgery. The higher the risk of the patient to be tested having acute kidney injury after surgery, the greater the degree of abnormality of the serum creatinine data of the patient to be tested during the preoperative analysis period, and the greater the preoperative creatinine abnormality degree.

[0065] In a specific implementation manner of the embodiment of the present invention, the preoperative creatinine abnormality degree is expressed by the formula:

[0066]

[0067] In the formula, is the preoperative creatinine abnormality degree; is the overall value of creatinine of the patient to be tested; is the overall value of creatinine of the a-th similar patient of the patient to be tested; LS is the discrete value of creatinine of the patient to be tested; is the discrete value of creatinine of the a-th similar patient of the patient to be tested; is the overall difference value of creatinine between the patient to be tested and the a-th similar patient; is the absolute value function; exp is the exponential function with the natural constant as the base. It should be noted that in this embodiment, the exponential function with the natural constant as the base is selected to perform negative correlation and normalization processing on

[0068] The change rate of the serum creatinine data at each moment during the postoperative analysis period reflects the degree of abnormality of the serum creatinine data at each moment. The position of each moment and the prominence degree of the serum creatinine data present the importance of the serum creatinine data at each moment for analyzing the degree of abnormality of the postoperative serum creatinine data. Combining the above factors to analyze the overall abnormality degree of the postoperative serum creatinine data, the initial postoperative creatinine abnormality degree is obtained.

[0069] Please refer to Figure 2 , which shows the step flowchart of a method for obtaining the initial postoperative creatinine abnormality degree provided by an embodiment of the present invention. The method includes:

[0070] Step S210: Use the ratio of the result of normalizing the difference between the serum creatinine data of the patient to be tested at each moment and the previous adjacent moment during the postoperative analysis period to the time interval as the abnormality index of the serum creatinine data at each moment during the postoperative analysis period.

[0071] It is known that when the kidney function is damaged, the filtration function of the kidney will decline, resulting in an increase in the plasma creatinine level.

[0072] If the degree of increase in the serum creatinine data of the patient to be tested at each moment in the postoperative analysis period compared to the previous adjacent moment is greater, it indicates that the decline rate of the renal physiological function of the patient to be tested at each moment is faster, the degree of abnormality of the serum creatinine data at each moment in the postoperative analysis period is greater, and the abnormality index of the serum creatinine data at each moment is greater.

[0073] Step S220: Obtain the creatinine weight at each moment in the postoperative analysis period according to the prominence degree of the serum creatinine data of the patient to be tested at each moment in the postoperative analysis period, the time interval between each moment and the previous adjacent moment, and the position of each moment in the postoperative analysis period.

[0074] Preferably, in some possible implementation manners of the embodiments of the present invention, the method for obtaining the creatinine weight includes: arranging the serum creatinine data at all moments in the local preset period of each moment in the postoperative analysis period of the patient to be tested in chronological order to obtain the local creatinine sequence at each moment in the postoperative analysis period; obtaining the first-order difference sequence of the local creatinine sequence, normalizing the mean value of all elements in the first-order difference sequence to obtain the prominence index of the serum creatinine data at each moment in the postoperative analysis period; using the time interval between each moment and the previous adjacent moment in the postoperative analysis period as the time error index at each moment in the postoperative analysis period; using the time interval between the start moment of the postoperative analysis period and each moment as the postoperative duration at each moment in the postoperative analysis period; and obtaining the creatinine weight at each moment in the postoperative analysis period according to the prominence index, the time error index, and the postoperative duration.

[0075] If the serum creatinine concentration level shows an increase or remains stable at a high level in the early stage after the patient undergoes cardiothoracic surgery, acute kidney injury is more likely to occur after the operation, and the degree of abnormality of the serum creatinine is greater; because cardiopulmonary bypass during the operation may cause an increase in the patient's blood volume, the serum creatinine concentration level will drop sharply after the operation and then gradually return to the normal level. The above sharp drop in the serum creatinine concentration level is a normal phenomenon and the degree of abnormality is small and needs to be excluded; after the serum creatinine concentration returns to the normal level and still shows an increase, the serum creatinine is also considered abnormal.

[0076] Therefore, if the prominence index is closer to the constant 1, it indicates that the upward trend of the serum creatinine data in the local preset period of each moment in the postoperative analysis period is more obvious, the degree of abnormality of the serum creatinine data at this moment is more obvious, then the serum creatinine data at this moment is more important for the detection of acute kidney injury, and the weight of the serum creatinine data at this moment should be greater. If the prominence index is closer to the constant 0, it indicates that the downward trend of the serum creatinine data in the local preset period of each moment in the postoperative analysis period is more obvious, which belongs to a normal phenomenon, then the importance of the serum creatinine data at this moment for the detection of acute kidney injury is lower, and the weight of the serum creatinine data at this moment should be smaller.

[0077] It should be noted that in the embodiments of the present invention, the Norm function is used for normalization processing. Other normalization methods can also be selected, such as function transformation, maximum-minimum normalization, etc. The normalization method is not limited herein; each local preset time period within the postoperative analysis period contains three time points, and this time point is located at the middle position among the three time points; the duration of the local preset time period is less than the duration of the postoperative analysis period. In this embodiment, the prominent index of the time point without a local preset time period within the postoperative analysis period is directly set to the constant 0.

[0078] If the time error index is smaller, the time interval between each time point within the postoperative analysis period and the previous adjacent time point is shorter. Due to factors such as measurement technology, equipment accuracy, and changes during sample collection, the possibility of random deviation in serum creatinine data is greater, resulting in a lower accuracy rate of the abnormal index of the serum creatinine data at each time point in step S210. In order to ensure the accuracy of the analysis of the abnormal degree of serum creatinine data within the postoperative analysis period, the weight of the serum creatinine data at each time point within the postoperative analysis period should be smaller.

[0079] The postoperative duration represents the position of each time point within the postoperative analysis period; if the postoperative duration is larger, it means that each time point within the postoperative analysis period is farther away from the end time of the operation, the patient's condition is more stable, and the serum creatinine data at this time point is more valuable for reference. Then the weight of the serum creatinine data at each such time point should be larger.

[0080] In summary, the prominent index, time error index, and postoperative duration at each time point within the postoperative analysis period are all positively correlated with the creatinine weight. In the embodiments of the present invention, the product of the prominent index, time error index, and postoperative duration at each time point within the postoperative analysis period is normalized to obtain the creatinine weight corresponding to the time point. The embodiments of the present invention use the Norm function for normalization processing.

[0081] Step S230: Weighted sum the abnormal indexes of the serum creatinine data at all time points within the postoperative analysis period according to the creatinine weight, and normalize the result of the weighted sum to obtain the initial postoperative creatinine abnormality degree.

[0082] Analyze the overall abnormal degree of the postoperative serum creatinine data through the abnormal indexes of the serum creatinine data at all time points within the postoperative analysis period and the creatinine weight to obtain the initial postoperative creatinine abnormality degree. The initial postoperative creatinine abnormality degree is expressed by the formula:

[0083]

[0084]

[0085] In the formula, is the initial postoperative creatinine abnormality degree; N2 is the total number of moments within the postoperative analysis period; is the creatinine weight at the n2-th moment other than the first moment within the postoperative analysis period; is the abnormality index of the serum creatinine data at the n2-th moment other than the first moment within the postoperative analysis period; is the serum creatinine data at the n2-th moment other than the first moment within the postoperative analysis period; is the serum creatinine data at the (n2 - 1)-th moment other than the first moment within the postoperative analysis period; is the time interval between the (n2 - 1)-th and the n2-th moments other than the first moment within the postoperative analysis period; Norm is the normalization function. It should be noted that the greater the initial postoperative creatinine abnormality degree, the greater the overall abnormality degree of the serum creatinine concentration level in the patient to be tested after cardiothoracic surgery.

[0086] Step S3: Obtain the final postoperative creatinine abnormality degree based on the difference between the preoperative creatinine abnormality degree and the initial postoperative creatinine abnormality degree, as well as the difference between the blood loss and blood transfusion volume of the patient to be tested during the operation.

[0087] Compared with analyzing the abnormality degree only based on the postoperative serum creatinine data of the patient to be tested, the difference between the preoperative creatinine abnormality degree and the initial postoperative creatinine abnormality degree can better highlight the abnormality degree of the postoperative serum creatinine data. At the same time, by analyzing the difference between the blood loss and blood transfusion volume caused by cardiopulmonary bypass during the operation, the obtained final postoperative creatinine abnormality degree can more accurately reflect the risk of acute kidney injury in the patient to be tested after the operation.

[0088] Preferably, in some possible implementation manners of the embodiments of the present invention, the method for obtaining the final postoperative creatinine abnormality degree includes: normalizing the difference between the initial postoperative creatinine abnormality degree and the preoperative creatinine abnormality degree to obtain the change value of creatinine abnormality before and after; normalizing the difference between the blood transfusion volume and blood loss volume of the patient to be tested during the operation to obtain the influence value of cardiopulmonary bypass; obtaining the final postoperative creatinine abnormality degree based on the change value of creatinine abnormality before and after and the influence value of cardiopulmonary bypass.

[0089] The change degree between the initial postoperative creatinine abnormality degree and the preoperative creatinine abnormality degree reflects the abnormality degree of the serum creatinine concentration level in the patient to be tested after the operation. If the difference between the initial postoperative creatinine abnormality degree and the preoperative creatinine abnormality degree, that is, the change value of creatinine abnormality before and after, is greater, it indicates that the postoperative serum creatinine data is more abnormal than the preoperative one, and thus the abnormality degree of the postoperative serum creatinine data is greater.

[0090] During cardiothoracic surgery, in order to ensure the patient's physiological health, extracorporeal circulation usually delivers sufficient blood volume to the patient, that is, the blood transfusion volume is greater than the blood loss volume, resulting in an increase in the patient's blood volume. The greater the impact value of extracorporeal circulation, the greater the patient's blood volume, and the greater the impact on the initial postoperative creatinine abnormality degree, thus making the abnormal change value of creatinine before and after less valuable as a reference.

[0091] Therefore, the abnormal change value of creatinine before and after is positively correlated with the final postoperative creatinine abnormality degree, and the extracorporeal circulation impact value is negatively correlated with the final postoperative creatinine abnormality degree.

[0092] The final postoperative creatinine abnormality degree is expressed by the formula:

[0093]

[0094]

[0095]

[0096] In the formula, is the final postoperative creatinine abnormality degree; R is the abnormal change value of creatinine before and after; IM is the extracorporeal circulation impact value; is the initial postoperative creatinine abnormality degree; is the preoperative creatinine abnormality degree; is the intraoperative blood transfusion volume; is the intraoperative blood transfusion volume; is a preset positive number, taking the empirical value 0.1, which serves to prevent the denominator from being zero and causing the fraction to be meaningless; Norm is a normalization function.

[0097] By adjusting the change degree of the abnormality of preoperative and postoperative serum creatinine data through the intraoperative blood transfusion volume and blood loss volume of the patient to be tested, the impact of the change in the patient's blood volume caused by extracorporeal circulation during the operation on the abnormality degree of postoperative serum creatinine data is reduced, effectively improving the accuracy of the abnormal analysis of the postoperative serum creatinine data of the patient to be tested.

[0098] Step S4: Perform acute kidney injury detection on the patient to be tested according to the preoperative creatinine abnormality degree, the final postoperative creatinine abnormality degree, and the total urine volume of the patient to be tested during the postoperative analysis period.

[0099] The preoperative creatinine abnormality degree and the final postoperative creatinine abnormality degree reflect the abnormality degree of the serum creatinine data of the patient to be tested before and after the operation, and further reflect the risk of the patient to be tested having acute kidney injury after the operation; a decrease in urine volume is a key indicator for analyzing acute kidney injury. The patient to be tested is detected for acute kidney injury by comprehensively considering the above factors.

[0100] In an embodiment of the present invention, the method for obtaining a renal injury risk index is as follows: perform a negative correlation mapping on the total urine volume during the postoperative analysis period of the patient to be tested, and perform a normalization process on the product of the preoperative creatinine abnormality degree, the final postoperative creatinine abnormality degree, and the mapping result to obtain the renal injury risk index.

[0101] When the preoperative creatinine abnormality degree and the final postoperative creatinine abnormality degree are larger, it indicates that the risk of acute kidney injury in the patient to be tested after surgery is higher, and the renal injury influence coefficient is larger; when the total urine volume is less, the risk of acute kidney injury in the patient to be tested after surgery is higher. Therefore, both the preoperative creatinine abnormality degree and the final postoperative creatinine abnormality degree have a positive correlation with the renal injury risk index, and the total urine volume has a negative correlation with the renal injury risk index.

[0102] The renal injury risk index is expressed by the formula:

[0103]

[0104] In the formula, P is the renal injury risk index of the patient to be tested; is the preoperative creatinine abnormality degree; is the final postoperative creatinine abnormality degree; UV is the total urine volume of the patient to be tested during the postoperative analysis period; exp is the exponential function with the natural constant as the base; Norm is the normalization function. It should be noted that in the embodiment of the present invention, the function is used to perform a negative correlation mapping on UV.

[0105] If the renal injury risk index is larger, the risk of acute kidney injury in the patient to be tested after cardiothoracic surgery is higher; based on the renal injury risk index, assist the doctor to judge whether the patient to be tested has acute kidney injury after cardiothoracic surgery. During the judgment process, the doctor also needs to combine auxiliary examinations such as kidney echocardiogram examination, blood gas analysis, and blood electrolyte determination.

[0106] So far, the present invention is completed.

[0107] Embodiment 2:

[0108] The present invention provides an acute kidney injury detection system based on missing data. Please refer to Figure 3 , which shows the system structure diagram of an acute kidney injury detection system based on missing data provided by an embodiment of the present invention. The system includes:

[0109] A data acquisition module 510, configured to obtain the serum creatinine data of the patient to be tested and similar patients at each moment during the preoperative analysis period, as well as the blood loss, blood transfusion volume of the patient to be tested during the operation, and the total urine volume and the serum creatinine data at each moment during the postoperative analysis period;

[0110] The initial creatinine abnormality analysis module 520 is configured to obtain the preoperative creatinine abnormality degree according to the difference in serum creatinine data between the patient to be tested and similar patients during the preoperative analysis period; and obtain the initial postoperative creatinine abnormality degree according to the change rate of the serum creatinine data at each moment during the postoperative analysis period of the patient to be tested, and the prominence of the serum creatinine data at each moment and the position.

[0111] The final creatinine abnormality analysis module 530 is configured to obtain the final postoperative creatinine abnormality degree according to the difference between the preoperative creatinine abnormality degree and the initial postoperative creatinine abnormality degree, and the difference between the blood loss and blood transfusion volume of the patient to be tested during the operation.

[0112] The kidney injury detection module 540 is configured to perform acute kidney injury detection on the patient to be tested according to the preoperative creatinine abnormality degree, the final postoperative creatinine abnormality degree, and the total urine volume of the patient to be tested during the postoperative analysis period.

[0113] It should be noted that: the device provided in the above embodiment is only illustrated by the division of the above functional modules. In practical applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the computer device is divided into different functional modules to complete all or part of the functions described above. In addition, an acute kidney injury detection system based on missing data and an acute kidney injury detection method embodiment provided in the above embodiment belong to the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0114] Embodiment 3:

[0115] Figure 4 This is a schematic diagram of a computer device of an acute kidney injury detection device based on missing data provided by an embodiment of the present invention. Exemplarily, as Figure 4 shown, the computer device includes: a memory 601, a processor 602, and a computer program 603 stored in the memory 601 and running on the processor 602. When the processor 602 executes the computer program 603, the computer device can execute any of the above-described acute kidney injury detection methods based on missing data.

[0116] In addition, an embodiment of the present application also protects a device, which may include a memory and a processor. Among them, the memory stores executable program code, and the processor is used to call and execute the executable program code to execute an acute kidney injury detection method provided by an embodiment of the present application.

[0117] In this embodiment, the device can be divided into functional modules according to the above method examples. For example, it can correspond to each functional module, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware. It should be noted that the division of modules in this embodiment is illustrative, only a logical function division, and there can be other division methods in actual implementation.

[0118] It should be understood that the device provided in this embodiment is used to execute the above-mentioned method for detecting acute kidney injury based on missing data, so the same effect as the above implementation method can be achieved.

[0119] In the case of adopting an integrated unit, the device can include a processing module and a storage module. Among them, when the device is applied to a device, the processing module can be used to control and manage the actions of the device. The storage module can be used to support the device to execute mutual program codes, etc.

[0120] Among them, the processing module can be a processor or a controller, which can implement or execute various exemplary logical blocks, modules, and circuits included in the disclosure of this application. The processor can also be a combination for implementing computing functions, such as including a combination of one or more microprocessors, a combination of digital signal processing (DSP) and a microprocessor, etc. The storage module can be a memory.

[0121] It should be noted that: the above sequence of embodiments of the present invention is only for description and does not represent the advantages or disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0122] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and the key points of each embodiment are the differences from other embodiments.

[0123] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An acute kidney injury detection method based on missing data, characterized in that The method includes: Obtaining the serum creatinine data of the patient to be tested and the similar patients at each moment during the preoperative analysis period, as well as the blood loss, blood transfusion volume during the operation of the patient to be tested, and the total urine volume during the postoperative analysis period and the serum creatinine data at each moment; the similar patients are patients with similar basic information to the patient to be tested and who have experienced acute kidney injury after cardiothoracic surgery; Obtaining the preoperative creatinine abnormality degree according to the difference in serum creatinine data between the patient to be tested and the similar patients during the preoperative analysis period; obtaining the initial postoperative creatinine abnormality degree according to the change rate of the serum creatinine data of the patient to be tested at each moment during the postoperative analysis period, the time interval between the start moment of the postoperative analysis period and each moment, and the prominent index of the serum creatinine data; Obtaining the final postoperative creatinine abnormality degree according to the difference between the preoperative creatinine abnormality degree and the initial postoperative creatinine abnormality degree, and the difference between the blood loss and blood transfusion volume of the patient to be tested during the operation; Performing acute kidney injury detection on the patient to be tested according to the preoperative creatinine abnormality degree, the final postoperative creatinine abnormality degree, and the total urine volume of the patient to be tested during the postoperative analysis period; The obtaining of the initial postoperative creatinine abnormality degree includes: Taking the ratio of the result of normalizing the difference between the serum creatinine data of the patient to be tested at each moment during the postoperative analysis period and its adjacent previous moment to the time interval as the abnormality index of the serum creatinine data at each moment during the postoperative analysis period; Obtaining the creatinine weight at each moment during the postoperative analysis period according to the prominent index of the serum creatinine data of the patient to be tested at each moment during the postoperative analysis period, the time interval between each moment and its adjacent previous moment, and the time interval between the start moment of the postoperative analysis period and each moment; Performing weighted summation on the abnormality indexes of the serum creatinine data at all moments during the postoperative analysis period according to the creatinine weight, and normalizing the result of the weighted summation to obtain the initial postoperative creatinine abnormality degree; The obtaining of the final postoperative creatinine abnormality degree includes: Normalizing the difference between the initial postoperative creatinine abnormality degree and the preoperative creatinine abnormality degree to obtain the change value of creatinine abnormality before and after; Normalizing the difference between the blood transfusion volume and blood loss of the patient to be tested during the operation to obtain the value affected by extracorporeal circulation; Obtaining the final postoperative creatinine abnormality degree according to the change value of creatinine abnormality before and after and the value affected by extracorporeal circulation; the change value of creatinine abnormality before and after and the final postoperative creatinine abnormality degree are in a positive correlation relationship, and the value affected by extracorporeal circulation and the final postoperative creatinine abnormality degree are in a negative correlation relationship; The method for obtaining the prominent index is: arranging the serum creatinine data at all moments within the local preset period at each moment during the postoperative analysis period of the patient to be tested in chronological order to obtain the local creatinine sequence at each moment during the postoperative analysis period; obtaining the first-order difference sequence of the local creatinine sequence, and normalizing the mean value of all elements in the first-order difference sequence to obtain the prominent index of the serum creatinine data at each moment during the postoperative analysis period; Each local preset period is a time period composed of each moment and its adjacent previous moment and next moment.

2. The method for detecting acute kidney injury based on missing data according to claim 1, wherein The obtaining of the preoperative creatinine abnormality degree includes: The patient to be tested and similar patients are recorded as analysis patients. The mean and variance of the serum creatinine data of each analysis patient at all times during the preoperative analysis period are respectively recorded as the overall creatinine value and the creatinine dispersion value of the corresponding analysis patient. Based on the differences in the overall creatinine values and the differences in the creatinine dispersion values between the patient to be tested and each similar patient, the overall creatinine difference values between the patient to be tested and each similar patient are obtained. The sum of the overall creatinine difference values between the patient to be tested and all similar patients is negatively correlated and normalized to obtain the preoperative creatinine abnormality degree.

3. The method for detecting acute kidney injury based on missing data according to claim 1, wherein The obtaining of the creatinine weight at each moment during the postoperative analysis period includes: Taking the time interval between each moment and its adjacent previous moment during the postoperative analysis period as the time error index at each moment during the postoperative analysis period. Taking the time interval between the start moment of the postoperative analysis period and each moment as the postoperative duration at each moment during the postoperative analysis period. Based on the prominent index, the time error index, and the postoperative duration, the creatinine weight at each moment during the postoperative analysis period is obtained; the prominent index, the time error index, and the postoperative duration are all positively correlated with the creatinine weight.

4. The method for detecting acute kidney injury based on missing data according to claim 1, wherein The performing of acute kidney injury detection on the patient to be tested according to the preoperative creatinine abnormality degree, the final postoperative creatinine abnormality degree, and the total urine volume of the patient to be tested during the postoperative analysis period includes: Performing a negative correlation mapping on the total urine volume during the postoperative analysis period of the patient to be tested, and normalizing the product of the preoperative creatinine abnormality degree, the final postoperative creatinine abnormality degree, and the mapping result to obtain a kidney injury risk index. Based on the kidney injury risk index, acute kidney injury detection is performed on the patient to be tested.

5. The method for detecting acute kidney injury based on missing data according to claim 2, wherein The obtaining of the overall creatinine difference values between the patient to be tested and each similar patient based on the differences in the overall creatinine values and the differences in the creatinine dispersion values between the patient to be tested and each similar patient includes: Taking the product of the absolute value of the difference in the overall creatinine values and the absolute value of the difference in the creatinine dispersion values between the patient to be tested and each similar patient as the overall creatinine difference value between the patient to be tested and each similar patient.

6. The method for detecting acute kidney injury based on missing data according to claim 3, wherein The duration of the local preset period is less than the duration of the postoperative analysis period.

7. The method for detecting acute kidney injury based on missing data according to claim 1, wherein The duration of the preoperative analysis period is less than the duration of the postoperative analysis period.

8. An acute kidney injury detection system based on missing data, characterized in that, The system includes: A data acquisition module, configured to obtain the serum creatinine data of the patient to be tested and similar patients at each moment during the preoperative analysis period, as well as the blood loss, blood transfusion volume of the patient to be tested during the operation, the total urine volume during the postoperative analysis period, and the serum creatinine data at each moment; the similar patients are patients who are similar in basic information to the patient to be tested and have acute kidney injury after cardiothoracic surgery. A creatinine initial abnormality analysis module, configured to obtain the preoperative creatinine abnormality degree according to the differences in the serum creatinine data of the patient to be tested and similar patients during the preoperative analysis period; obtain the initial postoperative creatinine abnormality degree according to the change rate of the serum creatinine data of the patient to be tested at each moment during the postoperative analysis period, the time interval between the start moment of the postoperative analysis period and each moment, and the prominent index of the serum creatinine data. The creatinine final abnormality analysis module is used to obtain the final postoperative creatinine abnormality degree according to the difference between the preoperative creatinine abnormality degree and the initial postoperative creatinine abnormality degree, and the difference between the blood loss and blood transfusion volume of the patient to be tested during the operation; The kidney injury detection module is used to detect acute kidney injury of the patient to be tested according to the preoperative creatinine abnormality degree, the final postoperative creatinine abnormality degree and the total urine volume of the patient to be tested during the postoperative analysis period; The obtaining of the initial postoperative creatinine abnormality degree includes: Taking the ratio of the result of normalizing the difference between the serum creatinine data of each moment and its adjacent previous moment during the postoperative analysis period of the patient to be tested to the time interval as the abnormality index of the serum creatinine data at each moment during the postoperative analysis period; According to the prominent index of the serum creatinine data at each moment during the postoperative analysis period of the patient to be tested, the time interval between each moment and its adjacent previous moment, and the time interval between the start moment of the postoperative analysis period and each moment, obtaining the creatinine weight at each moment during the postoperative analysis period; Weighted summing the abnormality indexes of the serum creatinine data at all moments during the postoperative analysis period according to the creatinine weight, and normalizing the result of the weighted summing to obtain the initial postoperative creatinine abnormality degree; The obtaining of the final postoperative creatinine abnormality degree includes: Normalizing the difference between the initial postoperative creatinine abnormality degree and the preoperative creatinine abnormality degree to obtain the change value of creatinine abnormality before and after; Normalizing the difference between the blood transfusion volume and blood loss volume of the patient to be tested during the operation to obtain the extracorporeal circulation influence value; Obtaining the final postoperative creatinine abnormality degree according to the change value of creatinine abnormality before and after and the extracorporeal circulation influence value; the change value of creatinine abnormality before and after and the final postoperative creatinine abnormality degree are in a positive correlation relationship, and the extracorporeal circulation influence value and the final postoperative creatinine abnormality degree are in a negative correlation relationship; The method for obtaining the prominent index is: arranging the serum creatinine data at all moments within the local preset period of each moment during the postoperative analysis period of the patient to be tested in chronological order to obtain the local creatinine sequence at each moment during the postoperative analysis period; obtaining the first-order difference sequence of the local creatinine sequence, and normalizing the mean value of all elements in the first-order difference sequence to obtain the prominent index of the serum creatinine data at each moment during the postoperative analysis period; Each local preset period is a time period composed of each moment and its adjacent previous moment and next moment.

Images