Information processing apparatus, computer program, information processing method, and learning model generation method

Abstract

Provided are an information processing device, a computer program, an information processing method, and a learning model generation method capable of predicting the onset risk of acute kidney injury after surgery before surgery.SOLUTION: The information processing device includes a control unit, and the control unit acquires examination data of a patient before surgery using an artificial heart-lung machine, and in a case where the examination data before surgery is input, inputs the acquired examination data to a learning model for predicting an onset risk of acute kidney injury after surgery, and predicts the onset risk of acute kidney injury after surgery of the patient.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an information processing device, a computer program, an information processing method, and a learning model generation method. [Background technology]

[0002] Acute kidney injury (AKI) is a condition in which kidney function declines over a period of days to weeks, resulting in the accumulation of nitrogen compounds in the blood. AKI is often caused by, for example, severe trauma, cardiovascular disease, intrinsic kidney disease, or reduced kidney perfusion due to surgery.

[0003] During surgery on the heart or abdominal vessels, a heart-lung machine is used to maintain blood circulation. The risk of acute kidney injury after surgery using a heart-lung machine is high, and some patients have a severely poor prognosis and must begin dialysis upon discharge. These patients suffer significant disadvantages in terms of quality of life (QoL) and medical costs after discharge.

[0004] Non-Patent Document 1 describes an AKI prediction model based on a machine learning approach that uses preoperative information such as gender and race, and intraoperative data obtained from tests performed during surgery, as variables. [Prior art documents] [Non-patent literature]

[0005] [Non-Patent Document 1] Lasith Adhikari et al.,PLOS ONE. 2019; Apr 4;14(4) :e0214904 Summary of the Invention [Problem to be solved by the invention]

[0006] However, the technology described in Non-Patent Document 1 does not describe predicting the risk of developing acute kidney injury after surgery using a patient's preoperative test data as variables for surgery using an artificial heart-lung machine. In addition, the above prior art does not allow for postponing surgery because it uses intraoperative data.

[0007] The present invention has been made in consideration of the above circumstances, and aims to provide an information processing device, a computer program, an information processing method, and a learning model generation method that can predict the risk of developing postoperative acute kidney injury before surgery. [Means for solving the problem]

[0008] The present application includes multiple means for solving the above-mentioned problems, and one example thereof is an information processing device that includes a control unit that acquires pre-operative test data of a patient for surgery using an artificial heart-lung machine, and when the pre-operative test data is input, inputs the acquired test data into a learning model that predicts the risk of developing acute kidney injury after surgery, thereby predicting the risk of developing acute kidney injury after surgery for the patient. [Effects of the Invention]

[0009] According to the present invention, the risk of developing postoperative acute kidney injury can be predicted before surgery. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a diagram illustrating an example of a configuration of an information processing system according to an embodiment of the present invention. [Figure 2] FIG. 10 is a diagram illustrating an example of patient information. [Figure 3] FIG. 10 is a diagram illustrating an example of test data. [Figure 4] FIG. 1 is a diagram showing an example of prediction of the risk of developing postoperative acute kidney injury using a learning model. [Figure 5] FIG. 10 is a diagram showing an example of a risk index output by a learning model. [Figure 6] FIG. 10 is a diagram illustrating an example of training data used to generate a learning model. [Figure 7] FIG. 10 is a diagram illustrating an example of a process for predicting a risk of onset by an information processing device. [Figure 8] FIG. 10 is a diagram illustrating an example of a learning model generation process performed by an information processing device. [Figure 9] FIG. 2 is a diagram showing a first example of a display screen displayed by the information processing device. [Figure 10] FIG. 10 is a diagram showing a second example of a display screen displayed by the information processing device. [Figure 11] FIG. 10 is a diagram showing a third example of a display screen displayed by the information processing device. DETAILED DESCRIPTION OF THE INVENTION

[0011] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. FIG. 1 is a diagram showing an example of the configuration of an information processing system of this embodiment. The information processing system includes information processing device 50. Patient data server 100, test data server 200, and blood test device 300 are connected to information processing device 50 via communication network 1. Note that in the example of FIG. 1, information processing device 50 and blood test device 300 are separate devices, but this configuration is not limited to this. For example, information processing device 50 may be incorporated into blood test device 300. Furthermore, information processing device 50 is not limited to a single device, and may be composed of multiple devices.

[0012] The patient data server 100 includes a patient information DB 110. In response to access from an external device, the patient data server 100 performs processes such as reading and writing of patient information in the patient information DB 110. Details of the patient information will be described later.

[0013] The test data server 200 includes a test result DB 210. The test data server 200 performs processes such as reading and writing test results (test data) in the test result DB 210 in response to access from an external device. The test data is managed by categorizing them by patient and test date. Details of the test data will be described later.

[0014] Blood test apparatus 300 is installed in a hospital and is capable of performing blood tests such as the number and morphology of red blood cells, white blood cells, and platelets, which are typical components of blood, and the amount of hemoglobin. Test data (blood test data) obtained by testing with blood test apparatus 300 is recorded in test result DB 210.

[0015] The information processing device 50 can predict the risk of developing post-operative acute kidney injury (AKI) before surgery based on patient information of the patient and test data from tests performed on the patient before surgery. The information processing device 50 includes a control unit 51 that controls the entire device, a communication unit 52, a memory 53, a display unit 54, an operation unit 55, a storage unit 56, and a recording medium reading unit 59. The information processing device 50 can be configured as a server, a computer, or the like.

[0016] The control unit 51 may be configured by incorporating a required number of central processing units (CPUs), micro-processing units (MPUs), graphics processing units (GPUs), etc. The control unit 51 may also be configured by combining digital signal processors (DSPs), field-programmable gate arrays (FPGAs), etc.

[0017] The communication unit 52 includes a communication module and has a function of communicating with the patient data server 100 and the examination data server 200 via the communication network 1. The communication unit 52 can acquire patient information of a patient from the patient data server 100. The communication unit 52 can also acquire pre-operative examination data of the patient from the examination data server 200.

[0018] The display unit 54 can be configured with a liquid crystal panel, an organic EL (Electro Luminescence) display, etc. Instead of the display unit 54, an external display device may be provided.

[0019] The operation unit 55 is configured with a touch panel or the like, and can be used to operate icons displayed on the display unit 54, move and operate a cursor, input characters, etc. The operation unit 55 may also be a mouse or a keyboard.

[0020] The storage unit 56 can be configured with a semiconductor memory, a hard disk, or the like, and stores a computer program 57 (program product), a learning model 58, and required information.

[0021] The computer program 57 can be stored in the storage unit 56 by reading the computer program 57 recorded on a recording medium (for example, an optically readable disk storage medium such as a CD-ROM) M using a recording medium reading unit 59. The computer program 57 may also be downloaded from an external device via the communication unit 52 and stored in the storage unit 56.

[0022] The memory 53 can be configured with a semiconductor memory such as a static random access memory (SRAM), a dynamic random access memory (DRAM), or a flash memory. A computer program 57 can be loaded into the memory 53, and the control unit 51 can execute the computer program 57. The control unit 51 can execute processing defined by the computer program 57. In other words, processing by the control unit 51 is also processing by the computer program 57.

[0023] FIG. 2 is a diagram showing an example of patient information. As shown in FIG. 2, the patient information includes the patient ID, name, date of birth, age, sex, BMI (Body Mass Index), height, weight, medication history, surgical history, medical history, blood transfusion history, pregnancy history, liver transplant history, etc. The medication history includes whether or not the patient has taken antiplatelet drugs or anticoagulants, and the duration of their use. Antiplatelet drugs are used to prevent angina pectoris, cerebral infarction, and other conditions, and prevent blood clots from forming in the arteries. Anticoagulants are used to prevent blood clots from forming in the heart and veins. Taking antiplatelet drugs or anticoagulants suppresses platelet activity, which is thought to increase the risk of developing acute kidney injury after surgery.

[0024] As described above, the patient information includes the patient's age, sex, and body mass index (BMI). The patient information also includes whether the patient is taking an antiplatelet drug or an anticoagulant. Note that the patient information is not limited to the example shown in FIG. 2.

[0025] 3 is a diagram showing an example of test data. As shown in FIG. 3, the test name of the blood test includes, for example, red blood cell distribution width (RDW), platelet distribution width (PDW), mean platelet volume (MPV), red blood cell count (RBC) ( / μL), white blood cell count (WBC) ( / μL), hemoglobin concentration (HGB), platelet count (PLT) ( / μL), platelet concentration (Pct), mean corpuscular volume (MCV), etc., and preferably includes blood cell morphology tests such as red blood cell distribution width (RDW), platelet distribution width (PDW), and mean platelet volume (MPV). The test data may also include test data obtained by a device other than blood test device 300 (e.g., a biochemical analyzer), such as protein amount.

[0026] The red blood cell distribution width (RDW) is the variation in the size of red blood cells and is used as a quantitative indicator of red blood cell size anomaly and an indicator of microcytic anemia. An increased red blood cell distribution width (RDW) may indicate decreased red blood cell production or iron deficiency.

[0027] Platelet distribution width (PDW) is the variation in platelet size and reflects the distribution width of platelet volume. The platelet distribution width (PDW) value increases when platelets are distributed widely from small to large. A large platelet distribution width (PDW) value suggests a decrease in platelets, which is thought to increase the risk of developing acute kidney injury after surgery.

[0028] Mean platelet volume (MPV) is the average platelet volume and represents the size of platelets. It is known that the value of mean platelet volume (MPV) increases when platelet production increases. When platelet production increases, it is expected that the number of platelets will decrease.

[0029] The red blood cell count (RBC) is the number of red blood cells per unit volume of blood being analyzed. The white blood cell count (WBC) is the number of white blood cells per unit volume of blood being analyzed. The hemoglobin concentration (HGB) is the amount of hemoglobin per unit volume of blood being analyzed. Hemoglobin is the main component of red blood cells and is the protein responsible for transporting oxygen. The platelet count (PLT) is the number of platelets per unit volume of blood being analyzed. Platelets are the blood cell component central to the hemostasis mechanism. The platelet concentration (Pct) is the concentration of platelets in the blood expressed as a percentage. The mean corpuscular volume (MCV) is the average volume of red blood cells.

[0030] As described above, the test data includes blood test data, preferably a blood cell morphology test. The test data includes a red blood cell distribution width (RDW). The test data also includes at least one of a platelet distribution width (PDW) and a mean platelet volume (MPV). Note that the test data is not limited to the example shown in FIG. 3.

[0031] FIG. 4 is a diagram showing an example of predicting the risk of developing postoperative acute kidney injury using the learning model 58. When the patient's preoperative test data and patient information are input, the learning model 58 can predict the patient's risk of developing postoperative acute kidney injury (risk index) and estimate risk factors that affect the risk. The test data includes RDW, PDW, MPV, etc. While PDW and MPV are not required test data, they may be included in the test data to improve prediction accuracy. Furthermore, combining RDW, PDW, and MPV allows for more accurate prediction of the risk of developing postoperative acute kidney injury. The patient information includes age, gender, BMI, and whether or not the patient is taking oral antiplatelet drugs or anticoagulants.

[0032] Risk factors are factors that affect the risk of developing acute kidney injury after surgery and can be expressed as positive or negative values. The number N of risk factors output by the learning model 58 can be set appropriately. For example, risk factors whose values ​​are equal to or greater than a predetermined value may be output, or the top risk factors from among multiple risk factors may be output. Risk factors are extracted, for example, from patient information and test data.

[0033] In this embodiment, the surgery may be performed using, for example, a heart-lung machine. The heart-lung machine takes in blood (venous blood) that has been returned to the heart from the patient's entire body using a roller pump through a tube at the vena cava. The taken-in blood is oxygenated in an artificial lung, and the blood (arterial blood) that has had impurities removed by filtration is then sent through a tube from the aorta to the entire body. It is thought that the risk of developing acute kidney injury after surgery increases due to the flow of blood through the tubes and the physical and chemical stress caused by coagulants, which can lead to a decrease in platelets and hemolysis of red blood cells.

[0034] In this embodiment, "post-surgery" includes immediately after surgery and a certain period after surgery.

[0035] FIG. 5 is a diagram showing an example of a risk index output by the learning model 58. The example in FIG. 5 shows three risk indices. Risk index 1 indicates that the risk of developing post-operative acute kidney injury is 80 to 100% and the risk level is high. Risk index 2 indicates that the risk of developing is 60 to 80% and the risk level is medium. Risk index 3 indicates that the risk of developing is 40 to 60% and the risk level is low. Note that the risk index, risk of developing, and risk level are merely examples and are not limited to the example in FIG. 5.

[0036] As described above, learning model 58 can predict a patient's risk of developing post-operative acute kidney injury by outputting a risk index. Learning model 58 can also predict a patient's risk of developing post-operative acute kidney injury and output risk factors that explain why such a risk was predicted. This allows medical professionals, such as doctors, to understand the basis for determining the risk of developing post-operative acute kidney injury predicted by information processing device 50.

[0037] The learning model 58 can be constructed using models and techniques such as SHAP (Shapley Additive Explanations), LIME (Local Interpretable Model-Agnostic Explanations), neural network interpreter, AM (Activation Maximization), decision tree, random forest, etc.

[0038] As described above, the control unit 51 acquires the patient's pre-operative test data, and when the pre-operative test data is input, the control unit 51 inputs the acquired test data into the learning model 58 that predicts the risk of developing acute kidney injury after surgery, thereby predicting the patient's risk of developing acute kidney injury after surgery.

[0039] Furthermore, when the control unit 51 acquires the patient information of the patient and inputs the patient information and test data, it can input the acquired patient information and test data into a learning model 58 that predicts the risk of developing acute kidney injury after surgery, thereby predicting the patient's risk of developing acute kidney injury after surgery.

[0040] In addition, the control unit 51 acquires the patient's pre-operative test data, and when the pre-operative test data is input, it inputs the acquired test data into a learning model 58 that predicts the risk of developing acute kidney injury after surgery and outputs risk factors that affect the risk of development, thereby predicting the patient's risk of developing acute kidney injury after surgery and estimating the risk factors that affect the predicted risk of development.

[0041] In addition, the control unit 51 acquires the patient information of the patient, and when the patient information and test data are input, the control unit 51 inputs the acquired patient information and test data into a learning model 58 that predicts the risk of developing acute kidney injury after surgery and outputs risk factors that affect the risk of development, thereby predicting the patient's risk of developing acute kidney injury after surgery and estimating the risk factors that affect the predicted risk of development.

[0042] Next, a method for generating the learning model 58 (learning method) will be described.

[0043] Fig. 6 is a diagram showing an example of training data used to generate the learning model 58. In Fig. 6, the training data includes input data for learning and teacher data for learning. To prepare the training data, data is collected in the following procedure.

[0044] (1) First, preoperative data for multiple patients is collected. The preoperative data includes preoperative examination data and patient information. The examination data includes RDW, PDW, MPV, etc. The patient information includes age, sex, BMI, and whether or not the patient is taking oral antiplatelet or anticoagulant drugs.

[0045] (2) Next, when the multiple patients actually undergo surgery, post-operative data is collected. The post-operative data includes, for example, data on creatinine, urinary protein, cystatin, etc. Note that the post-operative data is not limited to the example in FIG. 6, and may be any data related to the onset of acute kidney injury.

[0046] (3) The collected post-operative data is applied to a logistic regression analysis equation that shows the relationship between post-operative data and the risk index (risk of onset), and the risk index (risk of onset) for each post-operative data is calculated. In logistic regression analysis, the post-operative data corresponds to the explanatory variable, and the risk index corresponds to the target variable. The logistic regression analysis equation can be set in advance by treating each collected post-operative data as an event, classifying it into a binary value of "1" (onset) or "0" (no onset) depending on whether or not the event has occurred, and calculating the probability of belonging to the event "1" to calculate the risk index (risk of onset).

[0047] (4) The collected preoperative data and the calculated risk index (risk of onset) are applied to a logistic regression analysis equation showing the relationship between the preoperative data and the risk index (risk of onset), and factors influencing the calculated risk index (risk of onset) are extracted as risk factors. Risk factors can be extracted from the preoperative data. For example, if the risk factors are x1, x2, x3, ..., and the risk of onset is R, and the logistic regression analysis equation is "x1·w1+x2·w2+x3·w3+...=R," the influence of each risk factor x1, x2, x3, ... on the risk of onset R can be expressed by the magnitude of the coefficients w1, w2, w3, .... For example, the risk factor with the largest coefficient can be considered to have the greatest influence on the risk of onset.

[0048] (5) The preoperative data of each patient is associated with the patient's risk index (risk of developing the disease) and risk factors. This allows for obtaining preoperative data as input data for learning, and risk index (risk of developing the disease) and risk factors as training data for learning, for each of multiple patients.

[0049] The control unit 51 acquires training data including pre-operative test data of a patient (e.g., multiple patients) and the patient's risk of developing acute kidney injury after surgery, and based on the acquired training data, generates a learning model 58 that predicts the risk of developing acute kidney injury after surgery when pre-operative test data is input.

[0050] Furthermore, the control unit 51 acquires training data including pre-operative test data of a patient (e.g., multiple patients), the patient's risk of developing acute kidney injury after surgery, and one or more risk factors that affect the risk of development, and based on the acquired training data, generates a learning model 58 that predicts the risk of developing acute kidney injury after surgery when pre-operative test data is input, and outputs risk factors that affect the risk of development. Note that patient information may be input in addition to the test data.

[0051] The risk of developing the disease contained in the training data can be calculated using a logistic regression analysis formula with postoperative data, including at least the patient's creatinine level, as explanatory variables. The risk factors contained in the training data can be calculated using a logistic regression analysis formula with preoperative data as explanatory variables and the risk of developing the disease as a response variable.

[0052] As described above, the learning model 58 may be generated (learned) by the information processing device 50, or may be generated by another external learning device (not shown), and the generated learning model 58 may be acquired by the information processing device 50.

[0053] 7 is a diagram showing an example of a process for predicting the risk of developing a disease by the information processing device 50. The control unit 51 acquires pre-surgery examination data of a patient from the examination data server 200 (S11), and acquires patient information of the patient from the patient data server 100 (S12). The control unit 51 inputs the acquired examination data and patient information into the learning model 58 (S13).

[0054] The control unit 51 acquires the risk of developing post-operative acute kidney injury (risk index) output by the learning model 58 (S14), and determines whether the risk is high or not (S15). For example, as shown in FIG. 5, if the risk of development is 80% or more, it can be determined that the risk is high (high risk level). If the risk is high (YES in S15), the control unit 51 determines whether the surgery can be postponed (S16). Whether the surgery can be postponed can be determined in advance based on pre-operative test data and patient information. Alternatively, the control unit 51 may make a determination by displaying a question asking whether the surgery can be postponed on the display unit 54 and receiving a response from a medical professional such as a doctor.

[0055] If the surgery can be postponed (YES in S16), the control unit 51 outputs a warning message indicating that the risk of developing acute kidney injury is high and recommends postponing the surgery (S17), and performs the processing of step S19 described below.If the surgery cannot be postponed (NO in S16), the control unit 51 outputs a warning message indicating that the risk of developing acute kidney injury is high and recommends taking appropriate measures after the surgery (S18).

[0056] The control unit 51 outputs the risk of developing acute kidney injury after surgery and risk factors that affect the risk of developing the disease (S19), and ends the process. If the risk is not high (NO in S15), the control unit 51 notifies the patient that the surgery can be performed (S20), and ends the process.

[0057] 8 is a diagram showing an example of a process for generating a learning model 58 by the information processing device 50. The control unit 51 collects pre-operative data (examination data, patient information) of a plurality of patients (S31), and collects post-operative data of the plurality of patients (S32). The control unit 51 performs a logistic regression analysis on the collected post-operative data to estimate the risk (risk index) of developing post-operative acute kidney injury (S33).

[0058] The control unit 51 performs logistic regression analysis on the estimated risk of onset and the collected pre-operative data to estimate risk factors that affect the risk of onset (S34). The control unit 51 acquires the collected pre-operative data, the estimated risk of onset (risk index), and the risk factors as training data (S35).

[0059] The control unit 51 generates a learning model 58 that predicts the risk of developing acute kidney injury after surgery (risk index) and risk factors when preoperative data is input based on the acquired training data (S36), and then ends the process. The generated learning model 58 can be stored in the memory unit 56.

[0060] Next, a display screen displayed on the display unit 54 by the information processing device 50 will be described.

[0061] FIG. 9 is a diagram showing a first example of a display screen displayed by the information processing device 50. As shown in FIG. 9, the display screen displays the patient ID, name, scheduled surgery date, surgery name, and attending physician. The display screen also displays the risk of developing postoperative acute kidney injury. In the example of FIG. 9, the display screen displays an 80% risk of development, indicating a high risk. The display screen also displays a warning message. In the example of FIG. 9, a message such as "The risk of developing AKI is high. Postponement of surgery is recommended" is displayed. The display screen also displays risk factors that affect the predicted risk of development. In the example of FIG. 9, the risk factors RDW, MPV, and PDW are displayed, along with their respective numerical values. If postponement of surgery is possible, a "Preoperative Care" icon is displayed on the display screen. Operating the "Preoperative Care" icon displays a display screen such as that shown in FIG. 10, which will be described later.

[0062] As described above, the control unit 51 can output a warning message according to the predicted risk of onset. The control unit 51 can output risk factors that affect the predicted risk of onset. Furthermore, the control unit 51 can output a recommendation to postpone surgery when the predicted risk of onset is equal to or greater than a predetermined threshold (e.g., high risk).

[0063] By viewing the display screen shown in Figure 9, doctors and other medical professionals can understand the degree of risk of developing post-operative acute kidney injury before surgery on a patient. Postponing surgery in accordance with the warning message can prevent post-operative acute kidney injury.

[0064] Furthermore, because doctors and other medical professionals can identify risk factors that affect the risk of onset, they can understand the factors that may cause postoperative acute kidney injury in a patient before surgery, and if surgery is to be performed, they can take the necessary measures to reduce the risk during surgery and the onset of postoperative acute kidney injury.

[0065] FIG. 10 is a diagram showing a second example of a display screen displayed by the information processing device 50. The example in FIG. 10 shows a case where surgery can be postponed. As shown in FIG. 10, the display screen displays the patient ID, name, scheduled surgery date, surgery name, attending physician, and information regarding nutritional care up until the surgery. In the example in FIG. 10, the following message is displayed: "Moderate malnutrition is observed. Two weeks of nutritional therapy are required. We recommend correcting your current diet and taking nutritional supplements."

[0066] As described above, when the predicted risk of onset is equal to or greater than a predetermined threshold (for example, high risk) and surgery is postponed, the control unit 51 can output treatment details including nutritional care for the patient until surgery.

[0067] By looking at the display screen shown in Figure 9, doctors and other medical professionals can use the time leading up to a patient's surgery to provide appropriate nutritional care to the patient if the patient's surgery is postponed, thereby reducing risks during surgery and the occurrence of acute kidney injury after surgery.

[0068] FIG. 11 is a diagram showing a third example of a display screen displayed by the information processing device 50. The example of FIG. 11 shows a case where postponement of surgery is not possible. As shown in FIG. 11, the display screen displays the risk of developing postoperative acute kidney injury. In the example of FIG. 11, the display shows that the risk of development is 80%, which is a high risk. A warning message is also displayed on the display screen. In the example of FIG. 11, a message such as "The risk of developing AKI is high. Please take appropriate measures after surgery" is displayed. The display screen also displays risk factors that affect the predicted risk of development. In the example of FIG. 11, the history of oral administration of antiplatelet drugs, age, and BMI are displayed as risk factors, along with the numerical values ​​of each.

[0069] By looking at the display screen shown in Figure 11, doctors and other medical professionals can check the risk of developing postoperative acute kidney injury and the risk factors that affect the risk if a patient's surgery cannot be postponed, and can also reaffirm the importance of appropriate postoperative treatment.

[0070] In the example of FIG. 9, where surgery can be postponed, a warning message is output saying, "The risk of developing AKI is high. Postponement of surgery is recommended." In the example of FIG. 11, where surgery cannot be postponed, a warning message is output saying, "The risk of developing AKI is high. Please take appropriate measures after surgery." In this way, when the predicted risk of developing AKI is equal to or greater than a predetermined threshold, the control unit 51 can output different warning messages depending on whether or not the surgery can be postponed. If necessary, a warning sound may be generated along with the warning message. This allows an appropriate warning to be issued depending on whether or not the surgery can be postponed.

[0071] As described above, according to this embodiment, the risk of developing postoperative acute kidney injury can be predicted before surgery, and preoperative diagnosis enables intervention to avoid the risk, thereby reducing the risk to the surgeon and improving safety during and after surgery.

[0072] (Appendix 1) The information processing device includes a control unit that acquires pre-operative test data for a patient undergoing surgery using an artificial heart-lung machine, and when the pre-operative test data is input, inputs the acquired test data into a learning model that predicts the risk of developing acute kidney injury after surgery, thereby predicting the patient's risk of developing acute kidney injury after surgery.

[0073] (Supplementary Note 2) In the information processing device according to Supplementary Note 1, the test data includes blood cell morphology test data.

[0074] (Supplementary Note 3) In the information processing device according to Supplementary Note 1 or Supplementary Note 2, the test data includes a red blood cell distribution width (RDW).

[0075] (Supplementary Note 4) In the information processing device according to any one of Supplementary Note 1 to Supplementary Note 3, the test data further includes at least one of a platelet distribution width (PDW) and a mean platelet volume (MPV).

[0076] (Appendix 5) In the information processing device, in any one of Appendices 1 to 4, the control unit acquires patient information of the patient, and when further patient information is input, inputs the acquired patient information into a learning model that predicts the risk of developing acute kidney injury after surgery, thereby predicting the risk of developing acute kidney injury after surgery for the patient.

[0077] (Appendix 6) In the information processing device of Appendix 5, the patient information includes one or more pieces of information selected from the group consisting of the patient's height, weight, age, sex, and body mass index (BMI), and whether the patient is taking an antiplatelet drug or an anticoagulant drug.

[0078] (Supplementary Note 7) In the information processing device according to any one of Supplementary Note 1 to Supplementary Note 6, the control unit outputs a warning message according to the predicted risk of onset.

[0079] (Appendix 8) In the information processing device of any one of Appendices 1 to 7, the control unit outputs a different warning message depending on whether the surgery can be postponed or not when the predicted risk of onset is equal to or greater than a predetermined threshold.

[0080] (Supplementary Note 9) In the information processing device according to any one of Supplementary Note 1 to Supplementary Note 8, the control unit outputs risk factors that affect the predicted risk of developing a disease.

[0081] (Supplementary Note 10) In the information processing device according to any one of Supplementary Note 1 to Supplementary Note 9, the control unit outputs a recommendation to postpone the surgery when the predicted risk of onset is equal to or greater than a predetermined threshold.

[0082] (Appendix 11) In the information processing device, in any one of Appendices 1 to 10, the control unit outputs treatment details including nutritional care for the patient until the surgery if the predicted risk of onset is above a predetermined threshold and the surgery is postponed.

[0083] (Appendix 12) The computer program acquires pre-operative test data for a patient undergoing surgery using an artificial heart-lung machine, and when the pre-operative test data is input, inputs the acquired test data into a learning model that predicts the risk of developing acute kidney injury after surgery, thereby predicting the patient's risk of developing acute kidney injury after surgery.

[0084] (Appendix 13) The information processing method obtains pre-operative test data for a patient undergoing surgery using an artificial heart-lung machine, and inputs the obtained test data into a learning model that predicts the risk of developing acute kidney injury after surgery when the pre-operative test data is input, thereby predicting the risk of developing acute kidney injury after surgery for the patient.

[0085] (Appendix 14) The learning model generation method acquires training data including pre-operative test data for a patient undergoing surgery using an artificial heart-lung machine and the patient's risk of developing acute kidney injury after surgery, and generates a learning model that predicts the risk of developing acute kidney injury after surgery when the pre-operative test data is input based on the acquired training data.

[0086] The matters described in each embodiment can be combined with each other. In addition, the independent claims and dependent claims described in the claims can be combined with each other in any combination, regardless of the reference format. Furthermore, although the claims use a format in which a claim references two or more other claims (multiple claim format), this is not limited to this format. A multiple claim (multi-multi claim) that references at least one other multiple claim may also be used. [Explanation of symbols]

[0087] 1. Communication Network 50 Information processing equipment 51 Control section 52 Communications Department 53 Memory 54 Display section 55 Operation section 56 Memory section 57 Computer Programs 58 Learning Model 59 Recording medium reading unit 100 Patient Data Server 110 Patient information DB 200 Inspection Data Server 210 Test Results DB 300 Blood testing equipment

Claims

1. A control unit is provided, The control unit obtaining preoperative examination data for a patient's cardiopulmonary bypass surgery; The acquired test data is input into a learning model that predicts the risk of developing acute kidney injury after surgery when pre-operative test data is input, and the risk of developing acute kidney injury after surgery of the patient is predicted. Information processing device.

2. The test data includes blood cell morphology test data. The information processing device according to claim 1 .

3. The test data includes a red blood cell distribution width (RDW). The information processing device according to claim 1 .

4. The test data further includes at least one of a platelet distribution width (PDW) and a mean platelet volume (MPV). The information processing device according to claim 3 .

5. The control unit obtaining patient information for the patient; When patient information is further input, the acquired patient information is input into a learning model that predicts the risk of developing post-operative acute kidney injury, thereby predicting the risk of developing post-operative acute kidney injury for the patient. The information processing device according to claim 1 .

6. The patient information includes one or more pieces of information selected from the group consisting of the patient's height, weight, age, sex, and body mass index (BMI), and whether or not the patient is taking an antiplatelet drug or an anticoagulant drug. The information processing device according to claim 5 .

7. The control unit Output a warning message according to the predicted risk of onset. The information processing device according to claim 1 .

8. The control unit If the predicted risk of onset is equal to or greater than a predetermined threshold, a different warning message is output depending on whether the surgery can be postponed or not. The information processing device according to claim 1 .

9. The control unit Output risk factors that affect the predicted risk of developing the disease. The information processing device according to claim 1 .

10. The control unit If the predicted risk of onset is equal to or greater than a predetermined threshold, a recommendation to postpone the surgery is output. The information processing device according to claim 1 .

11. The control unit If the predicted risk of onset is equal to or greater than a predetermined threshold and the surgery is postponed, outputting treatment details including nutritional care for the patient until the surgery. The information processing device according to claim 1 .

12. obtaining preoperative examination data for a patient's cardiopulmonary bypass surgery; The acquired test data is input into a learning model that predicts the risk of developing acute kidney injury after surgery when pre-operative test data is input, and the risk of developing acute kidney injury after surgery of the patient is predicted. A computer program that causes a computer to perform a process.

13. obtaining preoperative examination data for a patient's cardiopulmonary bypass surgery; The acquired test data is input into a learning model that predicts the risk of developing acute kidney injury after surgery when pre-operative test data is input, and the risk of developing acute kidney injury after surgery of the patient is predicted. Information processing methods.

14. obtaining training data including preoperative examination data of a patient for a heart-lung machine operation and the patient's risk of developing acute kidney injury after the operation; Based on the acquired training data, a learning model is generated that predicts the risk of developing acute kidney injury after surgery when preoperative test data is input. Learning model generation method.

Images