Program, information processing method, and information processing device
Patent Information
- Application Number
- JP2024511570
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Filing Date
- 2024-06-27
- Publication Date
- 2024-12-11
AI Technical Summary
Current image diagnostic apparatuses cannot calculate the safe amount of contrast medium for endovascular treatments considering the risk of kidney damage, as they do not account for real-time changes in renal function during procedures.
An information processing system that calculates the intraoperative allowable amount of contrast medium using a renal status index and hemodynamic information, allowing real-time adjustments during endovascular treatments to minimize the risk of contrast-induced nephropathy.
Enables doctors to make informed decisions about contrast medium administration, reducing the risk of kidney damage and chronic kidney disease by providing real-time updates on the permissible amount, thus ensuring safe and effective treatment.
Abstract
Description
Program, information processing method and information processing device
[0001] The present invention relates to a program, an information processing method, and an information processing device.
[0002] Intravascular treatment is performed using an imaging diagnostic device, and an imaging diagnostic device that sets a contrast agent injection device to optimize the contrast of an image has been proposed (Patent Document 1).
[0003] Japanese Patent Application Laid-Open No. 2021-168814
[0004] By using the diagnostic imaging apparatus of Patent Document 1, even a relatively inexperienced user can capture an image with appropriate contrast.
[0005] However, it is known that administering a large amount of contrast agent increases the risk of developing kidney damage. The amount of contrast agent that can be administered without causing kidney damage varies from person to person due to differences in original kidney function, and may also fluctuate due to various events during intravascular treatment. The imaging diagnostic device disclosed in Patent Document 1 cannot calculate the administrable amount of contrast agent that takes into account the risk of developing kidney damage.
[0006] In one aspect, an object of the present invention is to provide a program or the like for calculating the possible dose of contrast agent taking into account the risk of developing kidney damage.
[0007] The program causes a computer to execute a process of acquiring a renal condition index relating to the state of the patient's kidneys during treatment of the patient, calculating an intraoperative allowable amount of contrast agent to be administered to the patient based on the renal condition index and patient information relating to the patient, and outputting information relating to the intraoperative allowable amount.
[0008] In one aspect, it is possible to provide a program or the like that calculates the possible amount of contrast agent that can be administered, taking into account the risk of developing kidney damage.
[0009] FIG. 1 is an explanatory diagram for explaining the configuration of an information processing system. FIG. 1 is an explanatory diagram for explaining a contrast agent amount model. FIG. 2 is a flowchart for explaining the processing flow of a program. FIG. 3 is an example of a screen. FIG. 4 is an example of a screen. FIG. 5 is an example of a screen. FIG. 6 is an example of a risk report. FIG. 7 is an explanatory diagram for explaining a renal status model. FIG. 8 is a flowchart for explaining the processing flow of a program of embodiment 2. FIG. 9 is an example of a screen of embodiment 2. FIG. 10 is an explanatory diagram for explaining a record layout of a treatment plan DB. FIG. 11 is an explanatory diagram for explaining a plan model. FIG. 11 is a flowchart for explaining the processing flow of a program of embodiment 3. FIG. 12 is an example of a graph column of embodiment 3. FIG. 13 is an explanatory diagram for explaining the configuration of an information processing system of embodiment 4.
[0010] [First Embodiment] Various types of endovascular treatments are performed, such as PCI (Percutaneous Coronary Intervention), TAVI (Transcatheter Aortic Valve Implantation), percutaneous mitral valve clipping using MITRACLIP (registered trademark), atherectomy, stent placement, and aneurysm coil embolization.
[0011] When performing these intravascular treatments, doctors use a diagnostic imaging device 15 (see FIG. 1) to confirm the position and status of the treatment instruments inserted into the patient's blood vessels. In the following explanation, the diagnostic imaging device 15 will be described as an example of a device that uses X-rays to take fluoroscopic images of the patient. When taking a contrast image that depicts the running state of the blood vessels on a fluoroscopic image, an iodine contrast agent is administered into the patient's blood vessels in X-ray angiography or CT angiography, or a gadolinium preparation is administered in MRI or the like.
[0012] Contrast agents can cause a side effect known as contrast-induced nephropathy (CIN). The more contrast agent administered, the higher the probability of developing contrast-induced nephropathy. It is known that patients with low creatinine clearance (CCr) and estimated glomerular filtration rate (eGFR), which are indicators of renal function, may develop contrast-induced nephropathy even with a relatively small amount of contrast agent.
[0013] Most patients who develop contrast induced nephropathy recover within a few days to two weeks. However, in some patients, the decline in renal function progresses to chronic kidney disease (CKD), and in severe cases, dialysis becomes necessary. Therefore, it is desirable to administer the minimum amount of contrast agent necessary. However, a certain amount of contrast agent is required to perform endovascular treatment appropriately.
[0014] Based on the above, physicians determine the acceptable dose of contrast agent for each individual patient, taking into account the balance between the risks and benefits of administering a contrast agent. The acceptable dose of contrast agent is determined based on the patient's background information, such as age, sex, and weight, information about the treatment procedure to be performed, and the results of biochemical tests performed preoperatively, such as creatinine clearance and estimated glomerular filtration rate. In the following explanation, the acceptable dose determined preoperatively may be referred to as the preoperative acceptable dose.
[0015] For example, when performing PCI, which is a relatively easy type of endovascular treatment, it is unlikely that an amount of contrast agent exceeding the allowable amount will be required. Because the time required for PCI is relatively short, there is also little possibility that the patient's kidney condition will change significantly during the procedure, reducing the allowable amount of contrast agent.
[0016] However, complex treatments such as TAVI require a long time, and the patient's renal condition may change during the procedure, potentially changing the contrast agent tolerance from the preoperative tolerance. Treatments using instruments that rotate within blood vessels, such as atherectomy catheters and auxiliary circulatory pump catheters, are prone to kidney damage due to hemolysis. Therefore, the patient's renal condition may change during surgery, increasing the likelihood that the contrast agent tolerance will change from the preoperative tolerance. In the following explanation, the tolerance that changes during surgery may be referred to as the intraoperative tolerance.
[0017] If the contrast agent tolerance level drops significantly, doctors may modify the treatment process to reduce the number of contrast injections. Doctors may also decide to use an amount of contrast agent that exceeds the tolerance level after comprehensively assessing the risks and benefits. To make accurate decisions, it is desirable for doctors to be able to grasp fluctuations in the contrast agent tolerance level in real time.
[0018] After a change in renal condition, it takes time for the serum creatinine value to change. Therefore, the creatinine clearance and estimated glomerular filtration rate used to calculate the preoperative tolerance change 2 to 3 days after the change in renal condition. Therefore, it is impossible to calculate the intraoperative tolerance in real time using the same method as that used to calculate the preoperative tolerance. In this embodiment, an information processing system 10 capable of calculating the intraoperative tolerance in real time will be described.
[0019] 1 is an explanatory diagram illustrating the configuration of an information processing system 10. The information processing system 10 includes an information processing device 20, a urine measurement device 31, a vital sign monitor 33, an imaging diagnostic device 15, a contrast agent administration pump 36, a display system 16, and an electronic medical record system 17, which are connected via a network such as an HIS (Hospital Information System).
[0020] A urine sensor 311 is connected to the urine measurement device 31. The urine measurement device 31 outputs a renal condition index relating to the state of the patient's kidneys, calculated using data acquired from the urine sensor 311, etc. The renal condition index will be described later. The vital monitor 33 is connected to various sensors (not shown), and measures and outputs circulatory dynamics information such as blood pressure. The urine measurement device 31 and the vital monitor 33 may be configured integrally.
[0021] The diagnostic imaging device 15 is, for example, an intraoperative angiography device or an intraoperative CT (Computed Tomography) imaging device. The diagnostic imaging device 15 may also be an intraoperative MRI (Magnetic Resonance Imaging) imaging device. When an intraoperative MRI imaging device is used, a gadolinium preparation is often used as the contrast agent. As with iodine contrast agents, it is desirable to use the minimum amount of gadolinium preparation necessary.
[0022] The contrast medium administration pump 36 is used to administer a contrast medium to a patient. The contrast medium administration pump 36 may be directly connected to and controlled by the diagnostic imaging apparatus 15. Alternatively, the contrast medium administration pump 36 may be a device that is not connected to a network or the diagnostic imaging apparatus 15 and is manually operated by a paramedical staff member such as a nurse.
[0023] The display system 16 is, for example, a large display device suspended from the ceiling of an operating room and its control system. The large display device displays fluoroscopic images and contrast images taken by the diagnostic imaging device 15, data from the vital signs monitor 33, and the like.
[0024] Patient information is recorded in the electronic medical record system 17. The patient information includes background information such as the patient's age, sex, height, and weight, medical history information regarding diseases the patient has suffered from in the past, biochemical test results, and the progress of ongoing treatment. The medical history information includes the type and amount of contrast agent administered to the patient during past treatment and the patient's condition after administration. The progress of ongoing treatment includes the type and amount of medication and contrast agent administered to the patient and images captured by the diagnostic imaging device 15. Data measured by the urine measurement device 31 and the vital signs monitor 33 may be sequentially recorded in the electronic medical record system 17.
[0025] The information processing device 20 includes a control unit 21, a main memory device 22, an auxiliary memory device 23, a communication unit 24, an output unit 25, an input unit 26, and a bus. The control unit 21 is an arithmetic and control device that executes the program of this embodiment. The control unit 21 uses one or more central processing units (CPUs), graphics processing units (GPUs), tensor processing units (TPUs), multi-core CPUs, or the like. The control unit 21 is connected to each hardware unit that constitutes the information processing device 20 via the bus.
[0026] The main memory device 22 is a storage device such as an SRAM (Static Random Access Memory), a DRAM (Dynamic Random Access Memory), a flash memory, etc. The main memory device 22 temporarily stores information required during processing performed by the control unit 21 and programs currently being executed by the control unit 21.
[0027] The auxiliary storage device 23 is a storage device such as an SRAM, a flash memory, a hard disk, or a magnetic tape. The auxiliary storage device 23 stores a contrast agent amount model 41, a program to be executed by the control unit 21, and various data required for executing the program. The contrast agent amount model 41 may be stored in an external large-capacity storage device connected to the information processing device 20. The communication unit 24 is an interface for communication between the information processing device 20 and a network.
[0028] The output unit 25 is, for example, a liquid crystal display device or an organic EL (Electro Luminescence) display device. The input unit 26 is, for example, an input device such as a keyboard, a mouse, a trackball, or a microphone. The output unit 25 and the input unit 26 may be stacked together to form a touch panel.
[0029] The output unit 25 may be a connection interface that connects the information processing device 20 with an external display device. The communication unit 24 that connects data to the display system 16 or the like via a network may also function as the output unit 25.
[0030] The information processing device 20 of this embodiment is an information device such as a general-purpose personal computer, a tablet, a smartphone, or a server computer. The information processing device 20 may be a mainframe computer, a virtual machine running on a mainframe computer, a cloud computing system, a quantum computer, or multiple personal computers performing distributed processing. The information processing device 20 may be integrated with, for example, a urine measurement device 31, a vital sign monitor 33, an imaging diagnostic device 15, or an electronic medical record system 17.
[0031] The following description will be made mainly on the assumption that the control unit 21 performs software processing. The processing and various models described using flowcharts may be realized by dedicated hardware.
[0032] 2 is an explanatory diagram illustrating the contrast agent amount model 41. The contrast agent amount model 41 is a model that receives patient information, a renal condition index, and hemodynamic information, and outputs an allowable amount of contrast agent. The renal condition index and hemodynamic information that are received as input by the contrast agent amount model 41 may be time-series data. As described above, the patient information is recorded in the electronic medical record system 17, and includes the patient's background information, medical history information, and biochemical test results. The patient information may also include the progress of ongoing treatment, etc.
[0033] The renal condition index is, for example, urine flow rate, urine volume, urinary oxygen partial pressure, urine color, urine absorbance, urinary sodium content, or urinary creatinine content. The control unit 21 acquires the renal condition index from the urine measurement device 31. The control unit 21 may calculate the renal condition index based on the measurement data acquired from the urine measurement device 31. The circulatory dynamics information is, for example, pulse pressure, mean blood pressure, heart rate, and blood oxygen saturation. The control unit 21 acquires the circulatory dynamics information from the vital sign monitor 33. The control unit 21 may calculate the circulatory dynamics information based on the measurement data acquired from the vital sign monitor 33.
[0034] The urine flow rate can be measured in real time, for example, based on the weight change of a urine bag placed at the end of an indwelling bladder catheter. A flow sensor may be provided in the indwelling bladder catheter. The principle for detecting the urine flow rate is not important. The urine volume is the total amount of urine discharged from the patient's bladder after measurement begins, and can be measured in real time based on the weight of the urine bag or the integrated value of the urine flow rate.
[0035] Urinary oxygen partial pressure can be measured in real time by inserting an oxygen sensor into the bladder through an indwelling bladder catheter. The oxygen sensor may be placed midway through the indwelling bladder catheter or at the entrance to a urine bag located at the end of the indwelling bladder catheter. Similarly, the amount of sodium in urine can be measured in real time using a sodium sensor, and the amount of creatinine in urine can be measured in real time using a creatinine sensor. The oxygen sensor, sodium sensor, and creatinine sensor can each be realized using a fluorescent dye sensor or by absorbance measurement.
[0036] Urine color and urine absorbance can be measured in real time, for example, by inserting an optical fiber connected to an optical measuring device such as a spectrophotometer into an indwelling bladder catheter. The renal condition indicators described above are all examples. Any indicator that quickly reflects the state of the patient's kidneys can be selected as the renal condition indicator.
[0037] Pulse pressure is the difference between systolic blood pressure and diastolic blood pressure. Mean blood pressure is calculated by diastolic blood pressure + (systolic blood pressure - diastolic blood pressure) / 3. All of the above-mentioned circulatory dynamics information can be measured by the vital signs monitor 33. The circulatory dynamics information may be tissue oxygen saturation in various body parts. Hemodynamic monitors that can measure tissue oxygen saturation in the brain or various body parts in real time in a minimally invasive manner are used in clinical settings.
[0038] The contrast agent allowable amount output by contrast agent amount model 41 in this embodiment is an intraoperative allowable amount obtained by correcting the preoperative allowable amount determined before surgery based on the state of the patient's kidneys. The doctor determines that the amount of contrast agent that can be additionally administered to the same patient is the intraoperative allowable amount minus the amount of contrast agent that has already been administered to the patient.
[0039] The contrast agent amount model 41 is a learned model trained using a large number of sets of recorded training data that correlate patient information, renal status indexes, hemodynamic information, the amount of contrast agent administered to the patient, and the patient's outcome. The contrast agent amount model 41 is generated using a machine learning algorithm such as XGBoost, Random Forest, or Convolutional Neural Network (CNN). The contrast agent amount model 41 may also be generated using an algorithm suitable for processing time-series data, such as Long Short Term Memory (LSTM) or Transformer.
[0040] The contrast agent amount model 41 may be a rule-based algorithm generated based on guidelines related to contrast agents, etc. The contrast agent amount model 41 may be a function that calculates the allowable amount of contrast agent using a renal condition index or hemodynamic information as a parameter.
[0041] 3 is a flowchart illustrating the flow of processing of the program. After attaching various sensors to the patient's body, a user such as a doctor starts the program described with reference to FIG.
[0042] The controller 21 acquires patient information, including the patient's background information, medical history information, and biochemical test results, as well as preoperative information, such as the preoperative allowable amount of contrast agent (step S501). The controller 21 acquires the amount of contrast agent already administered to the patient from the contrast agent administration pump 36 (step S502). The controller 21 acquires a renal status index from the urine measurement device 31 (step S503). The controller 21 acquires circulatory dynamics information from the vital sign monitor 33 (step S504).
[0043] The control unit 21 inputs the patient information, the renal status index, and the circulatory dynamics information into the contrast agent amount model 41 to obtain the intraoperative allowable amount (step S505). The control unit 21 outputs information regarding the intraoperative allowable amount to the output unit 25 or the display system 16 (step S506).
[0044] The control unit 21 determines whether to terminate the process (step S507). For example, if a termination instruction is received from the user, the control unit 21 determines to terminate the process. The control unit 21 may also determine to terminate the process if it becomes unable to acquire urine information and circulatory dynamics information from the urine measurement device 31 and the vital sign monitor 33.
[0045] If it is determined not to end the process (NO in step S507), the control unit 21 returns to step S502. If it is determined to end the process (YES in step S507), the control unit 21 outputs the report to the output unit 25 or the display system 16 (step S508). The control unit 21 may output the report to the electronic medical record system 17. The control unit 21 ends the process.
[0046] 4 to 7 are example screens. The control unit 21 outputs the screens shown in Fig. 4 to 7 in step S506 of the program described using Fig. 3. Fig. 4 to 7 are all examples. The control unit 21 may accept a selection of which screen to display from the user. The control unit 21 may also accept an instruction from the user to change the items and layout to be displayed on the screen.
[0047] The screen shown in Fig. 4 includes a dose gauge 61, an administered contrast agent amount field 62, and a difference field 63. The administered contrast agent amount field 62 displays the amount of contrast agent already administered to the patient, which was acquired in step S502 of the program described with reference to Fig. 3. As shown below the administered contrast agent amount field 62, the contrast agent administration pump 36 is set to administer the contrast agent diluted five times. The administered contrast agent amount field 62 displays the amount of contrast agent before dilution.
[0048] The difference column 63 displays the difference between the intraoperative allowable amount obtained in step S505 of the program described with reference to FIG. 3 and the contrast agent that has already been administered to the patient. The user can understand that if there are no significant changes in the patient's kidney condition in the future, the amount of contrast agent displayed in the difference column 63 can be administered. The difference column 63 also displays the amount of contrast agent before dilution. The control unit 21 may accept a selection of whether to display the amount of contrast agent before dilution or the amount after dilution. The control unit 21 may accept a selection of whether to display the amount of contrast agent both before and after dilution. The user can select a display format that they deem preferable. The control unit 21 changes the screen based on the user's selection.
[0049] The dose gauge 61 displays the relationship between the intraoperative allowable amount of contrast agent and the amount of contrast agent that has already been administered in five horizontal stages. In Fig. 4, the third stage is displayed. The dose gauge 61 is set at equal intervals, for example, with the first stage being 0% or more and less than 20%, the second stage being 20% or more and less than 40%, and the third stage being 40% or more and less than 60%.
[0050] The dose gauge 61 may be set at intervals of an arithmetic progression, such as a first step of 0% or more but less than 50%, a second step of 50% or more but less than 75%, and a third step of 75% or more but less than 87.5%. The dose gauge 61 may also be set at any other intervals. The dose gauge 61 is not limited to five steps. The dose gauge 61 may have four or fewer steps or six or more steps.
[0051] The user can intuitively grasp how much of the intraoperative allowable amount has already been administered by using the dosage gauge 61. Note that the intraoperative allowable amount is the maximum amount of contrast agent that can be administered while keeping the risk of developing contrast-induced nephropathy within an appropriate range, and therefore, in the example screen, it is displayed as "appropriate amount of contrast agent administered."
[0052] The screen shown in Fig. 5 includes a dose gauge 61, an administered contrast agent amount field 62, and an intraoperative allowable amount field 64. The intraoperative allowable amount field 64 displays the intraoperative allowable amount obtained in step S505 of the program described with reference to Fig. 3. By displaying the administered contrast agent amount and the intraoperative allowable amount in the form of a fraction, the user can easily understand that the administered amount of contrast agent relative to the administrable amount of contrast agent is displayed.
[0053] The screen shown in Figure 6 includes a dose gauge 61, an administered contrast agent amount column 62, and a graph column 65. The horizontal axis of the graph column 65 represents time, and the vertical axis represents the amount of contrast agent. A thick solid line indicates the change over time in the administered amount of contrast agent. A thin solid line indicates the change over time in the intraoperative allowable amount.
[0054] Figure 6A shows a screen output by the control unit 21 at time t3. Figure 6B shows a screen output by the control unit 21 at time t6. We will now explain Figure 6A. The origin of the horizontal axis indicates the time when the program described using Figure 3 was started. The initial value of the intraoperative tolerance is equal to the preoperative tolerance determined before surgery. At times t1 and t2, the condition of the kidneys deteriorates, causing a decrease in the intraoperative tolerance. By the current time, time t3, 35 milliliters of contrast medium have been administered.
[0055] Referring to Figure 6B, at times t4 and t5, the kidney condition improves and the intraoperative volume increases. By the current time, t6, 48 milliliters of contrast agent have been administered. This volume exceeds the intraoperative volume at time t3 but is below the intraoperative volume at time t6.
[0056] If the endovascular treatment continues after time t6, the controller 21 scrolls the graph field 65 to the left as time passes so that the current time is positioned at the right end of the graph field 65. The user can check the chronological changes in the intraoperative dose and the amount of contrast agent administered over a predetermined time period going back from the current time.
[0057] Note that the controller 21 may keep the origin of the horizontal axis fixed and gradually change the scale of the horizontal axis so that the current time is located at the right end of the graph field 65. The user can check the chronological changes in the intraoperative dose and the amount of administered contrast agent from the start of the endovascular treatment to the current time.
[0058] 7, in addition to the time-series changes in the amount of administered contrast agent and the amount of intraoperative contrast agent, the time-series changes in urinary oxygen partial pressure, indicated by a dashed line, are displayed in the graph field 65. The controller 21 may also display any renal condition index or hemodynamic information in the graph field 65.
[0059] As mentioned above, doctors may decide to use an amount of contrast agent that exceeds the intraoperative tolerance amount after weighing the risks and benefits comprehensively. Even if the amount of contrast agent administered temporarily exceeds the intraoperative tolerance amount, if the amount of contrast agent administered is less than the intraoperative tolerance amount at the end of the endovascular treatment, the risk of developing contrast-induced nephropathy is low, and even if it does develop, the risk of it progressing to chronic kidney disease is low.
[0060] Even if the amount of contrast agent administered is below the intraoperative tolerance level, it may decrease later as the kidney condition worsens, and the amount of contrast agent administered may exceed the final intraoperative tolerance level by the end of the endovascular procedure. If an amount of contrast agent administered exceeds the final intraoperative tolerance level, there is a high risk of developing contrast-induced nephropathy and progressing to chronic kidney disease. However, even for high-risk patients, more careful postoperative condition management can reduce the risk of developing contrast-induced nephropathy and progressing to chronic kidney disease. Furthermore, visualizing the intraoperative tolerance level and the amount of contrast agent administered makes it possible to appropriately determine the condition management process.
[0061] Fig. 8 is an example of a risk report 70. The control unit 21 outputs the risk report 70 shown in Fig. 8 in step S508 of the program described using Fig. 3. The risk report 70 shown in Fig. 8 is an example of a report on the administration status of a contrast agent, which is output by the control unit 21 after treatment is completed. The control unit 21 may accept an instruction from the user to change the items and layout to be displayed in the risk report 70.
[0062] The risk report 70 includes a preoperative information section 71, an intraoperative information section 72, a risk assessment section 73, a postoperative management policy section 74, and an IC section 75. Some of the text in each section is a so-called hyperlink. The following explanation will be given taking as an example a case where a user views the risk report 70 using an information device such as a personal computer or tablet.
[0063] When the selection of "Pre-test values (eGFR, CCr)" in the preoperative information field 71 is accepted, the control unit 21 displays the results of biochemical tests and the like performed before endovascular treatment that are recorded in the electronic medical record system 17. "Dialysis performed: No" in the preoperative information field 71 indicates that the patient was not undergoing dialysis before surgery.
[0064] When the control unit 21 receives a selection of "contrast agent administration graph" in the intraoperative information field 72, it displays a graph showing the administration results of the contrast agent, for example, as shown in the graph field 65 of Fig. 6B. When the control unit 21 receives a selection of "change in urinary oxygen partial pressure" in the intraoperative information field 72, it displays a graph showing the change in urinary oxygen partial pressure in addition to the administration results of the contrast agent, for example, as shown in the graph field 65 of Fig. 7.
[0065] "Medium CIN risk" in the risk assessment field 73 indicates that the patient is at a medium risk of developing contrast-induced nephropathy. The controller 21 determines the risk of developing contrast-induced nephropathy based on the amount of contrast agent administered at the end of endovascular treatment and the intraoperative allowable amount. For example, the controller 21 determines the risk of developing contrast-induced nephropathy based on the magnitude relationship between a determination threshold determined based on the intraoperative allowable amount and the amount of contrast agent administered. The controller 21 may also determine the risk of developing contrast-induced nephropathy based on the ratio between the intraoperative allowable amount and the amount of contrast agent administered.
[0066] A specific example will be given below. The controller 21 determines the risk to be "high" when an amount of contrast agent exceeding 1.2 times the intraoperative tolerable amount has been administered, determines the risk to be "medium" when an amount of contrast agent between 1 and 1.2 times the intraoperative tolerable amount has been administered, and determines the risk to be "low" when an amount of contrast agent equal to or less than the intraoperative tolerable amount has been administered.
[0067] The parameters of 1.2 times and 1 time are examples of parameters for calculating the determination threshold for determining risk, and are not limited to these. The threshold may be determined based on, for example, the patient's age or the presence or absence of a history of kidney disease. The control unit 21 may determine risk by dividing it into four or more stages.
[0068] Contrast induced nephropathy is an example of a complication associated with intravascular treatment. The controller 21 may also display the risk of developing a complication other than contrast induced nephropathy.
[0069] "Dialysis: Not required" in the postoperative management policy column 74 indicates that artificial dialysis is not required in postoperative management. "***: Required" indicates that treatment "***" is required in postoperative management. "***: Implemented to patient" in the IC column 75 indicates that informed consent regarding the matter "***" has been obtained from the patient.
[0070] According to the present embodiment, it is possible to provide an information processing system 10 that displays in real time the intraoperative allowable amount of contrast agent that changes in response to the state of the patient's kidneys. A doctor can comprehensively assess the risks and benefits of using a contrast agent and decide whether or not to use a contrast agent.
[0071] For example, for a patient whose kidney condition worsens during endovascular treatment and whose intraoperative tolerance is significantly reduced compared to the preoperative tolerance, the information processing system 10 of this embodiment displays the intraoperative tolerance in real time, allowing the doctor to take appropriate measures, such as reducing the number of angiography procedures from the initial plan to reduce the amount of contrast agent used.
[0072] For example, even when the amount of contrast agent used approaches the preoperative allowable amount nearing the end of an endovascular treatment, the information processing system 10 of this embodiment displays the intraoperative allowable amount that reflects the state of the patient's kidneys in real time, allowing the physician to determine whether to add more contrast agent by referring to the intraoperative allowable amount.
[0073] According to the present embodiment, it is possible to provide an information processing system 10 that supports the determination of whether the amount of contrast agent administered during intravascular treatment exceeds the intraoperative tolerance amount. For patients to whom a contrast agent exceeding the intraoperative tolerance amount has been administered, a doctor can, for example, prescribe a drug that protects the kidney or perform therapeutic intervention to prevent the onset of contrast-induced nephropathy and chronic kidney disease.
[0074] [Variation 1-1] The control unit 21 may display the error range of the intraoperative tolerance. The individual data constituting the renal status index and the hemodynamic information contain measurement errors. The measurement errors are quantified, for example, by the amount of variation in the raw data relative to data obtained by smoothing the raw time-series data using a moving average or the like.
[0075] The control unit 21 can calculate the upper and lower limits of the error range for the intraoperative allowable dose by inputting the upper and lower limits of the measurement error range for each of the renal status index and the circulatory dynamics information into the contrast agent amount model 41 described using Figure 2, for example.
[0076] The control unit 21 outputs, for example, an intraoperative tolerance of the lower limit of the error range. This makes it possible to provide an information processing system 10 that displays an intraoperative tolerance with low risk even when taking into account the effects of measurement errors. The control unit 21 may output intraoperative tolerances of both the upper and lower limits of the error range. The doctor can grasp the extent of the error range of the calculated intraoperative tolerance and make an appropriate decision.
[0077] A safety factor may be set for the intraoperative allowable amount. The control unit 21 outputs a value obtained by dividing the intraoperative allowable amount output from the contrast agent amount model 41 by the safety factor. The safety factor is set to a value of, for example, about 1.1 or 1.2. The control unit 21 may accept a setting of the safety factor by the user.
[0078] A safety constant may be used instead of the safety factor. The control unit 21 outputs a value obtained by subtracting the safety constant from the intraoperative allowable amount output from the contrast agent amount model 41. The control unit 21 may also accept a safety constant set by the user.
[0079] By using a safety factor or safety constant, it is possible to provide an information processing system 10 that displays an intraoperative tolerance with low risk even when taking into account the influence of measurement errors.
[0080] [Variation 1-2] Controller 21 may output a control signal to contrast agent administration pump 36 based on the intraoperative allowable amount and the amount of contrast agent already administered. For example, when the difference between the intraoperative allowable amount and the amount of contrast agent already administered falls below a predetermined threshold, controller 21 outputs a control signal to contrast agent administration pump 36 to reduce the amount of contrast agent administered per contrast injection.
[0081] The control unit 21 may display the contents of the planned instruction before transmitting the instruction to the contrast agent administration pump 36, and after obtaining approval from the user, transmit a control signal to the contrast agent administration pump 36. It is possible to provide an information processing system 10 that reduces the amount of contrast agent used when the amount of contrast agent already administered approaches the intraoperative amount, thereby preventing administration of contrast agent that exceeds the intraoperative amount.
[0082] [Variation 1-3] Controller 21 may receive a command from the user to change the dilution rate of the contrast agent. For example, if the amount of contrast agent administered at one time is reduced, increasing the dilution rate of the contrast agent can reliably image a wider range of blood vessels. When a command to change the dilution rate is received, controller 21 transmits a control signal to contrast agent administration pump 36 to change the dilution rate.
[0083] [Variation 1-4] The dilution rate of the contrast agent may be set manually by a nurse or the like. When the dilution rate is set manually, controller 21 accepts the input of the dilution rate via input unit 26. Controller 21 calculates the amount of contrast agent administered before dilution based on the amount of contrast agent administered obtained from contrast agent administration pump 36, i.e., the amount of contrast agent after dilution, and the dilution rate. Controller 21 executes the series of processes described above using the amount of contrast agent administered before dilution.
[0084] Second Embodiment This embodiment relates to an information processing system 10 that outputs a predicted value of a renal status index relating to the state of the kidneys of a patient. Description of parts common to the first embodiment will be omitted.
[0085] 9 is an explanatory diagram illustrating the renal condition model 42. The renal condition model 42 is a trained model that receives patient information, time-series data of past renal condition indices, and time-series data of past hemodynamic information, and outputs predicted values of future renal condition indices as time-series data.
[0086] The renal condition model 42 is generated by machine learning using a training database that stores many sets of patient information, time-series data of renal condition indicators, and time-series data of circulatory dynamics information. The renal condition model 42 of this embodiment uses an algorithm suitable for processing time-series data, such as LSTM or Transformer.
[0087] The renal condition model 42 may output predicted values for a plurality of renal condition indices. The renal condition model 42 may output predicted values for hemodynamic information.
[0088] 10 is a flowchart illustrating the processing flow of the program according to embodiment 2. The processing up to step S505 is the same as the processing flow of the program according to embodiment 1 described using FIG. 3, and therefore the description thereof will be omitted.
[0089] The control unit 21 inputs the patient information, the time-series renal status index acquired in the previous step S503, and the time-series hemodynamic information acquired in the previous step S504 into the renal status model 42 to acquire a predicted value of the future renal status index (step S511). The control unit 21 outputs information on the intraoperative capacity, the time-series renal status index acquired in the previous step S503, and the future renal status index acquired in step S511 to the output unit 25 or the display system 16 (step S512).
[0090] The control unit 21 determines whether to end the process (step S507). The subsequent process is the same as the process flow of the program of the embodiment described using Fig. 3, and therefore description thereof will be omitted. The loop process from step S502 to step S507 realizes the information processing system 10 that sequentially acquires the projected contrast agent amount, renal status index, and circulatory dynamics information, and outputs a future renal status index based on the changes in these parameters over time.
[0091] Fig. 11 is an example of a screen in the second embodiment. The screen shown in Fig. 11 shows a state in which urinary oxygen partial pressure, an example of a renal condition index, has been added to the graph field 65 of the screen described using Fig. 6. The horizontal axis of the graph field 65 represents time, and the vertical axis represents the amount of contrast agent and the urinary oxygen partial pressure. The thick solid line represents the change over time in the amount of administered contrast agent. The thin solid line represents the change over time in the intraoperative tolerance.
[0092] 11 shows an example of a screen output by the control unit 21 at time t3, which is the current time. The dashed line indicates the actual measured value of urinary oxygen partial pressure up to time t3. The two-dot chain line indicates the predicted value of urinary oxygen partial pressure from time t3 onwards. The black circles indicate each piece of data at the current time.
[0093] The controller 21 scrolls the graph field 65 to the left as time passes so that the current time is positioned in the center of the graph field 65. The user can check the time-series changes in the intraoperative dose, the amount of contrast agent administered, and the urinary oxygen partial pressure over a predetermined time range from the current time, as well as the predicted urinary oxygen partial pressure. At this time, the change in the allowable contrast agent amount after time t3 may also be predicted and displayed in the graph field 65.
[0094] According to the present embodiment, it is possible to provide an information processing system 10 that outputs predicted values of renal status indexes as time-series data. A doctor can check the predicted value of urinary oxygen partial pressure, for example, and take the necessary measures to stabilize the patient's condition.
[0095] [Variation 2-1] Coronary angiography (CAG) may be performed several days before or immediately before endovascular treatment. Based on the renal condition index and hemodynamic information before and after CAG, the accuracy of the future renal condition index output from the renal condition model 42 described using FIG. 9 can be calculated. Based on the calculated accuracy, the control unit 21 may display a prediction error along with the predicted value indicated by the two-dot chain line in FIG. 11.
[0096] Third Embodiment This embodiment relates to an information processing system 10 that outputs a contrast agent usage plan. Explanation of parts common to the first embodiment will be omitted.
[0097] 12 is an explanatory diagram illustrating the record layout of the treatment plan DB 46. The treatment plan DB 46 is a DB that records treatment plan numbers related to various surgical procedures and treatment plans in association with each other. The treatment plan DB 46 has a treatment plan ID field and a treatment plan field.
[0098] The treatment plan ID field records a treatment plan ID unique to each treatment plan. The treatment plan field records a series of treatment procedures and the amount of contrast agent to be administered in each procedure in chronological order. Although not shown, the amount of contrast agent may be recorded as a range value, such as "**±** mL."
[0099] Each procedure recorded in the treatment plan field is a standard procedure for performing a treatment, such as PCI or TAVI, on a patient with a different condition.
[0100] For example, even when the same TAVI treatment is performed, the appropriate treatment plan will differ depending on the patient's age, physique, location of calcification, whether or not they have had a history of open heart surgery, and their overall condition. For example, a series of endovascular treatments may involve multiple surgical procedures, such as PCI and TAVI. Treatment plans tailored to various situations are recorded in the treatment plan field. The treatment plan DB 46 has one record for each treatment plan.
[0101] FIG. 13 is an explanatory diagram illustrating the planning model 43. The planning model 43 is a model that receives input of patient information and surgical procedure information regarding the surgical procedure planned for the patient, and outputs a treatment plan ID. The planning model 43 is a trained model that has been trained using training data that records a large number of sets of patient information, surgical procedures, and treatment plan IDs selected by experienced physicians in association with each other. The planning model 43 is generated using a machine learning algorithm such as XGBoost, random forest, or CNN.
[0102] The planning model 43 may be a rule-based algorithm generated based on guidelines established by a medical society or the like. Instead of using the planning model 43, a doctor may select a treatment plan ID based on his or her specialized knowledge. The planning model 43 may output multiple treatment plan IDs and accept a doctor's selection from the output treatment plan IDs.
[0103] 14 is a flowchart illustrating the processing flow of the program according to the third embodiment. The control unit 21 acquires patient information including background information, medical history information, and biochemical test results of the patient, as well as preoperative information such as the preoperative allowable dose of contrast agent (step S501). The control unit 21 then acquires information regarding the surgical procedure planned for the patient (step S521).
[0104] The control unit 21 inputs the patient information acquired in step S501 and the surgical procedure acquired in step S521 into the planning model 43 to acquire a treatment plan ID (step S522). The control unit 21 searches the treatment plan DB 46 using the treatment plan ID acquired in step S522 as a key to extract a record. The control unit 21 outputs information about the treatment plan recorded in the treatment plan field of the extracted record to the output unit 25 or the display system 16 (step S523).
[0105] The control unit 21 acquires the amount of contrast agent already administered to the patient from the contrast agent administration pump 36 (step S502). The control unit 21 acquires the progress status of the treatment (step S531). For example, the control unit 21 acquires real-time images from the imaging diagnostic device 15, performs image analysis, and acquires the progress status, such as whether a guidewire has been inserted. The control unit 21 may accept input of information regarding the progress of the treatment by the user. The user can input the progress status by voice, for example, by saying, "POBA (Plain Old Balloon Angioplasty) completed."
[0106] The control unit 21 acquires a renal status index from the urine measurement device 31 (step S503). The control unit 21 acquires circulatory dynamics information from the vital sign monitor 33 (step S504). The control unit 21 inputs the patient information, renal status index, and circulatory dynamics information into the contrast agent amount model 41 to acquire the intraoperative allowable amount (step S505). The control unit 21 outputs information to update the information output in step S523 (step S532).
[0107] The control unit 21 determines whether or not to end the process (step S507). If it is determined not to end the process (NO in step S507), the control unit 21 returns to step S502. If it is determined to end the process (YES in step S507), the control unit 21 outputs the report to the output unit 25 or the display system 16 (step S508). The control unit 21 may output the report to the electronic medical record system 17. The control unit 21 ends the process.
[0108] Fig. 15 is an example of a graph column 65 in embodiment 3. Fig. 15 shows the graph column 65 portion of the screen example described using Fig. 6. The control unit 21 outputs the graph column 65 shown in Fig. 15A in step S523 of the program described using Fig. 14. The control unit 21 outputs the graph column 65 shown in Fig. 15B in step S532, which is executed around time t11 of the program described using Fig. 14.
[0109] In Figure 15, a treatment progress column 66 showing major treatment items is displayed below the horizontal axis. In the treatment plan shown in Figure 15, two POBAs are performed after guidewire insertion. The thin solid line indicates the preoperative allowable dose. The thick solid line indicates the planned amount of contrast agent to be used when contrast agent is administered according to the treatment plan. The thick solid line in Figure 15 is an example of the format in which the contrast agent use plan is output.
[0110] The dashed lines above and below the thick solid line indicate the upper and lower limits of the range of contrast agent dosages included in the treatment plan. The upper and lower limits may be a predetermined error range, such as ±5 percent. The dashed and dotted lines above and below the thin solid line indicate the upper and lower limits of the calculated error for the preoperative and intraoperative dosages.
[0111] 15A, when the contrast agent is administered according to the upper limit of the treatment plan, the amount of contrast agent administered between the first and second POBAs exceeds the preoperative tolerance amount. Based on the graph shown in FIG. 15A, a physician can recognize that it is desirable to use the contrast agent at an amount that does not exceed the standard amount of contrast agent.
[0112] In Figure 15B, the treatment plan up to time t11 has been executed. The amount of contrast agent administered up to time t11 is shown with a double line. In Figure 15B, the patient's renal condition is stable, and the intraoperative allowable amount has not changed from the preoperative allowable amount. The contrast agent is being administered in accordance with the standard values set forth in the treatment plan. Based on the graph shown in Figure 15B, the physician can check the progress of the treatment plan and the amount of contrast agent used, and recognize that treatment is proceeding according to the treatment plan.
[0113] The error ranges of the preoperative dose and intraoperative dose, indicated by thin solid lines, may be displayed in graph column 65. The error in the amount of contrast agent administered by contrast agent administration pump 36 may be displayed together with the actual value, indicated by double lines in Figure 15B.
[0114] According to the present embodiment, it is possible to provide an information processing system 10 that outputs a contrast agent use plan based on a treatment plan, and it is possible to provide an information processing system 10 that allows a user to easily confirm that a contrast agent is being administered in accordance with the treatment plan.
[0115] 15A . For example, the doctor can delete the second POBA by operating the input unit 26. The control unit 21 modifies the contrast agent administration plan based on the modified treatment plan and displays it in the graph field 65. Specifically, the control unit 21 displays in the graph field 65 a contrast agent administration plan in which the contrast agent that was scheduled to be administered in response to the deleted POBA has been reduced.
[0116] 16 is an explanatory diagram illustrating the configuration of an information processing system 10 according to a fourth embodiment. This embodiment relates to a form in which an information processing device 20 is realized by combining and operating a general-purpose computer 90 and a program 97. Explanations of parts common to the first embodiment will be omitted.
[0117] The computer 90 includes a reading unit 29 in addition to the control unit 21, main memory unit 22, auxiliary memory unit 23, communication unit 24, output unit 25, input unit 26 and bus.
[0118] The program 97 is recorded on a portable recording medium 96. The control unit 21 reads the program 97 via the reading unit 29 and stores it in the auxiliary storage device 23. The control unit 21 may also read the program 97 stored in a semiconductor memory 98, such as a flash memory, implemented in the computer 90. Furthermore, the control unit 21 may download the program 97 from another server computer (not shown) connected via the communication unit 24 and a network (not shown) and store it in the auxiliary storage device 23.
[0119] The program 97 is installed as a control program for the computer 90, and is loaded into the main storage device 22 and executed. In this way, the information processing device 20 described in the first embodiment is realized. The program 97 in this embodiment is an example of a program product.
[0120] The technical features (constituent elements) described in each embodiment can be combined with each other, and by combining them, new technical features can be formed. The embodiments disclosed herein are illustrative in all respects and should be considered not to be limiting. The scope of the present invention is defined by the claims, not by the meaning described above, and is intended to include all modifications within the meaning and scope of the claims.
[0121] (Supplementary Note 1) A program that causes a computer to execute the following processes: acquire patient information about a patient who will receive treatment and surgical procedure information about a surgical procedure planned for the patient; acquire a treatment plan based on the patient information and the surgical procedure information; and output a contrast agent usage plan for the patient based on the treatment plan.
[0122] (Supplementary Note 2) The program according to Supplementary Note 1, which acquires a preoperative allowable amount of a contrast agent to be administered to the patient, calculated based on the patient information, and outputs the preoperative allowable amount together with the contrast agent use plan.
[0123] (Supplementary Note 3) The program according to Supplementary Note 1 or Supplementary Note 2, which receives a modification of the treatment plan, modifies the contrast agent usage plan based on the modified treatment plan, and outputs the modified contrast agent usage plan.
[0124] (Supplementary Note 4) The program according to any one of Supplementary Note 1 to Supplementary Note 3, wherein the contrast agent usage plan includes information regarding an error range of the amount of contrast agent used.
[0125] (Supplementary Note 5) A program described in any one of Supplementary Note 1 to Supplementary Note 4, which outputs the contrast agent usage plan in the form of a graph showing the relationship between the progress of the treatment plan and the planned amount of contrast agent to be used, acquires the progress of the treatment plan, acquires the amount of contrast agent that has been administered to the patient, and changes the planned amount of contrast agent to the amount of contrast agent that has been administered for the portion of the graph where the treatment plan has been executed, and outputs the graph.
[0126] (Appendix 6) A program described in any one of Appendices 1 to 5, which acquires a renal status index relating to the state of the patient's kidneys during treatment, calculates an intraoperative tolerance amount of contrast agent to be administered to the patient based on the renal status index and the patient information, and outputs information relating to the intraoperative tolerance amount.
[0127] (Supplementary Note 7) An information processing method in which a computer executes the processes of acquiring patient information about a patient who will receive treatment and surgical procedure information about a surgical procedure planned for the patient, acquiring a treatment plan based on the patient information and the surgical procedure information, and outputting a contrast agent use plan for the patient based on the treatment plan.
[0128] (Supplementary Note 8) An information processing device including a control unit, wherein the control unit acquires patient information regarding a patient receiving treatment and surgical procedure information regarding a surgical procedure planned for the patient, acquires a treatment plan based on the patient information and the surgical procedure information, and outputs a contrast agent usage plan for the patient based on the treatment plan.
[0129] 10 Information processing system 15 Diagnostic imaging device 16 Display system 17 Electronic medical record system 20 Information processing device 21 Control unit 22 Main memory device 23 Auxiliary memory device 24 Communication unit 25 Output unit 26 Input unit 29 Reading unit 31 Urine measurement device 311 Urine sensor 33 Vital monitor 36 Contrast agent administration pump 41 Contrast agent amount model (trained model) 42 Renal status model 43 Planning model 46 Treatment planning DB 61 Dosage gauge 62 Administered contrast agent amount column 63 Difference column 64 Intraoperative allowable amount column 65 Graph column 66 Treatment progress column 70 Risk report 71 Preoperative information column 72 Intraoperative information column 73 Risk assessment column 74 Postoperative management policy column 75 IC column 90 Computer 96 Portable recording medium 97 Program 98 Semiconductor Memory
Claims
1. obtaining a renal status index relating to a renal status of a patient during treatment of said patient; calculating an intraoperative tolerance for a contrast agent to be administered to the patient based on the renal status index and patient information regarding the patient; Outputting information regarding the intraoperative allowance A program that causes a computer to carry out processing.
2. the patient information includes background information about the patient and medical history information of the patient; The patient information, the renal condition index, and the hemodynamic information of the patient are input to a trained model that outputs an intraoperative tolerance when the patient information, the renal condition index, and the hemodynamic information are input, and the intraoperative tolerance is obtained. The program according to claim 1.
3. The circulatory dynamics information includes at least one of pulse pressure, mean blood pressure, heart rate, blood oxygen saturation, tissue oxygen saturation, and intravesical pressure. The program according to claim 2.
4. The renal condition index is at least one of urine flow rate, urine volume, urinary oxygen partial pressure, and urine color. The program according to claim 1.
5. Sequentially acquiring the renal status index; Calculating a future renal status index based on the change in the renal status index over time; The calculated renal status index is output. The program according to claim 1.
6. obtaining an administered amount of contrast agent administered to the patient; A risk of the patient developing renal dysfunction is output based on the administered amount of contrast medium and the intraoperative allowable amount. The program according to claim 1.
7. obtaining an administered amount of contrast agent administered to the patient; A control signal for a contrast medium administration pump is output based on a difference between the intraoperative allowable amount and the administered amount of contrast medium. The program according to claim 1.
8. Outputting the renal status index to a display system. The program according to claim 1.
9. Outputting the calculation error of the intraoperative tolerance together with information about the intraoperative tolerance The program according to claim 1.
10. The information regarding the intraoperative tolerance is a value obtained by setting a safety factor for the calculated intraoperative tolerance. The program according to claim 1.
11. After the treatment of the patient is completed, a report on the administration of the contrast agent is output. The program according to claim 1.
12. The report may include information about the intraoperative tolerance, the amount of contrast administered to the patient, or the patient's risk of developing a complication. The program according to claim 11.
13. The patient information includes information regarding contrast agents previously administered to the patient. A program according to any one of claims 1 to 12.
14. obtaining a renal status index relating to a renal status of a patient during treatment of said patient; calculating an intraoperative tolerance for a contrast agent to be administered to the patient based on the renal status index and patient information regarding the patient; Outputting information regarding the intraoperative allowance An information processing method in which processing is performed by a computer.
15. An information processing device including a control unit, The control unit is obtaining a renal status index relating to a renal status of a patient during treatment of said patient; calculating an intraoperative tolerance for a contrast agent to be administered to the patient based on the renal status index and patient information regarding the patient; Outputting information regarding the intraoperative allowance Information processing device.
