Information processing device, information processing method, and program

Abstract

To provide an information processing device, an information processing method and a program capable of grasping a trend in prediction accuracy of a biological parameter.SOLUTION: A central monitor 200 includes an acquisition part 211 for acquiring object person information including at least one of information on a patient and information on a medical worker, measurement information on a biological parameter of the patient, and prediction information on the biological parameter of the patient predicted by the medical worker, an analysis part 215 for analyzing a relation between the object person information, and the degree of deviation between the prediction information and the measurement information, and an output part 216 for outputting analysis information representing a relation between the object person information and the degree of deviation.SELECTED DRAWING: Figure 5

Description

[Technical Field]

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

[0002] In medical institutions such as hospitals, for example, changes over time in a patient's biological parameters, such as heart rate, are measured (Patent Document 1, etc.). Medical professionals such as doctors, for example, check the changes in these biological parameters and predict the future condition of each patient to treat them. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Special Publication No. 2017-503569 Summary of the Invention [Problem to be solved by the invention]

[0004] The accuracy of predicting changes in biological parameters varies depending on the patient's age and disease, and also on the medical department and years of experience of the medical professional. By understanding such trends in prediction accuracy, medical institutions can provide more appropriate treatment for each patient.

[0005] Therefore, an object of the present invention is to provide an information processing device, an information processing method, and a program that are capable of grasping the trend in prediction accuracy of biological parameters. [Means for solving the problem]

[0006] The above-mentioned problems of the present invention are solved by the following means.

[0007] The information processing device of the present invention includes an acquisition unit that acquires subject information including at least one of information about a patient and information about a medical professional, measurement information about the patient's biological parameters, and predicted information about the patient's biological parameters predicted by the medical professional, an analysis unit that analyzes the relationship between the subject information and the degree of deviation between the predicted information and the measurement information, and an output unit that outputs analysis information representing the relationship between the subject information and the degree of deviation. [Effects of the Invention]

[0008] The information processing device according to the present invention analyzes the relationship between subject information and the degree of discrepancy between predicted information and measured information, and outputs the analysis information, allowing users such as medical professionals to confirm the relationship between at least one of the patient and the medical professional and the magnitude of the discrepancy, thereby making it possible to grasp the trend in the prediction accuracy of biological parameters. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is a diagram illustrating an example of the overall configuration of an information processing system according to an embodiment of the present invention. [Figure 2] 2 is a block diagram illustrating an example of the configuration of the bedside monitor illustrated in FIG. 1. FIG. [Figure 3] 2 is a block diagram illustrating an example of the configuration of a central monitor illustrated in FIG. 1. [Figure 4] 4 is a diagram illustrating an example of a screen displayed on the display unit illustrated in FIG. 3. FIG. [Figure 5] 4 is a block diagram illustrating an example of the functions of a control unit illustrated in FIG. 3. FIG. [Figure 6] 5A and 5B are diagrams illustrating an example of analysis information output from the output unit illustrated in FIG. 4. [Figure 7] 2 is a flowchart illustrating an example of a process of the central monitor illustrated in FIG. 1. [Figure 8] 10 is a flowchart illustrating an example of a process of a central monitor according to Modification 1. [Figure 9]9(A) and 9(B) are diagrams illustrating an example of analysis information output from the central monitor illustrated in FIG. 8. [Figure 10] FIG. 10 is a diagram illustrating an example of the overall configuration of an information processing system according to a second modification. [Figure 11] 11 is a diagram illustrating another example of the overall configuration of the information processing system illustrated in FIG. DETAILED DESCRIPTION OF THE INVENTION

[0010] An information processing device and an information processing system according to an embodiment of the present invention will be described in detail below with reference to the drawings. In the drawings, identical elements are designated by the same reference numerals, and duplicated descriptions will be omitted.

[0011] <Embodiment> [Configuration of Information Processing System 1] FIG. 1 is a schematic configuration diagram of an information processing system 1. The information processing system 1 includes, for example, a bedside monitor 100 and a central monitor 200. The central monitor 200 and the bedside monitor 100 are connected to each other so that they can communicate with each other via a wired or wireless network. The network may be, for example, a local area network (LAN) or a wide area network (WAN). The network communication standard may be, for example, Ethernet (registered trademark), Wi-Fi (registered trademark), Bluetooth (registered trademark), or 5G. For example, multiple bedside monitors 100 are connected to one central monitor 200. Here, the central monitor 200 corresponds to a specific example of an information processing device of the present invention.

[0012] (Bedside Monitor 100) 2 is a block diagram of the hardware configuration of the bedside monitor 100. The bedside monitor 100 includes, for example, a control unit 110, a storage unit 120, a communication unit 130, a sensor 140, a display unit 150, and an input unit 160. These components are interconnected by a bus. Some components may be connected to the bus via wireless communication. A bedside monitor 100 may be provided for each patient's bed or each patient's room, for example.

[0013] The control unit 110 is configured with, for example, a CPU (Central Processing Unit) and RAM (Random Access Memory), and controls each component of the bedside monitor 100 and performs various calculations. The control unit 110 transmits biological parameters measured by the sensor 140 to the central monitor 200 via the communication unit 130. The biological parameters measured by the sensor 140 include, for example, parameters related to the heart, blood pressure, respiration, circulation, brain, body temperature, and blood, and specifically, heart rate (HR), arterial oxygen saturation (SpO2), non-invasive blood pressure (NIBP), respiratory rate (rRESP), invasive blood pressure (ART), central venous pressure (CVP), regional cerebral oxygen saturation (rSO2), inhaled oxygen concentration (FiO2), expired carbon dioxide partial pressure (RR(CO2)), end-tidal carbon dioxide partial pressure (etCO2), arterial oxygen partial pressure (PaO2), arterial carbon dioxide partial pressure (PaCO2), P / F ratio (P / F Ratio), acidity (PH), continuous cardiac output (CCO2), and body temperature.

[0014] When an abnormality is detected in a biological parameter measured by the sensor 140, the control unit 110 may transmit an alarm notifying the abnormality to the central monitor 200 via the communication unit 130. Abnormalities notified by the alarm include, for example, an abnormality in the measured biological parameter, an abnormality in an apparatus including the measuring equipment (devices and elements) constituting the sensor 140, an abnormality in the attachment state such as the sensor 140 being removed from the patient, and an abnormality in the measurement environment such as radio wave loss or noise interference.

[0015] The control unit 110 transmits measurement information on the biological parameters of each patient measured by the sensor 140 to the central monitor 200. This measurement information is associated with, for example, identification information for identifying the patient. The identification information includes, for example, the patient's bed number, the patient's ID, and the IP address of the bedside monitor 100.

[0016] The storage unit 120 is configured by, for example, an SSD (Solid State Drive), and stores various programs including an operating system and various data.

[0017] The communication unit 130 is an interface for communicatively connecting the bedside monitor 100 and the central monitor 200. The communication unit 130 may be configured with, for example, an input terminal, an antenna, a front-end circuit, and the like.

[0018] The sensor 140 is a device or element that detects a biological parameter. Examples of the sensor 140 include an electrocardiogram electrode and an SpO2 probe. The bedside monitor 100 may have multiple sensors 140. The sensor 140 may be configured to be detachable from the bedside monitor 100.

[0019] The display unit 150 displays (outputs) the patient's biological parameters measured by the sensor 140 in a visually recognizable manner. The biological parameters are displayed, for example, as numerical values, waveforms, graphs, etc. on the display unit 150. The display unit 150 may be configured, for example, by a liquid crystal display, etc.

[0020] The input unit 160 accepts various inputs from the user. For example, medical professionals such as doctors and nurses input various pieces of information to the bedside monitor 100 via the input unit 160. The input unit 160 is configured, for example, by operation buttons, a mouse, or a keyboard. The display unit 150 and the input unit 160 may be configured integrally, and for example, they may be configured by a touch panel display or the like.

[0021] (Central Monitor 200) 3 is a block diagram of the hardware configuration of the central monitor 200. The central monitor 200 includes a control unit 210, a storage unit 220, a communication unit 230, a display unit 240, and an input unit 250. These components are connected to each other via a bus. The basic configurations of these components are similar to the basic configurations of the corresponding components of the bedside monitor 100, so redundant explanations will be omitted. The central monitor 200 is configured to be able to aggregate and display biological parameters of multiple patients received from each bedside monitor 100, for example, and is placed in a nurse's station or the like.

[0022] The control unit 210 receives measurement information relating to the patient's biological parameters measured by the sensor 140 and patient identification information from each bedside monitor 100 via the communication unit 230. Specific functions of the control unit 210 will be described later. The control unit 210 may receive an alarm from each bedside monitor 100 and output alarm information relating to this alarm to the display unit 240 or the like.

[0023] The storage unit 220 stores the measurement information and the identification information in association with the time of reception. The measurement information may be stored in association with the identification information. The storage unit 220 also stores prediction information regarding the patient's biological parameters predicted by a medical professional such as a doctor. The prediction information is input by the medical professional, for example, via the input unit 250. The medical professional inputs the prediction information based on, for example, the patient's current condition. The medical professional may input the prediction information by referring to the values ​​of the patient's current biological parameters measured by the sensor 140.

[0024] FIG. 4 shows an example of a screen (screen 241) displaying prediction information. This screen 241 displays prediction information obtained by Doctor A, a medical professional, predicting each biological parameter of Patient B. Doctor A predicts Patient B's ART, CVP, PaO2, and PaCO2 at 7:00 AM on September 1, 7:00 AM on September 2, and 7:00 AM on September 3, based on Patient B's ART, CVP, PaO2, and PaCO2 values ​​measured by the sensor 140 at 7:00 AM on August 31. That is, Doctor A inputs prediction information (predicted values) regarding Patient B's biological parameters 24 hours, 48 ​​hours, and 72 hours after the reference date and time of 7:00 AM on August 31. For example, the screen 241 displays measurement information regarding Patient B's biological parameters measured at the date and time corresponding to this prediction information (hereinafter referred to as the predicted date and time). In FIG. 4, the values ​​(actual measurements) of ART, CVP, PaO2 and PaCO2 of patient B measured by the sensor 140 at 7:00 on September 1st, 7:00 on September 2nd and 7:00 on September 3rd are displayed.

[0025] The storage unit 220 may store patient information about each patient. The patient information is, for example, information about the patient's condition and history, such as the patient's gender, age, body shape, smoking history, underlying diseases, medical history, height, weight, reason for hospitalization, reason for admission to an intensive care unit or the like, disease name, medication status, pneumonia onset status, and surgery status. The storage unit 220 may also store medical worker information about each medical worker. The medical worker information is, for example, information about the medical worker's condition and history, such as the medical worker's department of practice and years of experience.

[0026] The communication unit 230 is an interface for connecting to each bedside monitor 100. The communication unit 230 may be configured to enable the central monitor 200 to be further connected to other devices.

[0027] The display unit 240 aggregates and displays (outputs) the biological parameters of each patient received by the control unit 210 from multiple bedside monitors 100. The input unit 250 accepts various inputs from users such as medical professionals. Medical professionals input predicted information for each patient via this input unit 250. For example, the user may input numerical values ​​as predicted information from a keyboard or the like, or may select a predetermined position or area on a graph or the like using a mouse or the like.

[0028] 5 is a block diagram showing an example of the functional configuration of the control unit 210. In the central monitor 200, for example, the control unit 210 reads a program stored in the storage unit 220 and executes processing, thereby functioning as an acquisition unit 211, a classification unit 212, a type designation unit 213, a calculation unit 214, an analysis unit 215, and an output unit 216.

[0029] The acquisition unit 211 acquires subject information, measurement information, and prediction information. The subject information includes at least one of patient information about the patient and medical professional information about the medical professional. The patient information is information about the patient whose biological parameters are measured by the sensor 140, i.e., the subject of the measurement information (e.g., patient B in FIG. 4). The medical professional information is information about the medical professional who predicted the future biological parameters based on the measurement information of the subject at a specific date and time, i.e., the predictor of the prediction information (e.g., doctor A in FIG. 4). It is preferable that the subject information includes patient information and medical professional information. This increases the amount of information acquired, enabling more accurate analysis.

[0030] As described above, the measurement information is information about the biological parameters of the patient measured by the sensor 140, and is, for example, the measured values ​​(actual measured values) of the biological parameters (see FIG. 4). The measurement information acquired by the acquisition unit 211 includes, for example, information such as the measurement date and time (or measurement time). It is preferable that this measurement information includes information about the biological parameters measured around the predicted date and time of the prediction information acquired by the acquisition unit 211.

[0031] As described above, the prediction information is information about a patient's biological parameters predicted by a medical professional, for example, a predicted value of the biological parameter (see FIG. 4). The prediction information acquired by the acquisition unit 211 includes, for example, information about a reference date and time (or reference time) and the like. The reference date and time is, for example, the date and time when the prediction information is input by the input unit 250. The reference date and time may be the date and time when the patient's biological parameters, which are the basis for the prediction, are measured. The prediction information may include information about the prediction date and time. The prediction information may be an index of a biological parameter that represents the future condition of the patient, and may be, for example, a target value such as a value in a clinical guideline. The target value in the guideline may be a value in the guideline of various academic societies, or may be a value obtained by modifying the value in the guideline of various academic societies by each facility.

[0032] The prediction information preferably includes information related to the prediction of changes in the biological parameter over time, and preferably includes, for example, first prediction information measured a first time after the reference date and time and second prediction information measured a second time after the reference date and time. The first time is, for example, 24 hours, and the second time is, for example, 72 hours (see FIG. 4). In this case, the measurement information preferably includes first measurement information measured a first time after the reference date and time and second measurement information measured a second time after the reference date and time. That is, the measurement information acquired by the acquisition unit 211 preferably includes first measurement information and second measurement information measured at the predicted dates and times of the first prediction information and the second prediction information (see FIG. 4). This makes it possible to check changes over time in the degree of discrepancy between the measurement information and the prediction information. The prediction information may further include multiple pieces of prediction information for other predicted dates and times, and the measurement information may further include measurement information measured at other dates and times.

[0033] The acquisition unit 211 preferably acquires measurement information and prediction information relating to a plurality of types of biological parameters, thereby increasing the amount of acquired information and enabling more accurate analysis.

[0034] The acquisition unit 211 acquires, for example, a plurality of pieces of subject information, a plurality of pieces of measurement information, and a plurality of pieces of prediction information. The subject information, the measurement information, and the prediction information are associated with each other based on the relationship between the patient whose biological parameters are measured (e.g., patient B in FIG. 4) and the medical professional who makes the prediction (e.g., doctor A in FIG. 4).

[0035] The classification unit 212 classifies the subject information acquired by the acquisition unit 211 into a plurality of categories. For example, the classification unit 212 classifies patient information included in each of the plurality of subject information into a plurality of categories, and classifies medical professional information included in each of the plurality of subject information into a plurality of categories. The classification unit 212 classifies the patient information into a plurality of categories based on, for example, the patient's gender, age, body shape, smoking history, underlying disease, medical history, height, weight, reason for hospitalization, reason for admission to an intensive care unit or the like, disease name, medication status, pneumonia onset status, surgery status, etc. The classification unit 212 classifies the medical professional information into a plurality of categories based, for example, on the medical department and years of experience of the medical professional.

[0036] The classification unit 212 determines categories for classifying the subject information based on, for example, instructions from the user. The user inputs instructions, for example, via the input unit 250. This allows the user to freely determine categories according to the application. The categories may be determined in advance, or the classification unit 212 may determine categories using statistics, machine learning, or the like. The classification unit 212 may determine categories based on numerical values ​​or attributes included in the subject information. The numerical values ​​may be, for example, the patient's age and the medical professional's years of experience, and the attributes may be, for example, the patient's disease and the medical professional's medical department.

[0037] The type designation unit 213 designates the type of biological parameter for the measurement information and prediction information acquired by the acquisition unit 211. The type designation unit 213 designates the type of biological parameter based on, for example, an instruction from a user. The user inputs the instruction via, for example, the input unit 250. The acquisition unit 211 may acquire the measurement information and prediction information related to the type of biological parameter designated by the type designation unit 213. By designating the type of biological parameter, it becomes possible to perform analysis that is more suited to the user's purpose.

[0038] The calculation unit 214 calculates the degree of discrepancy between the predicted information and the measured information acquired by the acquisition unit 211. The degree of discrepancy is an index representing the accuracy of prediction of a patient's biological parameters by a medical professional. A large degree of discrepancy indicates low prediction accuracy, and a small degree of discrepancy indicates high prediction accuracy. The degree of discrepancy is, for example, the difference between the predicted information and the measured information. When multiple differences can be calculated, the degree of discrepancy may be the median, average value, etc. of the multiple differences. The calculation unit 214 calculates, for example, the degree of discrepancy between the predicted information and the measured information related to the type of biological parameter designated by the type designation unit 213.

[0039] The calculation unit 214 calculates, for example, the degree of deviation between prediction information at a predetermined prediction date and time and measurement information measured at this prediction date and time. For example, the calculation unit 214 calculates the difference (+8) between the predicted value 110 of ART at the prediction date and time, September 1st, 7:00 and the measurement value 102 of ART measured at September 1st, 7:00 (see FIG. 4). As described above, when the acquisition unit 211 acquires the first prediction information and the second prediction information and the first measurement information and the second measurement information, the calculation unit 214 calculates a first degree of deviation between the first prediction information and the first measurement information and a second degree of deviation between the second prediction information and the second measurement information.

[0040] The calculation unit 214 may calculate the discrepancy by normalizing each biological parameter. The calculation unit 214 may weight each biological parameter and calculate a composite discrepancy in which the discrepancies of multiple types of biological parameters are taken into consideration. This composite discrepancy is calculated, for example, as follows. First, a weight of the vector space is set for each biological parameter, and then the simplex discrepancy of each biological parameter axis is calculated, and a point on the vector space is found from the simplex discrepancy. The vector length from this point to the origin is calculated as the composite discrepancy.

[0041] The central monitor 200 may have a function of issuing a notification when the magnitude of the deviation calculated by the calculation unit 214 exceeds a predetermined value. This function can be switched on / off by, for example, a user setting, and this on / off can be set, for example, for each biological parameter. This allows the user to set an alert only for parameters of particular interest. Furthermore, a notification may be issued when the magnitude of the deviation for at least one biological parameter exceeds a predetermined value. Such a notification function allows medical personnel to easily notice a deviation between predicted information and measured information, allowing them to take action, such as changing a treatment plan, early on. The magnitude of the deviation and the threshold at which a notification is issued are set, for example, for each biological parameter.

[0042] The above notification may be made, for example, by displaying a warning message on the display unit 240, or by changing the way the deviation degree is displayed (for example, by changing the color of the numerical value, the background color, etc.). The notification may also be made by sending a warning email to the terminal of the person concerned, or by emitting an alarm sound from a speaker or the like.

[0043] The analysis unit 215 analyzes the relationship between the subject information acquired by the acquisition unit 211 and the degree of deviation calculated by the calculation unit 214. Specifically, the analysis unit 215 analyzes the relationship between the patient information and medical professional information included in the subject information and the magnitude of the degree of deviation. The analysis unit 215 analyzes the relationship between the subject information and the degree of deviation for each category of subject information classified by the classification unit 212, for example. This makes it possible to analyze the relationship between each category of patient or medical professional and the prediction accuracy. When the calculation unit 214 calculates the first degree of deviation and the second degree of deviation, the analysis unit 215 analyzes the relationship between the subject information and the first degree of deviation and also analyzes the relationship between the subject information and the second degree of deviation. This makes it possible to analyze the relationship between the subject information and the accuracy of each of the short-term prediction and the long-term prediction.

[0044] The output unit 216 outputs analytical information representing the relationship between the subject information analyzed by the analysis unit 215 and the degree of discrepancy. The output unit 216 outputs analytical information, for example, for each category classified by the classification unit 212. By checking this analytical information, users such as medical professionals can understand the level of prediction accuracy for each category to which the subject information belongs. The analytical information includes, for example, information regarding the confidence interval of the degree of discrepancy (for example, FIG. 6(A) described below). The confidence interval is, for example, a 95% confidence interval. The analytical information may also include information regarding the degree of discrepancy, i.e., a graded evaluation according to the prediction accuracy (for example, FIG. 6(B) described below).

[0045] 6(A) and 6(B) show examples of analysis information output by the output unit 216. FIGS. 6(A) and 6(B) show the prediction accuracy of medical professionals in categories 2 and 3 for the biological parameters of a patient in category 1. The types of predicted biological parameters are ART, CVP, PaO2, and PaCO2. FIG. 6(A) shows the discrepancy between the predicted information and the measured information for these biological parameters 24 hours and 72 hours after the reference date and time. In FIG. 6(A), the value outside the parentheses is the median of the difference between the predicted information and the measured information, and the value inside the parentheses is the 95% confidence interval of this difference. In FIG. 6(B), ratings A and B are graded according to the degree of discrepancy, with rating A indicating a smaller degree of discrepancy than rating B, i.e., indicating higher prediction accuracy. The graded rating is, for example, on a five-point scale. The rating is determined, for example, based on the median and 95% confidence interval of the discrepancy.

[0046] Patient category 1 and medical staff categories 2 and 3 are, for example, as follows:

[0047] (Patient Category 1) Age: 65 or older Gender: Male Reason for admission to an intensive care unit: After cardiac surgery Medication status: prescribed medication Underlying disease: hypertension (Category 2 for healthcare workers) Department: Cardiac surgeon Years of experience: 10+ years (Category 3 for healthcare workers) Department: Intensive care physician Years of experience: 10+ years.

[0048] In this embodiment, the central monitor 200 outputs analytical information that indicates the relationship between the subject information and the degree of discrepancy, allowing users such as medical professionals to confirm the relationship between at least one of the patient and the medical professional and the magnitude of the degree of discrepancy. As will be described in detail later, this allows users to understand the trend in the prediction accuracy of biological parameters.

[0049] The central monitor 200 may issue a notification when the deviation is large in the analysis information to be output. The notification may be made, for example, by displaying a warning message on the display unit 240, or by changing the display method of the deviation or category (for example, by changing the color of the numerical value, changing the background color, etc.). The magnitude of the deviation and the threshold at which the notification is issued are set, for example, for each biological parameter.

[0050] [How to process Central Monitor 200] Next, the analysis process of the subject information, measurement information, and prediction information by the central monitor 200, that is, the information processing method by the central monitor 200, will be described with reference to FIG. 7 together with FIG. 6(A).

[0051] 7 is a flowchart showing the analysis process of the central monitor 200. This flowchart can be executed by the control unit 210 of the central monitor 200 in accordance with a program.

[0052] First, the control unit 210 acquires the subject information, the measurement information, and the prediction information (steps S101 and S102). The control unit 210 may acquire the subject information, the measurement information, and the prediction information simultaneously, or may acquire the subject information after acquiring the measurement information and the prediction information.

[0053] Next, the control unit 210 receives a designation of the type of biological parameter (step S103). For example, the control unit 210 receives a designation of ART, CVP, PaO2, and PaCO2 from the user via the input unit 250 (FIG. 6(A)).

[0054] Next, the control unit 210 calculates the degree of discrepancy between the measurement information and prediction information acquired in step S102 for the type of biological parameter designated in step S103 (step S104). The control unit 210, for example, subtracts the measured values ​​of ART 24 hours and 72 hours after the reference date and time from the predicted values ​​of ART 24 hours and 72 hours after the reference date and time, and calculates the difference between them (FIG. 6(A)). When the magnitude of this discrepancy exceeds a predetermined value, the control unit 210 notifies the same using the display unit 240, for example.

[0055] Next, the control unit 210 determines a plurality of categories and classifies the subject information into the plurality of categories (step S105). For example, based on an instruction from the user via the input unit 250, the control unit 210 classifies the patient information according to age, sex, reason for admission to an intensive care unit or the like, and medication status, and classifies the medical professional information according to medical department and years of experience.

[0056] Next, the control unit 210 analyzes the relationship between the subject information and the deviation for each category classified in step S105 (step S106). The deviation calculated in step S104 is used. The control unit 210, for example, calculates and analyzes the median and 95% confidence interval of the deviation for each category (FIG. 6(A)).

[0057] Thereafter, the control unit 210 outputs the analysis information analyzed in step S106 (step S107) and ends the process. The control unit 210 outputs the analysis information by, for example, displaying the screen shown in FIG. 6(A) on the display unit 240.

[0058] [Effects of the central monitor 200 and the information processing system 1] In the central monitor 200 and information processing system 1 of this embodiment, analytical information indicating the relationship between subject information and the degree of discrepancy is output, allowing users such as medical professionals to confirm the relationship between at least one of the patient and the medical professional and the magnitude of the degree of discrepancy. This makes it possible to grasp the trend in the prediction accuracy of biological parameters. The effects of this are described below.

[0059] For example, when a 72-year-old male patient who has undergone cardiac bypass surgery, i.e., a patient belonging to Patient Category 1, is admitted to the intensive care unit and there is a difference of opinion between the attending physician (cardiac surgeon) and the intensive care physician regarding the date of discharge from the intensive care unit, a user such as a medical professional can use the analysis information shown in Figure 6(A). For example, the attending physician suggests that the patient be discharged from the intensive care unit 24 hours after the reference date and time, and the intensive care physician suggests that the patient's condition be monitored in the intensive care unit while undergoing respiratory management for at least 48 hours from the reference date and time.

[0060] From the analysis information shown in Figure 6(A), users can confirm the following: Regarding ART predictions, cardiac surgeons (category 2) tend to make lower predictions, while intensive care physicians (category 3) tend to make higher predictions, with the cardiac surgeons showing smaller variance in predictions (95% confidence interval). Regarding CVP predictions, no difference was observed between cardiac surgeons and intensive care physicians 24 hours after the reference date and time, but cardiac surgeons showed greater deviation and variance 72 hours after the reference date and time. Regarding PaO2 predictions, both cardiac surgeons and intensive care physicians showed greater variance 24 hours after the reference date and time, but the variance became smaller 72 hours after the reference date and time. Here, intensive care physicians showed slightly smaller variance. Regarding PaCO2 predictions, cardiac surgeons showed greater deviation and variance than intensive care physicians 24 hours after the reference date and time, but no difference was observed between cardiac surgeons and intensive care physicians 72 hours after the reference date and time. When the magnitude of the deviation exceeds a predetermined value, the central monitor 200 notifies the user by using the display unit 240, for example.

[0061] From the analysis information shown in Figure 6(A), it can be seen that intensive care physicians tend to have higher prediction accuracy than cardiac surgeons for the respiratory status (e.g., PaO2 and PaCO2) of patients belonging to Category 1. Furthermore, cardiac surgeons have smaller prediction variance for blood pressure (ART) than intensive care physicians. Therefore, by using this analysis information, users can more easily find appropriate policies, such as respecting the opinion of the intensive care physician for respiratory management and the opinion of the attending physician (cardiac surgeon) for blood pressure management.

[0062] Furthermore, by deriving prediction accuracy for each patient category and each healthcare professional category in this way, it becomes easier to find patient categories and healthcare professional categories with high prediction accuracy. For example, by using data from these categories with high prediction accuracy as training data, it can be useful for predicting patient conditions using AI (Artificial Intelligence) technology.

[0063] Furthermore, medical professionals in the high-prediction category can educate other medical professionals on how to focus on changes in biological parameters, effectively improving the prediction accuracy of each medical institution as a whole. For parameters in the low-prediction category (e.g., medical professionals), reports on prediction accuracy can be automatically or manually generated, which can be used for staff training and improving in-hospital protocols. Data on predicted values, actual measured values, and their deviations can also be accumulated, and the accumulated data can be used to improve analysis algorithms and thereby improve prediction accuracy.

[0064] Furthermore, by identifying patient categories that tend to have a large degree of deviation, i.e., patient categories that are difficult for medical professionals to predict, medical professionals can provide more appropriate care for patients. For example, for patients in such categories, they can take measures such as more thorough preparation for sudden changes in the patient's condition or assigning more experienced staff (e.g., nurses) to take care of them. This analytical information can be particularly effective in medical settings such as intensive care units, where patients of all ages and illnesses are admitted.

[0065] Furthermore, by identifying patient categories that tend to have a small discrepancy, i.e., patient categories for which medical professionals can predict outcomes with a relatively high degree of accuracy, it becomes possible to allocate appropriate personnel within a medical institution. For example, for patients in such categories, decision-making authority can be delegated to junior doctors, while experienced doctors can be assigned to patients in categories that are more difficult to predict. Furthermore, depending on the pathology, tasks can be delegated from doctors to nurses or pharmacists. Furthermore, for patients in categories that are extremely difficult to predict, experienced nurses can be assigned, or a system can be established in which assessments can be performed by multiple people.

[0066] In addition, by comparing the analytical information of each medical institution, it becomes easier to discover biases in prediction accuracy at each medical institution, making it possible to effectively utilize analytical information from other facilities.

[0067] As described above, the central monitor 200 outputs analytical information that indicates the relationship between subject information and the degree of discrepancy, allowing users such as medical professionals to confirm the relationship between at least one of the patient and the medical professional and the magnitude of the degree of discrepancy, thereby enabling them to grasp the trend in the prediction accuracy of biological parameters.

[0068] The following describes a modified example of the information processing system 1 described in the above embodiment. In order to avoid duplication of explanation, detailed explanations of the same components as those of the information processing system 1 described in the above embodiment will be omitted.

[0069] <Variation 1> Fig. 8 is a flowchart showing another example of the analysis process by the control unit 210 described in Fig. 7 above. After analyzing the relationship between the subject information and the deviation degree (step S205), the control unit 210 determines a category into which to classify the subject information (step S206). In this respect, the information processing system 1 according to the first modification differs from the information processing system 1 described in the above embodiment.

[0070] First, the control unit 210 performs the processes of steps S201 to S204 to calculate the degree of deviation in the same manner as steps S101 to S104 described above in Fig. 7. Next, the control unit 210 analyzes the relationship between the subject information and the degree of deviation (step S205).

[0071] Next, the control unit 210 determines a plurality of categories based on the relationship between the subject information and the deviation degree analyzed in step S205 (step S206). In other words, the classification unit 212 determines a plurality of categories based on the relationship between the subject information and the deviation degree analyzed by the analysis unit 215. The classification unit 212, for example, finds a characteristic of the subject information that correlates with the magnitude of the deviation degree, and determines a plurality of categories according to this characteristic. The classification unit 212 determines a plurality of categories using, for example, machine learning, statistics, or the like.

[0072] Next, the control unit 210 classifies each of the multiple pieces of subject information into the multiple categories determined in step S206 (step S207). After that, the control unit 210 outputs the analysis information analyzed in step S205 for each category (step S207), and ends the process.

[0073] In the information processing system 1 having such a central monitor 200, analytical information showing the relationship between subject information and the degree of discrepancy is output, similar to that described in the above embodiment, so that a user such as a medical professional can confirm the relationship between at least one of the patient and the medical professional and the magnitude of the degree of discrepancy, thereby making it possible to grasp the trend in the prediction accuracy of biological parameters.

[0074] 9(A) and 9(B) show examples of analysis information output by the central monitor 200 according to the first modification. In FIG. 9(A), the prediction accuracy is compared for patients in different categories based on age and reason for admission to the intensive care unit. In FIG. 9(B), the prediction accuracy of intensive care physicians and surgeons is compared for patients in different categories based on reason for admission to the intensive care unit. The predicted biological parameters are SpO2, PaO2, PaCO2, pH, etCO2, and RR. In FIGS. 9(A) and 9(B), grades A to E are grades based on the degree of discrepancy, with grade A representing the smallest degree of discrepancy, i.e., the highest prediction accuracy, and grade E representing the largest degree of discrepancy, i.e., the lowest prediction accuracy.

[0075] 9(A)(B), users such as medical professionals can understand the level of prediction accuracy due to the patient's age, the reason for the patient's admission to the intensive care unit, and the medical specialty of the medical professional. In other words, even if the user himself has no idea what characteristics of the patient and medical professional affect the level of prediction accuracy, he or she can compare prediction accuracy for each category of subject information.

[0076] <Variation 2> Figures 10 and 11 are schematic configuration diagrams showing other examples of the information processing system 1 described above in Figure 1. The information processing system 1 may further include a biological information management server 300 and an electronic medical record server 400 (Figure 10), and may further include a respiratory apparatus 500 (Figure 11).

[0077] The biological information management server 300 and the electronic medical record server 400 are connected to the bedside monitor 100 and the central monitor 200 via a wired or wireless network. A plurality of central monitors 200 may be connected to the biological information management server 300 and the electronic medical record server 400.

[0078] The biological information management server 300, for example, acquires and stores measurement information on the patient's biological parameters measured by each bedside monitor 100. This biological information management server 300 may have the functions of the acquisition unit 211, classification unit 212, type designation unit 213, calculation unit 214, analysis unit 215, and output unit 216 of the central monitor 200 described in the above embodiment. That is, the biological information management server 300 may be a specific example of the information processing device of the present invention. Note that an arbitrary device (not shown) that relays communication between the devices may be included as appropriate, and the relay device may convert the transmitted data as appropriate.

[0079] Electronic medical record information of a plurality of patients is stored in the electronic medical record server 400. The electronic medical record server 400 transmits patient information to the biological information management server 300, for example.

[0080] The ventilator 500 is a so-called artificial respirator and is connected to each bedside monitor 100. The ventilator 500 may be connected to the central monitor 200, the biological information management server 300, and the electronic medical record server 400 so as to be able to communicate directly with them. The biological parameters measured by the ventilator 500, the settings of the ventilator 500, and alarm information of the ventilator 500 are transmitted to the biological information management server 300. The ventilator 500 may function in the same manner as the input unit 250 of the central monitor 200 described above. The information processing system 1 may include a measuring device such as a blood gas measuring device and a spot check monitor in addition to the ventilator 500, or may include a measuring device that measures other biological parameters instead of the ventilator 500.

[0081] In this information processing system 1, similar to the embodiment described above, analysis information showing the relationship between subject information and the degree of discrepancy is output, so that a user such as a medical professional can confirm the relationship between at least one of the patient and the medical professional and the magnitude of the degree of discrepancy, thereby making it possible to grasp the trend in the prediction accuracy of biological parameters.

[0082] Although the embodiments of the present invention have been described in detail above, the present invention is not limited to the above-described embodiments. For example, some or all of the functions realized by the programs in the above-described embodiments may be realized by hardware such as circuits.

[0083] Furthermore, the above-described control unit 210 does not need to have all the functions, and may have other functions. Some or all of the functions of the acquisition unit 211, classification unit 212, type designation unit 213, calculation unit 214, analysis unit 215, and output unit 216 of the above-described control unit 210 may be provided in the biological information management server 300 or the electronic medical record server 400.

[0084] In addition, the biometric information management server 300, the electronic medical record server 400 or the respiratory apparatus 500 may have functions similar to some or all of the control unit 210, memory unit 220, communication unit 230, display unit 240 and input unit 250 of the central monitor 200 described above.

[0085] In the above-described embodiment, an example has been described in which the central monitor 200 corresponds to a specific example of the information processing device of the present invention, but the bedside monitor 100 may also correspond to a specific example of the information processing device of the present invention. For example, the control unit 110 of the bedside monitor 100 may function in the same manner as the above-described control unit 210. Both the bedside monitor 100 and the central monitor 200 may also correspond to a specific example of the information processing device of the present invention.

[0086] In addition, some steps in the above-described flowchart may be omitted, and other steps may be added. Furthermore, some of the steps may be executed simultaneously, or one step may be divided into multiple steps and executed. Furthermore, the order of the steps may be different. For example, the process of step S103 in FIG. 7 may be executed before the process of step S102. [Explanation of symbols]

[0087] 1 Information processing system, 100 bedside monitors, 110 control section, 120 storage section, 130 Communications Department, 140 sensors, 150 display section, 200 bedside monitors, 210 control section, 220 storage section, 230 Communications Department, 240 display section, 250 input section.

Claims

1. An acquisition unit that acquires subject information including information about a medical professional, measurement information about a patient's biological parameters, and predicted information about the patient's biological parameters predicted by the medical professional; an analysis unit that analyzes a relationship between the subject information and a degree of discrepancy between the prediction information and the measurement information; an output unit that outputs analysis information that indicates the relationship between the subject information and the degree of deviation; An information processing device comprising:

2. An information processing device as described in Claim 1, wherein the subject information further includes information about the patient.

3. An acquisition unit that acquires subject information including at least one of information about a patient and information about a medical professional, measurement information about the patient's biological parameters, and predicted information about the patient's biological parameters predicted by the medical professional; an analysis unit that analyzes a relationship between the subject information and a degree of discrepancy between the prediction information and the measurement information; an output unit that outputs analysis information that indicates the relationship between the subject information and the degree of deviation; Equipped with the prediction information includes first prediction information for a first time after a reference date and time and second prediction information for a second time after a reference date and time; the measurement information includes first measurement information measured after the first time from the reference date and time and second measurement information measured after the second time from the reference date and time; The analysis unit is an information processing device that analyzes the relationship between the subject information and a first deviation degree between the first prediction information and the first measurement information, and analyzes the relationship between the subject information and a second deviation degree between the second prediction information and the second measurement information.

4. An acquisition unit that acquires subject information including at least one of information about a patient and information about a medical professional, measurement information about the patient's biological parameters, and predicted information about the patient's biological parameters predicted by the medical professional; an analysis unit that analyzes a relationship between the subject information and a degree of discrepancy between the prediction information and the measurement information; an output unit that outputs analysis information representing the relationship between the subject information and the degree of deviation; a type designation unit for designating the type of the biological parameter; Equipped with The analysis unit is an information processing device that analyzes the relationship between the subject information and the degree of discrepancy between the predicted information and the measured information regarding the biological parameter of the specified type.

5. An acquisition unit that acquires subject information including at least one of information about a patient and information about a medical professional, measurement information about the patient's biological parameters, and predicted information about the patient's biological parameters predicted by the medical professional; an analysis unit that analyzes a relationship between the subject information and a degree of discrepancy between the prediction information and the measurement information; an output unit that outputs analysis information that indicates the relationship between the subject information and the degree of deviation; Equipped with The information processing device, wherein the analysis information includes information regarding a confidence interval of the degree of deviation.

6. 6. The information processing device according to claim 1, further comprising a classification unit that classifies the subject information into a plurality of categories.

7. An acquisition unit that acquires subject information including at least one of information about a patient and information about a medical professional, measurement information about the patient's biological parameters, and predicted information about the patient's biological parameters predicted by the medical professional; an analysis unit that analyzes a relationship between the subject information and a degree of discrepancy between the prediction information and the measurement information; an output unit that outputs analysis information representing the relationship between the subject information and the degree of deviation; a classification unit that classifies the subject information into a plurality of categories; Equipped with The analysis unit is an information processing device that analyzes the relationship between the subject information and the degree of deviation for each category.

8. The information processing device according to claim 7 , wherein the classification unit determines the plurality of categories based on an instruction from a user.

9. An acquisition unit that acquires subject information including at least one of information about a patient and information about a medical professional, measurement information about the patient's biological parameters, and predicted information about the patient's biological parameters predicted by the medical professional; an analysis unit that analyzes a relationship between the subject information and a degree of discrepancy between the prediction information and the measurement information; an output unit that outputs analysis information representing the relationship between the subject information and the degree of deviation; a classification unit that classifies the subject information into a plurality of categories; Equipped with the classification unit determines the plurality of categories based on the relationship between the subject information analyzed by the analysis unit and the degree of deviation; The output unit is an information processing device that outputs the analysis information for each category.

10. 10. The information processing apparatus according to claim 1, wherein the degree of deviation is a difference between the predicted information and the measured information.

11. 11. The information processing device according to claim 1, wherein the analysis information includes information regarding a staged evaluation according to the degree of deviation.

12. A computer-implemented information processing method, comprising: Obtaining subject information including information about a medical professional, measurement information about a patient's biological parameters, and predicted information about the patient's biological parameters predicted by the medical professional; Analyzing a relationship between the subject information and a degree of discrepancy between the prediction information and the measurement information; outputting analysis information representing the relationship between the subject information and the degree of deviation; An information processing method including:

13. A computer-implemented information processing method, comprising: Obtaining subject information including at least one of information about a patient and information about a medical professional, measurement information about a biological parameter of the patient, and predicted information about the biological parameter of the patient predicted by the medical professional; Analyzing a relationship between the subject information and a degree of discrepancy between the prediction information and the measurement information; outputting analysis information representing the relationship between the subject information and the degree of deviation; Including, the prediction information includes first prediction information for a first time after a reference date and time and second prediction information for a second time after a reference date and time; the measurement information includes first measurement information measured after the first time from the reference date and time and second measurement information measured after the second time from the reference date and time; An information processing method in which analyzing the relationship between the subject information and the deviation degree involves analyzing the relationship between the subject information and the first deviation degree of the first prediction information and the first measurement information, and analyzing the relationship between the subject information and the second deviation degree of the second prediction information and the second measurement information.

14. A computer-implemented information processing method, comprising: Obtaining subject information including at least one of information about a patient and information about a medical professional, measurement information about a biological parameter of the patient, and predicted information about the biological parameter of the patient predicted by the medical professional; Analyzing a relationship between the subject information and a degree of discrepancy between the prediction information and the measurement information; outputting analysis information representing a relationship between the subject information and the degree of deviation; Specifying the type of the biological parameter; Including, An information processing method for analyzing the relationship between the subject information and the degree of deviation, which analyzes the relationship between the subject information and the degree of deviation of the predicted information and the measured information regarding the biological parameter of the specified type.

15. A computer-implemented information processing method, comprising: Obtaining subject information including at least one of information about a patient and information about a medical professional, measurement information about a biological parameter of the patient, and predicted information about the biological parameter of the patient predicted by the medical professional; Analyzing a relationship between the subject information and a degree of discrepancy between the prediction information and the measurement information; outputting analysis information representing the relationship between the subject information and the degree of deviation; Including, An information processing method, wherein the analysis information includes information about a confidence interval of the degree of deviation.

16. A computer-implemented information processing method, comprising: Obtaining subject information including at least one of information about a patient and information about a medical professional, measurement information about a biological parameter of the patient, and predicted information about the biological parameter of the patient predicted by the medical professional; Analyzing a relationship between the subject information and a degree of discrepancy between the prediction information and the measurement information; outputting analysis information representing a relationship between the subject information and the degree of deviation; classifying the subject information into a plurality of categories; Including, In the information processing method, analyzing the relationship between the subject information and the degree of deviation analyzes the relationship between the subject information and the degree of deviation for each category.

17. A computer-implemented information processing method, comprising: Obtaining subject information including at least one of information about a patient and information about a medical professional, measurement information about a biological parameter of the patient, and predicted information about the biological parameter of the patient predicted by the medical professional; Analyzing a relationship between the subject information and a degree of discrepancy between the prediction information and the measurement information; outputting analysis information representing a relationship between the subject information and the degree of deviation; classifying the subject information into a plurality of categories; Including, In classifying the subject information into a plurality of categories, the plurality of categories are determined based on a relationship between the analyzed subject information and the degree of deviation; The information processing method includes outputting the analysis information for each of the categories.

18. A program for causing a computer to execute the information processing method according to any one of claims 12 to 17.

Images