Medical information processing device

Abstract

To easily grasp risks which increase due to complex reasons.SOLUTION: The medical information processor according to an embodiment includes an acquisition unit and a display control unit. The acquisition unit acquires patient information showing a plurality of methods for cure with different natures for at least one disease of a target patient. The display control unit exercises control to display mutual relation information showing mutual influences of the method for cure with different natures shown by the patient information on potential risks, in the display unit.SELECTED DRAWING: Figure 6

Description

Technical Field

[0001] The embodiments disclosed in this specification etc. relate to a medical information processing device.

Background Art

[0002] In recent years, due to the progress of aging, the number of patients with multimorbidity (coexistence of multiple diseases) has been increasing. In multimorbidity, multiple drugs are used in combination, so side effects that do not occur when each drug is used alone may occur, or other risks may occur due to treatment. It is known that the risks and burdens on patients are likely to increase due to complex factors.

[0003] Conventionally, a technique has been proposed to detect that symptoms do not conform to the disease definition due to side effects (for example, symptoms that should appear in a certain disease do not appear due to the side effects of a drug) from the relationship between the symptoms of a disease and the side effects of a drug.

[0004] However, in the prior art, it has been difficult for users such as doctors to grasp the relationship between multiple diseases and multiple treatments, and it has not been easy to grasp the risks increased by complex factors.

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0006] One of the problems that the embodiments disclosed herein aim to solve is to make it easier to understand risks that are amplified by a combination of factors. However, the problems solved by the embodiments disclosed herein are not limited to the above problem. Problems corresponding to the effects of each configuration shown in the embodiments described later can also be positioned as other problems solved by the embodiments disclosed in this specification. [Means for solving the problem]

[0007] The medical information processing device according to this embodiment comprises an acquisition unit and a display control unit. The acquisition unit acquires patient information indicating multiple different treatment methods for one or more diseases related to a target patient. The display control unit controls the display to show on a display device interrelationship information indicating the mutual influence of the multiple different treatment methods indicated in the patient information on potential risks. [Brief explanation of the drawing]

[0008] [Figure 1] Figure 1 shows an example of the configuration of a medical information processing system according to an embodiment. [Figure 2] Figure 2 shows an example of the data structure of a patient data table. [Figure 3] Figure 3 shows an example of the data structure of a disease data table. [Figure 4] Figure 4 shows an example of the data structure of a treatment data table. [Figure 5] Figure 5 shows an example of the data structure of the surrounding environment data table. [Figure 6] Figure 6 shows an example of the configuration of a medical information processing device according to the embodiment. [Figure 7] Figure 7 is an illustrative diagram showing an example of patient data acquisition according to this embodiment. [Figure 8] Figure 8 is an illustrative diagram showing an example of identifying potential risks according to this embodiment. [Figure 9] Figure 9 shows an example of a relationship graph according to the embodiment. [Figure 10] Figure 10 is an illustrative diagram showing an example of how to calculate the risk value according to the embodiment. [Figure 11] Figure 11 is an illustrative diagram showing an example of how to calculate the risk value according to the embodiment. [Figure 12] Figure 12 shows an example of a graph representing the interrelationships and risk values ​​according to the embodiment. [Figure 13] Figure 13 is an illustrative diagram showing an example of the extraction process according to the embodiment. [Figure 14] Figure 14 is an illustrative diagram showing an example of an alternative treatment method according to the embodiment. [Figure 15] Figure 15 is an illustrative diagram showing an example of a preview display of risk value changes according to the embodiment. [Figure 16] Figure 16 is an illustrative diagram showing an example of a graph representing the interrelationships and risk values ​​after substitution according to the embodiment. [Figure 17] Figure 17 is a flowchart showing an example of processing in a medical information processing device according to the embodiment. [Figure 18] Figure 18 is an illustrative diagram showing an example of the extraction process related to Modification Example 2. [Modes for carrying out the invention]

[0009] The following describes an embodiment of the medical information processing device with reference to the drawings.

[0010] Figure 1 is a diagram showing an example configuration of a medical information processing system according to an embodiment. As shown in Figure 1, the medical information processing system 1 includes a patient data DB (Data Base) 10, a disease data DB 20, a treatment data DB 30, a surrounding environment data DB 40, and a medical information processing device 100.

[0011] Here, the patient data database (DB) 10, the disease data DB 20, the treatment data DB 30, the surrounding environment data DB 40, and the medical information processing device 100 are connected to be communicable with each other via a network N such as an in-hospital LAN provided within a medical facility such as a hospital. Note that the number of each device is not limited to the number shown in FIG. 1.

[0012] The patient data DB 10 is a database that stores data related to patients. Specifically, the patient data DB 10 holds a patient data table 11.

[0013] The patient data table 11 stores patient data composed of information such as name, disease name, treatment method, severity, dependency, treatment priority score, hobbies, surrounding environment, and past diseases, in association with a patient ID that identifies the patient.

[0014] The patient data of each patient is registered in the patient data table 11 via, for example, the medical information processing device 100 or a terminal device provided in a medical facility such as a hospital. Also, the patient data may be registered based on information related to medical treatment such as an electronic medical record.

[0015] FIG. 2 is a diagram showing an example of the data structure of the patient data table 11. As shown in FIG. 2, the patient data table 11 stores by associating a "patient ID" with patient data. For example, in FIG. 2, the patient data of patients with patient IDs "P001" to "P003" is shown.

[0016] Here, the patient data has items such as "name", "disease ID", "disease name", "treatment method", "severity", "dependency", "treatment priority score", "hobbies", "surrounding environment", and "past diseases". Each item will be described below.

[0017] "Name" is the name of the patient in question. For example, in the example in Figure 2, the name "○○" is registered in association with the patient ID "P001". "Disease ID" is identification information that identifies the disease the patient currently has (hereinafter also referred to as the existing disease). For example, in the example in Figure 2, two disease IDs, "D001" and "D002", are registered in association with the patient ID "P001".

[0018] The "Disease Name" is information indicating the name of the patient's existing disease. For example, in the example in Figure 2, the disease name "Hypertension" is registered in association with disease ID "D001," and the disease name "Psychosis" is registered in association with disease ID "D002." Note that multiple "Disease IDs" and "Disease Names" may be registered for a single patient.

[0019] "Treatment methods" refer to information about treatments being performed for existing diseases. For example, in the example in Figure 2, treatment method "ACE inhibitors" is registered in association with disease ID "D001," and treatment method "psychotropic drugs" is registered in association with disease ID "D002." Note that multiple "treatment methods" may be registered for a single disease.

[0020] "Severity" is information indicating the current degree of symptoms (how serious the condition is) of the disease indicated by the "Disease ID" and "Disease Name". For example, in the example in Figure 2, a severity level of "1" is registered in association with disease ID "D001", and a severity level of "1" is registered in association with disease ID "D002".

[0021] "Dependency relationships" are information that represents the dependencies between diseases when a patient has multiple diseases. For example, in the patient data for patient ID "P001", disease name "psychosis" (disease ID "D002") may cause disease name "hypertension" (disease ID "D001"), so disease ID "D001" is registered in the "Dependency Relationships" column for disease ID "D002".

[0022] Furthermore, "dependency relationships" may be predetermined for each disease based on accumulated medical knowledge, etc. Also, for some diseases, there may be no diseases that are in a "dependency relationship" with other diseases.

[0023] Furthermore, information defining "dependencies" between diseases (for example, a data table that associates a specific disease with diseases that are dependent on that disease) may be held by any of the devices constituting the medical information processing system 1, or it may be held by an external server device or the like that is connected to the medical information processing system 1 via a network N in a manner that allows them to communicate with each other.

[0024] The "treatment priority score" is a score that indicates the priority of treatment for a patient's pre-existing conditions. For example, the "treatment priority score" is a numerical value determined by the physician in charge of the patient based on the patient's condition and other factors.

[0025] For example, Figure 2 shows an example where a treatment priority score of "1" is registered in association with the disease name "hypertension," and a treatment priority score of "2" is registered in association with the disease name "psychosis." This indicates that for the target patient "○○" identified by "P001," treatment for "psychosis" takes precedence over treatment for "hypertension."

[0026] "Hobbies and Preferences" refers to information about the patient's hobbies and preferences. For example, in the example in Figure 2, the hobby preference "I'm not good at exercise" is registered in association with patient ID "P001".

[0027] "Surrounding environment" refers to information about the patient's surroundings. This includes, for example, family history (such as a family history of illnesses in relatives), the patient's occupation, and the patient's lifestyle (e.g., smoking and drinking habits). It also includes information about insurance, such as whether the patient has insurance that covers expensive advanced medical treatments. For example, in the example in Figure 2, the surrounding environment "Family history: Diabetes" is registered in association with patient ID "P001".

[0028] "Past illnesses" refers to information about illnesses the patient has suffered from in the past. Specifically, "past illnesses" represent illnesses the patient has had in the past but which are not currently causing any symptoms. For example, in the example in Figure 2, the past illness "pneumonia" is registered in association with patient ID "P001".

[0029] In this example, "Family history: Diabetes" indicates that there is a relative within two degrees of kinship who has diabetes.

[0030] Furthermore, the items included in patient data are not limited to the example in Figure 2. For example, patient data may include items such as the patient's height and weight. In addition, disease data may include "disease ID," "disease name," "treatment method," and three or more "severity" entries, or disease data may include multiple entries such as "hobbies and preferences," "surrounding environment," and "past illnesses."

[0031] The disease data DB20 is a database that stores information about diseases. Specifically, the disease data DB20 holds the disease data table 21.

[0032] The disease data table 21 stores disease data, which consists of information such as disease name, severity (base), likelihood (base), potential disease, impact, severity, and likelihood, and associates it with a disease ID that identifies the disease.

[0033] Disease data for each disease is registered in the disease data table 21 for each disease, for example, via a medical information processing device 100 or a terminal device installed in a medical facility such as a hospital.

[0034] Figure 3 shows an example of the data structure of the disease data table 21. As shown in Figure 3, the disease data table 21 stores disease IDs in association with disease data.

[0035] Here, the disease data includes items such as "disease name," "severity (base)," "likelihood (base)," "potential disease," "impact," "severity," and "likelihood." For example, Figure 3 shows the disease data for diseases with disease IDs "D001" to "D003."

[0036] "Disease name" is the name of the target disease. In this embodiment, "disease" includes not only illnesses but also phenomena that occur in patients, such as falls, and frailty (a weakened state that is not quite a disability). For example, in the example in Figure 3, the disease name "hypertension" is registered in association with the disease ID "D001".

[0037] "Severity (Base)" indicates how serious the target disease is. For example, in the example in Figure 3, a severity (base) of "1" is registered in association with disease ID "D001". "Likelihood (Base)" indicates how likely the target disease is to occur. For example, in the example in Figure 3, a likelihood (base) of "3" is registered in association with disease ID "D001".

[0038] "Latent diseases" refer to information indicating secondary diseases that may arise as a result of having the target disease. Furthermore, "latent diseases" may be defined based on the "dependencies" between diseases. For example, in the example in Figure 3, the latent disease "myocardial infarction" is registered in association with disease ID "D001".

[0039] "Impact" is information that indicates whether having the target disease has a positive or negative impact on the "potential disease." For example, in the example in Figure 3, the impact is registered as "negative" in association with the disease ID "D001."

[0040] "Severity" is information that indicates how serious the condition will be if a person with the target disease develops a latent disease. For example, in the example in Figure 3, a severity of "0" is registered in association with disease ID "D001". "Likelihood of occurrence" is information that indicates how likely a person with the target disease is to develop a latent disease. For example, in the example in Figure 3, a likelihood of occurrence of "1" is registered in association with disease ID "D001".

[0041] Note that the items included in the disease data are not limited to the example in Figure 3. For example, information defining the "dependencies" in the patient data table 11 in Figure 2 may be registered as disease data. Also, for example, multiple entries of "potential disease," "impact," "severity," and "likelihood of occurrence" may be registered as disease data.

[0042] The treatment data DB30 is a database that stores information about treatment methods. Specifically, the treatment data DB30 holds the treatment data table 31.

[0043] The treatment data table 31 stores treatment data, which consists of information such as treatment name, target disease, expected effect, potential disease, side effects, severity, likelihood of occurrence, preferences, impact, and degree of impact, associated with a treatment ID that identifies the treatment.

[0044] Treatment data for each treatment method is registered in the treatment data table 31 for each treatment method, for example, via a medical information processing device 100 or a terminal device installed in a medical facility such as a hospital.

[0045] Figure 4 shows an example of the data structure of the treatment data table 31. As shown in Figure 4, the treatment data table 31 stores the "treatment ID" in association with the treatment data.

[0046] Here, the treatment data includes items such as "treatment name," "target disease," "expected effect," "potential disease," "side effects," "severity," "likelihood of occurrence," "personal preference," "impact," and "degree of impact." For example, Figure 4 shows the treatment data for treatments with treatment IDs "T001" to "T003."

[0047] "Treatment Name" is the name of the treatment method. Note that treatment methods include not only administered medications but also exercise therapy, dietary therapy, etc. For example, in the example in Figure 4, the treatment name "ACE inhibitor" is registered in association with treatment ID "T001". "Target Disease" is information indicating the disease targeted by the treatment method. For example, in the example in Figure 4, the target disease "hypertension" is registered in association with treatment ID "T001".

[0048] "Expected effect" is information indicating the extent to which a target treatment method can be expected to be effective against the "target disease." "Expected effect" can also be described as the expected value of how much the risk of the existing disease can be reduced. For example, in the example in Figure 4, an expected effect of "5" is registered in association with treatment method ID "T001."

[0049] "Latent diseases" is information indicating diseases other than the target disease that are related to the target treatment method. For example, in the example in Figure 4, the latent disease "aspiration pneumonia" is registered in association with treatment method ID "T001". "Side effects" is information indicating whether the target treatment method has a positive or negative effect on the "latent disease". For example, in the example in Figure 4, the side effect "positive" is registered in association with treatment method ID "T001".

[0050] "Severity" is information that indicates how serious the condition will be if the patient develops a latent disease as a result of undergoing the treatment in question. For example, in the example in Figure 4, a severity of "-1" is registered in association with treatment ID "T001". "Likelihood of occurrence" is information that indicates how likely the patient is to develop a latent disease as a result of undergoing the treatment in question. For example, in the example in Figure 4, a likelihood of occurrence of "0" is registered in association with treatment ID "T001".

[0051] "Hobbies and preferences" is information that represents the hobbies and preferences of patients who will be affected by the treatment method. For example, in the example in Figure 4, the hobby preference "I'm not good at exercise" is registered in association with the treatment method ID "T003".

[0052] "Impact" indicates whether the treatment in question will have a negative or positive effect on "hobbies and preferences." For example, in the example in Figure 4, the effect is registered as "negative" and is associated with the hobby / preference "dislikes exercise." "Degree of impact" indicates how much the treatment in question will affect "hobbies and preferences." For example, in the example in Figure 4, the degree of impact is registered as "10" and is associated with the hobby / preference "dislikes exercise."

[0053] It should be noted that the items included in the treatment data are not limited to the example in Figure 4. For example, the treatment data may include items such as "high medical cost" indicating that high medical expenses are required to perform the target treatment. In addition, multiple items such as "target disease" and "expected effect," or "potential disease," "side effects," "severity," and "likelihood of occurrence" may be registered as treatment data.

[0054] The surrounding environment data DB40 is a database that stores information about the surrounding environment. Specifically, the surrounding environment data DB40 holds the surrounding environment data table 41.

[0055] The surrounding environment data table 41 stores surrounding environment data, which consists of information such as the name of the surrounding environment, potential diseases, effects, and likelihood of occurrence, in association with a surrounding environment ID that identifies the surrounding environment.

[0056] The surrounding environment data for each surrounding environment is registered in the surrounding environment data table 41 for each surrounding environment, for example, via a medical information processing device 100 or a terminal device installed in a medical facility such as a hospital.

[0057] Figure 5 shows an example of the data structure of the surrounding environment data table 41. As shown in Figure 5, the surrounding environment data table 41 stores surrounding environment data in association with "surrounding environment IDs".

[0058] Here, the surrounding environment data includes items such as "surrounding environment name," "potential disease," "impact," and "likelihood of occurrence." For example, Figure 5 shows the surrounding environment data for surrounding environments with surrounding environment IDs "E001" to "E003."

[0059] "Surrounding environment name" is the name of the target surrounding environment. For example, in the example in Figure 5, the surrounding environment ID "E001" is registered with the surrounding environment name "Family history: Hypertension". "Latent disease" is information about diseases related to the target surrounding environment. For example, in the example in Figure 5, the surrounding environment ID "E001" is registered with the latent disease "Hypertension".

[0060] "Impact" is information indicating whether the presence of the target surrounding environment has a positive or negative impact on the "potential disease." For example, in the example in Figure 5, the surrounding environment ID "E001" is registered with an impact of "negative." "Severity" is information indicating how serious the condition will be if the potential disease is contracted due to the presence of the target surrounding environment. For example, in the example in Figure 5, the surrounding environment ID "E001" is registered with a severity of "0."

[0061] "Susceptibility to occurrence" is information that indicates how likely a person is to contract a potential disease due to the presence of the target surrounding environment. For example, in the example in Figure 5, the surrounding environment ID "E001" is registered with a susceptibility of occurrence of "3".

[0062] Note that the items included in the surrounding environment data are not limited to the example in Figure 5. For example, multiple items such as "potential disease," "impact," "severity," and "likelihood of occurrence" may be registered as surrounding environment data.

[0063] The medical information processing device 100 performs various processes using data stored in the patient data DB 10, disease data DB 20, treatment data DB 30, and surrounding environment data DB 40. Specifically, the medical information processing device 100 is used by physicians in their patient care operations. The medical information processing device 100 is implemented using computer equipment such as a workstation.

[0064] Figure 6 shows an example configuration of the medical information processing device 100. As shown in Figure 6, the medical information processing device 100 includes an I / F (interface) circuit 110, a storage circuit 120, an input circuit 130, a display 140, and a processing circuit 150.

[0065] The I / F circuit 110 is connected to the processing circuit 150 and controls the transmission and communication of various data via the network N. For example, the I / F circuit 110 accesses the patient data DB 10, disease data DB 20, and treatment data DB 30. For example, the I / F circuit 110 can be implemented by a network card, network adapter, NIC (Network Interface Controller), etc.

[0066] The memory circuit 120 is connected to the processing circuit 150 and stores various types of data. For example, the memory circuit 120 stores various setting information related to the operation of the medical information processing device 100. For example, the memory circuit 120 can be implemented using semiconductor memory elements such as RAM (Random Access Memory) or flash memory, or a hard disk or optical disc.

[0067] The input circuit 130 is connected to the processing circuit 150 and converts the input operation received from the operator into an electrical signal, which is then output to the processing circuit 150. For example, the input circuit 130 can be implemented by a trackball, switch buttons, mouse, keyboard, touch panel, etc.

[0068] The display 140 is connected to the processing circuit 150 and displays various information and image data output from the processing circuit 150. For example, the display 140 can be implemented using an LCD monitor, a CRT (Cathode Ray Tube) monitor, a touch panel, etc. The display 140 is an example of a display device.

[0069] The processing circuit 150 comprehensively controls the operation of the medical information processing device 100. For example, the processing circuit 150 is implemented by a processor.

[0070] The overall configuration of the medical information processing device 100 according to this embodiment has been described above. With this configuration, the medical information processing device 100 according to this embodiment has a function for displaying the interaction between different elements.

[0071] Specifically, the processing circuit 150 has an acquisition function 151, a specific function 152, a generation function 153, a calculation function 154, a display control function 155, an extraction function 156, a presentation function 157, and a selection function 158.

[0072] Here, the acquisition function 151 is an example of an acquisition unit in the claims. The calculation function 154 is an example of a calculation unit in the claims. The display control function 155 is an example of a display control unit in the claims. The presentation function 157 is an example of a presentation unit in the claims. The selection function 158 is an example of a selection unit in the claims.

[0073] The acquisition function 151 acquires patient data indicating multiple different treatment methods for one or more diseases related to the target patient. Patient data is an example of patient information. The acquisition function 151 also acquires patient data indicating one or more diseases related to the target patient. Furthermore, the acquisition function 151 acquires patient information indicating the family history of one or more target patients.

[0074] Specifically, the acquisition function 151 refers to the patient data table 11 and acquires information linked to the patient ID of the target patient for medical treatment, including "name," "disease ID," "disease name," "treatment method," "severity," "treatment priority score," "hobbies and preferences," "surrounding environment," and "past illnesses."

[0075] The specific function 152 identifies the potential risks associated with each of several different treatment methods indicated by the patient data acquired by the acquisition function 151. Furthermore, the specific function 152 identifies the potential risks associated with each of one or more diseases indicated by the patient data acquired by the acquisition function 151. Additionally, the specific function 152 identifies the potential risks associated with the family history of one or more target patients indicated by the patient data acquired by the acquisition function 151.

[0076] Specifically, the identification function 152 refers to the treatment data table 31 and identifies potential diseases linked to the treatment ID for each of the multiple treatments performed, which were acquired by the acquisition function 151, as potential risks.

[0077] Furthermore, the identification function 152 refers to the disease data table 21 and identifies potential diseases associated with each disease ID as potential risks for multiple existing diseases acquired by the acquisition function 151. In addition, the identification function 152 refers to the surrounding environment data table 41 and identifies potential diseases associated with the surrounding environment IDs of the surrounding environment acquired by the acquisition function 151 as potential risks.

[0078] Furthermore, the identification function 152 refers to the treatment data table 31 and identifies the relevant hobby preferences as such if the hobby preferences of the target patient acquired by the acquisition function 151 match those associated with the treatment ID of the target treatment method.

[0079] The generation function 153 generates a correlation graph that shows the mutual influence of multiple different treatment methods on potential risk, as indicated by patient data. The correlation graph is an example of correlation information.

[0080] The generation function 153 generates a relationship graph showing the relationships between multiple existing diseases in the target patient. Specifically, the generation function 153 refers to the patient data table 11 and obtains the "dependency relationships" of existing diseases identified by the "disease ID" and "disease name" obtained by the acquisition function 151. Then, based on the obtained "dependency relationships," the generation function 153 generates a relationship graph showing the relationships between the existing diseases of the target patient.

[0081] Furthermore, the generation function 153 generates a relationship graph of one or more diseases and multiple treatments of different characteristics shown in the patient data.

[0082] Specifically, first, the generation function 153 refers to the disease data table 21 and retrieves the "impact" ("good" or "bad") corresponding to the "potential disease" linked to the disease ID of the disease name (existing disease) in the patient data acquired by the acquisition function 151. The generation function 153 also refers to the disease data table 21 and retrieves the "impact" corresponding to the "potential disease" linked to the disease ID of the past disease in the patient data acquired by the acquisition function 151.

[0083] Furthermore, the generation function 153 refers to the treatment data table 31 and retrieves "side effects" corresponding to "potential diseases" linked to the treatment method ID of the implemented treatment acquired by the acquisition function 151. In addition, the generation function 153 refers to the surrounding environment data table 41 and retrieves "impacts" corresponding to potential diseases linked to the surrounding environment ID of the surrounding environment acquired by the acquisition function 151.

[0084] The generation function 153 integrates multiple acquired "impacts" and "side effects" to generate a graph of interrelationships between existing diseases, treatments performed, past diseases, and the surrounding environment. The interrelationship graph is a graph that represents the mutual influences between elements such as existing diseases, treatments performed, past diseases, and the surrounding environment, using multiple arrows to distinguish between positive and negative influences.

[0085] Furthermore, the interrelationship information is not limited to the above and may also be presented in tabular form, showing the relationships between elements such as existing diseases, treatments performed, past illnesses, and the surrounding environment.

[0086] The calculation function 154 calculates a risk value that indicates the degree of influence of multiple different types of treatments on a potential risk. The calculation function 154 also calculates a risk value that indicates the degree of influence of one or more diseases and multiple different types of treatments on a potential risk.

[0087] Furthermore, the calculation function 154 calculates a risk value that indicates the degree of influence of one or more diseases, multiple treatments of different natures, and one or more family histories on potential risk.

[0088] Specifically, the calculation function 154 calculates a risk value for each element of existing diseases, past diseases, and potential diseases, indicating the degree of influence of one or more existing diseases, multiple treatments performed, and one or more surrounding environmental factors.

[0089] Here, the risk value consists of an internal risk value, which represents the risk inherent in the element itself (such as existing diseases, past diseases, and potential diseases), and an external risk value, which represents the risk it places on other elements. The sum of the internal and external risk values ​​equals the risk value of the element (such as existing diseases, past diseases, and potential diseases). The internal and external risk values ​​are calculated based on severity and likelihood.

[0090] Furthermore, calculation function 154 calculates risk values ​​for hobbies and preferences. The risk value for hobbies and preferences indicates the degree to which other factors, such as diseases and treatments, influence those preferences. The process for calculating risk values ​​is described below.

[0091] First, let's explain the process for calculating the self-risk value for existing diseases. The self-risk value for existing diseases can be calculated as "likelihood of occurrence × current severity". Specifically, the calculation function 154 refers to the patient data table 11 and obtains the "severity" corresponding to the target existing disease that is the subject of the self-risk value calculation, which is linked to the patient ID of the target patient, as the current severity. Also, since the existing disease is already present, the calculation function 154 sets the "likelihood of occurrence" to the maximum value (for example, "10").

[0092] For example, the calculation function 154 refers to the patient data table 11 and, if the "severity" corresponding to the target existing disease linked to the patient ID of the target patient is "1", it sets the "current severity" to "1" and calculates the self-risk value as "10 (likelihood of occurrence) × 1 (current severity) = 10".

[0093] Next, we will explain how to calculate the risk value for pre-existing diseases. The risk value for pre-existing diseases can be calculated using the formula: "(likelihood of latent disease occurring due to the pre-existing disease × severity of latent disease (base)) + (likelihood of latent disease occurring (base) × severity of latent disease due to the pre-existing disease)".

[0094] For example, if the "likelihood of occurrence" of a target latent disease associated with the disease ID of a target existing disease registered in the disease data table 21 is "2", the calculation function 154 sets the "likelihood of occurrence of latent disease due to existing disease" to "2". Also, if the "severity (base)" associated with the disease ID of a target latent disease registered in the disease data table 21 is "2", the calculation function 154 sets the "severity (base) of latent disease" to "2".

[0095] Furthermore, if the "likelihood of occurrence (base)" associated with the disease ID of the target potential disease registered in the disease data table 21 is "3", the calculation function 154 sets the "likelihood of occurrence (base) of the potential disease" to 3. Also, if the "severity" corresponding to the target potential disease associated with the disease ID of the target existing disease registered in the disease data table 21 is "1", the calculation function 154 sets the "severity of the potential disease due to the existing disease" to "1".

[0096] The calculation function 154 then calculates the assigned risk value as "2 (likelihood of latent disease occurring due to existing disease) × 2 (severity of latent disease (base)) + 3 (likelihood of latent disease occurring (base)) × 1 (severity of latent disease occurring due to existing disease) = 7".

[0097] Next, we will explain how to calculate the risk value for past illnesses. Past illnesses include pure past illnesses, which have no possibility of recurrence, and past / latent illnesses, which currently have no symptoms but have the potential to recur.

[0098] Examples of pure past illnesses include appendicitis in patients who have undergone appendectomy. For pure past illnesses, calculation function 154 calculates the risk value by setting the likelihood and severity to "0". In other words, for pure past illnesses, both the self-risk value and the assigned risk value are "0". Past / latent illnesses are treated the same way as latent illnesses, which will be discussed later.

[0099] Next, we will explain how to calculate the self-risk value for latent diseases. The self-risk value for latent diseases is calculated as "likelihood of latent disease occurring × severity of latent disease".

[0100] The "likelihood of developing a latent disease" is expressed as "baseline likelihood of developing a latent disease + (sum of factors that increase or decrease the likelihood of developing a latent disease)," and the "severity of the latent disease" is expressed as "baseline severity of the latent disease + (sum of factors that increase or decrease the severity of the latent disease)." The sum of factors that increase or decrease the likelihood and severity represents the combined impact of pre-existing diseases, ongoing treatments, and the surrounding environment on the likelihood and severity of the latent disease.

[0101] For example, if the "likelihood of occurrence (base)" associated with the disease ID of the target potential disease registered in the disease data table 21 is "3", the calculation function 154 sets the "likelihood of occurrence (base) of the potential disease" to "3". Also, if the "likelihood of occurrence" corresponding to the potential disease associated with the disease ID of the target patient's existing disease registered in the disease data table 21 is "2", the calculation function 154 sets "+2" as one of the "factors for increasing or decreasing the likelihood of occurrence of the potential disease".

[0102] Furthermore, if the "likelihood of occurrence" corresponding to the latent disease linked to the treatment method ID of the treatment performed on the target patient, as registered in the treatment data table 31, is "2", the calculation function 154 sets "+2" as one of the "factors for increasing or decreasing the likelihood of latent disease occurring".

[0103] Furthermore, if the "likelihood of occurrence" corresponding to the latent disease linked to the surrounding environment ID of the target patient's surrounding environment, registered in the surrounding environment data table 41, is "2", the calculation function 154 sets "+2" as one of the "factors for increasing or decreasing the likelihood of latent disease occurring". Then, the calculation function 154 sets "3 (likelihood of latent disease occurring (base)) + (2 + 2 + 2) (sum of factors for increasing or decreasing the severity of latent disease) = 9" as the "likelihood of latent disease occurring".

[0104] Furthermore, for example, if the "severity (base)" associated with the disease ID of the target potential disease registered in the disease data table 21 is "1", the calculation function 154 sets the "severity (base) of the potential disease" to "1". Also, if the "severity" corresponding to the potential disease associated with the disease ID of the target patient's existing disease registered in the disease data table 21 is "2", the calculation function 154 sets "+2" as one of the "factors for increasing or decreasing the severity of the potential disease".

[0105] Furthermore, for example, if the "severity" corresponding to the latent disease linked to the treatment method ID of the treatment performed on the target patient, as registered in the treatment data table 31, is "-1", the calculation function 154 sets "-1" as one of the "factors that increase or decrease the likelihood of latent disease occurring".

[0106] Furthermore, for example, if the "severity" corresponding to the potential disease linked to the surrounding environment ID of the target patient's surrounding environment, registered in the surrounding environment data table 41, is "2", the calculation function 154 sets "+2" as one of the "factors that increase or decrease the likelihood of the potential disease occurring". Then, the calculation function 154 sets "1 (severity of the potential disease (base)) + (2 - 1 + 2) (sum of factors that increase or decrease the severity of the potential disease) = 4" as the "severity of the potential disease".

[0107] Subsequently, calculation function 154 calculates the self-risk value as "9 (likelihood of latent disease) × 4 (severity of latent disease) = 36". Note that the risk value for latent disease can be calculated using the same method as the risk value for existing disease, so the explanation is omitted.

[0108] Next, we will explain how to calculate the risk value for hobbies and preferences. The risk value for hobbies and preferences is calculated based on the "degree of influence on hobbies and preferences."

[0109] For example, if the "influence" corresponding to the target hobby / preference, linked to the treatment ID of a treatment performed on a target patient and registered in the treatment data table 31, is "10", the calculation function 154 will calculate "10" as the risk value. If there are multiple treatments linked to the target hobby / preference, the calculation function 154 will calculate the "sum of influences" as the risk value.

[0110] Here, the method for calculating risk values ​​described above is just one example; risk values ​​for existing diseases, past diseases, potential diseases, and hobbies and preferences may be calculated using other methods.

[0111] The display control function 155 controls the display 140 to show a correlation graph on which multiple different treatment methods, as indicated by patient data, have mutual effects on potential risk. The display control function 155 also controls the display 140 to show the risk value calculated by the calculation function 154.

[0112] Specifically, the display control function 155 controls the display 140 to show both the correlation graph generated by the generation function 153 and the risk value calculated by the calculation function 154. Alternatively, the display control function 155 may also control the display 140 to show only the correlation graph generated by the generation function 153.

[0113] Furthermore, the display control function 155 may also control the display of risk values ​​so that the breakdown of the risk value (the numerical value of the user's own risk value and the numerical value of the risk value given) is clear (for example, the display control function 155 may control the display of the breakdown of the risk value when the user hovers the mouse pointer over the displayed risk value). By displaying the breakdown of the risk value, the user can visually grasp whether the risk they are giving or receiving is large.

[0114] The extraction function 156 extracts a portion of the relationship graph generated by the generation function 153.

[0115] Specifically, the extraction function 156, in response to an extraction instruction from the user, extracts elements from the correlation graph generated by the generation function 153, starting from an element such as a potential disease specified by the user, and extending to a predetermined number of arrows (for example, 3). The display control function 155 then controls the display 140 to show only the portion extracted by the extraction function 156 and the risk values ​​associated with that portion.

[0116] Note that the above extraction conditions are just examples, and extraction may be performed according to other conditions. By having the extraction function 156 extract a portion of the relationship graph as described above, it is possible to prevent situations where the points of interest become blurred and it becomes difficult for the user to grasp the relationships when the relationship graph generated by the generation function 153 contains too many elements.

[0117] The presentation function 157 presents one or more alternative treatment methods that can reduce the risk level.

[0118] Specifically, the presentation function 157 presents one or more alternative treatment methods in accordance with the user's instructions. First, the presentation function 157 receives a designation of one potential disease from the user, refers to the disease data table 21, and extracts diseases that are related to the potential disease specified by the user and that are existing diseases (or past / potential diseases) of the target patient.

[0119] Next, the presentation function 157 refers to the treatment data table 31 and extracts multiple treatment methods (excluding the patient's current treatment) that could be used for the extracted disease. Then, the presentation function 157 has the calculation function 154 calculate the risk value for each of the potential diseases specified by the user, assuming that the extracted treatment methods are added to the current treatment.

[0120] The presentation function 157 then presents alternative treatment methods (additional) that result in a lower risk value for the latent disease compared to the current risk value for the latent disease, as calculated by the calculation function 154.

[0121] Furthermore, the presentation function 157 causes the calculation function 154 to calculate the risk value for the latent disease specified by the user, for each of the extracted treatment methods, assuming that each of them replaces one of the currently implemented treatments. Note that treatment methods presented as alternative (additional) treatments are not included in the calculation.

[0122] The presentation function 157 then presents alternative treatment methods (alternatives) that result in a lower risk value for the latent disease compared to the current risk value for the latent disease, as calculated by the calculation function 154.

[0123] Furthermore, the presentation function 157 instructs the calculation function 154 to calculate the risk value of the latent disease specified by the user if one of the currently implemented treatments is deleted (discontinued). If the risk value of the latent disease calculated by the calculation function 154 is lower than the current risk value of the latent disease, the presentation function 157 presents the deletion of the implemented treatment as an alternative treatment method (deletion).

[0124] Furthermore, if a certain treatment is removed, and the risk value of the disease targeted by that treatment exceeds a predetermined threshold, the presentation function 157 may choose not to present the removal of that treatment as an alternative treatment method (removal).

[0125] The alternative treatment methods presented by the presentation function 157 are displayed on the display 140 by the display control function 155.

[0126] The selection function 158 selects at least one alternative treatment method from the one or more alternative treatment methods presented by the presentation function 157.

[0127] Specifically, the selection function 158 selects an alternative treatment method when the user places the mouse pointer over one of the displayed alternative treatment methods and left-clicks. If the user provides input for two or more alternative treatment methods, the selection function 158 will select two or more alternative treatment methods.

[0128] When the selection function 158 selects an alternative treatment method, the generation function 153 generates a post-alternative interrelationship graph showing the effects of multiple treatments, including the selected alternative treatment method. Subsequently, the calculation function 154 calculates post-alternative risk values ​​for existing diseases, past diseases, and potential diseases, showing the effects of multiple treatments, including the selected alternative treatment method. The display control function 155 controls the display of the post-alternative interrelationship graph generated by the generation function 153.

[0129] Furthermore, the display control function 155 controls the display 140 to show the post-substitution risk value calculated by the calculation function 154. At this time, the display control function 155 may also control the display 140 to show the risk value before the treatment substitution (for example, by displaying it in the format "pre-substitution risk value" → "post-substitution risk value").

[0130] Furthermore, the selection function 158 tentatively selects at least one alternative treatment method from the one or more alternative treatment methods presented by the presentation function 157.

[0131] Specifically, the selection function 158 provisionally selects an alternative treatment method when the user places the mouse pointer over one of the displayed alternative treatment methods.

[0132] When the selection function 158 tentatively selects an alternative treatment method, the calculation function 154 calculates a tentative post-alternative risk value for the user-specified latent disease, indicating the impact of multiple treatments, including the selected alternative treatment method. This process can be omitted by using the user-specified latent disease risk value calculated by the calculation function 154 when the presentation function 157 presents alternative treatment methods.

[0133] The display control function 155 then controls the display 140 to show both the risk value before the actual treatment substitution and the risk value after the provisional substitution. The display control function 155 may also control the display to show the change in risk value in the form of, for example, "risk value before substitution" → "risk value after provisional substitution".

[0134] Here, the processing details of each of the above-mentioned functional units will be explained using Figures 7 to 16. Figure 7 is an illustrative diagram showing an example of the patient data acquisition process.

[0135] Figure 7 shows an example where the acquisition function 151 refers to the patient data table 11 and acquires "hypertension," "psychosis," "frailty: legs and lower back," "insomnia," and "diabetes" as "disease names" associated with the patient ID of the target patient. Figure 7 also shows an example where the acquisition function 151 refers to the patient data table 11 and acquires "aspiration pneumonia" and "myocardial infarction" as "past illnesses."

[0136] Furthermore, Figure 7 shows an example in which the acquisition function 151 referred to the patient data table 11 and acquired "1" as the "treatment priority score" for "hypertension," "2" as the "treatment priority score" for "psychosis," "1" as the "treatment priority score" for "frailty: legs and hips," "1" as the "treatment priority score" for "insomnia," and "2" as the "treatment priority score" for "diabetes."

[0137] Furthermore, Figure 7 shows an example where the acquisition function 151 referred to the patient data table 11 and acquired "ACE inhibitors," "psychotropic drugs," "anticoagulants," "exercise therapy (frailty: legs and hips)," "sleeping pills," "exercise therapy (diabetes)," and "dietary therapy" as "treatment methods." Also, Figure 7 shows an example where the acquisition function 151 referred to the patient data table 11 and acquired "I don't like exercise" and "I like sweets" as "hobbies and preferences."

[0138] Furthermore, Figure 7 shows an example where the acquisition function 151 refers to the patient data table 11 and acquires "Family history: Myocardial infarction" as "Surrounding environment".

[0139] Figure 8 is an illustrative diagram showing an example of a process for identifying a potential disease.

[0140] Figure 8 shows an example where specific function 152 refers to disease data table 21 and identifies "myocardial infarction," a latent disease linked to the disease ID of the existing disease "hypertension," as a latent disease. In this example, since "myocardial infarction" is a "past disease" of the target patient, it is treated as a "past / latent disease."

[0141] Furthermore, Figure 8 shows an example where specific function 152 refers to disease data table 21 and identifies "falls and fractures" as a latent disease linked to the disease ID of the existing disease "frailty: legs and hips".

[0142] Furthermore, Figure 8 shows an example where specific function 152 refers to treatment data table 31 and identifies "aspiration pneumonia," a latent disease linked to the treatment ID of "ACE inhibitors," which is the treatment being administered, as a latent disease. In this example, since "aspiration pneumonia" is a "past disease" of the patient, it will be treated as a "past / latent disease," similar to "myocardial infarction."

[0143] Figure 9 shows an example of a relationship graph. The process for generating relationship graphs will be explained below using Figures 2 through 5 and Figure 9.

[0144] First, the generation function 153 refers to the patient data table 11 and identifies the dependent diseases based on the information registered in the "dependencies" of the target patient. As a result, the generation function 153 can obtain information that "psychosis" is in a "dependency" relationship with "hypertension," which is identified by disease ID "D001." In this case, the "dependency" relationship between "psychosis" and "hypertension" indicates that "psychosis" causes "hypertension."

[0145] The generation function 153 then associates and sets display information representing the "dependency" between "psychosis" and "hypertension," which are in a "dependency relationship." The display information is represented, for example, as a solid arrow pointing from "psychosis" to "hypertension," as shown in Figure 9. Note that the arrow is just one example of how the display information can be represented, and the display information may be represented in other ways.

[0146] Furthermore, "dependency relationships" represent the relationships between existing diseases and are displayed separately from the relationships between "existing diseases" and "latent diseases." For example, as shown in Figure 9, "dependency relationships" are displayed with solid arrows that are larger than the dashed arrows that represent the negative impact that "existing diseases" have on "latent diseases." In the following explanation, the size of the arrows representing "dependency relationships" may be referred to as "large," and the size of the arrows representing relationships between elements other than "dependency relationships" may be referred to as "small."

[0147] Next, the generation function 153 refers to the disease data table 21 and identifies that the impact on "myocardial infarction," a latent disease associated with the disease ID of "hypertension," one of the patient's existing diseases, is "negative." Then, the generation function 153 associates and sets display information between "hypertension" and "myocardial infarction" that represents the negative impact that "hypertension" has on "myocardial infarction." For example, in this case, the display information is represented by a small dashed arrow pointing from "hypertension" to "myocardial infarction," as shown in Figure 9.

[0148] Next, the generation function 153 identifies that "ACE inhibitors," one of the treatments being administered to the target patient, are a treatment for "hypertension." Then, the generation function 153 associates and sets display information between "ACE inhibitors" and "hypertension" that represents the positive effect that "ACE inhibitors" have on "hypertension." For example, in this case, the display information is represented by a small solid arrow pointing from "ACE inhibitors" to "hypertension," as shown in Figure 9.

[0149] Furthermore, the generation function 153 refers to the treatment data table 31 and identifies that the effect on the underlying disease "aspiration pneumonia" associated with the treatment ID of "ACE inhibitors" is "positive". Next, the generation function 153 associates and sets display information between "ACE inhibitors" and "aspiration pneumonia" that represents the positive effect that "ACE inhibitors" have on "aspiration pneumonia".

[0150] The generation function 153 then performs the same processing on elements such as "mental illness" as described above, and generates a graph showing the relationship between "existing illness," "past illness," "latent illness," "treatment performed," "hobbies and preferences," and "surrounding environment," as shown in Figure 9, based on the set display information.

[0151] Figure 10 is an illustrative diagram showing an example of how to calculate risk values ​​for existing and latent diseases.

[0152] This section explains the calculation of risk values ​​for the existing condition "Frailty: Legs and Lower Back" and the latent condition "Falls and Fractures" as examples. First, we will explain the calculation of the risk value for the existing condition "Frailty: Legs and Lower Back". The calculation function 154 sets the severity level of the existing condition "Frailty: Legs and Lower Back" associated with the patient ID of the target patient, registered in the patient data table 11, to "1" as the current severity level of "Frailty: Legs and Lower Back".

[0153] Furthermore, since "frailty: legs and lower back" is a pre-existing condition, calculation function 154 sets the likelihood of "frailty: legs and lower back" to the maximum value of "10". Then, calculation function 154 calculates "10 (likelihood of pre-existing condition) × 1 (current severity) = 10" as the self-risk value for "frailty: legs and lower back".

[0154] Furthermore, the calculation function 154 sets the likelihood of the latent disease "falls and fractures" associated with the disease ID "Frailty: Legs and Lower Back" registered in the disease data table 21, which is "+2", to the increase or decrease in the likelihood of "falls and fractures" due to "Frailty: Legs and Lower Back". In addition, the severity of "falls and fractures" registered in the disease data table 21, which is "+1", is set to the increase or decrease in the severity of "falls and fractures" due to "Frailty: Legs and Lower Back".

[0155] Furthermore, the calculation function 154 sets the likelihood (base) of "falls and fractures" to "2", which is associated with the disease ID of "falls and fractures" registered in the disease data table 21. It also sets the severity (base) of "2", which is registered in the disease data table 21, to the severity (base) of "falls and fractures".

[0156] Calculation function 154 calculates the risk value as follows: "2 (increase or decrease in likelihood of falls and fractures due to frailty: legs and hips) × 2 (severity of falls and fractures (base)) + 2 (likelihood of falls and fractures (base)) × 1 (increase or decrease in severity of falls and fractures due to frailty: legs and hips) = 6".

[0157] Then, calculation function 154 calculates "10 (self-risk value for "frailty: legs and hips") + 6 (assigned risk value for "frailty: legs and hips") = 16" as the risk value for "frailty: legs and hips".

[0158] Next, we will explain how to calculate the risk value for the latent condition "falls and fractures". The calculation function 154 sets the likelihood of the latent condition "falls and fractures" associated with the treatment ID of "anticoagulant," one of the treatments performed on the target patient, which is registered in the treatment data table 31, as "±0" and is one of the factors for increasing or decreasing the likelihood of "falls and fractures". In addition, the severity of "falls and fractures" registered in the treatment data table 31, which is "+3", is set as one of the factors for increasing or decreasing the severity of "falls and fractures".

[0159] Next, the calculation function 154 sets the likelihood of the latent disease "falls and fractures" associated with the treatment ID of "sleeping pills," one of the treatments performed on the target patient, registered in the treatment data table 31, as "+2," and assigns this value to one of the factors that increase or decrease the likelihood of "falls and fractures." It also sets the severity of "falls and fractures," registered in the treatment data table 31, as "±0," and assigns this value to one of the factors that increase or decrease the severity of "falls and fractures."

[0160] Calculation function 154 sets "2 (likelihood of falls and fractures (base)) + (2 + 2) (total of factors that increase or decrease the likelihood of falls and fractures) = 6" as "likelihood of falls and fractures" and "2 (severity of falls and fractures (base)) + (3 + 1) (total of factors that increase or decrease the severity of falls and fractures) = 6" as "severity of falls and fractures".

[0161] The calculation function 154 then calculates "6 (likelihood of falling / fracture) × 6 (severity of falling / fracture) = 36" as the self-risk value for "falling / fracture". Since there are no arrows output from "falling / fracture", the assigned risk value is 0. Therefore, the calculation function 154 calculates "36 + 0 = 36" as the risk value for "falling / fracture".

[0162] Figure 11 is an illustrative diagram showing an example of how to calculate risk values ​​for hobbies and preferences.

[0163] The example in Figure 11 explains how to calculate the risk value for the hobby preference "I'm not good at exercise." The calculation function 154 sets the influence level of the hobby preference "I'm not good at exercise," which is linked to the treatment ID of "Exercise therapy (frailty: legs and hips)," one of the treatments performed on the target patient, which is registered in the treatment data table 31, as one of the factors for calculating the risk value.

[0164] Furthermore, the calculation function 154 sets the influence level of the hobby preference "I don't like exercise" ("10"), which is linked to the treatment ID of "Exercise therapy (diabetes)," one of the treatments performed by the target patient, as one of the factors for calculating the risk value.

[0165] Then, calculation function 154 calculates "10 (the degree of influence of "exercise therapy (frailty: legs and hips)" on "dislike of exercise") + 10 (the degree of influence of "exercise therapy (diabetes)" on "dislike of exercise") = 20" as the risk value for "dislike of exercise".

[0166] Figure 12 shows an example of a graph representing interrelationships and risk values.

[0167] The display control function 155 controls the display of the correlation graph generated by the generation function 153 on the display 140. The display control function 155 also controls the display of the risk values ​​of each element calculated by the calculation function 154 at the corresponding element positions on the graph. This enables the display control function 155 to display the correlation graph and the graph representing the risk values, as shown in Figure 12, on the display 140.

[0168] Furthermore, the display control function 155 controls the display of an alert when a predetermined risk value threshold (for example, "30") is exceeded. In the example in Figure 12, the display control function 155 displays "!" as an alert because the risk value for "falls and fractures" exceeds the threshold. Note that different numerical values ​​may be set for each element such as disease.

[0169] As described above, displaying an alert when a threshold is exceeded allows users to intuitively grasp the points that require attention.

[0170] Figure 13 shows an example of a graph extracted from a correlation graph and a graph representing risk values.

[0171] Figure 13 illustrates the case where the user focuses on "falls and fractures" and issues an extraction instruction. In this case, the extraction function 156 extracts elements from the correlation graph and the graph representing risk values, starting with "falls and fractures" and extending to the element at the end of the third arrow.

[0172] For example, if the arrows are followed starting from "falls / fractures" to "anticoagulants," "myocardial infarction," and "hypertension," the element at the end of the third arrow is "hypertension." Therefore, the extraction function 156 extracts the elements up to "anticoagulants," "myocardial infarction," and "hypertension" along with the arrows and risk values. The display control function 155 controls the display 140 to show the elements extracted from the correlation graph and the graph representing the risk values ​​by the extraction function 156.

[0173] Figure 14 is an illustrative diagram showing an example of an alternative treatment method.

[0174] Figure 14 illustrates an example where the user focuses on "falls and fractures" and requests the presentation of alternative treatment methods. Note that in Figures 14 through 16, only elements related to "falls and fractures" are shown as graphs for clarity.

[0175] In this case, the presentation function 157 presents alternative treatment methods that are registered in the treatment data table 31 as treatments for "myocardial infarction," "frailty: legs and hips," and "insomnia," and that can also reduce the risk value of "falls and fractures."

[0176] The display control function 155 controls the display 140 to show the list L of alternative treatment methods presented by the presentation function 157. In the example in Figure 14, the presentation function 157 presents "digital medicine (alternative: sleeping pills)" for "insomnia," "robot suit (additional)" and "walking aid (additional)" for "frailty: legs and hips," and "anticoagulant (removed)" for "myocardial infarction," and the display control function 155 displays these as list L on the display 140.

[0177] The display control function 155 allows users to tentatively select or select each treatment method displayed as a list L of alternative treatment methods using their mouse. Specifically, when the user places the mouse pointer over "Digital Medicine (Alternative)" in list L, the selection function 158 tentatively selects "Digital Medicine (Alternative)".

[0178] In this case, the display control function 155 may perform actions such as flashing "sleeping pills" in the graph to indicate that "digital medicine" is a substitute for "sleeping pills".

[0179] Furthermore, when a user places the mouse pointer over "Digital Medicine (Alternative)" in list L and performs a left single click, "Digital Medicine (Alternative)" is selected via selection function 158. The user can also select multiple alternative treatment methods by continuing to select other alternative treatment methods.

[0180] Figure 15 is an illustrative diagram showing an example of a preview display of changes in risk values.

[0181] Figure 15 illustrates the process of the display control function 155 when the user tentatively selects "Digital Medicine (Alternative)". In this case, the display control function 155 displays the change in the risk value of "falls and fractures" when the treatment for "insomnia" is replaced from "sleeping pills" to "digital medicine" in the format "36→20" along with "Digital Medicine (Alternative)" on list L.

[0182] The change from "36 to 20" indicates that if the "sleeping pills" used in the treatment for "insomnia" are replaced with "digital medication," the risk value for "falls and fractures" decreases from "36" to "20." By previewing the change in risk values ​​at the provisional selection stage, users can see the change in risk values ​​before actually selecting an alternative treatment, allowing them to efficiently consider changes to their treatment.

[0183] Figure 16 is an illustrative diagram showing an example of a graph displayed after the treatment substitution has been performed.

[0184] The example in Figure 16 describes the process when the user selects "Digital Medicine (Alternative)" and "Robo-Suit (Additional)" as alternative treatment methods. In this case, first, the specific function 152 identifies the underlying disease (and other potential risks) associated with the treatment IDs of "Robo-Suit" and "Digital Medicine" registered in the treatment data table.

[0185] In the example shown in Figure 16, the identification function 152 identifies "high-cost medical treatment" as a new potential risk, which is linked to the treatment ID of the "robosuit" registered in the treatment data table 31. The generation function 153 generates a graph representing the interrelationships of each element, including the new potential risk "high-cost medical treatment" identified by the identification function 152. The calculation function 154 calculates the risk value for each element that is subject to risk value calculation, including "high-cost medical treatment".

[0186] The display control function 155 then displays a correlation graph and a graph representing risk values ​​so that it is clear that the "sleeping pills" used in the treatment of "insomnia" have been replaced with "digital medicine," and that a "robot suit" has been added as a treatment method for "frailty: legs and hips." In addition, the display control function 155 displays both the risk value before and after the treatment substitution so that the change in risk values ​​can be seen.

[0187] In the example shown in Figure 16, the display control function 155 displays that the risk value for "Frailty: Legs and Lower Back" changes from "16" to "10", the risk value for "Poor Exercise" changes from "20" to "15", and the risk value for "Falls and Fractures" changes from "36" to "20". The display control function 155 may also control the display to show a new indication (for example, "New") for "High-Cost Medical Care," which is a new potential risk arising from the substitution of the treatment being performed.

[0188] Next, the processing of the medical information processing device 100 according to this embodiment will be described. Figure 17 is a flowchart showing an example of the processing of the medical information processing device 100.

[0189] First, the acquisition function 151 acquires patient data (step S1). Specifically, the acquisition function 151 acquires patient data such as "name," "disease ID," "disease name," "treatment method," "severity," "treatment priority score," "hobbies and preferences," "surrounding environment," and "past illnesses," which are linked to the patient ID of the target patient and registered in the patient data table 11.

[0190] Next, the identification function 152 identifies the potential risks of the target patient (step S2). Specifically, the identification function 152 identifies potential risks associated with the disease IDs of the target patient's existing diseases, which are registered in the disease data table 21.

[0191] Furthermore, the specific function 152 identifies potential risks associated with the treatment method ID of the treatment performed by the target patient, which is registered in the treatment data table 31. In addition, the specific function 152 identifies potential risks associated with the surrounding environment ID of the target patient's surrounding environment, which is registered in the surrounding environment data table 41.

[0192] Next, the generation function 153 generates a relationship graph (a graph in which the relationships between each element of disease, treatment, hobbies and preferences, and surrounding environment are represented by arrows) (step S3). Specifically, first, the generation function 153 obtains information on the "dependencies" of existing diseases registered in the patient data table 11. Then, based on the obtained dependencies, the generation function 153 generates a graph showing the dependencies of existing diseases.

[0193] Furthermore, the generation function 153 identifies the influence (positive or negative influence) that diseases, treatments, and the surrounding environment have on diseases or preferences, based on the disease data table 21, treatment data table 31, and surrounding environment data table 41, and generates a graph showing the relationships between each element based on these.

[0194] Next, the calculation function 154 calculates risk values ​​for each element (step S4). Specifically, the calculation function 154 identifies the likelihood of disease occurrence, the severity of disease, and the impact on hobbies and preferences, which are registered in the disease data table 21, the treatment data table 31, and the surrounding environment data table 41, and calculates risk values ​​for each element based on these.

[0195] Next, the display control function 155 controls the display of the treatment priority score acquired by the acquisition function 151, the dependency relationships generated by the generation function 153, the correlation relationships generated by the generation function 153, and the risk values ​​of each element calculated by the calculation function 154 (step S5). If the extraction function 156 extracts some elements from the correlation relationships and risk values, the display control function 155 controls the display to show only the elements extracted by the extraction function 156.

[0196] Next, the presentation function 157 checks whether the user has entered any alternative treatment methods (step S6). If there is no input (step S6: No), the process in step 6 is repeated. On the other hand, if there is input (step S6: Yes), the presentation function 157 presents alternative treatment methods that can reduce the risk value of the potential risk specified by the user (step S7).

[0197] Next, the display control function 155 controls the display of the alternative treatment methods presented by the presentation function 157 as a list (step S8).

[0198] Next, the selection function 158, following the user's instructions, tentatively selects one of the alternative treatment methods presented by the presentation function 157 (step S9). Specifically, the selection function 158 tentatively selects the alternative treatment method that the user places the mouse pointer over.

[0199] Next, the display control function 155 controls the display of the change in risk value together with the alternative treatment method tentatively selected by the selection function 158 (step S10). Specifically, the display control function 155 controls the display of the change in risk value together with the tentatively selected alternative treatment method in the format "(risk value before alternative) → (risk value after alternative)".

[0200] Next, the display control function 155 checks whether the user has selected an alternative treatment method (step S11). If there is no selection input (step S11: No), the process proceeds to step S9.

[0201] On the other hand, if a selection input is made (step S11: Yes), the display control function 155 controls the display of the correlation graph and the change in risk value after the treatment substitution, and then terminates this process (step S12).

[0202] The medical information processing device 100 according to the embodiment described above includes an acquisition function 151 as an acquisition unit and a display control function 155 as a display control unit.

[0203] The acquisition function 151 acquires patient data showing multiple different types of treatments for one or more diseases related to the target patient. The display control function 155 controls the display 140 to show a correlation graph on the display showing the mutual influence of multiple different types of treatments shown in the patient data on potential risks.

[0204] This allows users to visually grasp how different elements, such as multiple diseases and multiple treatments, each affect the potential risk. Therefore, for example, if multiple elements negatively impact one potential risk, users can easily understand that the potential risk is increased by multiple elements.

[0205] In other words, the medical information processing device 100 according to this embodiment makes it easy to grasp the risks that increase due to a combination of factors. Furthermore, if the risks that increase due to a combination of factors can be easily grasped, it is thought that users can efficiently consider discontinuing, substituting, or adding treatment methods.

[0206] The embodiments described above can also be modified and implemented as appropriate by changing some of the configurations or functions of each device. Therefore, several modifications of the embodiments described above will be described below as other embodiments. In the following, we will mainly describe the differences from the embodiments described above, and will omit detailed explanations of points that are common with what has already been described. Furthermore, the modifications described below may be implemented individually or in combination as appropriate.

[0207] (Variation 1) In the embodiments described above, the generation function 153 was described in which it generates a graph of the interrelationships between the patient's disease, treatment method, hobbies and preferences, and surrounding environment. However, the generation function 153 may also generate a graph of the interrelationships between elements that include genetic information in addition to these elements.

[0208] Here, genetic information refers to information related to heredity, such as "having a certain gene makes one susceptible to a particular disease" or "having a certain gene makes one less susceptible to the effects of a particular drug."

[0209] This modified version is expected to enable more accurate simulations regarding the "likelihood" of a disease and the "expected effect" of a drug.

[0210] (Modification 2) In the embodiment described above, the extraction function 156 was described in which elements up to the third arrow are extracted from the correlation graph and the graph representing the risk value, starting from the potential risk that the user is interested in. However, the extraction function 156 may also perform the extraction process using the degree of relevance.

[0211] Here, relevance is an indicator that represents the degree of relationship between elements. Relevance may be predetermined for each element, or it may be calculated based on the increase or decrease values ​​of "likelihood of occurrence," "severity," and "impact" used in calculating risk values.

[0212] Figure 18 is an illustrative diagram showing an example of the extraction process related to Modification Example 2.

[0213] In the example in Figure 18, we will explain the case where we start with "falls and fractures" and follow the arrow towards "anticoagulants." In this case, first, the extraction function 156 sets the initial score to "1" and subtracts "1 / 4," which is the reciprocal of the correlation between "falls and fractures" and "anticoagulants" ("4"). As a result, the score becomes "1 - 1 / 4 = 0.75."

[0214] The extraction function 156 similarly subtracts the reciprocal of the relevance score from the score, extracting elements until the score becomes 0 or greater. In the example in Figure 18, "Family history: Myocardial infarction" and "ACE inhibitors" have scores less than 0, and therefore are not extracted by the extraction function 156. Note that the extraction method using relevance is not limited to the above, and other methods may be used. For example, the score may be a numerical value other than "1".

[0215] According to this modified example, since the extraction function 156 performs extraction while considering the degree of relationship between elements, it is possible to reduce the possibility of extracting elements with low relevance compared to when extraction is performed based on the number of arrows.

[0216] In the embodiments described above, an example was given in which the functional configuration of the medical information processing device 100 is realized by the processing circuit 150, but the embodiments are not limited to this. For example, the functional configuration described herein may be realized by hardware alone, or by a combination of hardware and software.

[0217] Furthermore, the term "processor" used in the above explanation refers to circuits such as CPUs (Central Processing Units), GPUs (Graphics Processing Units), Application Specific Integrated Circuits (ASICs), and Programmable Logic Devices (e.g., Simple Programmable Logic Devices (SPLDs), Complex Programmable Logic Devices (CPLDs), and Field Programmable Gate Arrays (FPGAs)).

[0218] The processor performs its functions by reading and executing the program stored in the memory circuit 120. Alternatively, instead of storing the program in the memory circuit 120, the processor may be configured to directly incorporate the program into its own circuitry. In this case, the processor performs its functions by reading and executing the program incorporated into the circuitry.

[0219] Furthermore, the processor of this embodiment is not limited to being configured as a single circuit; it may also be configured as a single processor by combining multiple independent circuits, and its functions may be realized in this way.

[0220] Here, the program executed by the processor is provided pre-installed in ROM (Read Only Memory) or memory circuits. Alternatively, this program may be provided as a file in an installable or executable format on a computer-readable storage medium such as a CD (Compact Disc)-ROM, FD (Flexible Disc), CD-R (Recordable), or DVD (Digital Versatile Disc).

[0221] Furthermore, this program may be provided or distributed by being stored on a computer connected to a network such as the Internet and downloaded via the network. For example, this program is composed of modules, each containing the functional parts described above. In terms of actual hardware, the CPU reads the program from a storage medium such as ROM and executes it, thereby loading each module into main memory and creating it in main memory.

[0222] According to the embodiments described above, it is possible to easily identify risks that are increased by a combination of factors.

[0223] While several embodiments (modifications) have been described, these embodiments are presented as examples only and are not intended to limit the scope of the invention. These embodiments can be carried out in a variety of other forms, and various omissions, substitutions, modifications, and combinations of embodiments can be made without departing from the spirit of the invention. These embodiments and their variations are included in the scope and spirit of the invention, as well as in the claims and their equivalents. [Explanation of symbols]

[0224] 1. Medical Information Processing System 10. Patient Data Database 11. Patient Data Table 20 Disease Data Database 21 Disease Data Table 30 Treatment Data Database 31 Treatment Data Table 40. Surrounding Environment Data Database 41. Surrounding Environment Data Table 100 Medical Information Processing Devices 151 Acquisition function 152 Specific Functions 153 Generation function 154 Calculation Function 155 Display control function 156 Extraction function 157 Presentation function 158 Selection Functions

Claims

1. An acquisition unit that acquires patient information indicating multiple different treatment methods currently being implemented for one or more diseases related to the target patient, A first potential risk identification unit identifies the first potential risk for each of the multiple treatments of different characteristics, based on one or more diseases related to the target patient, multiple treatments of different characteristics indicated by the acquired patient information, and first potential risk identification information that stores multiple pairs of disease, treatment, and first potential risk. A first impact identification unit identifies the positive or negative effects on each of the multiple different treatments indicated by the patient information obtained, the identified first potential risk, and first impact identification information that stores multiple pairs of treatments, the first potential risk, and the positive or negative effects that the treatment has on the first potential risk, for each of the multiple different treatments indicated by the patient information. A generation unit generates first relational information indicating the positive or negative effects that each of the identified multiple different treatments has on each of the first potential risks, based on the positive or negative effects that each of the multiple different treatments indicated by the patient information has on each of the identified first potential risks. A display control unit that controls the display of the first relational information on a display device, A medical information processing device equipped with [a specific feature].

2. The aforementioned patient information includes information about multiple diseases that the patient is currently suffering from. A dependency identification unit identifies the dependencies between the diseases currently afflicting the target patient, based on the multiple diseases currently afflicting the target patient as indicated by the acquired patient information, and dependency information defining the dependencies between the diseases. The display control unit performs control to display the identified dependency on the display device. The medical information processing device according to claim 1.

3. The patient information includes a treatment priority score representing the priority of treatment for each of the aforementioned diseases. The display control unit performs control to display the treatment priority score together with the name of the disease on the display device. The medical information processing device according to claim 2.

4. A first indicator identification unit that identifies the first indicator based on a plurality of different treatment methods indicated by the acquired patient information, the identified first potential risk, and first indicators relating to the calculation of a first risk value indicating the degree of adverse impact that the treatment method has on the first potential risk. The system further comprises a first calculation unit that calculates the first risk value based on the identified first indicator, The display control unit performs control to display the first risk value calculated by the first calculation unit on the display device. A medical information processing device according to any one of claims 1 to 3.

5. A presentation unit that presents one or more alternative treatments that can reduce the first risk value, The presenting unit further comprises a selection unit that selects at least one of the alternative treatments from the one or more alternative treatments presented by the presenting unit, The first potential risk identification unit receives a designation of the first potential risk from the user, and extracts at least one treatment method associated with the designated first potential risk from the first potential risk identification information. The first impact identification unit identifies the positive or negative effects of the extracted at least one treatment method on each of the first potential risks, based on the extracted at least one treatment method, the specified first potential risk, and the first impact identification information. The first indicator identification unit identifies the first indicator of the extracted at least one treatment method based on the extracted at least one treatment method, the first potential risk of the extracted at least one treatment method, and the first indicator identification information. The first calculation unit calculates a first risk value for the extracted at least one treatment method based on the first indicator of the extracted at least one treatment method, The presentation unit presents, as the alternative treatment, a treatment method among the at least one extracted treatment method in which the first risk value decreases below the first risk value corresponding to each of the plurality of treatment methods of different properties calculated by the first calculation unit. The generation unit generates post-alternative first relational information indicating the positive or negative effects that multiple treatments of different properties, including the selected at least one alternative treatment, have on the first potential risk, based on the positive or negative effects that the selected at least one alternative treatment has on each of the first potential risks. The display control unit performs control to display the replacement first relationship information on the display device. The medical information processing device according to claim 4.

6. The first calculation unit calculates, from among the extracted first risk values ​​of the at least one treatment method, the first risk value corresponding to the selected at least one alternative treatment method as a post-alternative risk value that shows the adverse effect that the at least one alternative treatment method selected by the selection unit has on the first potential risk. The display control unit performs control to display the replacement risk value calculated by the first calculation unit on the display device. The medical information processing device according to claim 5.

7. The selection unit, based on instructions from the user, provisionally selects at least one of the alternative treatments from among one or more alternative treatments. The first calculation unit calculates, from among the extracted first risk values ​​of the at least one treatment method, the first risk value corresponding to the at least one alternative treatment method that has been tentatively selected, as a tentative post-substitution risk value that indicates the adverse effect that the at least one alternative treatment method tentatively selected by the selection unit has on the first potential risk. The display control unit performs control to display together the first risk value and the provisional substitute risk value corresponding to each of the plurality of different treatment methods. The medical information processing device according to claim 5 or 6.

8. The alternative treatments include replacing at least one of several treatments with another, discontinuing at least one of several treatments, and adding at least one other treatment. A medical information processing device according to any one of claims 5 to 7.

9. The patient information includes information indicating one or more diseases related to the subject patient. A second potential risk identification unit identifies the second potential risk for one or more diseases related to the target patient, based on the acquired patient information indicating one or more diseases related to the target patient, and second potential risk identification information which stores multiple pairs of diseases and second potential risks. A second impact identification unit identifies the adverse effects on each of the second potential risks for one or more diseases related to the target patient indicated by the patient information, based on the identified second potential risk and second impact identification information which stores multiple pairs of the second potential risk and the adverse effects that the disease has on the second potential risk. The generation unit generates second relational information showing the adverse effects of one or more diseases related to the identified target patient on each of the second potential risks, based on the adverse effects of one or more diseases related to the target patient shown in the patient information on each of the second potential risks, and generates first integrated relational information by integrating the first relational information and the second relational information. The display control unit performs control to display the first integrated relationship information on the display device. A medical information processing device according to any one of claims 4 to 8.

10. A second indicator identification unit that identifies the second indicator based on a plurality of pairs of the patient information obtained, which includes one or more diseases relating to the target patient, the identified second potential risk, and the second indicator for calculating a second risk value that indicates the degree of adverse impact the disease has on the second potential risk. The system further comprises a second calculation unit that calculates the second risk value based on the second indicator, The display control unit performs control to display the second risk value calculated by the second calculation unit on the display device. The medical information processing device according to claim 9.

11. The aforementioned patient information includes information indicating the family history of diseases in the relatives of one or more of the target patients. A third potential risk identification unit identifies the third potential risk for the family history disease based on the acquired patient information, the family history disease indicated by the family history disease, and the third potential risk identification information which stores multiple pairs of family history disease and third potential risk. A third impact identification unit identifies the impact of the family history disease indicated by the patient information on the third potential risk, based on the identified third potential risk, third impact identification information which stores multiple pairs of the third potential risk, a family history disease, and the adverse impact of the family history disease on the third potential risk. The generation unit generates third relational information showing the adverse effects of the family history disease indicated in the patient information on each of the third potential risks, based on the adverse effects that the identified family history disease has on each of the third potential risks, and generates second integrated relational information by integrating the first relational information and the third relational information. The display control unit performs control to display the second integrated relationship information on the display device. A medical information processing device according to any one of claims 4 to 10.

12. A third indicator identification unit that identifies the third indicator based on a third indicator, which stores a plurality of sets of the family history disease indicated by the acquired patient information, the identified third potential risk, and the third indicator for calculating a third risk value that indicates the degree of adverse impact that the family history disease, the third potential risk, and the family history disease have on the third potential risk. The system further comprises a third calculation unit that calculates the third risk value based on the third indicator, The display control unit performs control to display the third risk value calculated by the third calculation unit on the display device. The medical information processing device according to claim 11.

Images