Information processing device, information processing method, and program

The information processing device addresses physician bias by comparing patient attributes with historical data to suggest more appropriate treatments, enhancing treatment suitability and clinical outcomes.

JP7580977B2Active Publication Date: 2024-11-12CANON MEDICAL SYST CORP
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
JP2020147517
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Filing Date
2020-09-02
Publication Date
2024-11-12
Estimated Expiration
2040-09-02

AI Technical Summary

Technical Problem

Physicians' treatment recommendations are influenced by personal biases and institutional factors, leading to variability in clinical outcomes and a lack of awareness of alternative treatment options.

Method used

An information processing device that acquires patient attributes, calculates and compares attribute distributions with historical patient data to suggest more suitable treatment methods, reducing cognitive bias through stratification based on hospital and disease indices.

Benefits of technology

Enhances the suitability of treatment recommendations by minimizing physician bias and improving clinical outcomes for individual patients.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007580977000001
    Figure 0007580977000001
  • Figure 0007580977000002
    Figure 0007580977000002
  • Figure 0007580977000003
    Figure 0007580977000003
Patent Text Reader

Abstract

To provide an information processor, a method for processing information, and a program that can reduce the cognitive bias of a doctor and allow a doctor to propose a more desirable method for diagnosis for a patient.SOLUTION: An information processor 100 includes an acquisition unit 121, a first calculation unit 122, a second calculation unit 123, and an output unit. The acquisition unit 121 acquires the attribute of a target patient. The first calculation unit 122 calculates a first distribution, which quantitatively expresses an attribute acquired by the acquisition unit 121. The second calculation unit 123 calculates a second distribution, which quantitatively expresses the attribute of each of a plurality of hierarchical groups of patients on the basis of diagnosis information of a plurality of patients who has been diagnosed before. The output unit outputs information based on the result of comparison between the first distribution calculated by the first calculation unit 122 and the second distribution calculated by the second calculation unit 123.SELECTED DRAWING: Figure 3
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The embodiments disclosed in this specification and the drawings relate to an information processing device, an information processing method, and a program. [Background technology]

[0002] It is known that the treatment methods recommended by the attending physician vary depending on the country, facility, and physician, and that clinical outcomes also vary. The physician may not realize that there is a bias in the recommended options, and may not pay attention to other options. In other words, the recommended treatment method is selected based on the attending physician's specialty, preferences, values, and facility equipment, making it difficult for the physician to realize that there is a bias in the selection of the treatment method. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Special Publication No. 2014-503894 Summary of the Invention [Problem to be solved by the invention]

[0004] The problem to be solved by the embodiments disclosed in this specification and the drawings is to reduce the cognitive bias of doctors and allow them to propose a treatment method that is more suitable for the patient. However, the problem to be solved by the embodiments disclosed in this specification and the drawings is 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. [Means for solving the problem]

[0005] The information processing device of the embodiment has an acquisition unit, a first calculation unit, a second calculation unit, and an output unit. The acquisition unit acquires attributes of a target patient. The first calculation unit calculates a first distribution that quantitatively represents the attributes acquired by the acquisition unit. The second calculation unit calculates a second distribution that quantitatively represents attributes of each of a plurality of groups stratified from a plurality of patients based on medical information of the plurality of patients who have been treated in the past. The output unit outputs information based on a comparison result between the first distribution calculated by the first calculation unit and the second distribution calculated by the second calculation unit. [Brief description of the drawings]

[0006] [Figure 1] 1 is a diagram illustrating an example of the configuration of an information processing system 1 according to a first embodiment. [Diagram 2] 1 is a diagram illustrating an example of the configuration of a terminal device 10 according to a first embodiment. [Diagram 3] 1 is a diagram illustrating an example of the arrangement of an information processing device 100 according to a first embodiment. [Figure 4] 4 is a flowchart showing the flow of a series of processes of the processing circuit 120 according to the first embodiment. [Diagram 5] FIG. 13 is a diagram illustrating an example of an attribute distribution. [Figure 6] FIG. 13 is a diagram for explaining a stratification process. [Figure 7] FIG. 11 is a diagram for explaining a method for comparing attribute distributions. [Figure 8] FIG. 2 is a diagram showing an example of a screen of the display 13 of the terminal device 10. [Figure 9] 10 is a flowchart showing the flow of a series of processes of a processing circuit 120 according to the second embodiment. [Figure 10] 11 is a flowchart showing the flow of a series of processes of a processing circuit 120 according to the third embodiment. [Figure 11] FIG. 13 is a diagram showing another example of the screen of the display 13 of the terminal device 10. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0007] Hereinafter, an information processing apparatus, an information processing method, and a program according to embodiments will be described with reference to the drawings.

[0008] (First embodiment) [Information processing system configuration] 1 is a diagram illustrating an example of the configuration of an information processing system 1 in the first embodiment. The information processing system 1 includes, for example, a terminal device 10 and an information processing device 100. The terminal device 10 and the information processing device 100 are communicatively connected via a communication network NW.

[0009] The communication network NW may refer to any information and communication network that uses electrical communication technology. For example, the communication network NW includes wireless / wired LANs such as hospital backbone LANs (Local Area Networks) and the Internet, as well as telephone communication line networks, optical fiber communication networks, cable communication networks, and satellite communication networks.

[0010] The terminal device 10 is a terminal device such as a personal computer, a tablet terminal, or a mobile phone used by a medical worker P2. The medical worker P2 is typically a doctor, but may be a nurse or other person involved in medical treatment. The medical worker P2 inputs information about a patient (hereinafter referred to as a target patient P1) who is the subject of medical treatment, for example, into the terminal device 10.

[0011] In this embodiment, "medical treatment" may include not only treatments such as surgery and medication, but also examinations leading up to or after treatment, and any other medical procedures.

[0012] The terminal device 10 transmits information input by the medical worker P2 to the information processing device 100 via the communication network NW, or receives information from the information processing device 100.

[0013] The information processing device 100 receives information from the terminal device 10 via the communication network NW, processes the received information, and transmits the processed information to the terminal device 10 via the communication network NW.

[0014] The information processing device 100 may be a single device, or may be a system in which multiple devices connected via a communication network NW operate in cooperation with each other. That is, the information processing device 100 may be realized by multiple computers (processors) included in a distributed computing system or a cloud computing system. In addition, the information processing device 100 does not necessarily need to be a separate device different from the terminal device 10, and may be a device integrated with the terminal device 10.

[0015] [Terminal device configuration] 2 is a diagram illustrating an example of the configuration of the terminal device 10 in the first embodiment. The terminal device 10 includes, for example, a communication interface 11, an input interface 12, a display 13, a memory 14, and a processing circuit 20.

[0016] The communication interface 11 communicates with the information processing device 100 and the like via the communication network NW. The communication interface 11 includes, for example, a network interface card (NIC) and an antenna for wireless communication.

[0017] The input interface 12 accepts various input operations from an operator (e.g., medical worker P2), converts the accepted input operations into electrical signals, and outputs the electrical signals to the processing circuit 20. For example, the input interface 12 includes a mouse, a keyboard, a trackball, a switch, a button, a joystick, a touch panel, etc. The input interface 12 may be, for example, a user interface that accepts voice input from a microphone or the like. When the input interface 12 is a touch panel, the input interface 12 may also have the display function of the display 13.

[0018] In this specification, the input interface 12 is not limited to an interface having physical operation parts such as a mouse, a keyboard, etc. For example, an example of the input interface 12 also includes an electrical signal processing circuit that receives an electrical signal corresponding to an input operation from an external input device provided separately from the device and outputs the electrical signal to a control circuit.

[0019] The display 13 displays various types of information. For example, the display 13 displays an image generated by the processing circuit 20, a GUI (Graphical User Interface) for receiving various input operations from the medical worker P2, etc. For example, the display 13 is an LCD (Liquid Crystal Display), a CRT (Cathode Ray Tube) display, an organic EL (Electro Luminescence) display, etc.

[0020] The memory 14 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, a hard disk, or an optical disk. These non-transient storage media may be realized by other storage devices connected via a communication network NW, such as a network attached storage (NAS) or an external storage server device. The memory 14 may also include other non-transient storage media, such as a read only memory (ROM) or a register.

[0021] The processing circuitry 20 includes, for example, an acquisition function 21, a display control function 22, and a communication control function 23. The processing circuitry 20 realizes these functions by, for example, a hardware processor (computer) executing a program stored in a memory 14 (storage circuit).

[0022] The hardware processor in the processing circuit 20 means a circuit such as a central processing unit (CPU), a graphics processing unit (GPU), an application specific integrated circuit (ASIC), a programmable logic device (e.g., a simple programmable logic device (SPLD) or a complex programmable logic device (CPLD), or a field programmable gate array (FPGA)). Instead of storing the program in the memory 14, the program may be directly embedded in the circuit of the hardware processor. In this case, the hardware processor realizes the function by reading and executing the program embedded in the circuit. The above program may be stored in the memory 14 in advance, or may be stored in a non-transitory storage medium such as a DVD or a CD-ROM, and may be installed in the memory 14 from the non-transitory storage medium by mounting the non-transitory storage medium in a drive device (not shown) of the terminal device 10. The hardware processor is not limited to being configured as a single circuit, but may be configured as a single hardware processor by combining multiple independent circuits to realize each function. Also, multiple components may be integrated into a single hardware processor to realize each function.

[0023] The acquisition function 21 acquires input information via the input interface 12 and acquires information from the information processing device 100 via the communication interface 11 .

[0024] The display control function 22 causes the information acquired by the acquisition function 21 to be displayed on the display 13 .

[0025] The communication control function 23 transmits information input to the input interface 12 to the information processing device 100 via the communication interface 11 .

[0026] [Configuration of information processing device] 3 is a diagram illustrating an example of the configuration of the information processing device 100 in the first embodiment. The information processing device 100 includes, for example, a communication interface 110, a processing circuit 120, and a memory .

[0027] The communication interface 110 communicates with the terminal device 10 and the like via the communication network NW. The communication interface 110 includes, for example, a NIC.

[0028] The processing circuit 120 includes, for example, an acquisition function 121, a first calculation function 122, a second calculation function 123, an estimation function 124, a communication control function 125, and a stratification processing function 126. The acquisition function 121 is an example of an "acquisition unit", the first calculation function 122 is an example of a "first calculation unit", the second calculation function 123 is an example of a "second calculation unit", the estimation function 124 is an example of an "estimation unit", and the communication interface 110 and the communication control function 125 are an example of an "output unit". In addition, the "output unit" may be a combination of the communication interface 110 and the communication control function 125 of the information processing device 100 and the display 13 and the display control function 22 of the terminal device 10.

[0029] The processing circuitry 120 realizes these functions by, for example, a hardware processor (computer) executing a program stored in a memory 130 (storage circuitry).

[0030] The hardware processor in the processing circuit 120 means a circuit such as a CPU, a GPU, an application specific integrated circuit, a programmable logic device (e.g., a simple programmable logic device or a composite programmable logic device, a field programmable gate array, etc.). Instead of storing the program in the memory 130, the program may be directly embedded in the circuit of the hardware processor. In this case, the hardware processor realizes the function by reading and executing the program embedded in the circuit. The above program may be stored in the memory 130 in advance, or may be stored in a non-transitory storage medium such as a DVD or a CD-ROM, and may be installed in the memory 130 from the non-transitory storage medium by mounting the non-transitory storage medium in a drive device (not shown) of the information processing device 100. The hardware processor is not limited to being configured as a single circuit, and may be configured as one hardware processor by combining multiple independent circuits to realize each function. Furthermore, multiple components may be integrated into one hardware processor to realize each function.

[0031] The memory 130 is realized by, for example, a semiconductor memory element such as a RAM or a flash memory, a hard disk, or an optical disk. These non-transient storage media may be realized by other storage devices connected via a communication network NW, such as a NAS or an external storage server device. The memory 130 may also include non-transient storage media such as a ROM or a register.

[0032] [Processing flow of information processing device] The following describes the processing of each function by the processing circuit 120 of the information processing device 100 with reference to the flowcharts. Fig. 4 is a flowchart showing the flow of a series of processes by the processing circuit 120 according to the first embodiment.

[0033] First, the acquisition function 121 acquires the attributes of the target patient P1 from the terminal device 10 via the communication interface 110 (step S100).

[0034] The attributes of the target patient P1 are composed of multiple properties and characteristics such as the current state of the target patient P1, the transition of the state of the target patient P1 since the target patient P1 visited the hospital, the transition of the state of the target patient P1 while being followed up, medical history, and genetic information. Some of these multiple properties and characteristics may be omitted or may be replaced with other properties and characteristics that are not exemplified. For example, the attributes of the target patient P1 may include a treatment method, a treatment history, and the like.

[0035] The current condition of the target patient P1 includes, for example, age, sex, weight, blood type, vital signs, disease, image parameters indicating disease characteristics, non-image parameters indicating disease characteristics, concurrent diseases and their characteristics, expected complications, etc. The transition of the condition of the target patient P1 after the visit to the hospital includes, for example, weight, cardiac function state, respiratory state, metabolic state, image parameters indicating disease characteristics, non-image parameters indicating disease characteristics, etc. The transition of the condition while following up the target patient P1 includes, for example, weight, cardiac function state, respiratory state, metabolic state, image parameters indicating disease characteristics, non-image parameters indicating disease characteristics, etc.

[0036] For example, suppose that a medical worker P2 such as a doctor inputs the current condition, transition of condition, medical history, and genetic information of a target patient P1 to the terminal device 10. In this case, the terminal device 10 transmits the input information to the information processing device 100 as attributes of the target patient P1. When the communication interface 110 receives the attributes of the target patient P1 from the terminal device 10, the acquisition function 121 of the information processing device 100 acquires the attributes from the communication interface 110.

[0037] Next, the first calculation function 122 calculates a distribution (hereinafter referred to as an attribute distribution) that quantitatively represents the attribute of the target patient P1 acquired by the acquisition function 121 (step S102). The attribute distribution of the target patient P1 is an example of a "first distribution."

[0038] For example, the first calculation function 122 converts each of a plurality of attributes of the target patient P1 into a quantitative value in accordance with guidelines established by government agencies or medical standards established by each medical institution, and calculates the quantified attributes as a distribution. The first calculation function 122 may quantify the attributes of the target patient P1 using a predetermined database, or may quantify the attributes of the target patient P1 using machine learning (deep learning, etc.).

[0039] FIG. 5 is a diagram showing an example of attribute distribution. As shown in the figure, for example, the attribute distribution may be represented as a radar chart in which the degree of each attribute is graded in five stages from 0 to 5. That is, the value of each attribute may be normalized so that the minimum value is 0 and the maximum value is 5, and then expressed as a distribution like a radar chart. In the attribute distribution, for example, quantitative values ​​of age, sex, and blood type are plotted in the area (a). In the area (b), for example, quantitative values ​​of vital signs at the current time are plotted. In the area (c), for example, quantitative values ​​of disease parameters (image parameters and non-image parameters) at the current time are plotted. In the area (d), for example, quantitative values ​​of transition information during a visit are plotted. In the area (e), for example, quantitative values ​​of transition information during follow-up are plotted. In the area (f), for example, quantitative values ​​of medical history and genetic information are plotted.

[0040] The attributes (b) and (c) (e.g., weight, vital signs, comorbid diseases, and parameters representing disease characteristics) are controllable factors (i.e., control factors) at the current time when the subject patient P1 is receiving medical treatment. The attributes (a), (d), (e), and (f) (e.g., age, blood type, medical history, and family history) are uncontrollable factors (i.e., uncontrollable factors) at the current time when the subject patient P1 is receiving medical treatment.

[0041] In the example of Fig. 5, the attribute distribution is described as a radar chart, but is not limited to this. For example, the attribute distribution may be represented by other statistical charts such as a histogram, a stacked graph, or a heat map. The number of stages of the attribute is also not limited to 5, and may be 4 or less, or 6 or more.

[0042] Note that the first calculation function 122 may integrate all the attributes of the target patient P1 and calculate them as one index value (scalar value) instead of or in addition to calculating the attributes of the target patient P1 as a distribution. For example, when the number of attributes of the target patient P1 is n, the first calculation function 122 may calculate the sum T(i)=Σαi×τ(i) taking into account the degree of influence αi on the disease QI (Quality Index) of each attribute (τ(i); i=1 to n) as an index value representing the entire attributes of the target patient P1. The disease QI will be described later.

[0043] Returning to the explanation of the flowchart in Fig. 4, the second calculation function 123 then calculates the attribute distribution of each of the multiple groups included in the population (step S104).

[0044] The population is composed of a medical professional P2 who is going to treat a target patient P1, or a plurality of patients who have been treated in the past by a medical institution where the medical professional P2 works. The medical institution may be, for example, a hospital, a clinic, or other facility where medical care is provided. The population may also be a patient population in medical statistics. The population can be stratified (also called classified, grouped, or clustered) into a plurality of groups based on a hospital performance index (PI) and / or a disease QI.

[0045] The hospital PI is an index value related to the time or economic cost spent by each patient in the population, such as the number of days of hospitalization or medical expenses. From another perspective, the hospital PI is an index value related to the time or economic cost spent by a medical institution, such as the number of days of hospitalization or medical fees. The hospital PI is an example of a "first index value."

[0046] The disease QI is an index value for measuring the treatment effect, that is, the degree to which the disease of each patient in a population has been treated when the patient is treated according to a certain treatment method. For example, if the patient's disease is cancer, the disease QI may be the 5-year survival rate, the number of days of hospitalization after surgery, the recurrence rate, the cancer remaining rate, the rate of breast-conserving surgery, etc. If the patient's disease is acute myocardial infarction, the disease QI may be the average number of days of hospitalization, etc. If the patient's disease is diabetes, the disease QI may be the HbA1c (Hemoglobin A1c) improvement rate, the number of patient referrals, the number of patient reverse referrals, etc. If the patient's disease is pneumonia, the disease QI may be the average number of days of hospitalization, the initial treatment success rate, etc. The disease QI is an example of a "second index value."

[0047] First, the second calculation function 123 selects one or more index values ​​as a hospital PI and / or a disease QI from among multiple index values ​​for measuring treatment effects in order to calculate the attribute distribution of each group of the population. At this time, the second calculation function 123 may filter the patients of the population according to the medical treatment method.

[0048] When the second calculation function 123 selects the hospital PI and / or disease QI, the second calculation function 123 stratifies the population into a plurality of groups based on the selected hospital PI and / or disease QI. The second calculation function 123 may perform such stratification processing at a timing different from that of this flowchart. The timing may be, for example, a day when the medical institution is closed or at night when there are relatively few patients to be treated. In other words, when the processing of this flowchart is started, the population may already be stratified into a plurality of groups.

[0049] 6 is a diagram for explaining the stratification process. As shown in the figure, for example, the second calculation function 123 calculates a probability density distribution F(X) of a population when a hospital PI or a disease QI is a random variable X. Then, the second calculation function 123 stratifies the population into a plurality of groups on the probability density distribution F(X) according to a certain criterion.

[0050] For example, the second calculation function 123 may classify a group in which the random variable X is less than the second threshold TH2 into group A, a group in which the random variable X is equal to or greater than the second threshold TH2 and less than the first threshold TH1 into group B, and a group in which the random variable X is equal to or greater than the first threshold TH1 into group C. The first threshold TH1 and the second threshold TH2 may be fixed values ​​determined based on, for example, medical statistical results or guidelines, or may be reference values ​​to which a certain margin is added or subtracted from the national average or the average within each medical institution. The first threshold TH1 and the second threshold TH2 may be standard deviations such as ±1σ, ±2σ, or ±3σ. The number of thresholds is not limited to two, and may be one, or three or more. That is, the number of groups may be two, or four or more.

[0051] For example, when the second calculation function 123 selects the cancer recurrence rate as the disease QI, it extracts cancer patients or patients to whom a cancer treatment method has been applied from the population by filtering, and calculates a probability density distribution F(X) in which the cancer recurrence rate of the extracted set of patients (i.e., a sample group) is set as a random variable X. Then, the second calculation function 123 stratifies the population on the probability density distribution F(X) regarding the cancer recurrence rate into a total of three groups, for example, A, B, and C. In this case, group A is a group with a low cancer recurrence rate, group B is a group with a higher cancer recurrence rate than group A, and group C is a group with a higher cancer recurrence rate than group B.

[0052] When the population is stratified into a plurality of groups, the second calculation function 123 calculates the attribute distribution of each group. For example, the second calculation function 123 averages the attribute distribution of each of the plurality of patients included in each group, and sets the averaged attribute distribution as the attribute distribution of each group. Specifically, when group A includes 100 patients, the second calculation function 123 averages the attribute distribution of each of the 100 patients, and sets the averaged attribute distribution of the 100 patients as the attribute distribution of group A. The second calculation function 123 may similarly calculate the attribute distribution of each group by averaging the attribute distributions of multiple patients for other groups such as group B and group C. The attribute distribution of each group is an example of a "second distribution".

[0053] Returning to the description of the flowchart in Fig. 4, the estimation function 124 then compares the attribute distribution of the target patient P1 calculated by the first calculation function 122 with the attribute distribution of each of the multiple groups calculated by the second calculation function 123 (step S106).

[0054] 7 is a diagram for explaining a method for comparing attribute distributions. For example, assume that there are three groups of attribute distributions, group A, group B, and group C. In this case, the estimation function 124 compares the attribute distribution of the target patient P1 with the attribute distributions of each of groups A, B, and C, and calculates the similarity between the attribute distributions.

[0055] For example, when the attribute distribution is a diagram with features appearing in shape, such as a radar chart, the estimation function 124 calculates the similarity between the geometric shape of the attribute distribution of the target patient P1 and the geometric shape of the attribute distribution of group A as similarity a. Similarly, the estimation function 124 calculates the similarity between the geometric shape of the attribute distribution of the target patient P1 and the geometric shape of the attribute distribution of group B as similarity b, and calculates the similarity between the geometric shape of the attribute distribution of the target patient P1 and the geometric shape of the attribute distribution of group C as similarity c. The closer the two attribute distributions to be compared are to similar shapes, the greater the similarity. Furthermore, when the attribute distribution is a diagram with features appearing in color or shading, such as a heat map, the estimation function 124 may calculate the distance between the colors or shading (so-called color difference) of the two attribute distributions to be compared as the similarity. Specifically, the estimation function 124 may calculate a color histogram of each attribute distribution, and calculate the similarity between the two attribute distributions from the Euclidean distance or cosine similarity of the color histograms.

[0056] Returning to the description of the flowchart in Fig. 4, the estimation function 124 next estimates at least one of the hospital PI and disease QI index values, or both index values, for the target patient P1 based on the comparison result between the attribute distribution of the target patient P1 and the attribute distribution of each group (step S108).

[0057] For example, the estimation function 124 estimates the hospital PI used when stratifying the group with the greatest similarity in attribute distribution among multiple groups compared with the attribute distribution of the target patient P1 as the hospital PI for the target patient P1, and estimates the disease QI used when stratifying the group with the greatest similarity in attribute distribution as the disease QI for the target patient P1.

[0058] For example, in FIG. 7, the similarity b is the largest. In this case, the estimation function 124 estimates the cancer recurrence rate used when group B was stratified from the population as the disease QI of the target patient P1. Group B is a group whose cancer recurrence rate is equal to or greater than the second threshold TH2 and less than the first threshold TH1. Therefore, the value estimated as the cancer recurrence rate of the target patient P1 is in the range from the second threshold TH2 to the first threshold TH1.

[0059] Furthermore, when estimating the disease QI of the target patient P1, the estimation function 124 may take into account the influence βi of each attribute (τ(i); i = 1 to n) on the disease QI. Specifically, the estimation function 124 may add the product of an arbitrary conversion coefficient γ and the sum Σ{βi × (f(i) - τ(i))} to the estimated disease QI within a certain reference range. The influence βi is a coefficient for weighting an attribute that is desired to be more focused on among the attributes of the target patient P1. In addition, the estimation function 124 may estimate the disease QI based on a similarity probability obtained by machine learning or deep learning.

[0060] Furthermore, the estimation function 124 may calculate statistical values ​​such as the average, maximum, and minimum of all the hospital PIs and disease QIs of the multiple groups compared with the attribute distribution of the target patient P1. For example, if the multiple groups compared with the attribute distribution of the target patient P1 are three groups, A, B, and C, the estimation function 124 may calculate the average of the hospital PIs and the average of the disease QIs of the groups A, B, and C.

[0061] Next, the communication control function 125 transmits (outputs) the difference between the attribute distribution of the group with the highest similarity and the attribute distribution of the target patient P1, the estimated hospital PI and / or disease QI of the target patient P1, etc. to the terminal device 10 via the communication interface 110 (step S110). Furthermore, the communication control function 125 may transmit other information, such as the medical treatment method already applied to the target patient P1, the evaluation result according to the guideline of the medical treatment method, and the average hospital PI and disease QI of all groups compared with the attribute distribution of the target patient P1, to the terminal device 10 via the communication interface 110. As a result, the display 13 of the terminal device 10 displays the difference in the attribute distribution, the estimated hospital PI and / or disease QI of the target patient P1, etc. This ends the processing of this flowchart.

[0062] FIG. 8 is a diagram showing an example of the screen of the display 13 of the terminal device 10. As shown in the example, the display 13 may display the attribute distribution of group B, which has the highest similarity, and the attribute distribution of the target patient P1 in a superimposed state. In this case, the display 13 may further display various information such as the treatment method already applied to the target patient P1 (AAA in the figure), the evaluation result according to the guideline of the treatment method (D+ in the figure), the treatment method recommended for the target patient P1 (BBA, CAB in the figure), the estimated disease QI of the target patient P1, and the estimated hospital PI of the target patient P1. In the example shown in the figure, the estimated disease QI of the target patient P1 represents the recurrence rate of the disease, and the estimated hospital PI of the target patient P1 represents the number of days of hospitalization. For example, it is assumed that the recurrence rate of group B is 60[%] and the number of days of hospitalization is 20 days, and the average recurrence rate of groups A, B, and C is 48[%] and the average number of days of hospitalization is 14 days. In this case, these specific numerical values ​​are also transmitted from the information processing device 100 to the terminal device 10, and are displayed on the display 13 of the terminal device 10 together with the specific numerical values.

[0063] According to the first embodiment described above, the information processing device 100 acquires attributes of the medical worker P2 or the target patient P1 who is treated by the medical institution where the medical worker P2 works. The information processing device 100 calculates an attribute distribution (an example of a first distribution) of the target patient P1 based on the acquired attributes. The information processing device 100 calculates the attribute distribution (an example of a second distribution) of each of a plurality of groups stratified based on the hospital PI (an example of a first index value) and disease QI (an example of a second index value) of a population consisting of a plurality of patients who have received medical treatment in the past. The information processing device 100 compares the attribute distribution of the target patient P1 with the attribute distribution of each group, and calculates the similarity between these attribute distributions. The information processing device 100 estimates at least one index value of the hospital PI and disease QI of the target patient P1 based on the calculated similarity. Then, the information processing device 100 transmits various information such as the estimated hospital PI and disease QI of the target patient P1, the attribute distribution of the target patient P1, and the attribute distribution of the group to a terminal device 10 operable by a medical worker P2. In response to this, various information is displayed on the display 13 of the terminal device 10. This can reduce the cognitive bias of the doctor. As a result, the doctor can propose a more suitable medical treatment method for the target patient P1. In other words, the target patient P1 can receive more suitable medical treatment.

[0064] Second embodiment The second embodiment will be described below. In the above-mentioned first embodiment, it has been described that patients in a population may be filtered by a medical treatment method. In the second embodiment, filtering by this medical treatment method will be described in detail. Below, differences from the first embodiment will be mainly described, and points in common with the first embodiment will be omitted. In the description of the second embodiment, the same parts as those in the first embodiment will be described with the same reference numerals.

[0065] 9 is a flowchart showing a series of processing steps of the processing circuit 120 according to the second embodiment. First, the acquisition function 121 acquires information on the attributes of the target patient P1 and the medical treatment method selected by the medical worker P2 from the terminal device 10 via the communication interface 110 (step S200).

[0066] For example, the display control function 22 of the terminal device 10 causes a plurality of medical treatment methods applicable to a target patient P1 to be displayed on the display 13. A medical worker P2 (particularly a doctor) selects one or more of the medical treatment methods from the plurality of medical treatment methods displayed on the display 13, and inputs the selection result to the input interface 12. The communication control function 23 transmits the selection result of the medical treatment method input by the medical worker P2 to the input interface 12 to the information processing device 100 via the communication interface 11. In response to this, the acquisition function 121 of the information processing device 100 acquires the selection result of the medical treatment method selected by the medical worker P2 from the terminal device 10 via the communication interface 110.

[0067] Next, the first calculation function 122 calculates an attribute distribution that quantitatively represents the attribute of the target patient P1 acquired by the acquisition function 121 (step S202).

[0068] Next, the second calculation function 123 filters the patients in the population based on the selection result of the medical treatment method acquired by the acquisition function 121 (step S204). For example, if the medical treatment method selected by the medical worker P2 is the method "AAA", the second calculation function 123 extracts from the population a plurality of patients who have received the medical treatment method "AAA" in the past.

[0069] Next, the second calculation function 123 stratifies a plurality of patients (hereinafter referred to as samples) extracted from the population based on the medical treatment method into a plurality of groups, and calculates the attribute distribution of each of the stratified groups (step S206).

[0070] For example, the second calculation function 123 selects a hospital PI and / or disease QI related to the medical treatment method selected by the medical professional P2. Then, the second calculation function 123 stratifies the specimen into a plurality of groups based on the selected hospital PI and / or disease QI, and calculates the attribute distribution of each group. For example, if the medical treatment method "AAA" is a cancer-specific medical treatment method, the second calculation function 123 selects index values ​​such as "recurrence rate" and "cancer survival rate" related to cancer as disease QIs, and stratifies the specimen into a plurality of groups based on the disease QI related to the cancer. The group stratified based on the hospital PI and / or disease QI related to the medical treatment method is an example of a "specific group."

[0071] The second calculation function 123 may perform the stratification process at a different timing from that of this flowchart. The different timing may be, for example, a day when the medical institution is closed or at night when there are relatively few patients to be treated. In other words, when the process of this flowchart is started, the specimen may already be stratified into a plurality of groups. In this case, the second calculation function 123 only needs to select a specific group based on the hospital PI and / or disease QI related to the medical treatment method from among the plurality of groups already stratified.

[0072] Next, the estimation function 124 compares the attribute distribution of the target patient P1 calculated by the first calculation function 122 with the attribute distribution of each of the multiple groups calculated by the second calculation function 123, and calculates the similarity between the attribute distributions (step S208).

[0073] Next, the estimation function 124 estimates at least one of the hospital PI and disease QI index values, or both index values, for the target patient P1 based on the comparison result, i.e., the similarity, between the attribute distribution of the target patient P1 and the attribute distribution of each group (step S210).

[0074] Next, the communication control function 125 transmits the difference between the attribute distribution of the group with the highest similarity and the attribute distribution of the target patient P1, the estimated hospital PI and / or disease QI of the target patient P1, etc. to the terminal device 10 via the communication interface 110 (step S212). Furthermore, the communication control function 125 may transmit other information, such as the medical treatment method already applied to the target patient P1, the evaluation result according to the guideline of the medical treatment method, and the average hospital PI and disease QI of all groups compared with the attribute distribution of the target patient P1, to the terminal device 10 via the communication interface 110. As a result, the difference in attribute distribution, the estimated hospital PI and / or disease QI of the target patient P1, etc. are displayed on the display 13 of the terminal device 10.

[0075] Next, the communication control function 125 judges whether the estimated hospital PI and / or disease QI of the target patient P1 are within an acceptable range (step S214). The acceptable range may be a numerical range calculated from the target hospital PI and / or disease QI determined for each medical worker P2, medical institution, local government, or country. For example, if the target number of days of hospitalization (number of days of hospitalization) of a patient at a certain medical institution is 10 days, the acceptable range of the hospital PI may be determined to be a period of 0 to 10 days.

[0076] If the communication control function 125 determines that the hospital PI and / or disease QI are outside the acceptable range, it transmits other recommended treatment methods to the terminal device 10 via the communication interface 110, or transmits specified information to a terminal device of a third party other than the medical professional P2 (e.g., a personal computer or a mobile phone) (step S216).

[0077] The recommended alternative treatment method is a treatment method different from the treatment method selected by medical professional P2, and is a treatment method that will improve hospital PI and / or disease QI compared to the treatment method selected by medical professional P2.

[0078] As a result, a medical treatment method other than the medical treatment method selected by the medical worker P2 is displayed on the display 13 of the terminal device 10. As a result, the medical worker P2 can be prompted to reselect another medical treatment method that will improve the hospital PI and / or disease QI (to apply another medical treatment method to the target patient P1).

[0079] The third party may be, for example, the superior or colleague of the medical professional P2, the manager of the medical institution where the medical professional P2 works, an external supervisory agency that evaluates the function of the medical institution, etc. The predetermined information may be, for example, information that the medical professional P2 selected a medical treatment method that is estimated to cause the hospital PI and / or disease QI to be outside the acceptable range, or may be some kind of signal that has been agreed upon in advance with the third party.

[0080] This allows a third party to know that the medical worker P2 has selected an undesirable medical treatment method for the target patient P1, and can provide guidance to the medical worker P2 for correction or improvement.

[0081] According to the second embodiment described above, the information processing device 100 filters the population by the medical treatment method selected by the medical worker P2, estimates the hospital PI and / or disease QI of the target patient P1 based on the comparison result between the attribute distribution of the sample group (one example of a specific group) obtained by the filtering and the attribute distribution of the target patient P1, and outputs the estimation result. Thus, when the estimated hospital PI and / or disease QI are outside the allowable range and the medical treatment method selected by the medical worker P2 is not preferable, the information processing device 100 can prompt the medical worker P2 to reselect another medical treatment method that improves the hospital PI and / or disease QI, or notify a third party of predetermined information. This can reduce the cognitive bias of the doctor. As a result, the doctor can propose a more suitable medical treatment method for the target patient P1. In other words, the target patient P1 can receive more suitable medical treatment.

[0082] Third embodiment The third embodiment will be described below. In the above-mentioned second embodiment, when the estimated hospital PI and / or disease QI are outside the allowable range, another medical treatment method is proposed to the medical worker P2. In contrast, the third embodiment differs from the above-mentioned embodiments in that further processing is performed depending on whether the other medical treatment method proposed to the medical worker P2 is accepted by the medical worker P2. Hereinafter, the differences from the first and second embodiments will be mainly described, and the points in common with the first and second embodiments will be omitted. In the description of the third embodiment, the same parts as those in the first or second embodiment will be described with the same reference numerals.

[0083] Fig. 10 is a flowchart showing the flow of a series of processes in the processing circuit 120 according to the third embodiment. The processes in S300 to S314 in this flowchart are the same as the processes in S200 to S214 in the flowchart in Fig. 9, and therefore will not be described.

[0084] If the communication control function 125 determines in the processing of S314 that the hospital PI and / or disease QI are outside the acceptable range, it further determines whether the medical professional P2 adopted the treatment method selected by him / herself (a treatment method in which the hospital PI and / or disease QI are outside the acceptable range) (step S316).

[0085] For example, assume that a medical worker P2 inputs to the display 13 of the terminal device 10 through the input interface 12 that the medical method selected by the medical worker P2 will be adopted. In this case, the communication control function 23 of the terminal device 10 transmits information to the information processing device 100 through the communication interface 11 that the medical method has been adopted (hereinafter referred to as adoption information). On the other hand, if the medical worker P2 does not input to the input interface 12 that the medical method will be adopted for a certain period of time, or if the medical worker P2 inputs that a different medical method will be adopted, the communication control function 23 of the terminal device 10 transmits information to the information processing device 100 through the communication interface 11 that the medical method has not been adopted (hereinafter referred to as non-adoption information).

[0086] When the communication interface 110 receives adoption information from the terminal device 10, the communication control function 125 of the information processing device 100 determines that the medical worker P2 has adopted the treatment method selected by him / herself, and when the communication interface 110 receives non-adoption information from the terminal device 10, it determines that the medical worker P2 has not adopted the treatment method selected by him / herself.

[0087] When the communication control function 125 determines that the medical worker P2 has adopted the medical treatment method selected by the medical worker P2, it transmits to the terminal device 10 via the communication interface 110 the state or condition that the target patient P1 should be in when the medical treatment method selected by the medical worker P2 is applied to the target patient P1 (step S318). Furthermore, the communication control function 125 may transmit predetermined information to a third party's terminal device as the process of S318.

[0088] For example, when considering the utilization of limited medical resources such as the facilities and personnel of a medical institution, there may be cases where it is unavoidable to apply a treatment method to a target patient P1 even if it is not necessarily the best option. In such cases where the available treatment methods are limited, it is preferable to improve the hospital PI and disease QI by changing the state or conditions of the target patient P1 when the treatment method is applied, rather than changing the treatment method.

[0089] Therefore, assuming that the medical professional P2 takes the above case into consideration and decides to continue using the treatment method without changing it, the information processing device 100 presents to the medical professional P2 what the state or condition of the target patient P1 is that will improve the hospital PI and disease QI as much as possible when the current treatment method is applied to the target patient P1.

[0090] Specifically, when the information processing device 100 compares the attribute distribution of the target patient P1 with the attribute distribution of the group with the highest similarity, it finds differences in the distributions, calculates what state or condition the target patient P1 should be in to eliminate the differences, and outputs the calculation result to the terminal device 10.

[0091] FIG. 11 is a diagram showing another example of the screen of the display 13 of the terminal device 10. As shown in the figure, when the attribute distribution of the target patient P1 is compared with the attribute distribution of the group with the highest similarity, there may be differences in the distribution shape. As described above, there are controlled factors and non-controlled factors among the attributes of the target patient P1, and when the difference in the attribute distribution corresponds to a controlled factor, it is possible to improve the hospital PI and disease QI by adjusting the controlled factor. In the illustrated example, as shown by arrows V1 and V2, the attribute (b) and the attribute (d) in the attribute distribution of the target patient P1 are significantly different from the attribute distribution of the comparison group. The attribute (b) represents a vital sign, and the attribute (d) represents transition information during the visit. Both of these attributes are controlled factors. Therefore, the information processing device 100 transmits information to the terminal device 10 that prompts the terminal device 10 to take measures to improve attributes such as vital signs and transition information during the visit without changing the medical treatment method. For example, if the weight of the target patient P1 is lighter than the weight of the comparison group, the communication control function 125 may transmit information indicating measures to increase the weight of the target patient P1 to the terminal device 10. In addition, if the target patient P1 suffers from a complication and the comparison group does not suffer from a complication, the communication control function 125 may transmit information indicating measures to reduce the complication of the target patient P1 to the terminal device 10.

[0092] Returning to the description of the flowchart in Fig. 10, on the other hand, if the communication control function 125 determines in the process of S316 that the medical worker P2 did not adopt the medical treatment method that he or she selected, the second calculation function 123 changes the medical treatment method (step S320) and returns the process to S304.

[0093] For example, the second calculation function 123 may select one of the medical treatment methods that can be taken in the medical institution where the medical worker P2 works, and filter the patients in the population by the selected medical treatment method. In this way, when the hospital PI and / or disease QI of the target patient P1 are outside the allowable range, the information processing device 100 can propose to the medical worker P2 a medical treatment method that can be taken in the medical institution and that matches the attributes of the target patient P1.

[0094] In this flowchart, the hospital PI and / or disease QI of the target patient P1 are repeatedly estimated while changing the treatment method until it is determined in the processing of S314 that the hospital PI and / or disease QI of the target patient P1 are within the acceptable range (S314; YES), or until it is determined in the processing of S316 that the medical professional P2 has adopted the treatment method of his / her own choice (S316; YES).

[0095] During the above-mentioned repetitive process, the communication control function 125 may transmit, among the medical treatment methods for which the hospital PI and / or disease QI of the target patient P1 have been estimated repeatedly, the medical treatment method for which the hospital PI and / or disease QI are optimal (for example, in the case of a disease QI called a recurrence rate, the medical treatment method for which the disease QI is the minimum value) to the terminal device 10 via the communication interface 110. In response to this, the display 13 of the terminal device 10 displays the medical treatment method for which the hospital PI and / or disease QI are optimal. This ends the process of this flowchart.

[0096] According to the third embodiment described above, when a medical treatment method is adopted by a medical worker P2 that causes the hospital PI and / or disease QI to be outside the allowable range, the information processing device 100 presents the state or condition that the target patient P1 should be in when the medical treatment method is applied to the target patient P1. This allows the medical worker P2 to take measures to improve the hospital PI and disease QI even in a situation where the medical treatment method cannot be changed.

[0097] (Other embodiments) Other embodiments will be described below. In the above-mentioned embodiment, the terminal device 10 and the information processing device 100 are described as different devices, but this is not limited thereto. For example, the terminal device 10 and the information processing device 100 may be integrated into one device. For example, the processing circuit 20 of the terminal device 10 may further include a first calculation function 122, a second calculation function 123, and an estimation function 124 provided in the processing circuit 120 of the information processing device 100, in addition to the acquisition function 21, the display control function 22, and the communication control function 23. In this case, the terminal device 10 can perform the processes of the various flowcharts described above in a stand-alone (offline) manner.

[0098] Although some embodiments have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their modifications are included in the scope of the invention and its equivalents as described in the claims, as well as in the scope and spirit of the invention. [Explanation of symbols]

[0099] 1...information processing system, 10...terminal device, 11...communication interface, 12...input interface, 13...display, 14...memory, 20...processing circuit, 21...acquisition function, 22...display control function, 23...communication control function, 100...information processing device, 110...communication interface, 120...processing circuit, 121...acquisition function, 122...first calculation function, 123...second calculation function, 124...estimation function, 125...communication control function, 130...memory

Claims

1. An acquisition unit for acquiring attributes of a target patient; a first calculation unit that calculates a first distribution that quantitatively represents the attribute acquired by the acquisition unit; a second calculation unit that calculates a second distribution that quantitatively represents an attribute of each of a plurality of groups stratified from the plurality of patients based on medical information of the plurality of patients who have been treated in the past; an output unit that outputs information based on a comparison result between the first distribution calculated by the first calculation unit and the second distribution calculated by the second calculation unit, the second calculation unit stratifies the plurality of patients into the plurality of groups based on at least the second index value of a first index value related to a time or economic cost of each of the plurality of patients and a second index value related to a treatment effect of each medical treatment method used for each of the plurality of patients; an estimation unit that compares the first distribution calculated by the first calculation unit with the second distribution calculated by the second calculation unit, and estimates at least one of the first index value and the second index value for the target patient based on a comparison result between the first distribution and the second distribution, The output unit further outputs information based on the index value estimated by the estimation unit; The acquisition unit acquires information representing a medical treatment method selected by a doctor from one or more medical treatment methods that can be taken for the target patient, The second calculation unit selects a specific group from the plurality of groups, which is a group stratified using the second index value related to the therapeutic effect of the medical treatment method represented by the information acquired by the acquisition unit, and calculates the second distribution quantitatively representing an attribute of the specific group; The estimation unit estimates at least one of the first index value and the second index value for the target patient based on a comparison result between the first distribution and the second distribution of the specific group. Information processing device.

2. and when the index value estimated based on a comparison result between the first distribution and the second distribution of the specific group is outside an allowable range, the output unit outputs information prompting the doctor to select another medical treatment method. The information processing device according to claim 1 .

3. the output unit outputs predetermined information to a terminal device of a third party other than the doctor when the index value estimated based on a comparison result between the first distribution and the second distribution of the specific group is outside an allowable range.

3. The information processing device according to claim 1 or 2.

4. When the index value estimated based on a comparison result between the first distribution and the second distribution of the specific group is outside an allowable range, the output unit outputs a state or condition that the target patient should be in when the medical treatment method is applied. The information processing device according to claim 1 .

5. When the index value estimated based on a comparison result between the first distribution and the second distribution of the specific group is outside an allowable range, the output unit outputs information prompting the doctor to select a medical treatment method that is possible in a medical institution treating the target patient and that matches the attributes of the target patient. The information processing device according to claim 1 .

6. The estimation unit is Calculating a similarity between the first distribution and the second distribution of each of the plurality of groups; The first index value used when the group having the highest similarity is stratified is estimated as the first index value for the target patient, or the second index value used when the group having the highest similarity is stratified is estimated as the second index value for the target patient. The information processing device according to claim 1 .

7. The second calculation unit is calculating a probability density distribution using at least one of the first index value and the second index value as a random variable; stratifying the plurality of patients into the plurality of groups based on the probability density distribution. The information processing device according to claim 1 .

8. The computer Acquire the attributes of the target patients, Calculating a first distribution that quantitatively represents the acquired attribute; Calculating a second distribution that quantitatively represents attributes of each of a plurality of groups stratified from the plurality of patients based on medical information of the plurality of patients who have been treated in the past; outputting information based on a comparison result between the calculated first distribution and the calculated second distribution; Stratifying the plurality of patients into the plurality of groups based on at least a first index value related to the time or economic cost of each of the plurality of patients and a second index value related to the treatment effect of each medical treatment method used for each of the plurality of patients; comparing the calculated first distribution with the calculated second distribution; estimating at least one of the first index value and the second index value for the target patient based on a comparison result between the first distribution and the second distribution; Outputting information based on the estimated index value; obtaining information representing a treatment method selected by a physician from one or more treatment methods available for the target patient; Selecting a specific group from the plurality of groups, the specific group being a group stratified using the second index value related to the therapeutic effect of the medical treatment method represented by the acquired information; Calculating the second distribution quantitatively representing the attribute of the specific group; estimating at least one of the first index value and the second index value for the target patient based on a comparison result between the first distribution and the second distribution of the specific group; Information processing methods.

9. On the computer, Obtaining the attributes of the target patients; calculating a first distribution quantitatively representing the acquired attribute; Calculating a second distribution that quantitatively represents attributes of each of a plurality of groups stratified from the plurality of patients based on medical information of the plurality of patients who have been treated in the past; and outputting information based on a comparison result between the calculated first distribution and the calculated second distribution; stratifying the plurality of patients into the plurality of groups based on at least a first index value related to a time or economic cost of each of the plurality of patients and a second index value related to a treatment effect of each medical treatment method used for each of the plurality of patients; comparing the calculated first distribution with the calculated second distribution; estimating at least one of the first index value and the second index value for the target patient based on a comparison result between the first distribution and the second distribution; outputting information based on the estimated index value; obtaining information representing a treatment method selected by a physician from one or more treatment methods available for the target patient; selecting a specific group from the plurality of groups, the specific group being a group stratified using the second index value related to the therapeutic effect of the medical treatment method represented by the acquired information; calculating the second distribution quantitatively representing an attribute of the specific group; estimating at least one of the first index value and the second index value for the target patient based on a comparison result between the first distribution and the second distribution of the specific group; A program for executing.

Citation Information

Patent Citations

  • A system and method for supporting medical decision-making in treatment planning using case-based reasoning.

    JP2014503894A

  • Computerized medical planning method and system using mass medical analysis

    JP2017502439A

  • Analysis of individual and group healthcare data in order to provide real time healthcare recommendations

    US20090287503A1

  • Medical system and method for predicting future outcomes of patient care

    US20170199965A1

  • Information analysis program, information analysis method, and information analysis device

    WO2016147290A1