Medical information processing device, medical information processing method, and program
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- CANON KK
- Filing Date
- 2022-07-21
- Publication Date
- 2026-08-03
Smart Images
Figure 0007898972000001 
Figure 0007898972000002 
Figure 0007898972000003
Abstract
Description
[Technical Field]
[0001] Embodiments disclosed herein and in the drawings relate to medical information processing devices, medical information processing methods, and programs. [Background technology]
[0002] The choice of treatment method is determined to some extent by the patient's functional status and the severity of the disease, as stipulated by guidelines. However, predicting the prognosis of a treated patient is difficult. While prognosis requires assessment of the patient's overall physical strength, the condition of other organs, and immune function, in addition to understanding the condition of the affected organ or tumor, the relationship between these factors is not clear. Furthermore, prioritizing the understanding of the affected organ or tumor often leads to insufficient assessment of the patient's overall physical strength, the condition of other organs, and immune function. As a result, patients and their families may be unable to choose a treatment method that improves their outcome. [Prior art documents] [Patent Documents]
[0003] [Patent Document 1] Japanese Patent Publication No. 2022-042204 [Overview of the project] [Problems that the invention aims to solve]
[0004] The problem that the embodiments disclosed herein and in the drawings aim to solve is to enable patients and their families to choose a more suitable treatment method. However, the problem that the embodiments disclosed herein and in the drawings aim to solve 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 medical information processing device of this embodiment includes an acquisition unit, an estimation unit, and an output control unit. The acquisition unit acquires a first attribute factor group, which is a plurality of attribute factors relating to the disease of a target patient, and which are a plurality of attribute factors at a first timing. The estimation unit estimates a second attribute factor group, which is a plurality of attribute factors at a second timing later than the first timing, based on the first attribute factor group. The output control unit outputs information including the first attribute factor group and the second attribute factor group via an output interface. [Brief explanation of the drawing]
[0006] [Figure 1] A diagram showing an example configuration of the medical information processing system 1 in an embodiment. [Figure 2] A diagram showing an example configuration of the terminal device 10 in the embodiment. [Figure 3] A diagram showing an example configuration of the medical information processing device 100 in an embodiment. [Figure 4] A flowchart illustrating the sequence of processes in the processing circuit 120 according to the embodiment. [Figure 5] A diagram illustrating the stratification process. [Figure 6] A diagram illustrating an example of attribute distribution. [Figure 7] A diagram illustrating the method for extracting related attribute factors. [Figure 8] A flowchart illustrating the sequence of processes in the processing circuit 120 according to the embodiment. [Figure 9] A diagram illustrating the method for estimating outcomes. [Figure 10] A diagram showing an example of the relationship strength αi for each attribute factor. [Figure 11] A diagram showing other examples of relationship strength αi for each attribute factor. [Figure 12] This figure compares the attribute factors when prerehabilitation was performed before treatment with those when it was not. [Figure 13] This figure compares the attribute factors when prerehabilitation was performed before treatment with those when it was not. [Embodiments for Carrying out the Invention]
[0007] Hereinafter, a medical information processing apparatus, a medical information processing method, and a program according to embodiments will be described with reference to the drawings.
[0008] [Configuration of Medical Information Processing System] FIG. 1 is a diagram showing a configuration example of a medical information processing system 1 according to an embodiment. The medical information processing system 1 includes, for example, a terminal device 10 and a medical information processing apparatus 100. The terminal device 10 and the medical information processing apparatus 100 are communicably connected via a communication network NW.
[0009] The communication network NW may mean an entire information communication network using telecommunication technologies. For example, the communication network NW includes wireless / wired LANs such as a hospital backbone LAN (Local Area Network), the Internet, as well as a telephone communication line network, an optical fiber communication network, a cable communication network, and a satellite communication network.
[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 staff P2. The medical staff P2 is typically a doctor, but may also be a nurse or other person involved in medical care, or a person involved in regional care services. The medical staff P2 inputs, for example, information regarding a patient (hereinafter referred to as the target patient P1) to be treated into the terminal device 10.
[0011] Alternatively, instead of the medical staff P2 inputting, the target patient P1 or their family may input information regarding the target patient P1 into the terminal device 10. Also, similar to the target patient P1, their family may also input information regarding themselves into the terminal device 10.
[0012] In this embodiment, "treatment" may include not only direct treatments such as surgery, drug therapy, chemotherapy, and photoimmunotherapy, but also all medical actions that may be performed before, during, or after treatment. For example, "treatment" in this embodiment may include "prerehabilitation" performed before direct treatments such as surgery, drug therapy, chemotherapy, and photoimmunotherapy, or it may include "rehabilitation" performed after such direct treatments.
[0013] The terminal device 10 transmits information entered by medical personnel P2, etc., to the medical information processing device 100 via the communication network NW, or receives information from the medical information processing device 100.
[0014] The medical information processing device 100 receives information from the terminal device 10 via the communication network NW and processes the received information. Then, the medical information processing device 100 transmits the processed information to the terminal device 10 via the communication network NW.
[0015] The medical information processing device 100 may be a single device, or it may be a system in which multiple devices connected via a communication network NW work together. In other words, the medical information processing device 100 may be implemented by multiple computers (processors) included in a distributed computing system or a cloud computing system. Furthermore, the medical information processing device 100 does not necessarily have to be a separate device from the terminal device 10, but may be an integrated device with the terminal device 10.
[0016] [Terminal device configuration] Figure 2 is a diagram showing an example configuration of the terminal device 10 in the embodiment. The terminal device 10 includes, for example, a communication interface 11, an input interface 12, an output interface 13, a memory 14, and a processing circuit 20.
[0017] The communication interface 11 communicates with the medical information processing device 100 and other devices via the communication network NW. The communication interface 11 includes, for example, a NIC (Network Interface Card) and an antenna for wireless communication.
[0018] The input interface 12 receives various input operations from the operator (e.g., medical professional P2), converts the received input operations into electrical signals, and outputs them to the processing circuit 20. For example, the input interface 12 includes a mouse, keyboard, trackball, switch, button, joystick, touch panel, etc. The input interface 12 may also be a user interface that accepts audio input, such as from a microphone. If the input interface 12 is a touch panel, it may also have the display function of the display 13a described later.
[0019] In this specification, the input interface 12 is not limited to those equipped with physical operating components such as a mouse or keyboard. For example, 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 this electrical signal to a control circuit is also included as an example of the input interface 12.
[0020] The output interface 13 outputs information under the control of the processing circuit 20. For example, the output interface 13 includes a display 13a and a speaker 13b.
[0021] The display 13a displays various types of information. For example, the display 13a displays images generated by the processing circuit 20, or a GUI (Graphical User Interface) for receiving various input operations from the operator. For example, the display 13a may be an LCD (Liquid Crystal Display), a CRT (Cathode Ray Tube) display, or an organic EL (Electro Luminescence) display.
[0022] Speaker 13b converts various types of information into sound and outputs it. For example, speaker 13b outputs information input from processing circuit 20 as sound.
[0023] Memory 14 can be implemented by, for example, semiconductor memory elements such as RAM (Random Access Memory) or flash memory, a hard disk, or an optical disc. These non-transient storage media may also be implemented by other storage devices connected via a communication network NW, such as NAS (Network Attached Storage) or external storage server devices. Memory 14 may also include non-transient storage media such as ROM (Read Only Memory) or registers.
[0024] The processing circuit 20 includes, for example, an acquisition function 21, an output control function 22, and a communication control function 23. The processing circuit 20 realizes these functions, for example, by a hardware processor (computer) executing a program stored in the memory 14 (storage circuit).
[0025] In the processing circuit 20, the hardware processor refers to circuits such as a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an Application Specific Integrated Circuit (ASIC), or 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 memory 14, the program may be directly embedded within the hardware processor's circuitry. In this case, the hardware processor functions by reading and executing the program embedded within the circuitry. The program may be stored in memory 14 beforehand, or it may be stored on a non-temporary storage medium such as a DVD or CD-ROM, and installed from the non-temporary storage medium to memory 14 when the non-temporary storage medium is inserted into the drive device (not shown) of the terminal device 10. A hardware processor is not limited to being a single circuit; it may also be composed of multiple independent circuits combined to perform various functions. Alternatively, multiple components may be integrated into a single hardware processor to perform various functions.
[0026] The acquisition function 21 acquires input information via the input interface 12 or acquires information from the medical information processing device 100 via the communication interface 11.
[0027] The output control function 22 displays the information acquired by the acquisition function 21 as an image on the display 13a or outputs it as sound from the speaker 13b.
[0028] The communication control function 23 transmits the information input to the input interface 12 to the medical information processing device 100 via the communication interface 11.
[0029] [Configuration of medical information processing device] Figure 3 is a diagram showing an example configuration of the medical information processing device 100 in an embodiment. The medical information processing device 100 includes, for example, a communication interface 111, an input interface 112, an output interface 113, a memory 114, and a processing circuit 120.
[0030] The communication interface 111 communicates with terminal devices 10 and the like via the communication network NW. The communication interface 111 includes, for example, a NIC.
[0031] The input interface 112 receives various input operations from the operator, converts the received input operations into electrical signals, and outputs them to the processing circuit 120. For example, the input interface 112 includes a mouse, keyboard, trackball, switch, button, joystick, touch panel, etc. The input interface 112 may also be a user interface that accepts audio input, such as from a microphone. If the input interface 112 is a touch panel, it may also have the display function of the display 113a described later.
[0032] In this specification, the input interface 112 is not limited to those equipped with physical operating components such as a mouse or keyboard. For example, 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 this electrical signal to a control circuit is also included as an example of the input interface 112.
[0033] The output interface 113 outputs information under the control of the processing circuit 120. For example, the output interface 113 includes a display 113a and a speaker 113b.
[0034] Display 113a displays various types of information. For example, display 13a displays images generated by the processing circuit 120, a GUI for receiving various input operations from the operator, etc. For example, display 113a may be an LCD, CRT display, organic EL display, etc.
[0035] Speaker 113b converts various types of information into sound and outputs it. For example, speaker 113b outputs information input from processing circuit 120 as sound.
[0036] Memory 114 can be implemented by, for example, semiconductor memory elements such as RAM or flash memory, a hard disk, or an optical disc. These non-transient storage media may also be implemented by other storage devices connected via a communication network NW, such as a NAS or an external storage server device. Memory 114 may also include non-transient storage media such as ROM or registers.
[0037] The processing circuit 120 includes, for example, an acquisition function 121, a stratification processing function 122, an extraction function 123, an estimation function 124, and an output control function 125. The acquisition function 121 is an example of an "acquisition unit," the stratification processing function 122 is an example of a "stratification processing unit," the extraction function 123 is an example of an "extraction unit," the estimation function 124 is an example of an "estimation unit," and the output control function 125 is an example of an "output control unit."
[0038] The processing circuit 120 realizes these functions, for example, by having a hardware processor (computer) execute a program stored in the memory 114 (storage circuit).
[0039] In the processing circuit 120, the hardware processor refers to, for example, a CPU, GPU, application-specific integrated circuit, or programmable logic device (e.g., a simple programmable logic device or a complex programmable logic device, a field-programmable gate array, etc.). Instead of storing the program in memory 114, the program may be directly incorporated into the hardware processor's circuit. In this case, the hardware processor realizes its function by reading and executing the program incorporated into the circuit. The program may be stored in memory 114 beforehand, or it may be stored in a non-temporary storage medium such as a DVD or CD-ROM, and installed from the non-temporary storage medium to memory 114 when the non-temporary storage medium is mounted in the drive device (not shown) of the medical information processing device 100. The hardware processor is not limited to being configured as a single circuit; it may be configured as a single hardware processor by combining multiple independent circuits to realize each function. Alternatively, multiple components may be integrated into a single hardware processor to realize each function.
[0040] [Processing flow and pre-processing for medical information processing equipment] The following describes the processing of each function by the processing circuit 120 of the medical information processing device 100, following the flowchart. Figure 4 is a flowchart showing a series of processing steps of the processing circuit 120 according to this embodiment. The processing in this flowchart is a pre-processing step for the outcome estimation process described later. For example, the processing in this flowchart may be performed on days when the medical institution is closed or at night when there are relatively few outpatients.
[0041] First, the acquisition function 121 acquires a group of attribute factors consisting of multiple attribute factors of different types (step S100).
[0042] Attribute factors (attribute parameters) include various factors such as epidemiological information, patient functional capacity indicators, primary disease state, overall health status, genetic predisposition, medical history, family history, treatment history, lifestyle, diseased organ status, non-disease organ status, and tumor status. Non-disease organ status includes, for example, factors related to the body's immune function and cardiopulmonary function.
[0043] More specifically, attribute factors may include factors indicating the patient's current condition, factors indicating the progression of the patient's condition since their first visit, factors indicating the progression of the patient's condition during follow-up, factors indicating pre-existing conditions, or factors indicating genetic information. Some of these attribute factors may be omitted or replaced with other attribute factors not exemplified. For example, attribute factors may include treatment methods and treatment history.
[0044] Current status includes, for example, age, sex, weight, blood type, vital signs, co-existing diseases, and expected complications. Changes in the patient's condition since admission include, for example, weight, cardiac function status, respiratory status, metabolic status, imaging parameters indicating disease characteristics, and non-imaging parameters indicating disease characteristics. Changes in the patient's condition during follow-up include, for example, weight, cardiac function status, respiratory status, metabolic status, imaging parameters indicating disease characteristics, and non-imaging parameters indicating disease characteristics.
[0045] For example, suppose a healthcare professional P2 interviews an unspecified number of patients and their families to gather information on their current condition, the progression of their condition, their medical history, and genetic information, and inputs the results of these interviews into a terminal device 10. In this case, the terminal device 10 transmits this input information as a group of attribute factors to the medical information processing device 100. When the communication interface 111 receives the group of attribute factors from the terminal device 10, the acquisition function 121 of the medical information processing device 100 acquires the group of attribute factors from the communication interface 111.
[0046] The attribute factors described above vary in type and number depending on the disease and its treatment method. For example, the attribute factors related to cancer treatment consist of 60 to 80 attribute factors. In the pre-processing step of this flowchart, attribute factors highly relevant to the disease are extracted from this group of several dozen attribute factors. This attribute factor extraction process will be described later.
[0047] Attribute factors may be graded according to guidelines established by administrative agencies or other organizations. Alternatively, attribute factors may be graded according to diagnostic criteria or diagnostic trees independently established by each medical institution. Furthermore, attribute factors may be graded using databases, machine learning, or deep learning.
[0048] Next, the stratification processing function 122 selects one treatment method (j) (step S102). j is a temporary internal parameter in the processing circuit 120, a so-called temporary parameter.
[0049] For example, the output control function 22 of the terminal device 10 displays multiple treatment methods applicable to the patient on the display 13a. The medical professional P2 selects one treatment method from the multiple treatment methods displayed on the display 13a and inputs the selection result to the input interface 12. The communication control function 23 transmits the selection result of the treatment method input by the medical professional P2 to the input interface 12 to the medical information processing device 100 via the communication interface 11. In response, the stratification processing function 122 of the medical information processing device 100 obtains the selection result of the treatment method selected by the medical professional P2 from the terminal device 10 via the communication interface 111.
[0050] Next, the stratification function 122 extracts a sample of patients who have previously received treatment using treatment method (j) from a population that includes various patients, and stratifies this sample of patients into multiple groups (step S104). The population is an example of "other patient groups".
[0051] The population may consist, for example, of a healthcare professional P2 who is treating a target patient P1, or of multiple patients who have previously received treatment at the healthcare institution where that healthcare professional P2 works. A healthcare institution is, for example, a hospital, clinic, or other facility that provides medical care. The population may also be a patient population in medical statistics. The population can be stratified (classified, grouped, or clustered) into multiple groups based on the outcome.
[0052] Outcomes refer to various indicators that patients should achieve during their treatment, including, for example, the time taken to remission, survival period, and period of independent living.
[0053] For example, if the treatment method (j) obtained by processing S102 is the treatment method "AAA", the stratification processing function 122 extracts multiple patients from the population who have previously received the treatment method "AAA" as a sample.
[0054] The stratification function 122 then stratifies the multiple patients (i.e., the sample) extracted from the population based on the treatment method (j) into multiple groups. Prior to stratifying the sample, the stratification function 122 selects one or more indicator values from among the multiple indicator values included in the outcome (typically, one indicator value is selected).
[0055] Figure 5 is a diagram illustrating the stratification process. As shown in the figure, for example, the stratification function 122 calculates the probability density distribution F(X) of the sample when the outcome is a random variable X. Then, the stratification function 122 stratifies the sample into multiple groups on the probability density distribution F(X) according to a certain criterion.
[0056] For example, the stratification function 122 may classify groups where the random variable X is less than the second threshold TH2 into group A, groups where the random variable X is greater than or equal to the second threshold TH2 and less than the first threshold TH1 into group B, and groups where the random variable X is greater than or equal to 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 they may be reference values to which a certain margin has been added or subtracted from the national average or the average within each medical institution. The first threshold TH1 and the second threshold TH2 may also be standard deviations such as ±1σ, ±2σ, or ±3σ. There are not limited to two thresholds; there may be one or more. In other words, there may be two groups or more than four.
[0057] For example, if the treatment method (j) is "cancer treatment method" and the outcome is "survival time", the stratification processing function 122 filters out patients to whom the cancer treatment method has been applied (cancer patients) as a sample from the population, and calculates a probability density distribution F(X) with the survival time of the extracted sample, i.e., the survival time of cancer patients, as the random variable X. Then, the stratification processing function 122 stratifies the sample on the probability density distribution F(X) for the survival time of cancer patients into a total of three groups, for example, A, B, and C. In this case, group A is the group of cancer patients with a long survival time, group B is the group of cancer patients with a shorter survival time than group A, and group C is the group of cancer patients with a shorter survival time than group B. In other words, group A is the group whose outcome improved the most after treatment, group B is the group whose outcome improved the next most after group A, and group C is the group whose outcome did not improve the least. Group C is an example of "group 1", and group A is an example of "group 2".
[0058] Returning to the flowchart explanation, the stratification processing function 122 then calculates a distribution that quantitatively represents the attribute factors of each group (hereinafter referred to as the attribute distribution) (step S106).
[0059] Figure 6 shows an example of an 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 factor is graded on a scale of 0 to 5. In other words, the values of each attribute factor may be normalized so that the minimum value is 0 and the maximum value is 5, and then represented as a distribution like a radar chart. In the region (a) of the attribute distribution, attribute factors related to age, sex, and blood type are plotted, for example. In the region (b), attribute factors related to the overall physical condition are plotted, for example. In the region (c), attribute factors related to lifestyle are plotted, for example. In the region (d), attribute factors related to medical history and heritability are plotted, for example. In the region (e), attribute factors related to conditions other than diseased organs are plotted, for example. In the region (f), attribute factors related to the condition of diseased organs are plotted, for example. In the region (g), attribute factors related to tumor status are plotted, for example.
[0060] For example, the stratification function 122 averages the attribute distributions of multiple patients (samples) included in each group, and uses that averaged attribute distribution as the attribute distribution for each group. Specifically, if group A includes 100 patients, the stratification function 122 averages the attribute distributions of each of those 100 patients, and uses the single attribute distribution obtained by averaging the attribute distributions of those 100 patients as the attribute distribution for group A. The stratification function 122 may similarly calculate the attribute distribution for other groups such as group B and group C by averaging the attribute distributions of multiple patients. The attribute distribution for group C is an example of a "first attribute distribution," and the attribute distribution for group A is an example of a "second attribute distribution."
[0061] The attribute factors (b), (c), (e), and (f) (general condition, lifestyle, condition of organs other than the diseased organ, condition of the diseased organ) are controllable attribute factors (i.e., controllable factors) before, after, or during direct treatment such as surgery. On the other hand, the attributes (a), (d), and (g) (age, sex, blood type, medical history, hereditary status, tumor status) are uncontrollable attribute factors (i.e., uncontrollable factors) before, after, or during direct treatment such as surgery.
[0062] In the example in Figure 6, the attribute distribution is explained as a radar chart, but it is not limited to this. For example, the attribute distribution may be represented by other statistical charts such as histograms, stacked bar graphs, or heatmaps. The number of stages for attribute factors is also not limited to 5. For example, a criterion may be set to limit the number of stages for attribute factors to 4 or less, or to 6 or more. The criterion may be a fixed value based on medical statistics or guidelines, or a reference value (national average, facility average) ± a set margin, or within or outside the range of ±2σ or 80%CV of the overall distribution. Non-quantified information (medical history, family history, lifestyle) may be scored based on its impact on the disease.
[0063] Furthermore, the stratification function 122 may, instead of calculating the attribute factors of each group as a distribution, or in addition to doing so, integrate all the attribute factors of each group and calculate them as a single index value (scalar value). For example, if the number of attribute factors is n, the stratification function 122 may calculate the influence α of each attribute factor (τ(i); i=1~n) on the outcome. i The sum T(i) = Σαi × τ(i), which takes this into account, can be used as an index value representing all attribute factors. Similarly, when grouping each attribute information factor by category, it can be expressed as fn(i) = Σαi × τ(i). For example, when grouping by tumor status (f1), diseased organ as a whole (f2), systemic condition (lifestyle) (f3), and condition of organs other than the diseased organ (immune function (f4), cardiac function (f5), respiratory function (f6)), f 1-6 (i) = Σα i It can be expressed as ×τ(i).
[0064] Returning to the flowchart explanation, the extraction function 123 then compares the attribute distribution of each group (step S108) and, based on the comparison results, extracts one or more relevant attribute factors from the attribute factor group (step S110). As mentioned above, relevant attribute factors are attribute factors that are highly related to the disease, and specifically, they are attribute factors that have a higher degree of influence on (1) the selection of treatment methods for the disease and / or (2) the improvement of outcomes compared to other attribute factors.
[0065] Figure 7 is a diagram illustrating the method for extracting related attribute factors. As shown in the figure, for example, the extraction function 123 compares the attribute distribution of group A, which has the best outcome among the three groups, with the attribute distribution of group C, which has the worst outcome. For example, the extraction function 123 may extract attribute factors as related attribute factors if the amount of variation is greater than or equal to a threshold when comparing the attribute distributions of group A and group C.
[0066] Furthermore, the extraction function 123 is related to the relationship strength α i Attribute factors whose correlation strength α exceeds a certain threshold may be extracted as related attribute factors. i This refers to (1) the selection of treatment methods for the disease and / or (2) each attribute factor f for improvement of outcomes. i This represents the strength of the influence and can be determined, for example, by the correlation coefficient in statistical analysis, the allocation probability of each classifier for each layer of a random forest, and the output information from machine learning.
[0067] Returning to the flowchart explanation, the stratification function 122 then determines whether all treatment methods have been selected (step S112). If all treatment methods have been selected, the stratification function 122 terminates the process in this flowchart.
[0068] On the other hand, if the stratification processing function 122 has not yet selected all treatment methods, it increments the temporary parameter j (step S114) and returns to S102. In other words, the stratification processing function 122 re-selects the treatment methods that have not yet been selected as new treatment methods (j). This makes it possible to stratify the population into multiple groups according to each treatment method, and furthermore, to extract appropriate related attribute factors for each treatment method.
[0069] [Processing flow and outcome estimation process of medical information processing equipment] The following describes the processing of each function by the processing circuit 120 of the medical information processing device 100, following the flowchart. Figure 8 is a flowchart showing a series of processing steps of the processing circuit 120 according to this embodiment. The processing in this flowchart is performed, for example, before direct treatment such as surgery, drug therapy, chemotherapy, or photoimmunotherapy is performed on the target patient P1.
[0070] First, the acquisition function 121 acquires multiple attribute factors (hereinafter referred to as the attribute factor group) related to the disease of the target patient P1 before direct treatment such as surgery or drug therapy is performed (step S200). This attribute factor group includes at least the related attribute factors mentioned above, and more preferably, it may be narrowed down to only the related attribute factors.
[0071] Next, the stratification processing function 122 calculates an attribute distribution that quantitatively represents the attribute factor group of target patient P1 (step S202). The attribute distribution of target patient P1 is an example of a "third attribute distribution".
[0072] Next, the stratification processing function 122 selects one treatment method (k) applicable to the target patient P1 (step S204). Like j, k is a temporary internal parameter in the processing circuit 120, a so-called temporary parameter.
[0073] Next, the estimation function 124 selects a group to which treatment method (k) has been applied from among the multiple groups stratified by treatment method in the preprocessing (step S206). In other words, the estimation function 124 selects a group from among the multiple stratified groups that suffer from the same disease as target patient P1 and to which the same treatment method (k) that is planned to be applied to target patient P1 has been applied in the past.
[0074] Next, the estimation function 124 estimates the outcome of the target patient P1 at a future time t, based on the attribute factors of the group to which treatment method (k) was applied (step S208).
[0075] Next, the estimation function 124 determines whether it has selected all treatment methods applicable to patient P1 (step S210).
[0076] If the estimation function 124 has not yet selected all treatment methods, it increments the temporary parameter k (step S212) and returns to S204. In other words, the estimation function 124 re-selects a treatment method that has not yet been selected as a new treatment method (k).
[0077] On the other hand, if all treatment methods are selected, the output control function 125 outputs the calculation results from the estimation function 124, etc., via the output interface 113 (step S214).
[0078] For example, the output control function 125 may display information including the attribute factors of the target patient P1 obtained in the processing of S200, the attribute factors of the target patient P1 estimated by the estimation function 124, and the outcomes of the target patient P1 estimated by the estimation function 124 (hereinafter referred to as output information) on the display 113a of the output interface 113. Alternatively, the output control function 125 may transmit the output information to the terminal device 10 via the communication interface 111. This completes the processing of this flowchart.
[0079] Figure 9 is a diagram illustrating the method for estimating outcomes. As shown in the example, the attribute factors of the stratified groups in pre-processing can be divided into, for example, tumor status, diseased organ status, general status (lifestyle), and status of organs other than the diseased organ (immune function, cardiac function, respiratory function). The attribute factors of each group exist at each sampling time, such as t0, t1, t2, t3, t4, ..., tn. If the horizontal axis is time and the vertical axis is each attribute factor, the changes in each attribute factor over time can be graphed as shown in the figure. For example, sampling time t0 could be at the time of arrival at the hospital, time t1 could be immediately before receiving direct treatment such as surgery, time t2 could be immediately after receiving direct treatment, time t3 could be 6 months after treatment, time t4 could be 1 year after treatment, and time tn could be 5 years after treatment. Times t0 and t1 are examples of "first timing," and times t2, t3, t4, ..., tn are examples of "second timing."
[0080] For example, if patient P1 is still in the pre-treatment stage (i.e., at time t0 or t1), the estimation function 124 estimates the attribute factors of patient P1 that are expected to change after receiving direct treatment (i.e., the attribute factors at times t2, t3, t4, ..., tn) based on the temporal changes in the attribute factors of the group that received the same treatment method as patient P1.
[0081] More specifically, the estimation function 124 may estimate the attribute factor group f(tn) of the target patient P1 at a future time tn according to formula (1).
[0082] f(tn)=z(f1(t),f2(t),f3(t)), f4(t), f5(t), f6(t))...(1)
[0083] For example, f1(t) represents the tumor state of the target patient P1 at time t, f2(t) represents the entire diseased organ of the target patient P1 at time t, f3(t) represents the overall physical state of the target patient P1 at time t, f4(t) represents the state (immune function) other than the diseased organ of the target patient P1 at time t, f5(t) represents the state (cardiac function) other than the diseased organ of the target patient P1 at time t, and f6(t) represents the state (respiratory function) other than the diseased organ of the target patient P1 at time t. z is a sixth-degree equation with arbitrary weighting factors z1 to z6. Equation (1) can be obtained by statistically analyzing each attribute factor, or by inputting the attribute factor and the state at each time for machine learning.
[0084] For example, the estimation function 124 inputs the group of attribute factors of the target patient P1 at either the time of arrival at the hospital (t0) or immediately before treatment (t1), or both times, as explanatory variables into Equation (1), estimates the group of attribute factors of the target patient P1 that will change after treatment (t2, t3, t4,..., tn), and further estimates the future outcome of the target patient P1.
[0085] A typical example will be given for explanation. For example, assume that at time t1 immediately before receiving direct treatment, it is desired to know how much the outcome (e.g., survival rate) of the target patient P1 will change at time t3, six months after receiving the treatment. In this case, the estimation function 124 inputs each attribute factor at time t3 into the explanatory variables f1(t) to f6(t) of Equation (x), and estimates each attribute factor at time t3. For example, if the attribute factor of the target patient P1 at time t3 is close to the attribute factor of group A, it can be estimated that the outcome of the target patient P1 will be maintained well six months after treatment.
[0086] When estimating the outcome of the target patient P1, as described above, the estimation function 124 calculates the relationship strength α i representing the strength of the influence of each attribute factor f i on the improvement of the outcome, etc., and uses the relationship strength α i as each attribute factor f i(t) can also be multiplied. That is, the functional state fn(t) at a certain time t is given by fn(i) = Σα i It can be expressed as ×τ(i).
[0087] Figure 10 shows the relationship strength α for each attribute factor. i This figure illustrates an example. As shown in the figure, the attribute factors "ECOG," "Albumin," and "PT-INR" have a stronger correlation α compared to other attribute factors. i These factors are significant. "ECOG," "Albumin," and "PT-INR" will be given more weight compared to other attribute factors.
[0088] As described above, patient attribute factors can be classified into regulatory factors such as overall health, lifestyle, condition of organs other than the diseased organ, and condition of the diseased organ, and non-regulatory factors such as age, sex, blood type, medical history, hereditary status, and tumor status. Therefore, the estimated function 124 separates these regulatory and non-regulatory factors and then calculates the relationship strength α. i You may calculate this.
[0089] Figure 11 shows the relationship strength α for each attribute factor. i This figure illustrates another example. The estimation function 124 calculates the mean and variance for each of the control factors: Group B with average outcomes, Group C with poor outcomes, and Group A with good outcomes, and determines the range of the distribution (upper and lower 2σ or 80% CV). These values may be stored and used as a database, or they may be calculated each time. Alternatively, values from guidelines or evidence may be used. The attribute factor group of target patient P1 may be normalized by these values. The output control function 125 relates to the attribute factors and their relationship strength α, as illustrated in Figures 10 and 11. i A diagram showing the relationship may be output via the output interface 113.
[0090] Furthermore, the functional state fn(t) at a certain time t is given by fn(i) = Σαi × τ(i). However, considering both controlling and uncontrolled factors, if we let the coefficient θi represent the effect of adjusting the controlling factors, then fn(i) = Σαi × τ(i) × θi. The controlling factors should be treated as externally variable information. The coefficient θi representing the effect of adjusting the controlling factors can be calculated from the rate of change of the factor per unit period, or it can be set as a constant. For example, for uncontrolled factors, the coefficient θi = 1.
[0091] In the case of new treatments, some attribute factors may not be present in the existing patient population. In such cases, the range of outcome improvement should be determined and used based on evidence from clinical trials and the latest studies related to the new treatment.
[0092] Furthermore, the relational equations used to obtain changes in this patient attribute information may be determined and updated for each facility or country. Additionally, the system may be operated solely using the function to create the relational equations, or it may be used under fixed conditions in combination with the attribute factors that constitute the equation (i.e., the attribute factors that serve as explanatory variables in the equation).
[0093] Furthermore, the estimation function 124 may estimate how the outcome of patient P1 improves if the control factors included in the attribute factor group of patient P1 are adjusted so that the attribute distribution of patient P1 calculated in processing S202 approaches the attribute distribution of group A, which has a good outcome.
[0094] Figure 12 compares the attribute factors when prerehabilitation is performed before treatment with those when it is not. For example, if patient P1 undergoes prerehabilitation before treatment, it is expected that control factors such as overall physical condition and lifestyle will improve to better values. More specifically, if exercise is performed as part of prerehabilitation, it is expected that patient P1's weight will approach the standard value (weight of group A). In such cases, the control factors such as overall physical condition and lifestyle obtained from the attribute factors of patient P1 at the time of visit (t0) and immediately before treatment (t1) are adjusted to approach the attribute factors of group A, and then the attribute factors of patient P1 (including the adjusted control factors) are input as explanatory variables into formula (1). This allows us to estimate the future outcomes of patient P1 when prerehabilitation is performed before treatment.
[0095] The output control function 125 may output a comparison diagram of attribute distributions, as illustrated in Figure 12, via the output interface 113. This allows the target patient P1 and their family to understand the extent to which post-treatment outcomes improve with and without pre-rehabilitation.
[0096] Figure 13 compares the attribute factors when prerehabilitation is performed before treatment with those when it is not. In the figure, "poor" means that the attribute factors are approaching those of group C, where the outcome is poor, and "good" means that the attribute factors are approaching those of group A, where the outcome is good. The output control function 125 may output a comparison diagram of attribute factors, such as the one exemplified in Figure 13, via the output interface 113.
[0097] According to the embodiment described above, the medical information processing device 100 acquires a group of attribute factors of the target patient P1 before treatment (an example of the "first group of attribute factors"). Based on the group of attribute factors of the target patient P1 before treatment, the medical information processing device 100 estimates a group of attribute factors of the target patient P1 after treatment (an example of the "second group of attribute factors"). The medical information processing device 100 then outputs information including the group of attribute factors of the target patient P1 before treatment and the group of attribute factors of the target patient P1 after treatment via the output interface 113. This makes it possible to show the patient and their family how the attribute factors and outcomes change after treatment. As a result, the patient and their family can choose a more suitable treatment method.
[0098] (Other embodiments) Other embodiments will be described below. In the embodiments described above, the terminal device 10 and the medical information processing device 100 were described as separate devices, but the invention is not limited to this. For example, the terminal device 10 and the medical information processing device 100 may be a single integrated device. For example, the processing circuit 20 of the terminal device 10 may, in addition to the acquisition function 21, output control function 22, and communication control function 23, further include some or all of the stratification processing function 122, extraction function 123, and estimation function 124 provided by the processing circuit 120 of the medical information processing device 100. In this case, the terminal device 10 can perform the various flowchart processing described above in a standalone (offline) manner.
[0099] Furthermore, although the flowcharts in Figures 4 and 8 are described as being performed solely by the medical information processing device 100, this is not limited to that. For example, some of the processing in these flowcharts may be performed by the terminal device 10.
[0100] While several embodiments 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, and modifications 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]
[0101] 1...Medical information processing system, 10...Terminal device, 11...Communication interface, 12...Input interface, 13...Output interface, 14...Memory, 20...Processing circuit, 21...Acquisition function, 22...Output control function, 23...Communication control function, 100...Medical information processing device, 111...Communication interface, 112...Input interface, 113...Output interface, 114...Memory, 120...Processing circuit, 121...Acquisition function, 122...Stratification processing function, 123...Extraction function, 124...Estimation function, 125...Output control function
Claims
1. An acquisition unit that acquires a first group of attribute factors, which are multiple attribute factors related to the disease of the target patient, and which are multiple attribute factors at the first time point. An estimation unit that estimates a second group of attribute factors, which are the multiple attribute factors at a second timing later than the first timing, based on the first group of attribute factors; An output control unit that outputs information including the first attribute factor group and the second attribute factor group via an output interface, A medical information processing device equipped with [a specific feature].
2. The second timing is the timing after the patient has received treatment for the disease. The medical information processing device according to claim 1.
3. The treatment for the aforementioned patient is determined based on the treatment outcomes of other patient groups suffering from the same disease as the aforementioned patient. The medical information processing device according to claim 2.
4. The treatment for the aforementioned target patient is determined based on the treatment outcomes of other patients in the aforementioned patient group who have previously received treatment and whose outcomes have improved. The medical information processing device according to claim 3.
5. A stratification processing unit that stratifies other patient groups suffering from the same disease as the aforementioned target patient into multiple groups based on the outcomes of those other patient groups, and calculates an attribute distribution that quantitatively represents the attribute factor group, which is the multiple attribute factor of each group, The system further includes an extraction unit that, based on a comparison between a first attribute distribution, which is the attribute distribution of a first group, and a second attribute distribution, which is the attribute distribution of a second group having a better outcome than the first group, extracts relevant attribute factors from the attribute factor group that have a higher degree of influence on at least one of the selection of the treatment method for the disease and the improvement of the outcome compared to other attribute factors. The medical information processing device according to claim 1 or 2.
6. The first attribute factor group includes control factors, which are attribute factors that the target patient can control, and non-control factors, which are attribute factors that the target patient cannot control. The stratification processing unit calculates a third attribute distribution, which is the attribute distribution of the target patients. The estimation unit estimates the second attribute factor group based on the first attribute factor group, in which the control factors are adjusted so that the third attribute distribution approaches the second attribute distribution. The medical information processing device according to claim 5.
7. A medical information processing method performed by a computer, To obtain a group of primary attribute factors, which are multiple attribute factors related to the disease of the target patient, and which are multiple attribute factors at the first time point. Based on the first set of attribute factors, estimate the second set of attribute factors, which are the multiple attribute factors at a second timing that occurs after the first timing. To output information including the first attribute factor group and the second attribute factor group via an output interface, A medical information processing method including [the specified term].
8. A program to be executed by a computer, To obtain a group of primary attribute factors, which are multiple attribute factors related to the disease of the target patient, and which are multiple attribute factors at the first time point. Based on the first set of attribute factors, estimate the second set of attribute factors, which are the multiple attribute factors at a second timing that occurs after the first timing. To output information including the first attribute factor group and the second attribute factor group via an output interface, A program that includes this.