Medical information processing device, method, and program

Abstract

To allow for effectively improving the speed and degree of improvement in clinical decisions.SOLUTION: A medical information processing device according to an embodiment comprises an update unit configured to update a model for computing effect evaluation values of clinical decisions. The update unit comprises a first update unit configured to update parameters of the model while fixing a structure of the model, and a second update unit configured to update the structure of the model less frequently than updating of the parameters.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] In clinical research and daily clinical practice, patients are assigned a specific treatment decision from among multiple treatment decisions. Methods for adaptively changing the allocation include adaptive design and bandit algorithms. Compared to methods such as supervised learning, these methods can improve treatment decisions even while data is being accumulated. However, there is a trade-off: if the model is made more complex, the improvement in treatment decisions will be slower, and if the model is made simpler, the estimation accuracy will decrease, resulting in a lower degree of improvement in the final treatment decision. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] International Publication No. 2021 / 065845 Summary of the Invention [Problem to be solved by the invention]

[0004] One of the problems to be solved by the embodiments disclosed in this specification and drawings is to efficiently improve the speed and degree of improvement in clinical judgment. However, the problems to be solved by the embodiments disclosed in this specification and drawings are not limited to the above problem. Problems corresponding to the effects of each configuration shown in the embodiments described below can also be positioned as other problems. [Means for solving the problem]

[0005] A medical information processing apparatus according to an embodiment includes an update unit that updates a model for calculating an effect evaluation value of medical care decisions. The update unit includes a first update unit that updates parameters of the model while fixing the structure of the model, and a second update unit that updates the structure of the model less frequently than the parameters. [Brief explanation of the drawings]

[0006] [Figure 1] FIG. 1 is a diagram showing an example of the configuration of a medical image processing apparatus according to this embodiment. [Figure 2] FIG. 2 is a diagram showing the flow of medical information processing performed by a processing circuit in accordance with a medical information processing program. [Figure 3] FIG. 3 is a diagram schematically illustrating the medical information processing shown in FIG. [Figure 4] FIG. 4 is a diagram showing the progress of treatment results in the method according to this embodiment and the methods according to Comparative Examples 1 and 2. In FIG. [Figure 5] FIG. 5 is a diagram illustrating a medical information processing according to the first embodiment. [Figure 6] FIG. 6 is a diagram illustrating structural models and their parameters before and after differentiation. [Figure 7] FIG. 7 is a diagram illustrating structural models and their parameters before and after integration. [Figure 8] FIG. 8 is a diagram illustrating a medical information processing according to the second embodiment. [Figure 9] FIG. 9 is a diagram illustrating a structural model before and after the addition of the feature x2. [Figure 10] FIG. 10 is a diagram illustrating a structural model before and after the deletion of the feature x2. [Figure 11] FIG. 11 is a diagram illustrating a structural model before and after changing the feature quantity x1 to the feature quantity x2. [Figure 12] FIG. 12 is a diagram illustrating an example of the structural model before and after the addition of the clinical judgment C. [Figure 13] FIG. 13 is a diagram illustrating a structural model before and after the abolition of clinical judgment C. DETAILED DESCRIPTION OF THE INVENTION

[0007] Hereinafter, embodiments of a medical information processing device, method, and program will be described in detail with reference to the drawings.

[0008] In the medical field, efforts are being made to realize clinical decision support (CDS) using data and artificial intelligence (AI) technology. Supervised learning, typified by deep learning, is widely used in AI technology, and some AI technologies have emerged that can detect lesions with greater accuracy than humans, particularly in the field of diagnostic imaging.

[0009] However, the following issues may arise when implementing clinical decision support using supervised learning. 1. In order to improve accuracy, a large amount of data is required, and the cost of collecting the data is high. 2. Even if the accuracy is high, it may not lead to appropriate medical decision-making.

[0010] Problem 2 is technically equivalent to the problem that "supervised learning can reveal correlations, but not causal relationships." For example, even if there is an AI model that can predict with 100% accuracy whether a patient with heart failure will die within five years, this AI model will be useless to a doctor who wants to know how to extend this patient's life expectancy to more than five years.

[0011] Identifying causal relationships in medical treatment and identifying optimal treatment is something that cannot currently be achieved through supervised learning; this is the role of randomized controlled trials (RCTs) (or medical statistics). In other words, with the extension of current AI technology, there is no true "clinical decision support for treatment optimization," and randomized controlled trials will never disappear.

[0012] However, randomized controlled trials also have many problems, such as the following: 1. Because it takes a long time to complete research, it is difficult to keep up with the latest trends, and the results are likely to become outdated. 2. Research is inefficient because it requires huge costs and there is a risk of hypothesis verification failing. 3. Eligibility criteria for studies tend to be strict, so the results may not apply to the general patient population (low external validity). 4. Only the average effect of interventions can be compared, and it is not possible to clarify the different effects for each patient. For example, it is not possible to consider cases such as personalized medicine. 5. Overreliance on statistical significance is prone to publication bias and p-value hacking.

[0013] In particular, the limitations of randomized controlled trials are becoming apparent these days as treatment methods change rapidly and the importance of personalized medicine is emphasized.

[0014] Therefore, there is a need to efficiently optimize clinical decisions without requiring large amounts of prior data or conducting randomized controlled trials, and there is also a need to develop a clinical decision support model for this purpose.

[0015] Fig. 1 is a diagram showing an example of the configuration of a medical information processing device 1 according to this embodiment. As shown in Fig. 1, the medical information processing device 1 is an information processing terminal such as a computer having a processing circuit 11, a storage device 12, an input device 13, a communication device 14, and a display device 15. The processing circuit 11, the storage device 12, the input device 13, the communication device 14, and the display device 15 are connected via a bus so that signals can be input and output to and from each other.

[0016] The processing circuitry 11 has processors such as a CPU (Central Processing Unit) and a GPU (Graphics Processing Unit). The processing circuitry 11 executes a medical information processing program to realize an allocation function 111, an observation function 112, a storage function 113, an update function 114, a display control function 115, and the like. Note that each of the functions 111 to 115 is not limited to being realized by a single processing circuit. A processing circuit may be configured by combining multiple independent processors, and each processor may execute a program to realize each of the functions 111 to 115. Furthermore, the functions 111 to 115 may each be a modular program that constitutes a medical information processing program. These programs are stored in the storage device 12.

[0017] The storage device 12 is a read-only memory (ROM), a random access memory (RAM), a hard disk drive (HDD), a solid state drive (SSD), an integrated circuit storage device, or the like that stores various information. In addition to the above storage devices, the storage device 12 may also be a portable recording medium such as a compact disc (CD), a digital versatile disc (DVD), or a flash memory, or a drive that reads and writes various information from and to a semiconductor memory element, or the like. The storage device 12 may also be located in another computer connected via a network.

[0018] The input device 13 receives various input operations from an operator, converts the received input operations into electrical signals, and outputs the electrical signals to the processing circuit 11. Specifically, the input device 13 is connected to input devices such as a mouse, a keyboard, a trackball, a switch, a button, a joystick, a touchpad, and a touch panel display. The input device 13 outputs electrical signals corresponding to the input operations to the input device to the processing circuit 11. The input device 13 may also be an input device provided in another computer connected via a network or the like.

[0019] The communication device 14 is an interface for transmitting and receiving various types of information to and from other computers. Information communication by the communication device 14 is performed in accordance with a standard suitable for medical information communication, such as DICOM (Digital Imaging and Communications in Medicine).

[0020] The display device 15 displays various information using the display control function 115 of the processing circuit 11. As the display device 15, for example, a liquid crystal display (LCD), a cathode ray tube (CRT) display, an organic electroluminescence display (OLED), a plasma display, or any other display can be used as appropriate. Also, a projector may be used as the display device 15.

[0021] The processing circuit 11 according to this embodiment determines a medical decision to be assigned to a subject, such as a patient, based on the effect evaluation value of the medical decision by implementing the allocation function 111. The effect evaluation value of the medical decision is calculated using a model for calculating the effect evaluation value of the medical decision. A medical procedure corresponding to the assigned medical decision is administered to the subject. An effect resulting from the medical procedure occurs in the subject. The processing circuit 11 observes the effect occurring in the subject by implementing the observation function 112. The effect is expressed as a numerical value, which will be referred to as an effect observation value. The processing circuit 11 associates the effect observation value, the medical procedure, and other features and stores them in the storage device 12 as observation data by implementing the storage function 113. The above-described medical decision assignment, effect observation, and observation data storage are performed for various subjects. The processing circuit 11 updates the model parameters and structure individually and sequentially based on the observation data as the observation data is accumulated by implementing the update function 114. The processing circuit 11 displays various data on the display device 15 by implementing the display control function 115.

[0022] The update function 114 is divided into a first update function 116 and a second update function 117. By implementing the first update function 116, the processing circuit 11 updates the parameters of the model while fixing the structure of the model. By implementing the second update function 117, the processing circuit 11 updates the structure of the model less frequently than the parameters.

[0023] The subject according to this embodiment is typically a single patient with a disease. However, the subject according to this embodiment is not limited to this and may be a patient group consisting of two or more patients. Furthermore, the subject according to this embodiment does not necessarily have to be a person with a disease, but may also be a healthy person. The model may be used for each doctor, each department, each hospital, each region, or each subject.

[0024] The model according to this embodiment is a function for calculating an effect evaluation value of a medical decision. The function may be a function determined manually, a function determined by an experimental method or a deterministic method, a function trained by machine learning, or a function determined by any other method. The effect evaluation value is an index value for evaluating the effect of the medical decision of the allocation candidate, and may be, for example, an index value such as a confidence interval of the effect, an expected value of the effect, the maximum expected value, or the difference from the maximum expected value.

[0025] Types of clinical decisions related to this embodiment are expected to include decisions regarding whether to perform a procedure, decisions regarding content, decisions regarding amount, and decisions regarding timing. Examples of decisions regarding whether to perform a procedure include decisions regarding whether to perform surgery or whether to perform a blood test. Examples of decisions regarding content include decisions regarding the selection of a therapeutic drug to be used or the selection of a disease name to diagnose. Examples of decisions regarding amount include decisions regarding the selection of a drug dosage or the selection of rehabilitation implementation time. Examples of decisions regarding timing include decisions regarding the selection of when to visit the hospital or when to perform surgery.

[0026] Those who make medical decisions include not only medical professionals such as doctors, nurses, and paramedical staff, but also the subjects themselves, their families, and anyone related to the subject. Medical decisions do not necessarily have to be highly medical, nor do they have to be decisions made for the purpose of improving health. In other words, decisions that have a negative effect on medical care or health also fall within the scope of medical decisions. For example, the decision of whether or not a healthy person should smoke at a certain time is also within the scope of medical decisions.

[0027] As a result of a clinical decision, some effect occurs. This effect is also called a reward or an outcome. Possible effects according to this embodiment include, for example, clinical outcomes, patient-reported outcomes, and economic outcomes. Examples of clinical outcomes include incidence rates (including the presence or absence of morbidity), 5-year survival rates (including the presence or absence of survival), complication rates (including the presence or absence of complications), readmission rates (including the presence or absence of readmission), test values ​​(or the degree of improvement in test values), and the degree of independence in daily living. Examples of patient-reported outcomes include subjective symptoms, subjective health status, satisfaction with treatment, and subjective happiness. Examples of economic outcomes include medical expenses, invested medical resources, and length of hospital stay.

[0028] Effects are expressed as numerical values ​​and can be ranked for learning purposes. Numeric values ​​may be assigned to things that are not originally numerical. Effects may be observed immediately after a clinical decision. For example, the effect on a clinical decision on whether to notify a healthy individual's smartphone of a message encouraging exercise may be whether or not the individual exercises within five minutes of receiving the message.

[0029] The effectiveness can also take into account the cost required for medical decisions. For example, in the smartphone message example above, the benefit of receiving a notification is that it is easier to achieve the desired effect than not receiving a notification. However, notifications also have the disadvantage of increasing communication costs and hindering user behavior. To take these advantages and disadvantages into account, for example, if the first message always incurs a cost of "5" and the exerciser receives a reward of "100," the effectiveness can be calculated as follows: Reward "100" - Cost "5" = Effectiveness "95." This makes it possible to obtain an effect that reflects cost-effectiveness.

[0030] The feature quantities according to this embodiment include the attributes and / or conditions of the subject. The attributes are information such as the gender and age of the subject, which have properties that do not change depending on the immediately preceding medical decision. The conditions are information such as the subject's current blood pressure and blood glucose level, which have properties that change depending on the immediately preceding medical decision.

[0031] An example of the operation of the medical information processing apparatus 1 according to this embodiment will be described below.

[0032] 2 is a diagram showing the flow of medical information processing performed by the processing circuitry 11 in accordance with the medical information processing program. FIG. 3 is a diagram showing a schematic diagram of the medical information processing shown in FIG.

[0033] 2 and 3, the processing circuitry 11 allocates medical decisions to patients based on a model by implementing the allocation function 111 (step S1). Specifically, allocation is performed through the following process.

[0034] The processing circuit 11 has a model for calculating an effect evaluation value of a medical judgment. A model for calculating an effect evaluation value of an individual medical judgment is referred to as a structural model. The model may be configured to be able to calculate effect evaluation values ​​of multiple medical judgments, or may be configured to be able to calculate an effect evaluation value of a single medical judgment. In the following description, as an example, the model is assumed to calculate effect evaluation values ​​of multiple medical judgments. Note that one medical judgment means a medical judgment that can be distinguished by one structural model. As an example, the model according to this embodiment has multiple structural models corresponding to multiple medical judgments, respectively. The processing circuit 11 uses multiple structural models to calculate multiple effect evaluation values ​​corresponding to multiple clinical decisions, respectively. Specifically, the processing circuit 11 calculates the effect evaluation value corresponding to each structural model by applying observation data including observed effect observation values ​​to the structural models. The effect evaluation value may be calculated based only on observation data observed at the time immediately before the target processing time (target processing step), or may be calculated based on observation data observed at multiple times before the target processing time.

[0035] The processing circuit 11 assigns an appropriate medical decision from multiple medical decisions based on multiple effect evaluation values ​​according to an adaptive design or bandit algorithm. The specific algorithm used for the bandit algorithm is not particularly limited. The bandit algorithm of this embodiment refers to an algorithm that solves the problem of sequentially selecting an appropriate medical decision from multiple medical decisions (options) so as to maximize the total effect (reward). The bandit algorithm of this embodiment includes not only narrow bandit algorithms in which effects do not depend on features, but also contextual bandit algorithms in which effects do depend on features, and reinforcement learning for solving sequential decision-making problems in which the state changes depending on previous medical decisions. Specific examples of the bandit algorithm of this embodiment include Epsilon Greedy, Thompson Sampling, Linear Thompson Sampling, PSRL (Posterior Sampling for Reinforcement Learning), and BDQN (Bayesian Deep Q-Networks). A medical procedure corresponding to the medical judgment is performed on the subject by a medical professional or the subject himself / herself. Note that a medical judgment different from the medical procedure corresponding to the medical judgment selected by the processing circuit 11 may be performed on the subject. The performed medical procedure produces an effect on the subject.

[0036] As an example, as shown in Fig. 3, the processing circuit 11 holds a structural model Mn corresponding to a medical judgment Dn. Here, "n" is a natural number in the range of 0≦n≦N, and is an index indicating the number of the medical judgment and the structural model. The number N of medical judgments and structural models is set to 1 or 2 or more. In the example of Fig. 3, in step S1, a medical judgment D2 is assigned from among multiple medical judgments D1 to DN.

[0037] When step S1 is performed, the processing circuit 11 observes the effect occurring in the subject by implementing the observation function 112 (step S2). The effect is observed numerically as an effect observation value. For example, if the medical decision Dn is "perform surgery," the effect observation value may be a 5-year survival rate or the occurrence of complications. The effect observation value may be obtained by any method. For example, it may be input by an operator via the input device 13, or a measurement value obtained by an examination device may be input. Alternatively, it may be received from another computer via the communication device 14.

[0038] When step S2 is performed, the processing circuit 11 realizes the storage function 113 to store the observation data in a database DB managed by the storage device 12 (step S3). The observation data includes the subject's identifier, a medical judgment corresponding to the medical procedure performed on the subject, and an effect observation value of the effect produced in the subject by the medical procedure.

[0039] When step S3 is performed, the processing circuit 11 determines whether or not to update the structure of the model (i.e., the structural model) by implementing the second update function 117 (step S4). The timing for updating the structural model varies, but is set to be less frequent than the timing for updating the parameters of the structural model. Specifically, it is preferable to update the structural model when a reference number of observation data has been accumulated or when a certain period of time has passed. As another example, the model may be updated when a structural model corresponding to a new medical judgment is added to the model or when a structural model corresponding to an existing medical judgment is discontinued. As another example, the structural model may be updated when an improvement in model performance is expected due to the update.

[0040] If it is determined in step S4 that the structural model is not to be updated (step S4: NO), the processing circuit 11 determines whether or not to update the parameters of the structural model by implementing the first update function 116 (step S5). The parameters of the structural model are parameters that define the posterior distribution of the expected value of the effect occurring in the subject. The timing for updating the parameters varies, but is set to be more frequent than the timing for updating the structural model. As an example, the parameters may be updated when the effect is observed (when the effect observation value is obtained). As another example, the parameters may be updated when a reference number of observation data is accumulated or when a certain period of time has elapsed.

[0041] If it is determined in step S5 that the parameters of the structural model are to be updated (step S5: YES), the processing circuit 11 updates the parameters of the structural model based on the observation data by implementing the first update function 116 (step S6). In step S6, the processing circuit 11 updates the parameters of the structural model while fixing the structural model. There are various parameter update methods. For example, the update method may be determined according to the classification of the decision-making problem. When a clinical decision is made once per subject, updating may be performed using a narrow bandit algorithm. The narrow bandit algorithm can be applied to both a contextual bandit algorithm that takes context into account and a context-free bandit algorithm that does not. When a clinical decision is made multiple times per subject, i.e., in the case of sequential decision making, updating may be performed using reinforcement learning. Reinforcement learning can be applied to both table format and function approximation. The table format refers to the case where the feature amount (state) or medical decision (action) is a discrete value, and the function approximation refers to the case where the feature amount or medical decision is a continuous value.

[0042] On the other hand, if it is determined in step S4 that the structural model is to be updated (step S4: YES), the processing circuit 11 updates the structural model based on the observation data by implementing the second update function 117 (step S7). There are various ways to update the structural model. Examples of the update include differentiation and integration of structural models. Other examples of the update include adding, changing, and deleting features incorporated into the structural model. The change of features also includes conversion between a contextual bandit algorithm and a contextless bandit algorithm. Other examples of the update include adding a structural model corresponding to a new clinical decision and eliminating a structural model corresponding to an existing clinical decision. Other examples of the update include changing the type of prior distribution to which the effect occurring in the subject follows and changing the network structure (hyperparameters) of a deep neural network used in reinforcement learning.

[0043] If it is determined that the parameters of the structural model are not to be updated (step S5: NO), if the parameters of the structural model are updated (step S6), or if the structural model is updated (step S7), the medical information processing according to this embodiment ends. The medical information processing shown in Figures 2 and 3 is repeated multiple times for the same model on the same patient or multiple patients belonging to the same patient group.

[0044] FIG. 4 shows the progress of treatment outcomes for the method according to the present embodiment and the method according to the comparative example. The graph shown in FIG. 4 shows the progress of treatment outcomes for each method, with the vertical axis representing the treatment outcomes for the model of each method and the horizontal axis representing time. Comparative Example 1 is an example using a randomized controlled trial (RCT) or machine learning. According to Comparative Example 1, updates are performed at any timing, such as when a large amount of observation data, on the order of thousands or tens of thousands, has been accumulated. When accumulating observation data, the model structure and parameters are not updated, and the model's treatment outcomes do not improve. Simply put, treatment outcomes are poor while accumulating observation data. Comparative Example 2 is an example in which parameters are updated using adaptive design or a bandit algorithm. According to Comparative Example 2, model parameters are updated while accumulating observation data, so treatment outcomes improve when the observation data is accumulated. However, since the model structure is fixed, the degree of improvement in treatment outcomes is low. Simply put, treatment outcomes are good when accumulating observation data, but the improvement in treatment outcomes is slow.

[0045] According to the method of this embodiment, parameters are updated while the model structure is fixed at the time T41 when observation data is accumulated, and the model structure is updated at a predetermined timing T42. Therefore, it can be said that treatment outcomes are good when observation data is accumulated, and treatment outcomes also improve quickly. For example, the model structure is updated at the time T42 when a new treatment is introduced, the parameters are updated thereafter, and the model structure is updated again at the time T42 when the new treatment is introduced, and the parameters are updated thereafter. This cyclical update of the model structure and parameters can be repeated. Note that whether or not to implement a treatment is an example of a clinical decision. According to the method of this embodiment, it is possible to construct an adaptive EBM (Evidence-Based Medicine) model that adaptively selects the optimal treatment decision while comparing the effects of a new treatment and an old treatment. This also enables adaptive selection of the optimal clinical decision for each subject, thereby realizing personalized medicine (precision medicine). Furthermore, because this is a subject-specific model for personalized medicine, it is possible to build a model with a smaller amount of observation data than general-purpose models. It is also expected that models can be built without conducting randomized controlled trials.

[0046] Hereinafter, several examples according to this embodiment will be described.

[0047] Example 1 In the first embodiment, model differentiation is performed as a method for updating the structure of the model.

[0048] Fig. 5 is a diagram schematically illustrating medical information processing according to Example 1. Steps S11 to S17 according to Example 1 correspond to steps S1 to S7 shown in Fig. 2 and Fig. 3, respectively. In the following description of Example 1, a description of parts common to the medical information processing described with reference to Fig. 2 and Fig. 3 will be omitted.

[0049] In Example 1, parameters are updated using Thompson sampling, a type of bandit algorithm. Thompson sampling is a method in which the expected value parameters of rewards are modeled within a Bayesian statistical framework and a strategy based on the probability matching method is applied. Here, Bayesian statistics is a statistical theory that interprets that probability can change each time new information is obtained, and the probability (or probability distribution) before and after the information is obtained is updated based on Bayes' theorem. Furthermore, the probability matching method is a method in which each option in each trial is selected based on the "probability that the option has the maximum expected value," and is a method (probabilistic strategy) in which the options adopted are randomized. In the probability matching method, the "probability that the option has the maximum expected value" can be formulated in any way, but Thompson sampling is a method in which the probability is calculated from the posterior probability using a Bayesian approach.

[0050] As shown in Fig. 5, the initial structural model according to Example 1 has a structural model A corresponding to the clinical decision to prescribe a therapeutic drug A and a structural model B corresponding to the clinical decision to prescribe a therapeutic drug B. The structural model for the therapeutic drug A has an effect evaluation value Y A The structural model B for therapeutic drug B calculates the effect evaluation value Y B Calculate the effect evaluation value Y A and Y B The type of the model is not particularly limited, but is illustratively assumed to be the degree of symptom relief. Note that the structural model according to the first embodiment is based on a context-free bandit algorithm that does not depend on the feature amount of the subject.

[0051] In step S11, the processing circuitry 11 determines a medical decision to be assigned to a subject from medical decisions A and B using a structural model for therapeutic drug A and a structural model for therapeutic drug B. As described above, in Example 1, a medical decision to be assigned is determined based on Thompson sampling.

[0052] The update of the probability distribution in Thompson sampling is calculated assuming a conjugate prior distribution. The probability distribution of the effect (reward) that occurs to the subject due to a medical decision follows the Bernoulli distribution. In this case, the beta distribution, which is the conjugate prior distribution of the Bernoulli distribution, is used as the posterior distribution of the expected value of the effect of the medical decision. The Bernoulli distribution is a discrete probability distribution that takes the value 1 at probability p and 0 at probability 1-p. For example, the posterior distribution of the expected value of the effect of medical decision A is calculated using the parameter α A ,β A Using Beta(α A ,β A ) where the parameter α A means the number of times that the effect observation value "1" is observed as the effect of medical decision A, and parameter α B means the number of times the observed effect value "0" was observed. Similarly, the posterior distribution of the expected value of the effect of treatment decision B is B ,β B Using Beta(α B ,β B )

[0053] In this case, the effect evaluation value Y A is the Bernoulli distribution that the effect follows and the parameter p A Similarly, the effect evaluation value Y B is the Bernoulli distribution that the effect follows and the parameter p B Based on the above, it is calculated according to the following formula (2): Formula (1) is a mathematical expression of the structural model for clinical judgment A, and formula (2) is a mathematical expression of the structural model for clinical judgment B.

[0054]

number

[0055] In Thompson sampling, the processing circuit 11 sequentially determines the current option (medical decision A or medical decision B) based on a series of medical decision selections and effect observation values ​​observed before the processing time (current step). More specifically, the processing circuit 11 calculates the expected value μ of the effect for each of the options A and B. A ,μ B The posterior distribution Beta(α A ,β A ), Beta(α B ,β B ) and generate it randomly, and the expected value μ A ,μ B The clinical decision corresponding to the maximum expected value is selected and assigned to the subject. In Figure 5, it is assumed that clinical decision A is assigned.

[0056] A medical treatment corresponding to the medical judgment A is performed on the subject by a medical professional or the like, and an effect occurs in the subject. In step S12, the processing circuit 11 calculates the effect as an effect observation value Y1 A In step S13, the processing circuit 11 stores the effect observation value Y1 in the database DB. A The observation data includes at least a patient identifier and an effect observation value Y1. A The observed data may further include any feature such as the patient's gender x1. In the first embodiment, the structural model is differentiated using the feature, and therefore, the feature that is likely to differentiate is included in the observed data and accumulated.

[0057] In step S16, the processing circuit 11 updates the parameters of the structural model at a first timing based on the observation data. In the first embodiment, the processing circuit 11 updates the parameters at the first timing every time an effect is observed, in other words, every time an effect observation value is obtained. Specifically, when the effect observation value Y1 A If obtained, the effect observation value Y1 A Based on the observed data, including the parameter α A ,β A is updated. Parameter α A ,β AThe effect observation value Y1 A If is "1", then the parameter α A Add "1" to the effect observation value Y1 A If is other than "1", the parameter β A Add "1" to.

[0058]

number

[0059] In step S17, the processing circuit 11 updates the structural model at a second timing based on the observation data. In the first embodiment, the structural model is updated by differentiating the structural model into structural models corresponding to possible values ​​of the feature of the subject. In the first embodiment, the feature used for differentiation is assumed to be gender. Since the possible values ​​of the feature "gender" are "male" and "female," the gender-independent structural model is differentiated into a structural model for gender "male" and a structural model for gender "female."

[0060] As described above, the frequency of differentiation of the structural model is set to a value lower than the frequency of parameter updates. Various modes are possible for the timing of differentiation. As one example, the processing circuit 11 performs differentiation when a reference number or more of observation data related to the feature used for differentiation is acquired. Specifically, the processing circuit 11 monitors the number of observation data related to the feature used for differentiation stored in the database DB and determines whether the number has reached the reference number. If the number has reached the reference number, the structural model is differentiated with respect to the feature based on the observation data related to the feature used for differentiation stored in the database DB. The reference number can be set to any value.

[0061] Fig. 6 is a diagram illustrating structural models and their parameters before and after differentiation. As shown in Fig. 6, the structural model of medical judgment i is differentiated into a structural model of medical judgment i for men and a structural model of medical judgment i for women. Here, i represents the type of medical judgment, i = A or B. The structural model of medical judgment i for men is differentiated into a structural model of medical judgment i for men, i = A or B. i,M and β i,M The structural model for the female treatment decision i has the parameter α i,F and β i,F In other words, as the structural model differentiates, the parameter α i is α i,M and α i,F and the parameter β i is β i,M +β i,F α i,M means the number of times the observed effect value of treatment decision i was "1" for male patients, and α i,F means the number of times the observed effect value of treatment decision i for female patients was "1". Regarding the parameter α, the following equation (4) holds before and after differentiation. Similarly, β i,F means the number of times the observed effect value of treatment decision i was "0" for female patients, and β i,F means the number of times the observed effect value of treatment decision i for female patients was "0." Regarding parameter β, the following equation (5) holds before and after differentiation.

[0062]

number

[0063] In step S17, the processing circuit 11 generates a post-differentiation structural model from the pre-differentiation structural model based on the observation data acquired before the processing time. Specifically, the acquired observation data is divided into observation data related to medical decision A and gender "male", observation data related to medical decision A and gender "female", observation data related to medical decision B and gender "male", and observation data related to medical decision B and gender "female". Based on the observation data related to medical decision A and gender "male", the processing circuit 11 calculates a parameter α A,M ,β A,MA structural model of the medical decision A for men including the following is generated, and the parameter α A,F ,β A,F A structural model of medical decision A for women including B,M ,β B,M A structural model of the medical decision B for men including B,F ,β B,F After differentiation, the first update function 116 is implemented to generate a structural model of the medical decision B for women, which includes the added parameter α i,M ,α i,F , β i,M , β i,F will be updated.

[0064] With the above, the medical information processing according to the first embodiment is completed.

[0065] Various modifications of the first embodiment are possible. For example, the feature used for differentiation may be other than gender. For example, the presence or absence of an underlying disease may be used as another example of a feature taking two values. Furthermore, a feature taking three or more discrete or continuous values ​​may be used, and any feature such as birth year, weight, height, blood pressure, etc. can be used for differentiation.

[0066] As another method for updating the structural model, possible values ​​of the feature may be integrated. In this case, the processing circuitry 11 integrates a first number of structural models corresponding to possible values ​​of the feature of the subject into one structural model that is independent of the feature. An example of the integration process when the feature is "gender" will be briefly described below.

[0067] Fig. 7 is a diagram illustrating structural models and their parameters before and after integration. As shown in Fig. 7, the structural model of medical judgment A for men and the structural model of medical judgment A for women are integrated into a structural model of medical judgment A that does not distinguish between men and women, and the structural model of medical judgment B for men and the structural model of medical judgment B for women are integrated into a structural model of medical judgment B that does not distinguish between men and women. The structural model of medical judgment A after integration has a parameter α A ,β A The structural model of the integrated clinical decision B includes the parameter α B ,β B This will include:

[0068] As described above, according to the first embodiment, when observation data is accumulated, it is possible to repeatedly update the parameters of the structural model according to the context-free bandit algorithm and differentiate or integrate the structural models at different frequencies, thereby efficiently improving the speed and degree of improvement in clinical judgment.

[0069] Example 2 In the second embodiment, new features are incorporated into the model as a way of updating the model structure.

[0070] Fig. 8 is a diagram schematically illustrating medical information processing according to Example 2. Steps S21 to S27 according to Example 2 correspond to steps S1 to S7 shown in Fig. 2 and Fig. 3, respectively. In the following description of Example 2, a description of parts common to the medical information processing described with reference to Fig. 2 and Fig. 3 will be omitted.

[0071] As shown in Fig. 8, the initial structural model according to Example 2 has a structural model A corresponding to the clinical decision to prescribe a therapeutic drug A, a structural model B corresponding to the clinical decision to prescribe a therapeutic drug B, and a structural model C corresponding to the clinical decision to prescribe a therapeutic drug C. The structural model A is a structural model corresponding to the effect evaluation value Y A The structural model B calculates the effect evaluation value Y B The structural model C calculates the effect evaluation value Y CCalculate the effect evaluation value Y A , Y B and Y C The type of the symptom is not particularly limited, but is illustratively the degree of symptom relief.

[0072] In Example 2, linear Thompson sampling, a type of contextual bandit algorithm, is used as the algorithm for determining the treatment decisions to be assigned. In linear Thompson sampling, the expected value and posterior distribution of the parameter θ for calculating the expected value of the reward are estimated by the least squares method, and a treatment decision (option) is selected based on the probability matching method. The parameter θ is a matrix with elements of "number of treatment decisions" x "number of features." In this case, the effect evaluation value Y A , Y B and Y C can be expressed by equations (6), (7), and (8), respectively. Equation (6) is the mathematical expression of the structural model for clinical decision A, equation (7) is the mathematical expression of the structural model for clinical decision B, and equation (8) is the mathematical expression of the structural model for clinical decision C.

[0073]

number

[0074] x1 means the first feature. θ1 A means the parameter θ1 acting on the first feature of patient A, and ε A means the bias of patient A. Similarly, θ1 B means the parameter θ1 acting on the first feature of patient B, and ε B means the bias of patient B, and θ1 C means the parameter θ1 acting on the first feature of patient C, and ε C means the bias of patient C. θ1 A , θ1 B and θ1 C The above parameter θ is obtained by combining these into a single matrix.

[0075] In step S21, the processing circuit 11 determines the medical decision to be assigned from among medical decisions A, B, and C based on the structural model of medical decision A, the structural model of medical decision B, and the structural model of medical decision C, according to the linear Thompson sampling algorithm. In the linear Thompson sampling algorithm when the reward follows a normal distribution, the posterior distribution of θ is expressed as a multivariate normal distribution, so when selecting a medical decision for each patient, random numbers are sampled from the multivariate normal distribution and these random numbers are used to estimate the expected value of the reward for each option. The medical decision corresponding to the maximum expected value is then selected as the one to be assigned. The selected medical decision to be assigned is then assigned to the subject.

[0076] For each patient e = 1, 2, ..., E, a treatment decision i(e) is selected and the effect R i(e) When (e) is obtained, the least squares estimate θ^ of θ is calculated by the feature vector x i(e) (e) is expressed by the matrix representation of Ridge regression.

[0077]

number

[0078] A in equation (9) -1 and b are matrices that replace the following equations (10) and (11), respectively. d means a d×d dimensional identity matrix. A -1 and b are parameters to be updated according to the second embodiment.

[0079]

number

[0080] As shown in FIG. 8, assume that medical decision A is assigned to patient 1 in step S21. A medical procedure corresponding to medical decision A is performed on patient 1 by a medical professional or the like, and an effect occurs in patient 1. In step S22, the processing circuit 11 calculates the effect as an effect observation value Y1 AIn step S23, the processing circuit 11 stores the effect observation value Y1 in the database DB. A The observation data includes at least a patient identifier and an effect observation value Y1. A and an arbitrary first feature x1 such as the patient's gender x1. In the second embodiment, a new feature x2 is added to the structural model, so the feature x2 that is likely to be added may be included in the observed data and accumulated. In FIG. 8, the new feature x2 is assumed to be age.

[0081] In step S26, the processing circuit 11 updates the parameters of the structural model at a first timing based on the observation data. In the second embodiment, the processing circuit 11 updates the parameters every time an effect is observed, in other words, every time an effect observation value is obtained. Specifically, when the effect observation value Y1 A If obtained, the effect observation value Y1 A Based on the observed data including gender x1, parameter A -1 and b are updated according to (12) and (13) below, respectively.

[0082]

number

[0083] In step S27, the processing circuit 11 updates the structural model at a second timing based on the observation data. In the second embodiment, the processing circuit 11 updates the structural model by adding a feature to the structural model. Specifically, the processing circuit 11 changes the structural model incorporating the feature x1 ("gender") to a structural model incorporating the feature x1 and the feature ("age") x2. Various modes are possible for the timing of adding the feature x2. For example, the processing circuit 11 may add the feature when a reference number of observation data including the feature to be added has been accumulated in the database DB. The reference number is not particularly limited and may be any number equal to or greater than one.

[0084] 9 is a diagram illustrating a structural model before and after the addition of the feature quantity x2. As shown in FIG. 9, the effect evaluation value Y A , Y B and Y C can be expressed by the following equations (14), (15), and (16), respectively. Equations (14), (15), and (16) are mathematical expressions of the structural models for the clinical decisions A, B, and C, respectively, after the addition of feature x2.

[0085]

number

[0086] As shown in Figure 9 and equations (14), (15), and (16), a feature x2 is added to the structural model related to clinical judgment A, a feature x2 is added to the structural model related to clinical judgment B, and a feature x2 is added to the structural model related to clinical judgment C. By adding the feature x2, a parameter θ2 acting on the feature x2 is added to the parameter θ, and accordingly, the parameter A -1 An element corresponding to the parameter θ2 is added to b and b. In other words, the addition of the feature x2 expands the matrix size of the parameter θ of the structural model, and accordingly, the parameter A -1 The size of a and b will also be enlarged. -1 Since a and b cannot necessarily be calculated directly from the parameters before expansion, the processing circuit 11 calculates the expanded parameters A and b based on the observation data collected before the processing time. -1 Recalculate the parameter A after expansion. -1 By assigning and b to the structural model, the structural model with the feature x2 added is updated. -1 and b are updated as parameters of the structural model by the first update function 116.

[0087] To verify whether performance improves before and after adding features, the processing circuit 11 calculates the performance of each structural model after adding features using an off-policy evaluation method. Examples of methods that can be used include the Direct Method (DM), Inverse Propensity Score (IPS), Doubly Robust (DR) (Yahoo, 2011), Replay Method (Yahoo, 2012), Counterfactual Risk Minimization (CRM) (Cornell University, 2015), Self-Normalized Estimator (Cornell University, 2015), More Robust Doubly Robust (Google DeepMind, 2018), Efficient Value Estimation (Yale University, Cyber ​​Agent, 2018), and DR with Shrinkage (Cornell University, Netflix, Microsoft, 2019).

[0088] The processing circuit 11 calculates the performance of the structural model after adding the feature using off-policy evaluation for each of multiple feature candidates to be added to the structural model, and selects the feature candidate that will most improve performance as the one to be added. More specifically, for each feature candidate, the processing circuit 11 first calculates the performance of the structural model to which the feature candidate has been added and the performance of the structural model to which the feature candidate has not been added using off-policy evaluation. Next, for each feature candidate, the processing circuit 11 compares the performance of the structural model to which the feature candidate has been added with the performance of the structural model to which the feature candidate has not been added, and selects the feature candidate that is expected to have the best performance as the one to be added. The feature selected as the one to be added is added to the structural model using the above method. Note that if there is no feature candidate that will improve performance by more than a certain level, the processing circuit 11 may decide not to add the feature.

[0089] With the above, the medical information processing according to the second embodiment is completed.

[0090] Note that various modifications are possible to the second embodiment. As an example, feature deletion may be performed as an update of the structural model. In this case, the processing circuit 11 changes a first structural model incorporating multiple feature values ​​to a second structural model in which a predetermined feature value from among the multiple feature values ​​has been deleted. The feature value deletion may be performed at any timing. As an example, the feature value deletion may be performed at a timing when performance is expected to improve by the feature value deletion. An example of the feature value deletion process will be briefly described below.

[0091] FIG. 10 is a diagram illustrating a structural model before and after the deletion of feature x2. As shown in FIG. 10, the structural model before deletion is a structural model for clinical judgments A, B, and C incorporating feature x1 and x2. By deleting feature x2 from the structural model for clinical judgments A, B, and C before deletion, a structural model for clinical judgments A, B, and C incorporating only feature x1 is generated. By deleting feature x2, the matrix size of parameter θ of the structural model is reduced, and accordingly, parameter A is reduced. -1 The size of a and b will also be reduced. -1 Since a and b cannot be calculated directly from the parameters before reduction, the processing circuit 11 calculates the reduced parameters A and B based on the observation data collected before the current step. -1 Recalculate the parameter A after reduction. -1 By assigning a and b to the structural model, a structural model in which the feature x2 is deleted is generated.

[0092] As another example, a feature may be changed to update the structural model. In this case, the processing circuit 11 changes a first structural model incorporating a first feature to a second structural model incorporating a second feature instead of the first feature. An example of the feature change process will be briefly described below. The timing of the change is not particularly limited, but it is preferable, for example, to be when a reference number or more of observation data relating to the second feature has been accumulated.

[0093] FIG. 11 is a diagram illustrating structural models before and after changing from feature x1 to feature x2. As shown in FIG. 11, the structural model before the change includes structural models for clinical decisions A, B, and C, in which feature x1 is incorporated. By incorporating feature x2 instead of feature x1 from the structural models for clinical decisions A, B, and C before the change, structural models for clinical decisions A, B, and C, in which only feature x2 is incorporated, are generated. Even if feature x1 is changed to feature x2, the matrix size of parameter θ of the structural model and parameter A -1 The sizes of a and b are not changed. The processing circuit 11 calculates the parameter A related to the feature x2 based on the observation data collected before the current step. -1 Recalculate and b. Transformed parameter A -1 By assigning a and b to the structural model, a structural model in which the feature x1 is changed to the feature x2 is generated.

[0094] As described above, according to the second embodiment, when observation data is accumulated, it is possible to repeatedly update the parameters of the structural model according to the contextual bandit algorithm and add, delete, or change the features of the structural model at different frequencies, respectively. This makes it possible to efficiently improve the speed and degree of improvement in clinical judgment.

[0095] (others) This embodiment can be implemented in various other examples in addition to Example 1 and Example 2. As an example, a medical judgment may be added as an update to a structural model. More specifically, when a model includes a first structural model corresponding to a first medical judgment, the processing circuitry 11 adds a second structural model corresponding to a second medical judgment to the model. An example of the process of adding a medical judgment will be described below.

[0096] Fig. 12 is a diagram illustrating a structural model before and after the addition of clinical judgment C. As shown in Fig. 12, the structural model before the addition includes structural models for clinical judgments A and B. By adding the structural model for clinical judgment C to the structural model for clinical judgments A and B before the addition, a model including structural models for clinical judgments A, B, and C is generated.

[0097] Addition of a structural model for medical judgment C may be performed, for example, by the following procedure. First, a clinically new medical judgment C is added. Then, observation data including effect observation values ​​for medical judgment C is accumulated in the database DB in parallel with observation data including effect observation values ​​for medical judgments A and B. The processing circuit 11 monitors the number of observation data including effect observation values ​​for medical judgment C accumulated in the database DB. Then, when the number of observation data reaches a reference number, the processing circuit 11 generates a structural model for medical judgment C based on the reference number of observation data. As another example, the processing circuit 11 monitors the elapsed time from the start time when observation data including effect observation values ​​for medical judgment C were accumulated in the database DB. Then, when the elapsed time reaches a reference time length, the processing circuit 11 generates a structural model for medical judgment C based on the observation data for medical judgment C accumulated in the database DB.

[0098] As another example of updating the structural model, a medical decision may be abolished. More specifically, when a model includes a first structural model corresponding to a first medical decision and a second structural model corresponding to a second medical decision, the processing circuitry 11 abolishes the first structural model or the second structural model from the model. An example of the process of abolishing a medical decision will be described below.

[0099] Fig. 13 is a diagram illustrating structural models before and after the abolition of medical judgment C. As shown in Fig. 13, the structural model before the abolition includes structural models for medical judgments A, B, and C. By abolishing the structural model for medical judgment C from the structural model for medical judgments A, B, and C before the abolition, a model including structural models for medical judgments A and B is generated.

[0100] The structural model for the medical judgment C may be abolished after a certain period of time has elapsed or at any timing designated by the operator.

[0101] Note that the structural models shown in Figures 12 and 13 are structural models that follow a contextual bandit algorithm that incorporates features, but are not limited to this and can also be applied to structural models that follow a contextless bandit algorithm that does not incorporate features.

[0102] As another example of updating the structural model, the processing circuit 11 may change the type of prior distribution to which the effect occurring in the subject follows. One example is changing from a Bernoulli distribution to a normal distribution, or from a normal distribution to a Bernoulli distribution. As another example of updating the structural model, the processing circuit 11 may change the network structure (hyperparameters) of a deep neural network used in reinforcement learning. In reinforcement learning, a deep neural network is used as a structural model for calculating an effect evaluation value. In this embodiment, the network structure of this deep neural network can be changed by increasing or decreasing the number of layers of the neural network, or by changing whether or not to consider a time series.

[0103] As another example of parameter updating, the processing circuit 11 may perform degeneration (resetting). As an example of degeneration, the processing circuit 11 may initialize the parameters of the structural model at the timing of parameter update. As another example, the processing circuit 11 may update the parameters by limiting the range of observation data used for updating. For example, the observation data used for parameter update may be limited to observation data observed within a predetermined period going back from the processing target time, and the parameters of the structural model may be recalculated. Since old observation data is excluded from the observation data used for parameter update, it becomes possible to update the parameters by excluding observation data obtained under the old therapeutic drug, for example, when the effect of a therapeutic drug has changed. This makes it possible to improve the prediction accuracy of the effect evaluation value of the structural model.

[0104] The various embodiments described above can be combined as appropriate. As an example, the processing circuit 11 may update the structural model by both differentiating or integrating the structural models and changing the type of prior distribution. The differentiation or integration of the structural models and the change of the type of prior distribution may be performed at the same frequency or at different frequencies, as long as they are performed less frequently than parameter updates. Furthermore, the timing of the differentiation or integration of the structural models and the timing of the change of the type of prior distribution may be the same or different. As another example, the processing circuit 11 may update the structural model by both adding, deleting, or changing the feature quantities of the structural models and changing the network structure of the deep neural network. The addition, deletion, or change of the feature quantities of the structural models and the change of the network structure of the deep neural network may be performed at the same frequency or at different frequencies, as long as they are performed less frequently than parameter updates. Furthermore, the timing of the addition, deletion, or change of the feature quantities of the structural models and the change of the network structure of the deep neural network may be the same or different.

[0105] In the above embodiment, the allocation function 111, the observation function 112, the storage function 113, the update function 114, and the display control function 115 are installed in a single computer. However, this embodiment is not limited to this. The allocation function 111, the observation function 112, the storage function 113, the update function 114, and the display control function 115 may be installed in a distributed manner across multiple computers. In other words, the medical information processing device 1 may be a computer system configured with multiple computers in which the allocation function 111, the observation function 112, the storage function 113, the update function 114, and the display control function 115 are installed in a distributed manner. Furthermore, the database DB in which the observation data is accumulated is stored in the storage device 12 of the medical information processing device 1. However, this embodiment is not limited to this, and the database DB may be stored in a computer other than the medical information processing device 1. In this case, the medical information processing device 1 may acquire the observation data from the database DB via the communication device 14, or may copy the observation data from the database DB to a portable recording medium and acquire the observation data from the portable recording medium.

[0106] (Summary) According to at least one embodiment described above, the medical information processing device 1 has one or more processing circuits 11. The one or more processing circuits 11 have an update function 114 that updates a model that calculates an effect evaluation value of medical judgment, and the update function 114 includes a first update function 116 that updates parameters of the model while fixing the structure of the model, and a second update function 117 that updates the structure of the model less frequently than the parameters.

[0107] According to the above configuration, when observation data is accumulated, it is possible to individually update the model structure and parameters at appropriate times, thereby efficiently improving the speed and degree of improvement in clinical judgment.

[0108] According to at least one of the embodiments described above, the speed and degree of improvement in clinical judgment can be efficiently improved.

[0109] The term "processor" used in the above description refers to a circuit such as a CPU, a GPU, an application specific integrated circuit (ASIC), a programmable logic device (e.g., a simple programmable logic device (SPLD), a complex programmable logic device (CPLD), and a field programmable gate array (FPGA)). A processor realizes its functions by reading and executing a program stored in a memory circuit. Note that instead of storing a program in a memory circuit, a program may be directly embedded in the processor circuit. In this case, the processor realizes its functions by reading and executing the program embedded in the circuit. Alternatively, instead of executing a program, a function corresponding to the program may be realized by combining logic circuits. Note that each processor in this embodiment is not limited to being configured as a single circuit, but may be configured as a single processor by combining multiple independent circuits to realize its function. Furthermore, multiple components in FIG. 1 may be integrated into a single processor to realize its function.

[0110] Although several 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, modifications, and combinations of embodiments can be made without departing from the spirit of the invention. These embodiments and their modifications are included within the scope and spirit of the invention, as well as within the scope of the invention and its equivalents as defined in the claims.

[0111] With respect to the above embodiment, the following supplementary notes are disclosed as one aspect and optional features of the invention.

[0112] (Appendix 1) An update unit is provided for updating a model for calculating an effect evaluation value of medical treatment decisions, The update unit a first update unit that updates parameters of the model while fixing a structure of the model; a second update unit that updates the structure of the model less frequently than the parameters; Medical information processing equipment.

[0113] (Appendix 2) an allocation unit that determines a medical decision to be allocated to a subject based on the efficacy evaluation value; The device may further comprise a storage unit that stores observation data including observed values ​​of the effects occurring in the subject. The update unit may update the model based on the observation data.

[0114] (Appendix 3) The second update unit may update the structure by differentiating the model into structural models corresponding to possible values ​​of the feature of the subject.

[0115] (Appendix 4) The second update unit may update the structure at a timing when a reference number or more of the observation data relating to the feature amount is accumulated.

[0116] (Appendix 5) The model may include a first structural model corresponding to possible values ​​of the feature of the subject. The second update unit may integrate the first structural model into a structural model that does not depend on the feature amount as the structural update.

[0117] (Appendix 6) The model may include a first structural model incorporating a first feature amount of the subject. The second update unit may update the structure by changing the first structural model into a second structural model incorporating the first feature amount and the second feature amount.

[0118] (Appendix 7) The model may include a first structural model incorporating a first feature amount of the subject. The second update unit may update the structure by changing the first structural model to a second structural model in which a second feature amount is incorporated in place of the first feature amount.

[0119] (Appendix 8) The second update unit may update the structure when a reference number or more of the observation data relating to the second feature amount is accumulated.

[0120] (Appendix 9) The model may include a first structural model incorporating a plurality of feature quantities. The second update unit may update the structure by changing the first structural model to a second structural model in which a predetermined feature value among the plurality of feature values ​​is deleted.

[0121] (Appendix 10) The model may include a first structural model corresponding to a first one of the clinical decisions. The second update unit may update the structure by adding, to the model, a second structural model corresponding to a second medical judgment different from the first medical judgment.

[0122] (Appendix 11) The model may include a first structural model corresponding to a first one of the clinical decisions and a second structural model corresponding to a second one of the clinical decisions. The second update unit may abolish the first structural model or the second structural model as the structural update.

[0123] (Appendix 12) The second update unit may have, as the structure, a type of prior distribution to which an effect occurring in the subject due to a medical treatment corresponding to the medical judgment follows.

[0124] (Appendix 13) The second update unit may update the structure when a reference number or more of the observation data has been accumulated.

[0125] (Appendix 14) The second update unit may update the structure after a certain period of time has elapsed.

[0126] (Appendix 15) The second update unit may update the structure at a timing when an improvement in performance of the model is expected after updating the structure.

[0127] (Appendix 16) The first update unit may update the parameter that defines the posterior distribution of an expected value of an effect occurring in the subject due to a medical procedure corresponding to the medical judgment when a reference number or more of the observation data has been accumulated or when a certain period of time has passed.

[0128] (Appendix 17) An updating step of updating a model for calculating an effect evaluation value of medical treatment decisions, The updating step includes: a first updating step of updating parameters of the model while fixing the structure of the model; a second updating step of updating the structure of the model less frequently than the parameters; Medical information processing method.

[0129] (Appendix 18) On the computer, Realize an update function that updates the model that calculates the effectiveness evaluation value of medical decisions, The update function: a first update function that updates parameters of the model while fixing the structure of the model; a second update function that updates the structure of the model less frequently than the parameters; Medical information processing program. [Explanation of symbols]

[0130] 1 Medical information processing device 11 Processing circuit 12 Storage device 13 Input Devices 14. Communications equipment 15 Display equipment 111 Allocation function 112 Observation Function 113 Accumulation Function 114 Update function 115 Display control function 116 First Update Feature 117 Second Update Function

Claims

1. An allocation unit that calculates an effect evaluation value corresponding to a medical judgment using a model configured to be able to calculate the effect evaluation value corresponding to the medical judgment, and determines a medical judgment to be assigned to a subject based on the calculated effect evaluation value; an observation unit that observes an effect observation value relating to an effect occurring in the subject by administering to the subject a medical procedure corresponding to the determined medical judgment or a medical judgment different from the determined medical judgment; a storage unit that stores observation data in a storage device, the observation data including an identifier of the subject, a medical judgment corresponding to the medical treatment administered to the subject, and the observed effect observation value; an update unit that updates the model based on the observation data, The update unit a first update unit that updates parameters of the model based on the observation data while fixing a structure of the model; a second update unit that updates a structure of the model based on the observation data less frequently than the parameters; Medical information processing equipment.

2. The medical image processing apparatus according to claim 1 , wherein the second update unit updates the structure by differentiating the model into structural models corresponding to possible values ​​of the feature of the subject.

3. The medical image processing apparatus according to claim 2 , wherein the second update unit updates the structure when a reference number or more of the observation data relating to the feature amount is accumulated.

4. the model has a first structural model corresponding to possible values ​​of the feature of the subject; the second update unit integrates the first structural model into a structural model that does not depend on the feature amount as the structural update. The medical information processing device according to claim 1.

5. the model has a first structural model incorporating a first feature amount of the subject; the second update unit updates the structure by changing the first structural model into a second structural model incorporating the first feature amount and the second feature amount; The medical information processing device according to claim 1.

6. the model has a first structural model incorporating a first feature amount of the subject; the second update unit updates the structure by changing the first structural model to a second structural model in which a second feature amount is incorporated instead of the first feature amount; The medical information processing device according to claim 1.

7. The medical image processing apparatus according to claim 5 , wherein the second update unit updates the structure when a reference number or more of the observation data relating to the second feature amount is accumulated.

8. the model has a first structural model incorporating a plurality of feature quantities; the second update unit updates the structure by changing the first structural model to a second structural model in which a predetermined feature value among the plurality of feature values ​​is deleted. The medical information processing device according to claim 1.

9. the model has a first structural model corresponding to a first one of the clinical decisions; the second update unit adds, to the model as the update of the structure, a second structural model corresponding to a second medical judgment different from the first medical judgment; The medical information processing device according to claim 1.

10. the model includes a first structural model corresponding to a first medical judgment and a second structural model corresponding to a second medical judgment among the medical judgments; the second update unit abolishes the first structural model or the second structural model as the structural update. The medical information processing device according to claim 1.

11. The medical information processing apparatus according to claim 1 , wherein the second update unit has the structure of a type of prior distribution according to which an effect occurring in the subject due to a medical treatment corresponding to the medical judgment follows.

12. The medical image processing apparatus according to claim 1 , wherein the second update unit updates the structure when a reference number or more of the observation data is accumulated.

13. The medical image processing apparatus according to claim 1 , wherein the second update unit updates the structure after a certain period of time has elapsed.

14. The medical image processing apparatus according to claim 1 , wherein the second update unit updates the structure at a timing when an improvement in performance of the model is expected after updating the structure.

15. 15. The medical information processing device according to claim 1, wherein the first update unit updates the parameter that defines a posterior distribution of an expected value of an effect that occurs in the subject due to a medical procedure corresponding to the medical judgment when a reference number or more of the observation data has been accumulated or when a certain period of time has elapsed.

16. An allocation process for calculating an effect evaluation value corresponding to a medical judgment using a model configured to be able to calculate the effect evaluation value corresponding to the medical judgment, and determining a medical judgment to be assigned to a subject based on the calculated effect evaluation value; an observation step of observing an effect observation value relating to an effect occurring in the subject by administering to the subject a medical procedure corresponding to the determined medical judgment or a medical judgment different from the determined medical judgment; a storage step of storing observation data in a storage device, the observation data including an identifier of the subject, a medical judgment corresponding to the medical treatment administered to the subject, and the observed effect observation value; an updating step of updating the model based on the observation data; The updating step includes: a first updating step of updating parameters of the model based on the observation data while fixing a structure of the model; a second updating step of updating the structure of the model based on the observation data less frequently than the parameters; A computer-implemented method for processing medical information.

17. On the computer, an allocation function that calculates an effect evaluation value corresponding to a medical judgment using a model configured to be able to calculate the effect evaluation value corresponding to the medical judgment, and determines a medical judgment to be allocated to a subject based on the calculated effect evaluation value; an observation function for observing an effect observation value relating to an effect occurring in the subject by administering to the subject a medical procedure corresponding to the determined medical judgment or a medical judgment different from the determined medical judgment; a storage function for storing observation data in a storage device, the observation data including an identifier of the subject, a medical judgment corresponding to the medical treatment administered to the subject, and the observed effect observation value; an update function for updating the model based on the observation data; The update function: a first update function that updates parameters of the model based on the observation data while fixing the structure of the model; a second update function that updates the structure of the model based on the observation data less frequently than the parameters; Medical information processing program.

Images