Patient's intention reflection support device, patient's intention reflection support method, and program

Abstract

To determine a therapy with which a patient is satisfied.SOLUTION: A patient's intention reflection support device of an embodiment has an acquisition unit, a generation unit, and a presentation unit. The acquisition unit acquires first information on a first therapy based at least on an inspection result, and second information on a second therapy according to a request from a patient. The generation unit generates recommendation information according to the first information and the second information. The presentation unit presents presentation information based on the recommendation information.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The embodiments disclosed in this specification and the drawings relate to a patient intention reflection support device, a patient intention reflection support method, and a program.

Background Art

[0002] In recent years, the number of hospitals providing medical treatment has increased, and it has become an era in which hospitals are selected by patients. For this reason, hospitals have been aiming to improve patient satisfaction and be selected by patients. In order not to feel discomfort from receiving treatment that they do not understand or to receive treatment that is not satisfactory due to insufficient communication of intentions with doctors, patients tend to investigate health and treatment on their own, accumulate a certain amount of knowledge, and then receive treatment. In order to enhance patient satisfaction, it is important to improve communication of intentions between doctors and patients.

[0003] Conventionally, when making a decision regarding a patient's treatment policy, there has been a method of presenting several treatment methods from the clinical perspective considered by a doctor based on the results of analyzing the characteristics of the patient (or the decision maker who determines the patient's treatment policy). In this method, while grasping the psychological state of the patient or the like while the patient or the like is determining the doctor, the treatment method to be presented is dynamically changed.

[0004] However, since the treatment method to be changed is created from a clinical perspective, it has not always been a treatment method that conforms to the intentions of the patient or the like. For this reason, patients may sometimes still receive treatment with a treatment method with low satisfaction.

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0006] The problem to be solved by the embodiments disclosed in this specification and the drawings is to enable a patient to determine a treatment method that the patient can accept. However, the problems to be solved by the embodiments disclosed in this specification and the drawings are not limited to the above problems. It is also possible to position, as other problems, the problems corresponding to the respective effects of the respective configurations shown in the embodiments described later.

Means for Solving the Problem

[0007] The patient intention reflection support device according to the embodiment has an acquisition unit, a generation unit, and a presentation unit. The acquisition unit acquires at least first information regarding a first treatment method based on examination results and second information regarding a second treatment method according to the patient's wishes. The generation unit generates recommendation information according to the relationship between the first information and the second information. The presentation unit presents presentation information based on the recommendation information.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Mode for Carrying Out the Invention

[0009] Hereinafter, a patient intention reflection support device, a patient intention reflection support method, and a program according to an embodiment will be described with reference to the drawings.

[0010] The patient intention reflection support device according to the embodiment is used, for example, when a doctor determines a treatment policy for a patient. When treating a patient, first, examinations and tests are performed, and based on the results, a treatment policy is determined. As the treatment policy, for example, a policy of performing treatment using a treatment method considered appropriate from the patient's symptoms and test results is established.

[0011] However, only the patient's symptoms and test results do not fully reflect the patient's intention, and the patient may receive treatment while still having anxiety and discomfort. In the treatment decision support device according to the embodiment, in order to eliminate such patient anxiety and discomfort, support is provided for the doctor to establish a treatment policy that reflects the patient's intention.

[0012] (First Embodiment) FIG. 1 is a block diagram showing an example of the usage environment of the patient intention reflection support device 100 according to the first embodiment. The patient intention reflection support device 100 according to the embodiment can communicate with the doctor terminal 10 and the patient terminal 20 via, for example, a network NW. The network NW represents the entire information communication network using telecommunication technologies. The network NW includes, in addition to wireless / wired LAN and the Internet, a telephone communication line network, an optical fiber communication network, a cable communication network, and a satellite communication network, etc.

[0013] The doctor terminal 10 is a terminal installed in, for example, a hospital or the like. The doctor terminal 10 may be a mobile terminal such as a smartphone or tablet owned by a doctor or the like. The doctor terminal 10 includes a network interface used for communication via the network NW, an input interface such as a keyboard, and an output interface such as a display. The doctor uses the doctor terminal 10 to provide information to the patient terminal 20 or the patient preference support device 100, or to obtain information provided by the patient terminal 20 or the patient preference support device 100.

[0014] The patient terminal 20 is, for example, a mobile terminal such as a smartphone or tablet owned by a patient. The patient terminal 20 may be a terminal installed at the patient's home or the like. The patient terminal 20 includes a network interface used for communication via the network NW, an input interface such as a keyboard, and an output interface such as a display. The patient uses the patient terminal 20 to provide information to the doctor terminal 10 or the patient preference support device 100, or to obtain information provided by the doctor terminal 10 or the patient preference support device 100.

[0015] FIG. 2 is a block diagram showing an example of the configuration of the patient preference support device 100 according to the first embodiment. The patient preference support device 100 includes, for example, a network (hereinafter, NW) interface 110, a memory circuit 120, an input interface 130, a display 140, and a processing circuit 150.

[0016] The NW interface 110 controls data communication performed with other devices via the network NW. Specifically, the NW interface 110 controls the transmission and reception of various data performed with other devices under the control of the processing circuit 150. For example, the NW interface 110 is realized by a network card, a network adapter, a NIC (network interface controller), or the like.

[0017] The memory circuit 120 is connected to the processing circuit 150 and stores various data. Specifically, the memory circuit 120 stores various data under the control of the processing circuit 150, and reads and updates the stored data. For example, the memory circuit 120 is realized by a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, a hard disk, an optical disk, or the like.

[0018] The memory circuit 120 stores, for example, a standard medical database (hereinafter referred to as DB) 121, an examination DB 122, a patient DB 123, a doctor-recommended treatment method tag 124, and a patient-desired treatment method tag 125. The standard medical DB 121 is a DB compiled by collecting a plurality of standard medical treatments, which are treatment methods according to the results of examinations. A plurality of characteristic standard medical tags are set for each treatment method included in the standard medical DB 121. The standard medical tags are indicated by words. For example, for a treatment combining an anticancer agent and a bone marrow transplant, standard medical tags such as "♯transplantation", "♯surgery", "♯immediate efficacy", and "♯side effects" are set. Here, a ♯ symbol is attached before the word indicating the standard medical tag.

[0019] The examination DB 122 is a DB compiled with examination information based on the results of examining a patient. The examination DB 122 is created, for example, when a patient is examined and updated each time the examination is performed again. The patient DB 123 is a DB compiled with various patient information regarding the patient. The patient DB 123 is created, for example, at the first visit of the patient and updated each time an examination or treatment is performed.

[0020] The doctor-recommended treatment method tag 124 includes a plurality of standard medical tags set for the treatment method extracted as the doctor-recommended treatment method, which is the treatment method recommended by the doctor for the examination results, and information on the feature amounts of each standard medical tag for the treatment method. The feature amount indicates the importance of the word indicating the standard medical tag (hereinafter referred to as the doctor-side standard medical tag) included in the doctor-recommended treatment method, and is used, for example, for weighting. The doctor-recommended treatment method may be the standard medical treatment itself or a treatment method modified by a doctor or the like based on the standard medical treatment. The doctor-recommended treatment method is an example of the first treatment method.

[0021] The patient's desired treatment method tag 125 includes the extracted doctor-side standard medical tags and the feature quantities for the doctor-side standard medical tags. The feature quantity is the importance of the words indicating the standard medical tags. The feature quantity is extracted based on patient information, information reflecting the patient's thoughts and feelings, such as the content posted by the patient on SNS (Social networking service) or the content spoken by the patient during the examination. The patient's desired treatment method tag 125 includes, in addition to the standard medical tags, private tags related to the patient's privacy other than diseases and information on the feature quantities of the private tags. The feature quantity of the private tag is also extracted based on patient information such as the content spoken by the patient during the examination.

[0022] The input interface 130 is connected to the processing circuit 150 and receives input operations of various instructions and various information from the operator. Specifically, the input interface 130 converts the input operations received from the operator into electrical signals and outputs them to the processing circuit 150. The input interface 130 is realized by, for example, a trackball, a switch button, a mouse, a keyboard, a touch pad for performing an input operation by touching the operation surface, a touch screen in which the display screen and the touch pad are integrated, a non-contact input circuit using an optical sensor, a voice input circuit using a microphone, and the like.

[0023] Note that in this specification, the input interface 130 is not limited to only those equipped with physical operation components such as a mouse and a 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 the control circuit is also included in the examples of the input interface 130.

[0024] The display 140 is connected to the processing circuit 150 and displays various information and various data. Specifically, the display 140 converts various information and various data into electrical signals for display and outputs them under the control of the processing circuit 150. For example, the display 140 is realized by an LCD (Liquid Crystal Display), a touch panel, or the like. The patient intention reflection support device 100 may include a speaker that outputs sound, a vibrator that transmits vibration, or the like instead of or in addition to the display 140.

[0025] The processing circuit 150 controls the operation of the patient intention reflection support device 100 in response to an input operation received from an operator via the input interface 130. The processing circuit 150 includes, for example, an acquisition function 151, a generation function 152, and a presentation function 153. The processing circuit 150 realizes these functions, for example, by executing a program stored in a storage device (storage circuit 120) by a hardware processor.

[0026] A hardware processor means circuitry such as, for example, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an application specific integrated circuit (ASIC), a programmable logic device (e.g., a simple programmable logic device (SPLD) or a complex programmable logic device (CPLD), a field programmable gate array (FPGA)). Instead of storing a program in the storage circuit 120, it may be configured to directly incorporate the program into the circuit of the hardware processor. In this case, the hardware processor realizes its functions by reading and executing the program incorporated in the circuit. The hardware processor is not limited to being configured as a single circuit, and may be configured as one hardware processor by combining a plurality of independent circuits to realize each function. Also, a plurality of components may be integrated into one hardware processor to realize each function.

[0027] The acquisition function 151 acquires first information regarding a recommended treatment method recommended by a doctor and second information regarding a second treatment method according to the patient's wishes. The acquisition function 151 acquires the results of an examination performed on the patient by a technician or the like. The acquisition function 151 acquires information reflecting the patient's thoughts and feelings, for example, the content of the patient's speech during a medical examination performed by a doctor. The acquisition function 151 is an example of an acquisition unit.

[0028] The acquisition function 151 extracts and acquires, as a recommended treatment method recommended by a doctor, a treatment method corresponding to the acquired examination result from among a plurality of treatment methods included in the standard medical DB 121 stored in the storage circuit 120. The acquisition function 151 stores, in the storage circuit 120 as a doctor-recommended treatment method tag 124, the standard medical tag set for the extracted recommended treatment method and the standard medical tag extracted from the examination information. The doctor-recommended treatment method tag 124 is an example of the first information.

[0029] The acquisition function 151 formulates patient information, for example, the content spoken by the patient during a medical examination. The acquisition function 151 analyzes the formulated patient information and extracts the importance of words indicating the standard medical tags included in the recommended treatment method. The acquisition function 151 generates a patient-desired treatment method tag 125 in which the feature amount of the standard medical tag included in the recommended treatment method is set to the extracted importance.

[0030] The acquisition function 151 generates a private tag in which words other than the words indicating the standard medical tag are used as tags from the acquired patient information. The acquisition function 151 extracts the feature amount of each tag in the private tag, sets it for each tag, and generates a private tag. The acquisition function 151 adds the generated private tag to the patient-desired treatment method tag 125. The acquisition function 151 stores the acquired patient-desired treatment method tag 125 in the storage circuit 120. The patient-desired treatment method tag 125 is an example of the second information.

[0031] The generation function 152 generates recommendation information according to the relationship between the doctor-recommended treatment method tag 124 and the patient-desired treatment method tag 125 generated by the acquisition function 151 and stored in the storage circuit 120. The generation function 152 calculates the similarity of the feature amounts of the standard medical tags in the doctor-recommended treatment method tag 124 and the feature amounts of the standard medical tags in the patient-desired treatment method tag 125. The standard medical tag is assigned, for example, to important medical terms. The generation function 152 is an example of a generation unit.

[0032] The generation function 152 generates recommendation information based on the calculated similarity. The recommendation information includes, for example, information provided by a doctor to a patient. The information provided by a doctor to a patient varies depending on the similarity of the feature amounts of the standard medical tags in the doctor-recommended treatment method tag 124 and the patient-desired treatment method tag 125. For example, the generation function 152 generates recommendation information regarding a treatment method closer to standard medicine as the similarity is higher, and generates recommendation information regarding a treatment method closer to the treatment method (hereinafter referred to as the patient-desired treatment method) that is presumed or confirmed to be desired by the patient as the similarity is lower. The generation function 152 presents standard medicine, for example, when the similarity is high (for example, 0.7 to 1.0), and presents information such as the patient's concerns when the similarity is low (for example, 0 to 0.3).

[0033] The generation function 152 creates a follow-up timing for a patient who is continuously receiving medical examinations to receive a follow-up examination. The generation function 152 performs sentiment analysis on a patient and estimates a change in the patient's sentiment, for example, based on information reflecting the patient's thoughts and feelings during or outside of a medical examination. The patient's speech during or outside of a medical examination may be, for example, posting information or browsing records on an SNS (Social networking service) by the patient. The generation function 152 detects a change in sentiment, for example, when sentences such as "Cancer drugs are tough", "Cancer drug treatment is more painful than expected", "I can't endure the side effects", "Doctor XX seems to be good", "Another treatment method seems to suit me now", "I can't live anymore", "I want to die", "I'm concerned about the surgical treatment method", "What are other treatment methods, the most advanced treatment methods" are extracted from the posting information or search history of the SNS, or when there is a browsing record such as "Viewing articles on the cancer consultation window every day". The generation function 152 creates the timing of the follow-up examination (hereinafter referred to as the follow-up timing) when it determines that the estimated change in the patient's sentiment is large.

[0034] The prompting function 153 presents prompting information based on the recommendation information generated by the generation function 152. The prompting function 153 modifies the recommendation information to be provided based on the private tags included in the patient-preferred treatment method tag 125. The prompting function 153 presents the modified recommendation information to the doctor, such as by displaying it on the display 140. The prompting function 153 is an example of a prompting unit.

[0035] The prompting function 153 presents the follow-up timing created by the generation function 152 to the doctor, such as by displaying it on the display 140. The follow-up timing may be displayed as character information such as, for example, "For this patient, a rapid change in the score of the sentiment analysis result was detected during the period when side effects of the drug would occur. Since this is a matter of concern in daily life, let's create an opportunity for consultation."

[0036] The prompting function 153 displays, on the display 140 in the form of a radar chart, the feature amounts of the standard medical tags in the doctor-recommended treatment method tag 124 extracted by the acquisition function 151 and the feature amounts of the standard medical tags in the patient-preferred treatment method tag 125, and presents them to the doctor. In this way, instead of displaying the similarity, information such as the numerical values used as the basis for calculating the similarity may be presented. Alternatively, the prompting function 153 may present the similarity together with information such as the basis for calculating the similarity.

[0037] Subsequently, the process from the examination using the information presented to the doctor by the patient intention reflection support device 100 to the agreement between the doctor and the patient will be described. FIG. 3 is a diagram showing an example of the step-by-step process from the examination to the agreement formation between the doctor and the patient in the first embodiment. Here, an example will be described in which the doctor is treating a patient for lymphoblastic lymphoma (LBL).

[0038] The process from examination to agreement formation can be divided into stages from the first phase to the fourth phase, for example. In the process from examination to agreement formation, the acquisition function 151 collects and accumulates data. Here, the acquisition function 151 collects and accumulates information on the results of examinations and diagnoses and the treatment methods for treating the diseases suffered by the patient as judged by the examinations and diagnoses. The first phase is the "examination and medical treatment" phase. In the first phase, a technician or the like examines the patient, and a doctor examines the patient.

[0039] The second phase is the "analysis" phase. In the second phase, by analyzing the collected and accumulated data, the similarity (deviation) between the recommended treatment method by the doctor and the treatment method desired by the patient is obtained, or recommendation information based on the similarity is generated. The third phase is the "presentation and action on measures" phase.

[0040] In the third phase, the information obtained by the analysis is presented to the doctor. The doctor considers the treatment method in which the patient's will is reflected and the content of the explanation of the treatment method to the patient based on the information presented by the patient will reflection support device 100. The fourth phase is the "agreement formation" phase. In the fourth phase, the doctor explains the content of the treatment to the patient, and obtains the agreement on the treatment in a state where the patient is convinced.

[0041] The standard medical treatment for lymphoblastic lymphoma can be carried out, for example, in accordance with the medical treatment guidelines, and the doctor can promote the treatment in accordance with the medical treatment guidelines to the patient. Since the standard medical treatment is the best treatment method recommended at present, as a doctor, it is considered an appropriate treatment method to recommend the treatment by the standard medical treatment to the patient. However, since the individual background of the patient is not considered in the medical treatment guidelines, there may be cases where the patient cannot be convinced by the treatment in accordance with the medical treatment guidelines.

[0042] For example, in standard medical treatment, there is a treatment method in which a strong anticancer agent is used to weaken cancer as much as possible and then a bone marrow transplant is performed. However, major side effects may occur with the bone marrow transplant. Therefore, as a patient, it is conceivable to desire a treatment other than the treatment by standard medical treatment. Thus, the patient intention reflection support device 100 calculates the similarity between the treatment by standard medical treatment and the treatment desired by the patient, and presents information according to the calculated similarity.

[0043] As processing by the patient intention reflection support device 100, in the first phase, the acquisition function 151 mainly executes the processing, in the second phase, the generation function 152 mainly executes the processing, and in the third phase, the presentation function 153 mainly executes the processing. In the fourth phase, there is no processing by the patient intention reflection support device 100, and the fourth phase is performed, for example, by a doctor and a patient. Also, the examinations and diagnoses in the first phase are performed by, for example, a technician, a doctor, and a patient.

[0044] While executing the processing in each phase, the acquisition function 151 reads and acquires the examination information and patient information stored in the memory circuit 120. The examination information includes, for example, information regarding marker values, information on cancer gene tests, information on PET-CT (positron emission tomography-computed tomography), MRI (Magnetic Resonance Imaging), blood test information, etc. The information regarding marker values includes information such as (CD19, CD22, CD79a, CD79b, CD99 (MIC2) being positive). The examination information is used, for example, by the generation function 152 when determining the doctor-recommended treatment method.

[0045] Patient information includes, for example, past examination records for each patient, treatment methods selected in the past, age, gender, personality (behavior characteristics), risk tolerance, search history by the patient himself / herself, personal information, religion the patient believes in, and other information. Patient information is used, for example, when estimating the patient's preferred treatment method. Here, the patient's preferred treatment method may be a treatment method that is presumed to be desired by a specific patient or actually specified by the patient, or it may be a treatment method that takes into account the patient's preference for the doctor-recommended treatment method. The patient's preferred treatment method is an example of the second treatment method.

[0046] In the first phase, examinations and diagnoses of the patient are performed by technicians, doctors, etc. The patient's examinations include examinations on specimens collected from the patient and examinations performed by analyzing images of the patient taken using various devices. The patient's diagnosis includes, for example, the doctor's inquiry, auscultation, palpation, etc., as well as the input of patient information at the reception. The acquisition function 151 acquires the results of the patient's examinations and diagnoses by technicians, doctors, etc., and stores them in the memory circuit 120 as examination information and patient information, respectively.

[0047] In the subsequent second phase, the acquisition function 151 extracts a treatment method corresponding to the examination information from the treatment methods included in the standard medical DB121, and acquires the standard medical tags and the feature amounts set for the standard medical tags in the extracted treatment method. The extracted treatment method includes standard medical tags such as "♯transplantation: 0.8", "♯surgery: 0.8", "♯immediate effectiveness: 0.2", and "♯side effects: 0.3" as the standard medical tags and their feature amounts. The acquisition function 151 adds the standard medical tag of "♯medicine: 0.1" and its feature amount based on the examination information.

[0048] The acquisition function 151 extracts important medical terms shown in the clinical practice guidelines in advance and sets them as standard medical tags. The acquisition function 151 weights the standard medical tags based on the important medical terms included in the clinical practice guidelines. The acquisition function 151 weights, for example, the feature amounts of the medical terms that become standard medical tags included in the summary document and the detailed document included in the clinical practice guidelines by a method such as TF-IDF (Term Frequency - Inverse Document Frequency).

[0049] For example, elements (important medical terms) extracted from the summary document of the clinical practice guidelines may be common with elements (important medical terms) extracted from the detailed document. In this case, for example, the acquisition function 151 adds the average value of the importance of the entire detailed document to the importance of the elements of the summary document and performs weighting as a feature amount of the standard medical tag.

[0050] The acquisition function 151 calculates the feature amount of the standard medical tag included in the patient-preferred treatment method corresponding to the standard medical tag included in the extracted treatment method (hereinafter referred to as the patient-side standard medical tag). When calculating the feature amount of the standard medical tag, the acquisition function 151 formulates the content spoken by the patient during the examination. The acquisition function 151 evaluates the importance of words indicating the standard medical tag included in the acquired patient information, for example, the content spoken by the formulated patient, by a method such as TF-IDF.

[0051] The acquisition function 151 uses the evaluated result as the feature amount of the patient-side standard medical tag. The calculated feature amounts of the standard medical treatment are, for example, "♯transplantation: 0.01", "♯surgery: 0.01", "♯immediate effect: 0.5", "♯side effect: 0.3", "♯medicine: 0.9". The acquisition function 151 may calculate the importance and feature amount by another method instead of TF-IDF, for example, morphological analysis.

[0052] Furthermore, the acquisition function 151 extracts words that become private tags from words other than the words indicating the standard medical tag included in the content spoken by the formulated patient. The acquisition function 151 calculates and acquires the feature amount of each tag (word) included in each private tag. In the example shown in FIG. 3, the acquisition function 151 acquires "♯hobby: 0.9" and "♯mountain climbing: 0.8" as the tag and its feature amount.

[0053] The acquisition function 151 filters patient information in order to generate timing information in the generation function 152. The acquisition function 151 extracts, by filtering, terms that affect the patient's emotions (hereinafter referred to as influencing terms) from the patient information. The generation function 152 analyzes the influencing terms extracted by filtering and calculates the change in the patient's emotions.

[0054] When a certain period has elapsed, the generation function 152 generates timing information indicating the timing of a follow-up visit. The generation function 152 determines, at an appropriate timing, whether or not the change in the patient's emotions exceeds a threshold value. When the change in the patient's emotions exceeds the threshold value, the generation function 152 creates the timing of a follow-up visit at which the patient receives a follow-up visit and generates timing information indicating the timing of the follow-up visit. The criterion for creating the timing of a follow-up visit may be other than whether or not the change in the patient's emotions exceeds the threshold value. For example, it may be whether or not the change in the patient's emotions deviates from the predicted distribution.

[0055] Furthermore, in the second phase, the generation function 152 generates recommendation information. When generating the recommendation information, the generation function 152 calculates, for example, the similarity between the feature amounts of the doctor-side standard medical tags and the feature amounts of the patient-side standard medical tags using the vectors of each word (medical term).

[0056] The generation function 152 sets, for example, the feature amount of the doctor-side standard medical tag as "a" and the feature amount of the patient-side standard medical tag as "b". The generation function uses the feature amounts "a" and "b" to calculate the similarity between the feature amount of the doctor-side standard medical tag and the feature amount of the patient-side standard medical tag according to the following formula (1). cos(a,b)=a·b / ||a||||b|| ···(1)

[0057] The generation function 152 generates recommendation information according to the calculated similarity. For example, when the similarity calculated by the generation function 152 is within the range of "0" or more and less than "0.3" (hereinafter referred to as the low similarity range), it is determined that the degree of agreement between the doctor-recommended treatment method and the patient's preferred treatment method is low. In such a case, information for the doctor to understand how much the doctor-recommended treatment method does not match the patient's preferred treatment method is generated as the recommendation information.

[0058] When the degree of agreement between the doctor-recommended treatment method and the patient's preferred treatment method is low, in the treatment by standard medicine, there is a possibility of giving anxiety to the patient. Therefore, when the generation function 152 is within the low similarity range hereinafter, information such as the patient's interests and concerns about the treatment, for example, prognosis, transplantation, etc., is generated as the recommendation information.

[0059] When the calculated similarity is within the low similarity range, the generation function 152 generates, for example, information regarding the medical terms with a high degree of agreement between the doctor-recommended treatment method and the patient's preferred treatment method and the medical terms with a low degree of agreement (high degree of divergence) among the calculated similarity (numerical value) and the medical terms shown in the standard medical tag as the recommendation information. The similarity is mainly information serving as an index for the doctor to understand the necessity of explaining the treatment method to the patient, in other words, how much the doctor-recommended treatment method does not match the patient's preferred treatment method.

[0060] The medical terms with a high degree of agreement between the doctor-recommended treatment method and the patient's preferred treatment method are mainly information for the doctor to confirm that they are treatment methods commonly recognized between the doctor and the patient. The medical terms with a low degree of agreement between the doctor-recommended treatment method and the patient's preferred treatment method are information for the doctor to confirm that there is a divergence in the understanding of the treatment method between the doctor and the patient. When there are medical terms with a low degree of agreement between the doctor-recommended treatment method and the patient's preferred treatment method, the generation function 152 generates recommendation information for clarifying the issues, for example, the patient's interests and concerns about the treatment such as prognosis, transplantation, etc., when the patient makes a treatment decision.

[0061] The generation function 152 may generate recommendation information that clarifies the patient's interests and concerns regarding treatment, which are issues to be overcome during consensus formation, for standard medical tags with large feature amounts of patient-side standard medical tags and small feature amounts of physician-side standard medical tags, particularly for medical terms with a low degree of agreement between the physician-recommended treatment method and the patient-preferred treatment method. The generation function 152 modifies the recommendation information generated here based on private tags. Private tags are, for example, information used to imagine the patient's desired form of treatment and select a treatment method along that image.

[0062] For example, when the calculated similarity is within the range of "0.3" or more and less than "0.7" (hereinafter, the medium similarity range), the generation function 152 determines that the degree of agreement between the physician-recommended treatment method and the patient-preferred treatment method is medium. In such a case, the generation function 152 generates information for supporting the patient's medical decision-making as recommendation information.

[0063] When the calculated similarity is within the medium similarity range, the generation function 152 generates, for example, information regarding medical terms with a low degree of agreement (high degree of divergence) between the physician-recommended treatment method and the patient-preferred treatment method among the calculated similarity (numerical value) and the medical terms indicated by the standard medical tag as recommendation information. Regarding medical terms with a low degree of agreement between the physician-recommended treatment method and the patient-preferred treatment method, the generation function 152 generates, for example, information for supporting the patient's decision-making as recommendation information, which is different from the case where the similarity is within the low similarity range. The generation function 152 modifies the generated recommendation information based on private tags.

[0064] For example, when the calculated similarity is within the range of "0.7" or more and "1.0" or less (hereinafter, the high similarity range), the generation function 152 determines that the degree of agreement between the physician-recommended treatment method and the patient-preferred treatment method is high. In such a case, the generation function 152 generates recommendation information including information on the treatment method of standard medicine.

[0065] When the calculated similarity is within the high similarity range, the generation function 152 generates, as recommendation information, for example, the calculated similarity (numerical value), medical terms indicated in the standard medical tags where the degree of agreement between the physician-recommended treatment method and the patient's desired treatment method is low (the degree of divergence is high), and information regarding the treatment methods of standard medicine. The generation function 152 corrects the generated recommendation information based on the private tags.

[0066] In the subsequent third phase, the presentation function 153 presents the recommendation information generated by the generation function 152 to the physician, such as by causing it to be displayed on the display 140. For example, when the calculated similarity is within the low similarity range, the presentation function 153 causes the display 140 to display recommendation information regarding the similarity, medical terms with a high degree of agreement, and medical terms with a low degree of agreement. While looking at the recommendation information displayed on the display 140, the physician prepares for the interview with the patient. In this case, the physician proceeds with the preparation for the interview, centering around, for example, the patient's interests and concerns.

[0067] For example, when the calculated similarity is within the medium similarity range, the presentation function 153 causes the display 140 to display recommendation information regarding medical terms with a low degree of agreement and private tags. While looking at the recommendation information displayed on the display 140, the physician prepares for the interview with the patient. In this case, the physician proceeds with the preparation for the interview, centering around, for example, the point of supporting the patient's decision-making regarding treatment.

[0068] For example, when the calculated similarity is within the high similarity range, the presentation function 153 causes the display 140 to display recommendation information regarding medical terms with a low degree of agreement, private tags, and standard medicine. While looking at the recommendation information displayed on the display 140, the physician prepares for the interview with the patient. In this case, the physician proceeds with the preparation for the interview, centering around, for example, the point of explaining the content of standard medicine.

[0069] The prompting function 153 determines whether the timing information has been generated by the generation function 152. When it is determined that the timing information has been generated by the generation function 152, the prompting function 153 causes the display 140 to display the reexamination timing indicated by the timing information. The prompting function 153 further determines whether the reexamination timing has arrived. When it is determined that the reexamination timing has arrived, the prompting function 153 causes the display 140 to display a warning indicating that the reexamination timing has arrived, outputs an alert to the speaker, or vibrates the vibrator.

[0070] In addition to being displayed on the display 140, the timing information may be notified to the patient terminal 20 held by the patient. In this case, the patient terminal 20 that has received the timing information may display information corresponding to the timing information on a display (touch panel) or output an alert.

[0071] Subsequently, the processing in the patient intention reflection support device 100 will be described. FIG. 4 is a flowchart showing an example of the processing of the patient intention reflection support device 100. First, in the acquisition function 151, the patient intention reflection support device 100 acquires examination information (step S101), and subsequently acquires patient information (step S103).

[0072] Subsequently, the acquisition function 151 sets doctor-side standard medical tags based on the summary document and the detailed document included in the medical treatment guideline (step S105). Subsequently, the acquisition function 151 extracts the feature amount (importance) of the standard medical tags included in the recommended treatment method (step S107), and extracts the feature amount (importance) of the patient-side standard medical tags (step S109).

[0073] Subsequently, the generation function 152 calculates the similarity between the feature amounts of the doctor-side standard medical tags and the feature amounts of the patient-side standard medical tags (step S111). Subsequently, the generation function 152 generates recommendation information according to the calculated similarity of the feature amounts, for example, recommendation information on the similarity of the feature amounts included in the low similarity range, recommendation information on the similarity of the feature amounts included in the medium similarity range, and recommendation information on the similarity of the feature amounts included in the high similarity range (step S113).

[0074] Subsequently, the generation function 152 acquires patient information and generates private tags included in the patient information (step S115). Subsequently, the generation function 152 calculates the feature amounts of the standard tags included in the private tags (step S117). Subsequently, the generation function 152 corrects the generated recommendation information based on the calculated feature amounts (step S119). Subsequently, the presentation function 153 presents the recommendation information generated and corrected by the generation function 152 to the doctor, such as by displaying it on the display 140 (step S121).

[0075] Furthermore, the generation function 152 filters the patient information (step S123) and extracts influencing terms. The generation function 152 analyzes the extracted influencing terms to calculate the change in the patient's emotion. The generation function 152 generates timing information based on the calculated change in the patient's emotion (step S125) and presents the generated timing information to the doctor, such as by displaying it on the display 140 (step S127). Thus, the patient intention reflection support device 100 ends the process shown in FIG. 4.

[0076] Subsequently, the process of generating timing information will be described. The timing information is generated periodically, for example, by the generation function 152 when a certain period of time has elapsed. Here, in addition to generating timing information periodically, an example of generating timing information will be described.

[0077] FIG. 5 is a flowchart showing an example of a process of generating timing information. The acquisition function 151 first extracts persuasive terms from patient information (step S201). Subsequently, the generation function 152 analyzes the extracted persuasive terms and calculates the change in the patient's emotion (step S203).

[0078] Subsequently, the generation function 152 determines whether the change in the patient's emotion is large and exceeds a threshold value (step S205). If it is determined that the change in the patient's emotion does not exceed the threshold value, the generation function 152 returns the process to step S201. If it is determined that the change in the patient's emotion exceeds the threshold value, the generation function 152 creates a follow-up timing and generates timing information. Thus, the patient intention reflection support device 100 ends the process shown in FIG. 5.

[0079] FIG. 6 is a diagram for explaining the process when a patient receives treatment at a hospital. At the hospital, first, the first visit of the patient is received. After receiving the first visit of the patient, the hospital conducts examinations by doctors and tests by technicians and the like. At the hospital, data based on the results of examinations and tests and the like are collected and accumulated.

[0080] The data to be collected includes, for example, data related to the doctor-recommended treatment method, data related to the patient-preferred treatment method, and data related to the patient's privacy. When the data is collected and accumulated, the data related to the doctor-recommended treatment method is, for example, data indicating the feature amounts of the doctor-side standard medical tags. The data related to the patient-preferred treatment method is, for example, data indicating the feature amounts of the patient-side standard medical tags. The data related to the patient's privacy is, for example, data indicating the feature amounts of each tag included in each privacy tag.

[0081] The patient intention reflection support device 100 analyzes the collected and accumulated data, generates recommendation information and timing information, and presents them to the doctor. The doctor who is presented with the recommendation information and timing information prepares for the interview with the patient based on the recommendation information. After the preparation is complete, the doctor interviews the patient, explains the medical condition, and responds to consultations from the patient.

[0082] After the interview, the doctor treats the patient. After the patient's treatment is completed, the patient waits until the follow-up timing. The follow-up timing may be, for example, when a certain period of time has elapsed since the treatment, or when the follow-up timing generated based on patient information or the like has been reached. The follow-up timing may be, for example, the timing when the patient intention reflection support device 100 stores it and transmits (provides) information to the patient terminal 20 immediately before that, or

[0083] When the follow-up timing arrives, the patient intention reflection support device 100 that stores the follow-up timing notifies the patient terminal 20 of the follow-up information to prompt the patient to have a follow-up visit. The patient terminal 20 notifies the patient by displaying the notified latest information on the display 140 or outputting an alert. The patient who has received the notification undergoes the reception of the follow-up visit at the hospital.

[0084] The patient intention reflection support device 100 of the first embodiment generates recommendation information based on the similarity between the doctor-side standard medical tag and the patient-side standard medical tag. Therefore, it is possible to make it difficult to perform a treatment that is suitable for the treatment but goes against the patient's intention. Furthermore, the patient intention reflection support device 100 creates the follow-up timing according to the change in the patient's emotion. Therefore, it is possible to have a follow-up visit or consult a doctor at a necessary timing such as when the patient becomes anxious.

[0085] (Second Embodiment) Next, the second embodiment will be described. The second embodiment mainly differs from the first embodiment in the calculation method of the standard medical tag of the patient's desired treatment method and the content of the presentation in the presentation function 153. Hereinafter, the second embodiment will be described centering on the differences from the first embodiment. The common points with the first embodiment will be omitted as appropriate.

[0086] FIG. 7 is a diagram showing an example of a step-by-step process from the examination to the agreement formation between the doctor and the patient in the second embodiment. The patient intention reflection support device 100 in the second embodiment multiplies the feature amount of the patient-side standard medical tag by the feature amount of the doctor-side standard medical tag by the acquisition function 151 to generate an adjusted patient-side standard medical tag. In the second phase, the patient intention reflection support device 100 compares the feature amounts of the similarity between the doctor-side standard medical tag and the patient-side standard medical tag to generate recommendation information. The adjusted patient-side standard medical tag is an example of the third information.

[0087] The generation function 152 calculates the similarity between the doctor-side standard medical tag and the adjusted patient-side standard medical tag generated by the acquisition function 151, and performs the same processing as in the first embodiment to generate recommendation information based on the similarity between the two. The feature amount of the adjusted patient-side standard medical tag generated by the acquisition function 151 has a numerical value closer to the feature amount of the doctor-side standard medical tag than the feature amount of the patient-side standard medical tag.

[0088] The recommendation information in the second embodiment includes the numerical values of the feature amounts of the adjusted patient-side standard medical tag and the doctor-side standard medical tag.

[0089] The presentation function 153 presents, for example, the feature amounts of the adjusted patient-side standard medical tag and the doctor-side standard medical tag to the doctor by displaying them on the display 140 in a radar chart. In this way, instead of displaying the similarity, information such as the numerical values that are the basis for obtaining the similarity may be presented. Alternatively, the similarity may be presented together with information such as the information that is the basis for obtaining the similarity.

[0090] The patient intention reflection support device 100 of the second embodiment exhibits the same operational effects as the patient intention reflection support device 100 of the first embodiment. Furthermore, in the patient intention reflection support device 100 of the second embodiment, the feature amount of the adjusted patient-side standard medical tag generated by the acquisition function 151 has a numerical value closer to the feature amount of the doctor-side standard medical tag than the feature amount of the patient-side standard medical tag. Therefore, by calculating the similarity between the feature amount of the adjusted patient-side standard medical tag and the feature amount of the doctor-side standard medical tag, the occurrence of extreme numerical values can be suppressed more effectively than when calculating the similarity between the feature amount of the patient-side standard medical tag and the feature amount of the doctor-side standard medical tag.

[0091] (Third Embodiment) Next, the third embodiment will be described. The third embodiment mainly differs from the first embodiment in that the treatment method performance DB 126 is stored in the memory circuit 120. Furthermore, in the generation function 152, it also differs in that the similarity between the feature amount of the patient-side standard medical tag and the feature amount of the doctor-side standard medical tag is calculated using the treatment method performance DB 126.

[0092] FIG. 8 is a block diagram showing an example of the configuration of the patient intention reflection support device 100 of the third embodiment. In the patient intention reflection support device 100 of the third embodiment, the treatment method performance DB 126 is stored in the memory circuit 120. The treatment method performance DB 126 is a DB that summarizes information on treatment methods when treating diseases in the past. The treatment method performance DB 126 includes, for example, a plurality of pieces of information on treatment performance (hereinafter referred to as treatment performance information) related to treating diseases, such as patient name (patient ID), disease name, treatment method, treatment time, treatment period, etc. Treatment methods include, for example, anti-cancer drug treatment and maintenance therapy.

[0093] The generation function 152 generates recommendation information using the information included in the treatment method performance DB 126 stored in the memory circuit 120. Hereinafter, the processing of the patient intention reflection support device 100 of the third embodiment will be mainly described centering on the processing in the generation function 152. FIG. 9 is a flowchart showing an example of the processing of the patient intention reflection support device 100 of the third embodiment.

[0094] The patient intention reflection support device 100 executes the processes from the process of acquiring examination information (step S101) to the process of calculating the feature amounts of the doctor-side standard medical tags in the same procedure as in the first embodiment. Subsequently, in the generation function 152, the patient intention reflection support device 100 matches patients who have suffered from diseases similar to the current patient's disease among the patients included in the treatment result DB 126 (hereinafter referred to as similar patients) (step S301).

[0095] Subsequently, the generation function 152 extracts the treatment result information of the similar patients from the treatment result DB 126 (step S303). Subsequently, the generation function 152 calculates the feature amounts of the standard medical tags (hereinafter referred to as treatment result standard medical tags) included in the extracted treatment result information (step S305). Subsequently, the generation function 152 calculates the similarity between the calculated feature amounts of the doctor-side standard medical tags and the feature amounts of the treatment result standard medical tags (step S111).

[0096] Thereafter, the patient intention reflection support device 100 executes the processes from the process of generating recommendation information according to the similarity (step S113) to the process of presenting timing information (step S127) in the same manner as in the first embodiment. In this way, the patient intention reflection support device 100 ends the process shown in FIG. 9.

[0097] The patient intention reflection support device 100 of the third embodiment has the same operational effects as the patient intention reflection support device 100 of the first embodiment. Further, in the patient intention reflection support device 100 of the third embodiment, the generation function 152 generates treatment result standard medical tags from the treatment result information of similar patients, calculates the similarity between the feature amounts of the doctor-side standard medical tags and the feature amounts of the treatment result standard medical tags, and generates recommendation information. Therefore, even when there is little information regarding the patient's desired treatment method, it is possible to reflect an intention close to the patient's intention.

[0098] In the third embodiment, recommendation information is generated based on the similarity between the feature amounts of the doctor-side standard medical tags and the feature amounts of the treatment result standard medical tags. However, recommendation information may also be generated in consideration of the similarity between the feature amounts of the patient-side standard medical tags and the feature amounts of the doctor-side standard medical tags. Further, a trouble DB that collects the patient's troubles may be provided, and recommendation information may be generated using the information included in the trouble DB.

[0099] According to at least one of the embodiments described above, an acquisition unit that acquires first information regarding a first treatment method based on at least test results and second information regarding a second treatment method according to the patient's wishes, a generation unit that generates recommendation information according to the relationship between the first information and the second information, and a presentation unit that presents presentation information based on the recommendation information are provided, so that a treatment method that the patient can accept can be determined.

[0100] 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, replacements, and changes can be made without departing from the gist of the invention. These embodiments and their modifications are included in the scope and gist of the invention, and are also included in the invention described in the claims and its equivalent scope.

Explanation of Reference Numerals

[0101] 10 Doctor terminal 20 Patient terminal 100 Patient intention reflection support device 110 NW interface 120 Memory circuit 121 Standard medical DB 122 Test DB 123 Patient DB 124 Doctor-recommended treatment method tag 125 Patient-desired treatment method tag 126 Treatment result DB 130 Input interface 140 Display 150 Processing circuit 151 Acquisition function 152 Generation function 153 Presentation function LAN wired NW network

Claims

1. An acquisition unit that acquires at least first information regarding a first treatment method based on an examination result and second information regarding a second treatment method according to a patient's preference; A generation unit that generates recommendation information according to the relationship between the first information and the second information; A presentation unit that presents presentation information based on the recommendation information, A patient intention reflection support device.

2. The generation unit generates recommendation information according to the similarity between the first information and the second information. The patient intention reflection support device according to Claim 1.

3. The first treatment method is a treatment method based on standard medicine. The patient intention reflection support device according to Claim 2.

4. The generation unit generates recommendation information regarding a treatment method closer to the standard medicine as the similarity is higher. The patient intention reflection support device according to Claim 3.

5. The generation unit generates recommendation information regarding a treatment method closer to the second treatment method as the similarity is lower. The patient intention reflection support device according to Claim 3.

6. The generation unit creates the timing of a follow-up visit for the patient based on patient information regarding the patient. The patient intention reflection support device according to Claim 1.

7. The generation unit generates recommendation information according to the relationship between third information obtained by multiplying the first information by the second information and the first information, instead of the second information. The patient intention reflection support device according to Claim 1.

8. The acquisition unit extracts similar patients similar to the patient. The generation unit generates recommendation information according to the relationship between treatment result information regarding the treatment results of the similar patients instead of the second information and the first information. The patient intention reflection support device according to Claim 1.

9. A computer acquires at least first information regarding a first treatment method based on an examination result and second information regarding a second treatment method according to a patient's preference; generates recommendation information according to the relationship between the first information and the second information; presents presentation information based on the recommendation information, A patient intention reflection support method.

10. Causes a computer to acquire at least first information regarding a first treatment method based on an examination result and second information regarding a second treatment method according to a patient's preference; generate recommendation information according to the relationship between the first information and the second information; present presentation information based on the recommendation information, A program.

Images