Medical information management device, medical information information management method, and program

Abstract

To specify past anamnesis of a patient even in the case that a medical record of the patient cannot be referred to.SOLUTION: According to an embodiment, a medical information management device includes an acquisition part, a collection part, an extraction part, a first estimation part, and an output part. The acquisition part acquires medical examination information related to a present disease of a patient. The collection part collects past information related to past medical treatment or health of the patient on the basis of the medical examination information. The extraction part extracts date information related to a date on which the past information is generated or recorded from the past information. The first estimation part estimates anamnesis of the patient from medical treatment technology information related to a medical treatment technology of a period corresponding to the extracted date information. The output part outputs the estimated anamnesis.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Traditionally, medical records have been required by the Medical Practitioners Act to be kept for five years from the date medical treatment is completed, and can be destroyed once the retention period has expired. Even if the retention period has not yet expired, medical records may be lost due to reasons such as a hospital being damaged in a natural disaster. Generally, when past medical records are unavailable and a patient's current symptoms are thought to be related to a patient's past medical history, doctors may seek out the patient's past medical history by asking the patient or their family questions or by contacting other medical institutions the patient has visited in the past. However, when the patient or their family members are unsure of their memories, or when medical records have already been destroyed at other medical institutions, it can be difficult to identify past medical history information using these methods.

[0003] Furthermore, MRI (Magnetic Resonance Imaging) scans may not be possible if the patient has metal or other objects placed inside their body. If a patient's past medical records cannot be accessed, it may be difficult to perform an MRI scan, as it is not known what types of devices remain inside the patient's body from previous surgeries, etc. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Publication No. 2021-135989 Summary of the Invention [Problem to be solved by the invention]

[0005] One of the problems to be solved by the embodiments disclosed in this specification and the drawings is to identify a patient's past medical history even when the patient's medical record cannot be referenced. However, the problems to be solved by the embodiments disclosed in this specification and the 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]

[0006] A medical information management device according to an embodiment includes an acquisition unit, a collection unit, an extraction unit, a first estimation unit, and an output unit. The acquisition unit acquires medical information related to a patient's current illness. The collection unit collects past information related to the patient's past medical care or health based on the medical information. The extraction unit extracts date information related to the date on which the past information was generated or recorded from the past information. The first estimation unit estimates the patient's medical history from medical technology information related to medical technology at the time corresponding to the extracted date information. The output unit outputs the estimated medical history. [Brief explanation of the drawings]

[0007] [Figure 1] FIG. 1 is a diagram illustrating an example of the configuration of a medical information management apparatus according to the first embodiment. [Figure 2] FIG. 2 is a diagram showing an example of a weighting criterion based on the reliability of an information source according to the first embodiment. [Figure 3] FIG. 3 is a flowchart showing an example of the flow of the medical history estimation process performed by the medical information management apparatus according to the first embodiment. [Figure 4] FIG. 4 is a flowchart showing an example of the flow of a medical history estimation process performed by the medical information management apparatus according to the second embodiment. [Figure 5] FIG. 5 is a diagram showing an example of an input screen for medical information according to the third embodiment. [Figure 6] FIG. 6 is a flowchart showing an example of the flow of a medical history estimation process performed by a medical information management apparatus according to the third embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0008] Hereinafter, embodiments of a medical information management device, a medical information management method, and a program will be described in detail with reference to the drawings.

[0009] (First embodiment) 1 is a diagram showing an example of the configuration of a medical information management device 1 according to the first embodiment. The medical information management device 1 is used, for example, in a medical institution such as a hospital. The medical information management device 1 of this embodiment estimates the medical history of a patient related to the current symptoms of the patient for whom past medical records cannot be referenced.

[0010] The medical information management device 1 is, for example, a server device or a computer such as a PC (Personal Computer). As shown in Fig. 1, the medical information management device 1 includes an NW (network) interface 110, an input interface 120, a display 130, a memory circuit 140, and a processing circuit 150.

[0011] The NW interface 110 is connected to the processing circuit 150 and controls the transmission and communication of various data between the medical information management device 1 and external devices. The NW interface 110 is realized by a network card, a network adapter, a NIC (Network Interface Controller), etc.

[0012] The input interface 120 may be implemented by a pen tablet (drawing tablet) that combines a touch pen and tablet for accepting user operations, a trackball, switch buttons, a mouse, a keyboard, a touchpad that performs input operations by touching the operation surface, a touchscreen that integrates a display screen and a touchpad, a non-contact input circuit using an optical sensor, and a voice input circuit. The input interface 120 may include multiple devices that accept user operations. The input interface 120 is connected to the processing circuit 150 and converts input operations received from the user into electrical signals and outputs them to the processing circuit 150. Note that, in this specification, the input interface is not limited to those that have physical operating components such as a mouse and keyboard. For example, an electrical signal processing circuit that receives electrical signals corresponding to input operations from an external input device provided separately from the device and outputs these electrical signals to the processing circuit 150 is also included as an example of an input interface.

[0013] The display 130 displays various types of information under the control of the processing circuit 150. For example, the display 130 outputs a GUI (Graphical User Interface) or the like for receiving various operations from a user. Specifically, the display 130 is a liquid crystal display, a CRT (Cathode Ray Tube) display, or the like. The input interface 120 and the display 130 may be integrated together. For example, the input interface 120 and the display 130 may be realized by a touch panel. The display 130 is an example of a display unit.

[0014] The memory circuitry 140 stores in advance various types of information to be used by the processing circuitry 150. The memory circuitry 140 also stores various programs. The memory circuitry 140 is, for example, a storage device such as an HDD (Hard Disk Drive), an SSD (Solid State Drive), or an integrated circuit storage device that stores various types of information. In addition to an HDD or SSD, the memory circuitry 140 may also be a drive device that reads and writes various types of information from / to portable storage media such as a CD (Compact Disc), a DVD (Digital Versatile Disc), or a flash memory, or a semiconductor memory element such as a RAM (Random Access Memory).

[0015] The storage circuitry 140 also stores a disease-specific symptom database (DB) 141. The disease-specific symptom database 141 is a database in which disease names and symptoms are associated with each other.

[0016] The processing circuitry 150 is a processor that reads out programs from the storage circuitry 140 and executes them to realize functions corresponding to each program. The processing circuitry 150 of this embodiment includes an acquisition function 151, a generation function 152, a collection function 153, an extraction function 154, a first estimation function 155, a second estimation function 156, and a display control function 157. The acquisition function 151 is an example of an acquisition unit. The generation function 152 is an example of a generation unit. The collection function 153 is an example of a collection unit. The extraction function 154 is an example of an extraction unit. The first estimation function 155 is an example of a first estimation unit. The second estimation function 156 is an example of a second estimation unit. The display control function 157 is an example of an output unit and a display control unit.

[0017] Here, for example, each of the processing functions of the processing circuitry 150, namely, the acquisition function 151, the generation function 152, the collection function 153, the extraction function 154, the first estimation function 155, the second estimation function 156, and the display control function 157, is stored in the storage circuitry 140 in the form of a computer-executable program. The processing circuitry 150 is a processor. For example, the processing circuitry 150 realizes the function corresponding to each program by reading the program from the storage circuitry 140 and executing it. In other words, the processing circuitry 150 in a state in which each program has been read has each function shown in the processing circuitry 150 of FIG. 1. Note that, although FIG. 1 illustrates the processing functions performed by the acquisition function 151, the generation function 152, the collection function 153, the extraction function 154, the first estimation function 155, the second estimation function 156, and the display control function 157 being realized by a single processor, the processing circuitry 150 may be configured by combining multiple independent processors, and each processor may realize a function by executing a program. Furthermore, although FIG. 1 illustrates a single memory circuit 140 storing a program corresponding to each processing function, multiple memory circuits may be distributed and arranged, and the processing circuit 150 may read out the corresponding program from each memory circuit.

[0018] In the above description, an example has been described in which a "processor" reads and executes a program corresponding to each function from the storage circuitry 140, but the embodiment is not limited to this. The term "processor" refers to a circuit such as a central processing unit (CPU), a graphics processing unit (GPU), an application specific integrated circuit (ASIC), a programmable logic device (e.g., a simple programmable logic device (SPLD), a complex programmable logic device (CPLD), and a field programmable gate array (FPGA)). If the processor is a CPU, for example, the processor realizes the function by reading and executing a program stored in the storage circuitry. On the other hand, if the processor is an ASIC, instead of storing the program in the storage circuitry 140, the function is directly incorporated as a logic circuit within the processor circuitry. Note that each processor in this embodiment is not limited to being configured as a single circuit per processor, but may be configured as a single processor by combining multiple independent circuits to realize its function. Furthermore, the functions of the multiple components in FIG. 1 may be realized by integrating them into a single processor.

[0019] The medical information management device 1 is communicably connected to record information 2 including public medical records and private records, and medical technology information 3 via a network N such as the Internet.

[0020] Record information 2 is a general term for information including public medical records and private records. Public medical records are records created and stored by health insurance associations, hospitals, pharmacies, etc. Private records are records created by patients or people close to patients (e.g., their relatives). Private records include those stored on systems that require patient authentication information for viewing.

[0021] Record information 2 may include, for example, medical fee statement information 21, medical fee statement information 22, medical interview records 23 from various health checkups, SNS (Social Networking Service) 24, and personal schedule 25. Record information 2 may also include various health checkup results, the patient's medical records recorded at other medical institutions, prescription records, receipts, consent forms, diagnostic images, images of treatment scars left on the patient's body surface, personal diaries, personal blogs, and the like. The SNS 24, personal schedule 25, personal diary, and personal blog may be written by the patient himself or by someone close to the patient, such as a relative of the patient. These are just examples of record information 2, and other information may also be included as long as it is a record of the patient's past medical records, past actions, and past physical conditions, including date information.

[0022] The date information included in the record information 2 is information about the date on which each piece of information was generated or recorded. The date information includes not only information that can identify the year, month, and day, but also information that can identify the year or decade. Records of the patient's past behavior are, for example, records of hospital visits, illnesses, and injuries written in Schedule 25, SNS 24, diary, etc. Records of the patient's past physical condition may be, for example, records written by the patient in Schedule 25, SNS 24, diary, etc., such as "xx hurts" or "I had blood in my urine." Record information 2 may be any one of these pieces of information, or a combination of multiple pieces. This information may be generated in advance as digital data, or may be written on paper and then digitized using means such as OCR (optical character recognition).

[0023] The medical technology information 3 is information that associates technical information related to medical care with the date or era when the technical information was created or published. The medical technology information 3 includes, for example, clinical practice guidelines 31 and a medical device catalog 32. Medical devices are, for example, various devices that are placed on a patient's body during surgery or other procedures. In this embodiment, placing a medical device on a patient's body refers to a state in which the medical device remains inserted or implanted in the patient's body in a manner that makes it difficult to remove. In other words, various devices that are temporarily inserted into the body during examination or treatment and then immediately removed, and various devices that can be easily removed using non-surgical techniques, are not said to be placed on the patient's body.

[0024] In addition, medical technology information 3 may also include a database of package inserts for medical devices, medical drugs, and in vitro diagnostic drugs, a database of medical fee points, and medical records of other patients. Medical records of other patients are medical records of other patients who visited the same medical institution as the patient in question at the same time in the past and for whom medical records still exist. Medical technology information 3 may be any one of these pieces of information, or a combination of multiple pieces of information. This information may be generated in advance as digital data, or may be written on paper and digitized using OCR or other means.

[0025] 1 shows that the record information 2 and the medical technique information 3 are stored outside the medical information management device 1, but some or all of the record information 2 and the medical technique information 3 may be stored in the memory circuit 140 of the medical information management device 1. For example, past medical records, prescription notebooks, receipts, consent forms, etc. that the patient or the patient's family brings from home may be registered in the medical information management device 1.

[0026] In addition, the medical information management device 1 may be communicatively connected to an electronic medical record system, a specimen management system, a hospital information system (HIS), a laboratory information system (LIS), a radiology information system (RIS), etc. via a network such as an in-hospital LAN (Local Area Network).

[0027] Next, the functions realized by each component of the processing circuit 150 of the medical information management device 1 will be described.

[0028] The acquisition function 151 acquires medical information related to the patient's current illness. In this embodiment, "illness" also includes trauma. The medical information includes at least the patient's current symptoms, the name of a disease the patient may currently be suffering from, or a medical procedure the patient may have undergone in the past. As a specific example, the medical information may be medical images of the patient, blood test results, a medical questionnaire, a doctor's findings, a diagnosis, etc. The medical questionnaire includes the patient's chief complaint and other subjective symptoms. The acquisition function 151 may acquire the medical information from an electronic medical record system, or may acquire medical information input by a doctor via the input interface 120.

[0029] The acquisition function 151 may also acquire authentication information required to log in to the record information 2. The authentication information may be, for example, a login ID and a password. The acquisition function 151 may also acquire various types of identification information required to identify the information of the target patient from the record information 2. The identification information may be, for example, the patient's name, the patient's nickname on a blog or social media, a photo of the patient's face, the patient's My Number, the patient's health insurance card number, the patient card number from medical institutions where the patient has previously been treated, the employee ID number from a previous employer, etc. This authentication information and identification information are entered into the medical information management device 1 with the consent of the patient or the patient's relatives.

[0030] The generation function 152 generates, from the acquired medical information, search information that can search the record information 2. The search information is, for example, text data that includes keywords related to the patient's current or past illnesses.

[0031] The generation function 152 generates keywords, for example, by inputting medical information into a trained model. The trained model is, for example, a large language model (LLM), but is not limited to this, and various deep learning or machine learning models can be applied. The trained model is a model that has learned medical information and words that may be used in record information 2 in relation to the medical information. For example, the trained model may have learned symptoms, names of diseases that may cause the symptoms, synonyms that express the symptoms, names of organs related to the symptoms, etc.

[0032] In addition, the generation function 152 may generate search terms using a rule-based algorithm rather than a trained model, or a database that stores words contained in medical information in correspondence with words that may be used in record information 2.

[0033] The collection function 153 collects past information about the patient's past medical care or health based on the acquired medical information. More specifically, the collection function 153 uses the search information generated by the generation function 152 to search for various records included in the record information 2. For example, the collection function 153 uses a keyword to collect information including the keyword from the record information 2.

[0034] As described above, the record information 2 may include systems such as SNS that require login, and the collection function 153 logs into the system using the patient's authentication information acquired by the acquisition function 151 and collects past information using search information. The collection function 153 may also limit the target information from the record information 2 using various IDs such as the patient's My Number, health insurance card number, or employee ID number from a previous employer, and then use keywords to collect information containing the keywords from the patient's public medical records or private records.

[0035] The search results obtained by searching the record information 2 by the collection function 153 are called past information. The past information is information from the record information 2 that relates to the past medical care or health of the target patient.

[0036] The extraction function 154 extracts date information relating to the date on which the past information was created or recorded from the past information. For example, the extraction function 154 obtains the date information relating to the date on which the past information was created or recorded by reading a tag relating to a date embedded in the electronic data or by means of text analysis or the like. The date information is not limited to information that can identify the year, month, and day, but may also be information that can identify the year or decade.

[0037] The first estimation function 155 estimates the patient's medical history from medical technology information 3 related to medical technology for the period corresponding to the extracted date information. The medical history includes, for example, information on diseases that the patient is estimated to have suffered from in the past, the time of onset, and tests or treatments that the patient may have undergone in the past, and the time of onset. Hereinafter, past diseases and medical procedures may be collectively referred to as "diseases, etc." In this embodiment, the first estimation function 155 estimates the patient's past medical history based on past information searched using search information generated from the patient's current medical information and medical technology information 3 for the period corresponding to the date information of the past information. Therefore, the first estimation function 155 estimates those of the patient's entire past medical history that are related to the patient's current disease.

[0038] More specifically, the first estimation function 155 estimates the name of an injury or illness from the past information retrieved by the collection function 153. The first estimation function 155 then obtains information about examinations, treatments, etc., that were performed at the time of the extracted date information by collecting information related to the estimated name of an injury or illness from the medical technology information 3. For example, the clinical practice guidelines 31 may describe different treatment methods for the same illness over different periods. Furthermore, the medical device catalog 32 discloses different products over different periods. Therefore, the first estimation function 155 can obtain information about examinations, treatments, etc., that the patient may have received in the past by collecting information from the medical technology information 3 limited by date information.

[0039] Furthermore, when multiple pieces of past information about a patient's past medical care or health are obtained by the collection function 153, the first estimation function 155 will adopt all of them if the contents match, but if the contents do not match, the first estimation function 155 may select them by weighting them based on the reliability of the information source, etc. The contents of multiple pieces of past information that match include cases where the contents of the multiple pieces of past information are identical and cases where the multiple pieces of past information are consistent with each other. For example, if the multiple pieces of past information are about different diseases that the patient suffered from at different times, they will not contradict each other. Also, for example, if multiple pieces of past information corresponding to the same date information each describe different treatment details, the multiple pieces of past information will not match because they are inconsistent.

[0040] 2 is a diagram showing an example of a weighting standard based on the reliability of information sources according to the first embodiment. As a weighting standard, official medical records including records of diagnosis results or actual treatments are the most reliable and therefore are weighted the most heavily. The level of reliability is also referred to as the reliability.

[0041] Examples of official medical records that include records of diagnosis or actual treatment include medical fee statement information 21, medical fee statement information 22, prescription notebooks, receipts, consent forms, diagnostic images, and medical records of the patient recorded at other medical institutions. Next, medical records that do not include diagnosis results are weighted more heavily. Examples of medical records that do not include diagnosis results include interview records from various health checkups, various health checkup results, and images of treatment scars left on the patient's body surface. Finally, personal records are weighted least heavily. Examples of personal records include personal diaries, personal blogs, social media accounts 24, and personal schedules 25. For example, if the treatment details recorded in a private record such as a patient's blog differ from the treatment details received by the patient recorded in the medical fee statement information 21, the first estimation function 155 will prioritize the treatment details recorded in the medical fee statement information 21.

[0042] The collection function 153, the extraction function 154, and the first estimating function 155 may be realized, for example, by a search support AI (Artificial Intelligence) having an automatic web search function. In this case, the collection function 153, the extraction function 154, and the first estimating function 155 may all be realized consistently by a single search support AI, or only a part of the collection function 153, the extraction function 154, and the first estimating function 155 may be realized by a search support AI. Furthermore, the collection function 153, the extraction function 154, and the first estimating function 155 may be realized by a combination of multiple AIs. Alternatively, the collection function 153, the extraction function 154, and the first estimating function 155 may each be functions realized by a logic-based program.

[0043] The second estimation function 156 estimates the name of the patient's current disease based on the patient's current medical information acquired by the acquisition function 151 and the patient's medical history estimated by the first estimation function 155. The second estimation function 156 may be realized by a diagnostic support AI. The diagnostic support AI may be, for example, an AI system including a trained model that has learned the medical information and medical history of multiple patients and the disease names of the multiple patients. Alternatively, the second estimation function 156 may be a function realized by a logic-based program.

[0044] The display control function 157 displays various screens on the display 130. For example, the display control function 157 displays the patient's medical history estimated by the first estimation function 155 and the name of the patient's current illness estimated by the second estimation function 156. Note that the method of outputting the estimation results of the patient's past medical history and the estimation results regarding the current illness is not limited to displaying them on the display 130, and may be transmitting them to another information processing device, etc.

[0045] Next, the flow of the medical history estimation process performed by the medical information management device 1 configured as above will be described.

[0046] 3 is a flowchart showing an example of the flow of the medical history estimation process performed by the medical information management device 1 according to the first embodiment. Below, the flow of the estimation process will be explained, taking as a specific example a case where the medical information management device 1 estimates the past medical history of patient A (an 85-year-old male) for whom at least a portion of his past medical records has been discarded.

[0047] For example, suppose patient A's chief complaint is macroscopic hematuria. The doctor performs abdominal X-rays, abdominal ultrasound, blood tests, etc. on patient A and confirms that there are no causes such as malignant tumors, stones, medications, or viruses in the kidneys, ureters, or bladder. Because patient A has no abdominal surgical scars, the doctor determines that there is no history of illness that would require abdominal surgery. Since it is necessary to know the cause of the hematuria in order to treat it, the doctor asks patient A about his medical history, but because patient A has dementia, the doctor is unable to obtain a satisfactory answer. Furthermore, the doctor uses patient A's patient card from another hospital to inquire about patient A's medical history, but is unable to obtain any information because the other hospital has already discarded patient A's medical records. The doctor then attempts to identify patient A's medical history using medical information management device 1.

[0048] First, the acquisition function 151 acquires medical information related to the patient's current illness (S1). For example, the acquisition function 151 acquires information input by a doctor, such as the fact that patient A's chief complaint is macroscopic hematuria, various medical images of patient A, blood test results, etc.

[0049] Next, the generation function 152 generates search keywords based on the acquired medical information (S2). Here, the doctor, who is the user, may specify information from the medical information that will be the source of generation of the search keywords. For example, the display control function 157 may display on the display 130 an operation screen that allows the doctor to specify or input information that will be the source of generation of the search keywords. The instruction to create search keywords may be given in the form of the doctor inputting a text question.

[0050] For example, if the search keyword generation function is implemented using a large-scale language model, suppose a doctor asks for search keywords related to "hematuria." In this case, the generation function 152 inputs the received question into the large-scale language model. The generation function 152 then acquires the search keywords output by the large-scale language model. Keywords related to a chief complaint, such as "hematuria," include, but are not limited to, variations of the chief complaint, synonyms of the chief complaint, names of diseases that cause the chief complaint, names of categories that encompass the disease, and names of organs related to the disease or the chief complaint. The generation function 152 generates keywords such as "hemoglobinuria," "hemolinuria," "microscopic hematuria," "grossscopic hematuria," "urinary tract stones," "tumorous hematuria," "infectious hematuria," "urinary tract infection," "liver disease," "kidney disease," "prostate," "PSA (Prostate-Specific Antigen)," "urethra," "urinary system disease," "blood in urine," and "red urine." These keywords are used to search the patient's public medical records and private records contained in record information 2, so the generation function 152 generates a group of keywords that can be used to search for information related to "hematuria" widely, from terms used in public information to colloquial expressions used in general information. Note that the medical information from which search keywords are generated is not limited to the chief complaint, and may be, for example, the diagnosis of the patient's current illness or numerical values ​​from blood test results, etc.

[0051] Next, the acquisition function 151 acquires authentication information for logging in to the searched system (S3). The acquisition function 151 may also acquire identification information such as the patient's name, the patient's nickname on a blog or social networking site, a photograph of the patient's face, the patient's Individual Number (My Number), health insurance card number, patient registration card numbers from medical institutions visited in the past, and employee ID numbers from previous employers. This authentication information and identification information are input into the medical information management device 1 with the consent of the patient or the patient's relatives. The acquisition function 151 may acquire the authentication information and identification information from an input screen displayed on the display 130 by the display control function 157, for example. Alternatively, the authentication information and identification information provided by the patient or the patient's relatives may be stored in advance in the memory circuitry 140, and the acquisition function 151 may acquire the authentication information and identification information from the memory circuitry 140.

[0052] Next, the collection function 153 uses the generated keywords to search for various records included in the record information 2 (S4). At this time, the collection function 153 logs in to the search target SNS 24 or the like using the patient's authentication information. In addition, in order to identify the patient's information in the record information 2, the collection function 153 may use identification information for search or authentication, such as the patient's name, the patient's nickname on the blog or SNS, the patient's facial photo, the patient's My Number, health insurance card number, patient card numbers from medical institutions where the patient has previously been treated, and employee ID numbers from previous employers.

[0053] Here, for example, it is assumed that the collection function 153 was able to access the corporate health checkup results using the ID information of the health insurance association to which patient A belonged. The collection function 153 searches the found corporate health checkup results using the keyword group generated in S2. Here, it is assumed that the search result shows that a medical history of "prostate cancer" was found in the medical interview section of the corporate health checkup results that patient A had previously undergone. The data in the medical interview section of the corporate health checkup results, which includes a description of the medical history of "prostate cancer," is an example of patient A's past information.

[0054] Then, the extraction function 154 extracts date information from the search results by the collection function 153 (S5). For example, the extraction function 154 may read date-related tags embedded in the electronic data of past information obtained by searching record information 2. The extraction function 154 may also obtain date information of information obtained by medical record source search by means of text analysis or the like. Here, for example, the extraction function 154 identifies the date of issuance of the corporate health checkup results obtained by the search, including the description of "prostate cancer," as September 2000 from the tag of the electronic data and extracts it. The extraction function 154 also identifies the date information indicating when the patient was diagnosed with prostate cancer as June 1995 by text analysis and extracts it.

[0055] Then, when multiple pieces of past information about the patient have been collected by the collection function 153 (S6 "Yes") and the contents of the multiple pieces of past information do not match (S7 "No"), the first estimation function 155 performs weighting based on the reliability of the information source (S8). When only one piece of past information has been collected (S6 "No") or when the contents of the multiple pieces of past information match (S7 "Yes"), the first estimation function 155 does not perform any particular weighting and adopts the collected past information.

[0056] The first estimation function 155 then estimates the patient's medical history based on the collected past information and medical technology information from the period corresponding to the date information extracted from the past information (S9). For example, the first estimation function 155 determines that, based on the prostate cancer treatment guidelines at the time of the extracted date information (1995), radical prostatectomy, a surgical treatment, and whole pelvic irradiation, a radiation therapy, were widely used as standard treatments in 1995. Furthermore, since the medical images included in the medical information acquired in S1 indicate that Patient A has no abdominal surgical scars, the first estimation function 155 estimates that Patient A has a medical history of prostate cancer and may have received whole pelvic irradiation as radiation therapy. Note that if multiple pieces of inconsistent past information are collected, the first estimation function 155 selects the past information to be used as the source of estimation based on the weighting results.

[0057] Then, if it is possible to identify a past disease, etc. related to patient A's current symptoms based on the estimated past medical history (S10 "Yes"), the second estimation function 156 estimates the name of patient A's current disease from the estimated past medical history (S12). For example, because patient A has no abdominal surgical scars, the second estimation function 156 estimates that patient A's past treatments were radiation therapy, drug therapy (endocrine therapy), or wait-and-see therapy. Furthermore, because patient A was young, 55 years old, when he was diagnosed with prostate cancer, the second estimation function 156 estimates that the possibility of selecting wait-and-see therapy was low (e.g., feasibility 5%). Furthermore, the second estimation function 156 estimates that, based on treatment guidelines from 1995, there was no effective drug therapy (endocrine therapy) at the time of 1995 (e.g., feasibility 0%). Furthermore, the second estimation function 156 estimates that, according to treatment guidelines in 1995, HDR (high-dose-rate brachytherapy) and intensity-modulated radiation therapy (IMRT) of radiation therapy (external beam irradiation) have not been performed (for example, feasibility 0%). Therefore, the second estimation function 156 estimates that if patient A receives radiation therapy (external beam irradiation), there is an extremely high possibility of whole pelvic irradiation (for example, feasibility 95%). Therefore, the second estimation function 156 estimates that patient A's current illness (hematuria) may be delayed hemorrhagic cystitis caused by radiation.

[0058] Furthermore, if it is difficult to identify past diseases, etc., related to patient A's current symptoms based on the estimated past medical history (S10 "No"), the second estimation function 156 may search for past diseases related to the current symptoms from the disease-specific symptom database 141 (S11). For example, if a large amount of past information from reliable information sources is detected and it is difficult to identify which disease described in the multiple pieces of past information is related to the current patient's symptoms, the second estimation function 156 may search for a disease corresponding to symptoms similar to those of the current patient from the disease-specific symptom database 141, which is a database in which disease names and symptoms are associated. In this case, the second estimation function 156 may identify multiple diseases corresponding to the current patient's symptoms as a candidate group for the name of the patient's current disease.

[0059] Then, the display control function 157 displays the estimated medical history and the estimated result of the patient's current disease name (S13). For example, the display control function 157 displays on the display 130 the estimated result of the past medical history, that is, that patient A has a history of prostate cancer and may have received whole pelvic irradiation for radiotherapy, and the estimated result of the current disease of patient A, that is, that patient A's current disease (hematuria) may be delayed hemorrhagic cystitis. This allows the medical information management device 1 to support the doctor in selecting a treatment method for patient A. For example, the doctor can select hyperbaric oxygen therapy for radiation-induced hemorrhagic cystitis for patient A based on the estimated result of patient A's past medical history and the estimated result of the current disease. Here, the processing of this flowchart ends.

[0060] In S12, the second estimation function 156 estimates the name of the current disease of patient A from the estimated past medical history, but may also suggest a treatment method for the estimated current disease. For example, the second estimation function 156 may estimate hyperbaric oxygen therapy for radiation-induced hemorrhagic cystitis as a treatment method for patient A. In this case, the display control function 157 may suggest the treatment method estimated by the second estimation function 156 to the doctor by displaying it on the display 130.

[0061] The medical information management device 1 may be configured not to include the second estimation function 156. In this case, the display control function 157 may cause the display 130 to display only the patient's medical history estimated by the first estimation function 155.

[0062] In S9, the first estimation function 155 estimated the diseases that patient A may have suffered from and the medical procedures that patient A may have received to treat those diseases as the medical history. However, the estimated content of the medical history is not limited to this. For example, the first estimation function 155 may not identify the medical procedures that patient A may have received to treat the disease, but may simply list the treatment methods that were commonly used at the time patient A developed the disease based on medical technology information 3, such as clinical practice guidelines, that were in effect at the time patient A developed the disease. For example, the first estimation function 155 may only identify that radical prostatectomy, a surgical treatment, and whole pelvic irradiation, a radiation therapy, were widely used as standard treatments in 1995. In this case, the display control function 157 presents to the physician, as the medical history, the fact that the patient developed prostate cancer in 1995 and that radical prostatectomy, a surgical treatment, and whole pelvic irradiation, a radiation therapy, were widely used as standard treatments in 1995, by displaying this information on the display 130. In this case, it may be possible to estimate the treatments that Patient A may have received in the past based on the medical history provided and information such as the doctor's finding that Patient A has no abdominal surgical scars.

[0063] In this way, the medical information management device 1 according to this embodiment acquires medical information related to the patient's current illness, collects past information related to the patient's past medical care or health using search information based on the medical information, and extracts date information related to the date on which the past information was generated or recorded from the collected past information. The medical information management device 1 according to this embodiment estimates the patient's medical history from medical technology information 3 related to medical technology at the time corresponding to the extracted date information, and outputs the estimation result. Therefore, the medical information management device 1 according to this embodiment can identify the patient's past medical history even when the patient's medical record cannot be referenced.

[0064] Furthermore, the medical information management device 1 according to this embodiment generates search information from medical information and uses the search information to search the record information 2 to collect past information about the patient. Therefore, the medical information management device 1 according to this embodiment can estimate all of the patient's past medical history data related to diseases included in the patient's current medical information. Collecting information about all diseases the patient has suffered from in the past, especially in elderly patients, can result in a huge volume of information, potentially increasing the amount of information unnecessary for doctors to currently treat the patient. Therefore, the medical information management device 1 according to this embodiment collects past information related to the patient's current medical information, thereby providing doctors with medical history data that is useful for currently treating the patient.

[0065] Furthermore, the medical information management device 1 according to this embodiment generates text data containing keywords related to a patient's current or past illness as search information, and uses the keywords to search the record information 2. Because the record information 2 includes both public medical records and private patient records, the wording used may vary depending on the nature of the records. Furthermore, because a patient's current illness is not necessarily the same as an illness the patient suffered from in the past, searching using a variety of keywords can reduce omissions in the collection of past information.

[0066] Furthermore, the medical information management device 1 according to this embodiment logs in to a system requiring the patient's authentication information using the patient's authentication information and collects past information. Therefore, the medical information management device 1 according to this embodiment can collect past information not only from public medical records and patient blogs or social networking sites publicly available on the Web, but also from private patient information that is limited to the public or not. Because patient health information may be recorded without being publicly available, searching for private patient information that is limited to the public or not increases the likelihood of obtaining useful past information for estimating a patient's past medical history.

[0067] Furthermore, the medical information management device 1 according to this embodiment estimates the name of the patient's current illness based on the medical information and medical history. Therefore, the medical information management device 1 according to this embodiment can assist doctors in determining a treatment plan based on the patient's medical history.

[0068] (Second embodiment) In the first embodiment described above, the medical information management device 1 estimates past medical procedures that may be the cause of a patient's current symptoms. In this second embodiment, the medical information management device 1 estimates medical procedures previously performed on a current patient based on traces of past medical procedures remaining on the patient. In addition, in this second embodiment, the medical information management device 1 also estimates whether a medical device has been placed on the patient as part of a past medical procedure performed on the patient, and whether the medical device is compatible with MRI (Magnetic Resonance Imaging) testing.

[0069] 1, the medical information management device 1 of this embodiment includes a network interface 110, an input interface 120, a display 130, a memory circuitry 140, and a processing circuitry 150. Also, the processing circuitry 150 includes an acquisition function 151, a generation function 152, a collection function 153, an extraction function 154, a first estimation function 155, a second estimation function 156, and a display control function 157, similar to the first embodiment.

[0070] The acquisition function 151, generation function 152, collection function 153, and extraction function 154 of this embodiment have the same functions as those of the first embodiment.

[0071] The first estimation function 155 of this embodiment has the same functions as the first embodiment, and estimates medical procedures performed on a current patient in the past based on medical information including information on traces of past medical procedures remaining on the current patient. Traces of past medical procedures are, for example, surgical scars. The first estimation function 155 also estimates whether or not a medical device was placed on the patient as a result of a medical procedure performed on the patient in the past, based on the current medical information, collected past information, and medical technology information 3 corresponding to date information based on the past information.

[0072] In addition, the second estimation function 156 of this embodiment has the same function as the first embodiment, and when the first estimation function 155 estimates that a medical device has been placed on a patient as a result of a medical procedure performed on the patient in the past, it estimates whether or not an MRI examination of the placed medical device is possible.

[0073] For example, among medical devices inserted into a patient's body, pacemakers, cochlear implants, and stents containing magnetic materials (iron, cobalt, nickel, etc.) are not compatible with MRI scans, so if these medical devices are present in the patient's body, the patient cannot undergo an MRI scan. If the patient's past medical records have already been destroyed, it may not be possible to perform an MRI scan, as it is not known what type (material) of device remains in the body after surgery, etc. However, if the benefits of the MRI scan outweigh the risks, the MRI scan may be performed with the patient's consent.

[0074] The display control function 157 of this embodiment has the same functions as the first embodiment, and causes the display 130 to display the patient's medical history and the estimated results regarding the presence or absence of a medical device in the body.

[0075] Next, the flow of the medical history estimation process performed by the medical information management device 1 of this embodiment configured as above will be described.

[0076] 4 is a flowchart showing an example of the flow of the medical history estimation process performed by the medical information management device 1 according to the second embodiment. Below, the flow of the estimation process will be explained, taking as a specific example a case where the medical information management device 1 estimates the past medical history of patient B (an 85-year-old male) for whom at least a portion of his past medical records has been discarded.

[0077] For example, a doctor is considering performing an MRI scan of Patient B's head due to a suspected transient ischemic attack (TIA). Patient B has a slight scar on his eyeball, and if he has had surgery in the past, it is necessary to determine what kind of implant was placed as a result of that surgery. However, because Patient B has dementia, it is difficult to obtain a satisfactory answer. When checking with Patient B's family, they respond that they remember having had some kind of surgery in the past, but they do not remember the date or the name of the disease. Furthermore, the doctor attempts to inquire about Patient B's medical history at another hospital using Patient B's patient card from that hospital, but is unable to obtain any information because the other hospital has already discarded Patient B's medical record. The doctor then attempts to identify Patient B's medical history using the medical information management device 1.

[0078] The process of acquiring the patient's current medical information in S21 is the same as the process in S1 of the first embodiment described with reference to Fig. 3. For example, the acquisition function 151 acquires information input by a doctor, such as that patient B is suspected of having a transient ischemic attack, that patient B has a surgical scar indicating that he or she has previously undergone eye surgery, other diseases that patient B is currently suffering from, the results of patient B's blood test, and medical images of patient B.

[0079] Next, the generation function 152 generates search keywords based on the acquired medical information (S22). Here, the doctor, who is the user, may specify information from the medical information that will be the source of generating the search keywords. For example, if the search keyword generation function is realized by a large-scale language model, the doctor queries the large-scale language model for keywords related to "ophthalmic surgery." The processing flow when a query is received from the doctor is the same as the processing of S2 in the first embodiment described in FIG. 3.

[0080] Keywords related to medical procedures, such as "eye surgery," include, but are not limited to, variations of the medical procedure, synonyms for the medical procedure, names of diseases for which the medical procedure is used, names of categories that encompass the disease, and names of organs related to the disease or medical procedure. The generator 152 generates keywords such as "eye surgery," "eye surgery," "visual field test," "fundus examination," "retinal photocoagulation," "LASIK," "ICL (phakic intraocular lens insertion)," "cataract," "diabetic retinopathy," "glaucoma," "retinal detachment," "floaters," and "blindness." These keywords are used to search the patient's public and private medical records included in the record information 2, so the generator 152 generates a wide range of keywords that can be used to search for information related to "eye surgery," from terms used in public information to colloquial expressions used in general information.

[0081] The process of S23 for acquiring authentication information for logging in to the search destination system is the same as the process of S3 in the first embodiment described in Fig. 3. The acquisition function 151 may also acquire identification information such as the patient's name, the patient's nickname on a blog or SNS, a photograph of the patient's face, the patient's My Number, health insurance card number, patient registration card numbers from medical institutions where the patient has previously been treated, and employee ID numbers from previous employers.

[0082] The keyword-based search process in S24 is the same as the process in S4 of the first embodiment described with reference to Fig. 3. For example, it is assumed that the collection function 153 is able to access the corporate health checkup results using the ID information of the health insurance association to which patient B belonged. The collection function 153 searches the found corporate health checkup results using the keyword group generated in S22. Here, it is assumed that the search result shows a medical history of "floaters" in the medical interview section of the results of a corporate health checkup that patient B had previously undergone. It is also assumed that the collection function 153 has searched for medical statements containing the words "fundus examination" and "retinal photocoagulation" from past medical statement data that patient B or his / her family brought and registered in the medical information management device 1 in advance.

[0083] The process of extracting date information in S25 is the same as the process in S5 of the first embodiment described with reference to Fig. 3. For example, the extraction function 154 identifies the date on which the company health checkup results containing the description of "floaters" obtained by the search in S24 were issued as September 2010 from the tags of the electronic data and extracts it. The extraction function 154 also identifies the date on which the medical statement for the treatment of "fundus examination" and "retinal photocoagulation" was issued as November 2010 through text analysis and extracts it. The extraction function 154 may also identify the time when floaters appeared as September 2010 by performing text analysis on the company health checkup results containing the description of "floaters."

[0084] The weighting process based on the reliability of the information source in the case where a plurality of pieces of mismatched past information have been collected in S26 to S28 is the same as the process in S6 to S8 in the first embodiment described with reference to FIG.

[0085] In this embodiment, the first estimation function 155 estimates a target disease from the past information collected by the collection function 153 and then refers to the medical technology information 3. First, the first estimation function 155 estimates patient B's past disease from the results of the keyword search in S24 (S29). For example, "retinal photocoagulation" in the medical statement included in the results of the keyword search in S24 is a treatment performed for retinal detachment, diabetic retinopathy, and retinal vein occlusion. According to the medical information acquired in S21, patient B does not suffer from diabetes, so the first estimation function 155 excludes diabetic retinopathy. Furthermore, although retinal vein occlusion is generally difficult to cure permanently, according to the medical information acquired in S21, patient B currently has no symptoms of retinal vein occlusion, so the first estimation function 155 excludes retinal vein occlusion. In this case, according to the commercial practice method, the first estimation function 155 estimates that the disease patient B previously suffered from is likely to be retinal detachment. Furthermore, because patient B has surgical scars indicating that he has had ophthalmic surgery in the past, first estimation function 155 estimates that the retinal detachment was not completely cured by retinal photocoagulation and that scleral buckling surgery may have been performed. Note that when multiple pieces of inconsistent past information are collected, first estimation function 155 selects the past information to be used as the source of estimation based on the weighting results.

[0086] The processing in S30 to S31 when it is difficult to identify past diseases etc. related to patient A's current symptoms based on the estimated past medical history is the same as the processing in S10 to S11 of the first embodiment described in Figure 3.

[0087] Then, the first estimation function 155 searches for medical technique information 3 based on the extracted date information and the estimated past illnesses, etc. (S32).

[0088] Then, the first estimation function 155 estimates past medical treatments from the search results of the medical technology information 3 (S33). For example, the first estimation function 155 determines, from a surgical device catalog database for 2010 included in the medical technology information 3, that there is a high possibility that a silicone intraocular implant would be used in scleral buckling surgery in 2010.

[0089] If the first estimation function 155 estimates that a medical device has been placed in the body of patient B as a result of a past medical procedure (S34 "Yes"), the second estimation function 156 estimates whether an MRI examination of the medical device estimated to have been placed is possible (S35). The first estimation function 155 estimates that patient B has a silicone intraocular implant placed in it, and the second estimation function 156 estimates whether an MRI examination of the intraocular implant is possible based on a surgical device catalog database as of 2010. Alternatively, the second estimation function 156 may estimate whether an MRI examination of the intraocular implant is possible based on the material of the intraocular implant identified by the first estimation function 155.

[0090] Furthermore, if the first estimation function 155 estimates that patient B's intraocular implant is made of metal, the second estimation function 156 may obtain information on whether or not the metal implant is compatible with MRI examinations from a surgical device catalog from 2010. Furthermore, if multiple types of implants were registered in the surgical device catalog from 2010, the second estimation function 156 may estimate the degree of risk of patient B undergoing an MRI examination based on the prevalence rate of each implant and information such as the implant purchase slip from the hospital that is believed to have performed patient B's eye surgery.

[0091] Then, the display control function 157 displays the estimated medical history and the estimated results of the presence or absence of a medical device in the patient's body on the display 130 (S36). At this point, the processing of this flowchart ends.

[0092] It should be noted that the second estimation function 156 is not required to estimate whether or not an MRI examination of a medical device is possible, and the first estimation function 155 may simply estimate whether or not there is a medical device in the body of patient B and the type or material of the medical device. In this case, for example, the display control function 157 may display that patient B is estimated to have an intraocular implant and that the intraocular implant is estimated to be made of silicone. In this case, the doctor who confirms this display considers whether or not to perform an MRI examination of the head of patient B.

[0093] In this way, the medical information management device 1 according to this embodiment estimates medical procedures that have been performed on a current patient in the past from traces of past medical procedures remaining on the current patient. Therefore, the medical information management device 1 according to this embodiment can provide information for a doctor to use in making decisions about medical procedures to be performed on the current patient.

[0094] The medical information management device 1 according to this embodiment also estimates whether a medical device has been placed on the patient as part of a medical procedure performed on the patient in the past, and whether the medical device is compatible with MRI examinations. Therefore, the medical information management device 1 according to this embodiment can assist doctors in making decisions regarding the implementation of MRI examinations when the patient's past medical records cannot be referenced.

[0095] (Third embodiment) In the third embodiment, the medical information management apparatus 1 estimates the type of a medical device by using a medical image of the medical device currently inside the patient's body.

[0096] 1, the medical information management device 1 of this embodiment includes a network interface 110, an input interface 120, a display 130, a memory circuitry 140, and a processing circuitry 150. Also, the processing circuitry 150 includes an acquisition function 151, a generation function 152, a collection function 153, an extraction function 154, a first estimation function 155, a second estimation function 156, and a display control function 157, similar to the first embodiment.

[0097] The acquisition function 151, generation function 152, collection function 153, and extraction function 154 of this embodiment have the same functions as those of the first embodiment.

[0098] The medical information of this embodiment includes medical images of a medical device placed inside the patient's body. The medical images may be any images that depict the medical device placed inside the patient's body, such as MRI images, X-ray images, X-ray CT (Computed Tomography) images, ultrasound images, etc. The medical images may be two-dimensional data or three-dimensional data.

[0099] The medical technology information 3 of this embodiment includes at least either a product catalog or clinical practice guidelines for implantable medical devices. The product catalog and clinical practice guidelines for medical devices include an image showing the shape of the medical device. Note that the image showing the shape of the medical device is not limited to an image of the medical device actually photographed by a photographing device such as a camera, but may also be a diagram.

[0100] The first estimation function 155 of this embodiment has the same functions as the first embodiment, and estimates the type of medical device depicted in a medical image based on a medical image of a medical device placed inside a patient's body and an image included in a product catalog or clinical guidelines. The first estimation function 155 may identify the type of medical device by the product name and model number, or may estimate a rough classification at a level that allows the material of the medical device to be identified.

[0101] More specifically, the first estimation function 155 of this embodiment estimates the time when the medical device was placed inside the patient's body based on the date information extracted by the extraction function 154. Furthermore, the first estimation function 155 of this embodiment estimates the type of medical device depicted in the patient's medical image based on the medical image and a product catalog or clinical guidelines corresponding to that time period.

[0102] For example, the first estimation function 155 estimates that a fracture treatment plate is implanted in the patient's body by performing image recognition on a surgical device catalog database or the like for a medical device that matches the shape of a medical device depicted in an X-ray of the patient's arm. The first estimation function 155 also estimates that an esophageal stent is implanted in the patient by performing image recognition on a surgical device catalog database or the like for a medical device that matches the shape of a medical device depicted in an X-ray of the patient's chest. Because the shape of medical devices varies depending on the era, the first estimation function 155 may limit the product catalogs or clinical guidelines to be subjected to image recognition based on date information extracted from the patient's past information.

[0103] In addition, the first estimation function 155 of this embodiment calculates the reliability of the estimated type of medical device based on at least one of the following: the degree of similarity in shape between the medical device depicted in the patient's medical image and the medical device depicted in the image included in the product catalog or clinical practice guideline; the type of medical institution that performed the surgery; and the regional characteristics of the area where the medical institution is located. This is because, depending on the type of medical institution that previously performed the surgery on the patient and the area where the medical institution is located, the medical institution may use the latest technology that was being tested at the time of the medical procedure or may use technology that is older than the latest technology at the time. In this case, the first estimation function 155 may change the age of the product catalog or clinical practice guideline to be referenced depending on the type of medical institution that previously performed the surgery and the regional characteristics of the area where the medical institution is located.

[0104] Furthermore, the second estimation function 156 of this embodiment has the same functions as the first embodiment and estimates whether the medical device estimated by the first estimation function 155 is compatible with MRI examinations. The method of estimating whether an MRI examination is possible is the same as in the second embodiment. Furthermore, the second estimation function 156 calculates the reliability of the estimation result of whether an MRI examination is possible depending on the reliability of the type of medical device estimated by the first estimation function 155. For example, the higher the reliability of the estimation result of the reliability of the type of medical device, the higher the reliability of the estimation of whether an MRI examination is possible.

[0105] The display control function 157 of this embodiment has the same functions as the first embodiment, and displays on the display 130 an operation screen on which a doctor inputs medical information including medical images of the patient to be used to estimate the medical history.

[0106] Fig. 5 is a diagram showing an example of a medical information input screen 131 according to the third embodiment. As shown in Fig. 5, the medical information input screen 131 displayed on the display 130 includes a current information input field 131a for inputting current information about the patient. The current information input field 131a is a field in which the patient's age, sex, chief complaint, doctor's findings, various test results, and the like can be input. The information in the current information input field 131a may be manually entered by a doctor or the like, or the doctor or the like may press a "Read from electronic medical record" button 131b, which causes the acquisition function 151 to acquire this information from an electronic medical record system.

[0107] The medical information input screen 131 also has an entry field 131c where a doctor or the like can freehand input the parts of the patient's body where there are surgical scars on the anatomical diagram. The medical information input screen 131 also has a "Browse Files" button 131d where a doctor or the like can upload medical images. Note that while FIG. 5 shows "Please upload X-ray images," this is just an example, and other types of medical images may be uploaded. The medical information input screen 131 also has a "Start Medical History Estimation" button 131e. When a doctor or the like presses the "Start Medical History Estimation" button 131e, the medical information management device 1 starts the process of estimating the medical history.

[0108] The medical information input screen 131 may be adopted not only in the third embodiment but also in the first and second embodiments described above.

[0109] In addition, the display control function 157 of this embodiment may display on the display 130 the reliability of the estimation result of the type of medical device inside the patient's body and the reliability of the estimation result of whether or not the medical device can be subjected to MRI examination, together with the estimation result.

[0110] Next, the flow of the medical history estimation process performed by the medical information management device 1 of this embodiment configured as above will be described.

[0111] FIG. 6 is a flowchart showing an example of the flow of the medical history estimation process performed by the medical information management device 1 according to the third embodiment.

[0112] First, the acquisition function 151 acquires medical information related to the patient's current illness. In this embodiment, the medical information includes medical images of the current medical device inside the patient's body (S41). For example, the acquisition function 151 acquires information entered by a doctor or the like on the medical information input screen 131 shown in FIG. 5.

[0113] The process from the search keyword generation process in S42 to the date information extraction process in S45 is the same as the process in S2 to S5 in the first embodiment described with reference to FIG.

[0114] Next, the first estimation function 155 of this embodiment estimates the time when the medical device was placed inside the patient's body based on the extracted date information (S46).

[0115] Then, the first estimation function 155 of this embodiment estimates the type of medical device placed on the patient from the medical technology information 3 corresponding to the date information (S47). For example, the first estimation function 155 performs image recognition processing using the medical image of the medical device currently inside the patient's body acquired in S1, thereby estimating the medical device corresponding to the medical device depicted in the medical image from the product catalog or clinical guidelines included in the medical technology information 3.

[0116] Then, the second estimation function 156 estimates whether the medical device estimated in S47 can be subjected to an MRI examination (S48).

[0117] Then, the display control function 157 displays the estimated medical history and the estimation result as to whether the medical device inside the patient's body can be examined by MRI on the display 130 (S49). The display control function 157 may also display the reliability of the estimation result as to the type of medical device inside the patient's body and the reliability of the estimation result as to whether the medical device can be examined by MRI on the display 130 together with the estimation result. At this point, the processing of this flowchart ends.

[0118] In this way, the medical information management device 1 according to this embodiment estimates the type of medical device depicted in the medical image based on the patient's medical image and an image included in a product catalog or clinical guidelines. Therefore, the medical information management device 1 according to this embodiment can help doctors and other medical professionals to identify the type of medical device placed inside a patient whose past medical records are unavailable.

[0119] Furthermore, the medical information management device 1 according to this embodiment estimates the time when the medical device was placed inside the patient's body based on date information about the date when the past information was generated or recorded, and estimates the type of medical device depicted in the medical image based on the medical image and a product catalog or clinical guidelines corresponding to that time. Therefore, the medical information management device 1 according to this embodiment can accurately estimate the type of medical device placed inside the patient's body based on the technology available at the time the medical device was placed inside the patient.

[0120] Furthermore, the medical information management device 1 according to this embodiment estimates whether or not an MRI examination of a medical device is possible based on the type of the medical device estimated to be placed inside the patient's body. Therefore, the medical information management device 1 according to this embodiment can provide information to help a doctor decide whether or not to perform an MRI examination on a patient whose past medical history is unavailable.

[0121] Furthermore, the medical information management device 1 according to this embodiment calculates the reliability of the estimated type of medical device based on at least one of the following: the degree of similarity in shape between the medical device depicted in the medical image and the medical device depicted in the image included in the product catalog or clinical guidelines, the type of medical institution where the surgery was performed, and the regional characteristics of the area where the medical institution is located. Therefore, the medical information management device 1 according to this embodiment can estimate the type of medical device placed on the patient with higher accuracy.

[0122] In this embodiment, the processes of the generating function 152, collecting function 153, extracting function 154, and second estimating function 156 are not essential. For example, the first estimating function 155 may simply estimate the type of medical device placed on the patient from the medical technology information 3 by image recognition using a medical image of the medical device currently inside the patient's body, without limiting it by date information. Also, in this embodiment, the first estimating function 155 and the second estimating function 156 estimate the reliability of the estimation result of the type of medical device and the estimation result of whether or not an MRI examination is possible, but the function of calculating the reliability is not essential.

[0123] In the second and third embodiments, an MRI examination is given as an example of a medical procedure that has contraindications related to the patient's medical history, but the estimation process by the medical information management device 1 can be applied to procedures other than an MRI examination. For example, if there is a treatment that cannot be performed on a patient who has previously suffered from a specific disease, the medical information management device 1 may estimate whether or not the patient has a medical history of the specific disease.

[0124] It should be noted that application examples of the medical information management device 1 of the first to third embodiments are not limited to cases where the patient himself / herself has dementia, such as the above-mentioned patients A and B. For example, there may be cases where the patient himself / herself remembers having had a serious illness in the past, but has little recollection of it because it occurred in childhood, and there are no records. In such cases, the patient's vague memories of "which hospital he / she was hospitalized in" and "what medicine he / she was taking" may be used in the estimation process as part of the medical information.

[0125] Another application example of the first embodiment and the medical information management device 1 of the first embodiment can be used by a patient to check whether they are affected when serious side effects or drug-related injuries are later discovered. The medical information management device 1 can be used when, long after a surgery or treatment, it is learned through news reports that a particular surgery or treatment has serious side effects, allowing a doctor or patient to check whether the patient is affected. Furthermore, if a patient also has chronic symptoms similar to those reported in the news, the medical information management device 1 can be used by a doctor or patient to check whether the surgery or treatment the patient previously underwent matches the specific surgery or treatment that was found to have serious side effects. In this case, the medical technology information 3 may also include drug delivery records from medical institutions where the patient underwent surgery or treatment in the past.

[0126] The various data handled in this specification are typically digital data.

[0127] According to at least one of the embodiments described above, even when the patient's medical records cannot be referenced, the patient's past medical history can be identified.

[0128] 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. [Explanation of symbols]

[0129] 1. Medical information management device 3 Medical Technology Information 21 Medical fee statement information 22 Medical statement information 23 Medical interview record 25 Schedule 31 Clinical Practice Guidelines 32 Medical Device Catalog 110 Network Interface 120 input interface 130 Display 131 Input screen 131a Current information entry field 131b "Read from electronic medical record" button 131c Entry field 131d "Browse Files" button 131e "Start medical history estimation" button 140 Memory circuit 141 Disease-specific Symptom Database 150 Processing Circuit 151 Acquisition Function 152 Generation function 153 Collection Function 154 Extraction Function 155 First Estimated Function 156 Second Estimated Function 157 Display control function A,B patient N Network

Claims

1. an acquisition unit for acquiring medical information related to a patient's current illness; a collection unit that collects past medical or health information of the patient based on the medical information; an extraction unit that extracts date information relating to a date on which the past information was generated or recorded from the past information; a first estimation unit that estimates the medical history of the patient from medical technology information related to medical technology at a time corresponding to the extracted date information; an output unit that outputs the estimated medical history; A medical information management device comprising:

2. a generating unit that generates search information from the medical information, the search information being able to search record information including public medical records and private records of the patient; the collection unit collects the past information by searching the record information using the search information. The medical information management device according to claim 1 .

3. The medical information includes at least any one of the patient's current symptoms, the name of a disease that the patient may currently be suffering from, or a medical treatment that the patient may have received in the past; the generating unit generates the search information including keywords related to the patient's current or past illness; the collection unit searches for the recorded information using the keyword. The medical information management device according to claim 2 .

4. the private records are stored on a system that requires the patient's credentials for viewing; the collection unit logs into the system using the patient's authentication information and collects the past information; The medical information management device according to claim 2 .

5. a second estimation unit that estimates the name of a current disease of the patient based on the medical information and the medical history; The medical information management device according to claim 1 .

6. the medical information includes a medical image taken of a medical device placed inside the patient's body; The medical technology information includes at least one of a product catalog for implantable medical devices or clinical practice guidelines; the first estimation unit estimates the type of the medical device depicted in the medical image based on the medical image and an image included in the product catalog or the clinical guideline; The medical information management device according to claim 1 .

7. the first estimation unit estimates the time when the medical device was placed in the patient's body based on the date information, and estimates the type of the medical device depicted in the medical image from the medical image and the product catalog or the clinical guideline corresponding to the time. The medical information management device according to claim 6.

8. a second estimation unit that estimates whether or not the medical device can be subjected to an MRI (Magnetic Resonance Imaging) examination based on the estimated type of the medical device. The medical information management device according to claim 6 or 7.

9. an acquisition step of acquiring medical information related to the patient's current disease; a collecting step of collecting past medical or health information of the patient based on the medical information; an extraction step of extracting date information relating to a date on which the past information was generated or recorded from the past information; a first estimation step of estimating the medical history of the patient from medical technology information relating to medical technology at the time corresponding to the extracted date information; an output step of outputting the estimated medical history; A medical information management method including:

10. an acquisition step of acquiring medical information related to the patient's current disease; a collecting step of collecting past medical or health information of the patient based on the medical information; an extraction step of extracting date information relating to a date on which the past information was generated or recorded from the past information; a first estimation step of estimating the medical history of the patient from medical technology information relating to medical technology at the time corresponding to the extracted date information; an output step of outputting the estimated medical history; A program that causes a computer to execute the following.

Images