Medical information processing apparatus, medical information processing method, and program

The medical information processing apparatus addresses the challenge of creating accurate radiology reports by extracting similar patient data and using a large language model to generate reports based on comprehensive document summaries, improving report quality and reducing data reliance.

JP2025106697APending Publication Date: 2025-07-16CANON MEDICAL SYST CORP
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
JP2024000191
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2024-01-04
Publication Date
2025-07-16

AI Technical Summary

Technical Problem

Existing methods for creating radiology reports struggle to accurately identify similar cases from vast datasets, leading to potential inaccuracies in report generation due to reliance on image or text-based similarity searches, especially in the medical field where large-scale data collection is challenging.

Method used

A medical information processing apparatus with functions for acquiring additional patient information, extracting similar patients, acquiring medical documents for those patients, and creating a report based on summaries of these documents using a large language model.

Benefits of technology

Enables the creation of simple and appropriate medical documents by accurately identifying similar cases and incorporating common items and formats from multiple reports, enhancing report accuracy and reducing reliance on specific data sources.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2025106697000001_ABST
    Figure 2025106697000001_ABST
Patent Text Reader

Abstract

To support simple and appropriate preparation of a medical document.SOLUTION: A medical information processing apparatus according to an embodiment comprises an additional information acquisition unit, a similar patient extraction unit, a medical document acquisition unit, and a medical document preparation unit. The additional information acquisition unit acquires additional information on a target patient. The similar patient extraction unit extracts a similar patient similar to the target patient on the basis of the additional information acquired by the additional information acquisition unit. The medical document acquisition unit acquires a plurality of medical documents prepared for the similar patient extracted by the similar patient extraction unit. The medical document preparation unit prepares a medical document of the target patient on the basis of the additional information acquired by the additional information acquisition unit and the summary of the plurality of medical documents acquired by the medical document acquisition unit.SELECTED DRAWING: Figure 1
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The embodiments disclosed in this specification and the drawings relate to a medical information processing apparatus, a medical information processing method, and a program.

Background Art

[0002] When creating a radiology report of a medical image, sometimes a radiology report is created by referring to reports of past similar cases. However, it is difficult to identify similar cases from a huge number of past case data and create a report with similar content.

[0003] For example, a technique for searching for past similar radiology reports from the anatomical position of a key image and local structure information in its vicinity is known. Also, a technique for extracting keywords from a radiology report and searching for similar cases with a similar diagnostic flow is known. However, in these techniques, since similar cases are identified based on either image or radiology report information, there is a possibility that appropriate similar cases cannot be identified for creating a radiology report. In addition, an AI technique for learning data of hundreds of millions of combinations of images and explanatory texts and generating an explanatory text from an image is known. For example, OpenAI's CLIPCAP combines an image classification model CLIP and a large language model GPT to generate an explanatory text from an image. However, in such a technique, since it is difficult to collect large-scale data in the medical field, sufficient accuracy may not be obtained for medical images. Therefore, there is a need to support the creation of a simple and appropriate radiology report.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Patent Document 2

Patent Document 3

Patent Document 4

Summary of the Invention

Problems 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 assist in creating simple and appropriate medical documents. 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 the problems corresponding to the respective effects of each configuration shown in the embodiments described later as other problems.

Means for Solving the Problems

[0006] The medical information processing apparatus according to the embodiment includes an additional information acquisition unit, a similar patient extraction unit, a medical document acquisition unit, and a medical document creation unit. The additional information acquisition unit acquires the additional information of the target patient. The similar patient extraction unit extracts similar patients similar to the target patient based on the additional information acquired by the additional information acquisition unit. The medical document acquisition unit acquires a plurality of medical documents created for the similar patients extracted by the similar patient extraction unit. The medical document creation unit creates a medical document for the target patient based on the additional information acquired by the additional information acquisition unit and the summary of the plurality of medical documents acquired by the medical document acquisition unit.

Brief Description of the Drawings

[0007]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

[0008] Hereinafter, embodiments of the medical information processing apparatus will be described in detail with reference to the drawings. In the following description, components having substantially the same functions and configurations are denoted by the same reference numerals, and duplicate descriptions will be made only when necessary.

[0009] FIG. 1 is a block diagram showing a configuration example of a medical information processing apparatus 1 according to an embodiment. As shown in FIG. 1, the medical information processing apparatus 1 includes an input interface 2, an output interface 3, a communication interface 4, a storage circuit 5, and a processing circuit 6. The input interface 2, the output interface 3, the communication interface 4, and the storage circuit 5 are communicably connected to the processing circuit 6.

[0010] The input interface 2 receives various input operations from an operator. The input interface 2 converts the received input operation into an electrical signal and outputs it to the processing circuit 6. For example, the input interface 2 receives an input operation from the operator for creating a medical document of a target patient. As the input interface 2, for example, a mouse, a keyboard, a trackball, a switch, a button, a joystick, a touch pad, a touch panel display, etc. can be appropriately used.

[0011] The output interface 3 outputs various types of information. For example, the output interface 3 includes a display. The display outputs a medical document generated by the processing circuit 6 and a GUI (Graphical User Interface) for receiving various operations from the operator. For example, as the display, a liquid crystal display (LCD), a CRT (Cathode Ray Tube) display, an organic EL display (OELD), a plasma display, or any other arbitrary display can be appropriately used. The output interface 3 may include a speaker.

[0012] The communication interface 4 is an interface that communicably connects the medical information processing device 1 to an electronic medical record system or a radiology information system (RIS). The electronic medical record system may be included in a hospital information system (HIS). The communication interface 4 is constituted by, for example, a connector conforming to a parallel connection specification or a serial connection specification. The communication interface 4 performs communication control according to each standard, and connects the medical information processing device 1 to an electronic medical record system or a radiology information system via a network by connecting to the network.

[0013] The memory circuit 5 is a non-transitory storage device that stores various information, and is, for example, an HDD (Hard Disk Drive), an optical disk, an SSD (Solid State Drive), an integrated circuit storage device, or the like. The memory circuit 5 stores, for example, a control program for controlling the medical information processing device 1 and various data used for the execution of this control program. The memory circuit 5 may be a drive device that reads and writes various information between portable storage media such as a CD (Compact Disc), a DVD (Digital Versatile Disc), and a flash memory, or semiconductor memory elements such as a RAM (Random Access Memory), in addition to an HDD and an SSD. Note that the memory circuit 5 does not necessarily have to be realized by a single storage device. For example, the memory circuit 5 may be realized by a plurality of storage devices.

[0014] The processing circuit 6 is a circuit that controls the operation of the entire medical information processing device 1 according to an electrical signal of an input operation input from the input interface 2. The processing circuit 6 includes, for example, an attached information acquisition function 61, a similar patient extraction function 62, a medical document acquisition function 63, a medical document creation function 64, and a display control function 65. The attached information acquisition function 61 is an example of an attached information acquisition unit. The similar patient extraction function 62 is an example of a similar patient extraction unit. The medical document acquisition function 63 is an example of a medical document acquisition unit. The medical document creation function 64 is an example of a medical document creation unit. The display control function 65 is an example of a display control unit.

[0015] Here, for example, each processing function executed by the additional information acquisition function 61, the similar patient extraction function 62, the medical document acquisition function 63, the medical document creation function 64, and the display control function 65, which are components of the processing circuit 6 shown in FIG. 1, is recorded in the storage circuit 5 in the form of a program executable by a computer. The processing circuit 6 is, for example, a processor. The processor constituting the processing circuit 6 reads out each program from the storage circuit 5 and realizes the function corresponding to each read program by executing it. In other words, the processing circuit 5 in the state of having read out each program will have each function shown in the processing circuit 6 of FIG. 1.

[0016] Note that in FIG. 1, the case where the additional information acquisition function 61, the similar patient extraction function 62, the medical document acquisition function 63, the medical document creation function 64, and the display control function 65 are realized by a single processing circuit 6 is shown, but the embodiment is not limited to this. For example, the processing circuit 6 may be configured by combining a plurality of independent processors, and each processor may realize each processing function by executing each program. Also, each processing function of the processing circuit 6 may be realized by being appropriately distributed or integrated into a single or a plurality of processing circuits.

[0017] The additional information acquisition function 61 acquires the additional information of the target patient. The additional information includes, for example, at least one of the examination purpose, patient attributes, medical images, information regarding the image region of interest, and examination findings. The additional information acquisition function 61 acquires the additional information received, for example, through communication with an electronic medical record system or a radiology information system via the communication interface 4. The additional information acquisition function 61 may read and acquire the additional information received from the electronic medical record system or the radiology information system and stored in the memory circuit 5 from the memory circuit 5. Alternatively, the additional information acquisition function 61 may acquire the additional information input by the operator via the input interface 2. For example, when the operator fragmentarily inputs the image region of interest and the keywords of the findings for the medical image acquired via the communication interface 4, the additional information acquisition function 61 may acquire the input information as the additional information.

[0018] The similar patient extraction function 62 extracts similar patients similar to the target patient based on the additional information acquired by the additional information acquisition function 61. For example, the similar patient extraction function 62 extracts a plurality of similar patients similar to the target patient. The similar patient extraction function 62 may compare the additional information of the target patient with a plurality of medical documents created for each of a plurality of past patients for each of a plurality of items, and calculate the distance between the additional information and the plurality of medical documents for each item. Then, the similar patient extraction function 62 may calculate the similarity, which is the sum of the distances calculated for each item, and extract similar patients from among the plurality of past patients based on the calculated similarity. The similar patient extraction function 62 may extract, as similar patients, the patients with the highest similarity among the plurality of past patients.

[0019] The medical document acquisition function 63 acquires a plurality of medical documents, i.e., text information, created for the similar patients extracted by the similar patient extraction function 62. The medical document acquisition function 63 acquires, for example, the respective medical documents of a plurality of similar patients received from an electronic medical record system or a radiology information system through communication with the electronic medical record system or the radiology information system via the communication interface 4. The medical document acquisition function 63 may read and acquire the respective medical documents of a plurality of similar patients received from the electronic medical record system or the radiology information system and stored in the storage circuit 5 from the storage circuit 5.

[0020] The medical document creation function 64 creates a medical document for the target patient based on the supplementary information of the target patient acquired by the supplementary information acquisition function 61 and the summary of the plurality of medical documents of the similar patients acquired by the medical document acquisition function 63. The summary of the medical documents includes, for example, common items and formats (i.e., expressions) among the plurality of medical documents created for each of the plurality of similar patients.

[0021] The medical document creation function 64 may create a medical document for the target patient using, for example, a large language model (LLM) such as ChatGPT. For example, the medical document creation function 64 inputs the supplementary information of the target patient and the respective medical documents of the plurality of similar patients into the large language model, and causes the large language model to extract common items and formats in the input supplementary information of the target patient and the medical documents of the plurality of similar patients, thereby creating a medical model for the target patient. Further, the medical document creation function 64 may create a medical document for the target patient based on the summaries of two or more medical documents having a difference in content of a certain amount or more among the medical documents of the plurality of similar patients so that the medical documents of the similar patients with nearly identical content are not used repeatedly. In this case, the medical document creation function 64 may determine that the plurality of medical documents have a difference in content of a certain amount or more based on the similarity calculated based on classical natural language processing such as TF-IDF (Term Frequency - Inverse Document Frequency) and cosine similarity.

[0022] Further, the medical document creation function 64 may further create a medical image of the target patient based on the supplementary information of the target patient acquired by the supplementary information acquisition function 61 and the summary of a plurality of medical images of similar patients acquired by the medical document acquisition function 63. The summary of the medical images may include a common image area or the like among the plurality of medical images created for each of the plurality of similar patients.

[0023] In addition, the medical document creation function 64 may create not only one medical document but also a plurality of medical documents as the medical documents of the target patient. When the medical document creation function 64 creates a plurality of medical documents, the operator may select a desired medical document from among the created plurality of medical documents.

[0024] The display control function 65 displays the medical document of the target patient created by the medical document creation function 64. The display control function 65 may further display a medical image corresponding to the medical document of the target patient.

[0025] Next, an operation example of the medical information processing apparatus 1 according to the embodiment configured as described above will be described. FIG. 2 is a flowchart showing an operation example of the medical information processing apparatus 1 according to the embodiment. FIG. 3 is a flowchart showing an extraction process of similar patients in the operation example of the medical information processing apparatus 1 according to the embodiment. FIG. 4 is a flowchart showing a creation process of a medical report of a target patient in the operation example of the medical information processing apparatus 1 according to the embodiment.

[0026] As shown in FIG. 2, first, the additional information acquisition function 61 acquires the additional information of the target patient. Specifically, when an input operation by the operator for acquiring the additional information of the target patient is received by the input interface 2, the additional information acquisition function 61 acquires the additional information received from the electronic medical record system or the radiology information system via the communication interface 4. For example, when the operator inputs the identification number of the target patient, the additional information acquisition function 61 may acquire the additional information of the target patient associated with the input identification number from the electronic medical record system or the radiology information system. Alternatively, the additional information acquisition function 61 may acquire the additional information of the target patient manually input by the operator via the input interface 2. The additional information of the target patient includes, for example, at least one of the examination purpose, patient attributes, medical images, information regarding the image area of interest, and examination findings. These additional information may be acquired in the form of examination order data, image data, patient attribute data, and diagnostic phase information. The information regarding the image area of interest and the examination findings may be manually input by the operator.

[0027] After the incidental information of the target patient is acquired, the similar patient extraction function 62 extracts a plurality of similar patients based on the acquired incidental information (step S2). Specifically, as shown in FIG. 3, first, the similar patient extraction function 62 compares the incidental information of the target patient with the medical reports of a plurality of past patients item by item (step S21). The medical report includes a medical document and a medical image corresponding to the medical document. The medical report is, for example, a radiology report. The similar patient extraction function 62 receives and acquires the medical reports of a plurality of past patients from an electronic medical record system or a radiology information system, for example, by communicating with the electronic medical record system or the radiology information system via the communication interface 4. At least one of the examination purpose, patient attributes, medical images, information on the image regions of interest, and examination findings is included as an item in the medical reports of a plurality of past patients. Note that the image region of interest may be specified by attaching text information indicating the image region of interest (for example, "a nodule is observed in the right lung", etc.) to the image as a hyperlink. The examination findings may be associated with a hyperlink attached to the image.

[0028] Next, for each item, the similar patient extraction function 62 calculates the distance between the supplementary information of the target patient and the medical reports of a plurality of past patients. For example, when the item is "findings", the more keywords that match between the findings of the target patient and the findings of the past patients, the shorter the distance calculated by the similar patient extraction function 62. Also, for example, when the item is "image region of interest", the closer the anatomical position and structure between the image region of interest of the target patient and the image region of interest of the past patients, the shorter the distance calculated by the similar patient extraction function 62. Also, for example, when the item is "examination purpose", the similar patient extraction function 62 calculates the distance so that it is shorter when the examination purposes of the target patient and the past patient match than when they are different. Also, for example, when the item is "patient attributes" such as the gender and age of the patient, the closer the patient attributes of the target patient and the past patient, the shorter the distance calculated by the similar patient extraction function 62. Also, for example, when the item is "disease" or "treatment phase", the similar patient extraction function 62 calculates the distance so that it is shorter when the diseases and treatment phases of the target patient and the past patient match than when they are different.

[0029] After calculating the distance for each item, the similar patient extraction function 62 calculates the similarity, which is the sum of the distances for each item, for each past patient (step S23). The smaller the sum of the distances, the higher the similarity to the target patient.

[0030] After calculating the similarity, the similar patient extraction function 62 extracts similar patients from among the plurality of past patients based on the calculated similarity (step S24). Specifically, the similar patient extraction function 62 extracts a plurality of past patients with the highest similarities as similar patients.

[0031] After a plurality of similar patients are extracted, as shown in FIG. 2, the medical document acquisition function 63 acquires the medical reports of the plurality of similar patients (step S3). FIG. 5 is a diagram showing the process of acquiring the medical reports of a plurality of similar patients in an operation example of the medical information processing apparatus 1 according to the embodiment. In the example shown in FIG. 5, the medical document acquisition function 63 acquires the medical reports R1 to R3 of a plurality of similar patients #1 to #3 extracted by the similar patient extraction function 62. In the example shown in FIG. 2, the medical reports R1 to R3 of the plurality of similar patients #1 to #3 are stored in the storage circuit 5 as part of the medical reports of a plurality of past patients when extracting the similar patients. In the example shown in FIG. 5, the medical reports R1 to R3 of the plurality of similar patients #1 to #3 include medical documents D1 to D3 (i.e., findings) and medical images I1 to I3 (i.e., key images).

[0032] After the medical reports of the plurality of similar patients are acquired, as shown in FIG. 2, the medical document creation function 64 creates a medical report of the target patient based on the summary of the medical reports of the plurality of similar patients (step S4).

[0033] Specifically, as shown in FIG. 4, first, the medical document creation function 64 extracts common items and formats among the medical reports of the plurality of similar patients as a summary (step S41). In the example shown in FIG. 5, the medical document creation function 64 extracts "part A" and "abnormality C" as common items among the medical reports R1 to R3 of the plurality of similar patients #1 to #3, and extracts "~ is recognized" etc. as a common format.

[0034] After extracting common items and formats among the medical reports of the plurality of similar patients as a summary, the medical document creation function 64 creates a medical report of the target patient so as to include the extracted common items and formats (step S42).

[0035] FIG. 6 is a diagram showing a process of creating a medical report for a target patient in an operation example of the medical information processing apparatus 1 according to the embodiment. In the example shown in FIG. 6, the medical document creation function 64 creates a medical report R for the target patient, which is composed of a medical document D and a medical image I, including items and formats common to the medical reports R1 to R3 of a plurality of similar patients #1 to #3.

[0036] After the medical report for the target patient is created, as shown in FIG. 2, the display control function 65 displays the created medical report for the target patient (step S5).

[0037] As described above, in this embodiment, the additional information acquisition function 61 acquires the additional information of the target patient. Further, the similar patient extraction function 62 extracts similar patients similar to the target patient based on the additional information acquired by the additional information acquisition function 61. Further, the medical document acquisition function 63 acquires a plurality of medical documents created for the similar patients extracted by the similar patient extraction function 62. Further, the medical document creation function 64 creates a medical document for the target patient based on the additional information acquired by the additional information acquisition function 61 and the summary of the plurality of medical documents acquired by the medical document acquisition function 63.

[0038] Thereby, since the medical document for the target patient can be created based on the summaries of the plurality of medical documents created for the similar patients similar to the target patient, it is possible to support the creation of a simple and appropriate medical document.

[0039] Further, in this embodiment, the display control function 65 displays the medical document for the target patient created by the medical document creation function 64.

[0040] Thereby, the convenience can be improved.

[0041] Further, in this embodiment, the medical document creation function 64 creates a medical document for the target patient using a large language model.

[0042] Thereby, it is possible to support the creation of a simpler and more appropriate medical document.

[0043] Also, in this embodiment, the similar patient extraction function 62 compares the incidental information of the target patient with a plurality of medical documents created for each of a plurality of past patients for each of a plurality of items, and calculates the distance between the incidental information and the plurality of medical documents for each item. Further, the similar patient extraction function 62 calculates a similarity that is the sum of the distances calculated for each item, and extracts similar patients from among the plurality of past patients based on the calculated similarity.

[0044] Thereby, similar patients can be extracted simply and appropriately.

[0045] Also, in the embodiment, the similar patient extraction function 62 extracts, as similar patients, the patients with the top similarities among the plurality of past patients.

[0046] Thereby, similar patients can be extracted more appropriately.

[0047] Also, in the embodiment, the medical document creation function 64 may create a medical document of the target patient based on the summaries of two or more medical documents having differences in a certain amount or more of the content among the medical documents of a plurality of similar patients.

[0048] Thereby, it is possible to prevent the content of the medical document of the target patient from being biased towards the content of the medical documents of specific past similar patients, so that it is possible to support the creation of a more appropriate medical document.

[0049] Also, in the embodiment, the summary of the medical document includes common items and formats among the plurality of medical documents created for each of the plurality of similar patients.

[0050] Thereby, it is possible to support the creation of a more appropriate medical document based on the common items and formats among the medical documents of the plurality of similar patients.

[0051] In addition, in the embodiment, the medical document acquisition function 63 further acquires medical images created for the similar patients extracted by the similar patient extraction function 62. Further, the medical document creation function 64 further creates a medical image of the target patient based on the additional information acquired by the additional information acquisition function 61 and the summary of the medical images acquired by the medical document acquisition function 63.

[0052] Thereby, it is possible to assist in creating a simple and appropriate medical image.

[0053] In addition, in the embodiment, the additional information of the target patient includes at least one of the examination purpose, patient attributes, medical images, information regarding the image area of interest, and examination findings.

[0054] Thereby, it is possible to assist in creating a more simple and appropriate medical document.

[0055] (First Modification Example) Next, a first modification example in which medical documents and medical images created for similar patients are further displayed will be described focusing on the differences from the above-described embodiment.

[0056] In the first modification example, when displaying the medical document and medical image of the target patient, the display control function 65 further displays the medical document created for the similar patient and the medical image created for the similar patient.

[0057] FIG. 7 is a flowchart showing an operation example of the medical information processing apparatus 1 according to the first modification example of the embodiment. FIG. 8 is a diagram showing a display step of the medical report of the target patient and the medical reports of a plurality of similar patients in the operation example of the medical information processing apparatus 1 according to the first modification example of the embodiment. In the examples shown in FIGS. 7 and 8, after the medical report of the target patient is created by the medical document creation function 64, the display control function 65 displays the medical report R of the target patient and the medical reports R1 to R3 of the similar patients #1 to #3 (step S51).

[0058] As described above, in the first modification example, the display control function 65 further displays the medical document created for the similar patients and the medical image created for the similar patients.

[0059] Thereby, the operator can easily understand that the medical document and medical image of the target patient are created based on the medical document and medical image of the similar patients, so that the reliability regarding the support for the creation of the medical document and medical image can be improved.

[0060] (Second Modification Example) Next, a second modification example of modifying the medical document of the target patient according to the input operation will be described centering on the differences from the above-described embodiment.

[0061] In the second modification example, the input interface 2 receives an input operation for modifying (i.e., updating) the medical document of the target patient displayed by the display control function 65. The medical document creation function 64 modifies the medical document of the target patient according to the input operation. The input interface 2 may receive an input operation for modifying the medical image of the target patient displayed by the display control function 65. The medical document creation function 64 may modify the medical image of the target patient according to the input operation.

[0062] Specifically, in the second modification example, the medical document creation function 64 creates, as the medical document of the target patient, a medical document that includes items and formats common among the medical documents of a plurality of similar patients and that allows items having differences among the medical documents of the plurality of similar patients to be added by an input operation. Also, in the second modification example, the similar patient extraction function 62 narrows down the number of similar patients according to the input operation. Also, in the second modification example, the medical document acquisition function 63 narrows down the number of medical documents of the similar patients according to the fact that the number of similar patients has been narrowed down by the similar patient extraction function 62. Also, in the second modification example, the medical document creation function 64 modifies the medical document of the target patient based on the summary of the number of medical documents narrowed down by the medical document acquisition function 63.

[0063] FIG. 9 is a flowchart showing an operation example of the medical information processing apparatus 1 according to the second modification of the embodiment. FIG. 10 is a diagram showing a display step of the medical report of the target patient and the medical reports of a plurality of similar patients in the operation example of the medical information processing apparatus 1 according to the second modification of the embodiment.

[0064] In the example shown in FIG. 10, the medical document creation function 64 generates the medical report R of the target patient in a state where the specific numerical value [mm] of the "size" of the abnormality C, which is an item having a difference among the medical reports of a plurality of similar patients, can be added by an input operation. That is, the medical document creation function 64 generates the medical report R of the target patient in which the specific numerical value of the size of the abnormality C can be filled in by an input operation. Further, in the example shown in FIG. 10, the medical document creation function 64 generates the medical report R of the target patient including a correction button B1 that receives an input operation for correcting the content of the medical report R of the target patient and a completion button B2 that receives an input operation for determining the content of the medical report R of the target patient. When the correction button B1 is selected, an input operation for the specific numerical value of the size of the abnormality C is received.

[0065] As shown in FIG. 9, when an input operation for modifying the medical report R of the target patient is received by the input interface 2 (step S6: Yes), the attached information acquisition function 61 acquires the input information by the input operation as the attached information of the target patient (step S1). That is, in the example shown in FIG. 9, the attached information of the target patient includes the input information by the input operation for modifying the medical report R of the target patient. In the example shown in FIG. 10, the attached information acquisition function 61 acquires the specific numerical value of the size of the abnormality C input by the input operation as the attached information of the target patient. Next, the similar patient extraction function 62 narrows down the number of similar patients according to the input operation (step S2). In the example shown in FIG. 10, the similar patient extraction function 62 narrows down the number of similar patients by extracting, from among the plurality of already extracted similar patients, the similar patients whose medical reports contain the specific numerical value of the size of the abnormality C input by the input operation. Next, the medical document acquisition function 63 narrows down the number of medical reports of similar patients according to the fact that the number of similar patients has been narrowed down by the similar patient extraction function 62 (step S3). That is, the medical document acquisition function 63 acquires the narrowed-down medical reports of similar patients. Next, the medical document creation function 64 modifies, that is, re-creates, the medical report of the target patient based on the summaries of the number of medical reports narrowed down by the medical document acquisition function 63 (step S4).

[0066] On the other hand, when an input operation for modifying the medical report R of the target patient is not received by the input interface 2 (step S6: No), the process ends. Note that if the similar patient extraction function 62 can extract a similar patient with a very high similarity as described above, it is highly likely that the medical report of the similar patient can be directly diverted as the medical report of the target patient. Therefore, a threshold value may be set for the similarity, and when the similarity exceeds the threshold value, the medical report of that patient may be directly created as the medical report of the target patient, and the process may end without accepting any modification.

[0067] As described above, in the second modification example, the input interface 2 receives an input operation for correcting the medical document of the target patient displayed by the display control function 65. Further, the medical document creation function 64 corrects the medical document of the target patient according to the input operation.

[0068] By receiving an input operation for correcting the medical document of the target patient, it is possible to support the creation of a more appropriate medical document.

[0069] Also, in the second modification example, the additional information of the target patient includes input information by an input operation for correcting the medical document of the target patient. Further, the similar patient extraction function 62 narrows down the number of similar patients according to the input operation for correcting the medical document. That is, the similar patient extraction function 62 narrows down the number of similar patients in response to the acquisition information obtained by the additional information acquisition function 61 as additional information by an input operation for correcting the medical document of the target patient. Further, the medical document acquisition function 63 narrows down the number of medical documents in response to the narrowing down of the number of similar patients by the similar patient extraction function 62. Further, the medical document creation function 64 corrects the medical document of the target patient based on the summary of the number of medical documents narrowed down by the medical document acquisition function 63.

[0070] As a result, the medical document of the target patient can be brought closer to completion according to the progress of the input operation for correcting the medical document of the target patient, so that it is possible to support the creation of a more convenient and appropriate medical document.

[0071] Also, in the second modification example, the medical document creation function 64 creates a medical document that includes common items and formats among the medical documents of a plurality of similar patients as the medical document of the target patient, and items having differences among the medical documents of a plurality of similar patients can be added by an input operation.

[0072] As a result, it is possible to support the creation of a more convenient and appropriate medical document.

[0073] (Third Modification Example) Next, a third modification example of modifying a medical document of a target patient according to an input operation will be described focusing on differences from the above-described embodiments.

[0074] In the second modification example, the medical document creation function 64 creates, as a medical document of a target patient, a medical document that includes common items and formats among medical documents of a plurality of similar patients, and items having differences among medical documents of a plurality of similar patients can be added by an input operation. In addition to this, in the third modification example, the medical document creation function 64 creates a medical document in which some items having differences among medical documents of a plurality of similar patients can be selected from options by an input operation.

[0075] FIG. 11 is a diagram showing a display step of a medical report of a target patient and medical reports of a plurality of similar patients in an operation example of the medical information processing apparatus 1 according to the third modification example of the embodiment. In the example shown in FIG. 11, the medical document creation function 64 generates a medical report R of a target patient in a state where the "shape" of abnormality C, which is an item having a difference among medical reports of similar patients, can be selected from the options "B and H" by an input operation. Similar to the second modification example, for the "size" of abnormality C, specific numerical values can be input by an input operation. When the correction button B1 is selected in FIG. 11, an input operation for selecting the shape of abnormality C is accepted. When an input operation for selecting the shape of abnormality C is accepted, the selected shape is acquired as additional information of the target patient by the additional information acquisition function 61. In response to this, the number of similar patients is narrowed down by the similar patient extraction function 62, and the number of medical documents of similar patients is narrowed down by the medical document acquisition function 63. Then, the medical document creation function 64 corrects the medical document of the target patient based on the summary of the number of medical documents narrowed down by the medical document acquisition function 63.

[0076] As described above, in the third modification example, the medical document creation function 64 creates, as a medical document of a target patient, a medical document that includes common items and formats among medical documents of a plurality of similar patients, and items having differences among medical documents of a plurality of similar patients can be selected from options by an input operation.

[0077] This makes it possible to support the creation of more convenient medical documents. (The fourth modification example) FIG. 12 is a diagram showing a display step of a medical report of a target patient and medical reports of a plurality of similar patients in an operation example of the medical information processing apparatus 1 according to the fourth modification example of the embodiment.

[0078] In the fourth modification example, the medical document creation function 64 creates, as a medical document of a target patient, a medical document in which items having differences among medical documents of a plurality of similar patients and having smaller differences than items that can be added by an input operation or selected from options are described in a character color according to the magnitude of the differences.

[0079] In the example shown in FIG. 12, the medical document creation function 64 creates, as a medical document of a target patient, a medical document in which "Shape B", which is an item having smaller differences than "Size" among medical reports of similar patients, is described in a different character color from "Part A" and "Abnormality C", which are common items among medical reports of similar patients. The character color of the item varies according to the magnitude of the differences among medical reports of similar patients. For example, the character color of the item is different between when the difference is moderate and when the difference is small. "Shape B" may be modifiable by selecting the modification button B1.

[0080] As described above, in the fourth modification example, the medical document creation function 64 creates, as a medical document of a target patient, a medical document in which items having differences among a plurality of medical documents and having smaller differences than items that can be added by an input operation or selected from options are described in a character color according to the magnitude of the differences.

[0081] This makes it possible to support the creation of more appropriate medical documents.

[0082] Note that the term "processor" used in the above description means, for example, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), or a circuit such as 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)). The processor realizes its function by reading and executing a program stored in a storage circuit. Instead of storing a program in the storage circuit, the program may be directly incorporated into the circuit of the processor. In this case, the processor realizes its function by reading and executing the program incorporated into the circuit. Note that the processor is not limited to being configured as a single processor circuit, and a plurality of independent circuits may be combined to form one processor to realize its function. Further, a plurality of components in FIG. 1 may be integrated into one processor to realize its function.

[0083] According to at least one of the embodiments described above, it is possible to assist in creating a simple and appropriate medical document.

[0084] As described above, several embodiments have been described, but these embodiments are presented only as examples and are not intended to limit the scope of the invention. The novel devices and methods described in this specification can be implemented in various other forms. Also, various omissions, substitutions, and changes can be made to the forms of the devices and methods described in this specification without departing from the gist of the invention. The scope of the appended claims and equivalents thereof are intended to include such forms and modifications within the scope and gist of the invention.

Description of Symbols

[0085] 1 Medical information processing device 2 Input interface 61 Ancillary information acquisition function 62 Similar patient extraction function 63 Medical document acquisition function 64 Medical document creation function 65 Display control function

Claims

1. An incidental information acquisition unit that acquires incidental information of a target patient, A similar patient extraction unit that extracts similar patients similar to the target patient based on the incidental information acquired by the incidental information acquisition unit, A medical document acquisition unit that acquires a plurality of medical documents created for the similar patients extracted by the similar patient extraction unit, A medical document creation unit that creates a medical document of the target patient based on the incidental information acquired by the incidental information acquisition unit and the summary of the plurality of medical documents acquired by the medical document acquisition unit, A medical information processing device comprising the above.

2. The medical information processing device according to claim 1, further comprising a display control unit that displays the medical document of the target patient created by the medical document creation unit.

3. The medical information processing device according to claim 1, wherein the medical document creation unit creates the medical document of the target patient using a large language model.

4. The similar patient extraction unit compares the incidental information of the target patient with a plurality of medical documents created for each of a plurality of past patients for each of a plurality of items, calculates the distance between the incidental information and the plurality of medical documents for each item, calculates a similarity that is the sum of the distances calculated for each item, and extracts the similar patients from among the plurality of past patients based on the calculated similarity. The medical information processing device according to claim 1.

5. The medical information processing device according to claim 4, wherein the similar patient extraction unit extracts the patients with the highest similarity among the plurality of past patients as the similar patients.

6. The similar patient extraction unit extracts a plurality of similar patients, The medical document acquisition unit acquires a plurality of medical documents created for each of the plurality of similar patients, The medical document creation unit creates the medical document of the target patient based on the summaries of two or more medical documents having differences in content of a certain amount or more among the plurality of medical documents. The medical information processing device according to claim 1.

7. The medical information processing device according to claim 2, further comprising an input interface that receives an input operation for correcting the medical document of the target patient displayed by the display control unit, The medical document creation unit corrects the medical document of the target patient according to the input operation.

8. The similar patient extraction unit narrows down the number of similar patients according to the input operation, The medical document acquisition unit narrows down the number of the medical documents in response to the narrowing down of the number of the similar patients by the similar patient extraction unit. The medical document creation unit corrects the medical document of the target patient based on the summaries of the medical documents in the number narrowed down by the medical document acquisition unit. The medical information processing apparatus according to claim 7.

9. The similar patient extraction unit extracts a plurality of similar patients. The summary of the medical documents includes common items and formats among a plurality of medical documents created for each of the plurality of similar patients. The medical information processing apparatus according to claim 1.

10. The similar patient extraction unit extracts a plurality of similar patients. The summary of the medical documents includes common items and formats among a plurality of medical documents created for each of the plurality of similar patients. The medical document creation unit creates, as the medical document of the target patient, a medical document that includes common items and formats among the plurality of medical documents and in which items having differences among the plurality of medical documents can be added by the input operation or selected from options by the input operation. The medical information processing apparatus according to claim 7.

11. The medical document creation unit creates, as the medical document of the target patient, a medical document in which items having differences among the plurality of medical documents and having smaller differences than the items that can be added by the input operation or selected from the options are described in a character color corresponding to the magnitude of the differences. The medical information processing apparatus according to claim 10.

12. The medical document acquisition unit further acquires a plurality of medical images created for the similar patients extracted by the similar patient extraction unit. The medical document creation unit further creates a medical image of the target patient based on the additional information acquired by the additional information acquisition unit and the summary of the plurality of medical images acquired by the medical document acquisition unit. The medical information processing apparatus according to claim 2.

13. The display control unit further displays a plurality of medical documents created for the similar patients and a plurality of medical images created for the similar patients. The medical information processing apparatus according to claim 2.

14. The additional information includes at least one of an examination purpose, patient attributes, medical images, information on an image region of interest, and examination findings. The medical information processing apparatus according to claim 1.

15. The medical information processing apparatus according to claim 7, wherein the additional information includes at least one of an examination purpose, patient attributes, medical images, information regarding an image region of interest, and examination findings, and input information by the input operation for modifying a medical document of the target patient.

16. Obtain additional information of a target patient, Extract a similar patient similar to the target patient based on the obtained additional information, Obtain a plurality of medical documents created for the extracted similar patient, and Create a medical document of the target patient based on the obtained additional information and a summary of the obtained plurality of medical documents. A medical information processing method.

17. A program for causing a computer to execute a procedure for obtaining additional information of a target patient, a procedure for extracting a similar patient similar to the target patient based on the obtained additional information, a procedure for obtaining a plurality of medical documents created for the extracted similar patient, and a procedure for creating a medical document of the target patient based on the obtained additional information and a summary of the obtained plurality of medical documents. ​

Citation Information

Patent Citations

  • Diagnostic result explanation report creation device, diagnostic result explanation report creation method and diagnostic result explanation report creation program

    JP2012094127A

  • Image interpretation report creation support apparatus and image interpretation report creation support method

    JP2019105921A

  • Image diagnostic system and image diagnostic method

    JP2022146822A

  • Medical information analysis program, medical information analysis device, and medical information analysis method

    WO2014076777A1