Information processing device, information processing method, and information processing program

Abstract

The objective is to provide an information processing device, an information processing method, and an information processing program that can obtain information to facilitate the searching of medical documents. [Solution] The reception unit 20 receives medical documents such as image interpretation reports and electronic medical records from a client terminal 12 operated by a doctor or the like. The extraction unit 22 extracts treatment-related finding terms from the medical documents, such as terms corresponding to surgery, treatment, and at least one of predetermined artificial objects. The determination unit 24 determines the organ to be treated from the medical documents. The generation unit 26 generates treatment information representing the treatment status from the extracted treatment terms and the determined organ. The output unit 28 outputs the treatment information.

Description

Technical Field

[0001] The present disclosure relates to an information processing apparatus, an information processing method, and an information processing program.

Background Art

[0002] Patent Document 1 discloses an information processing apparatus including one or more processors and one or more memories in which instructions executed by the one or more processors are stored. The one or more processors acquire a sentence, classify attributes of information described in the sentence in a certain unit of the sentence, analyze the sentence for each same classification based on the classification result, and output the analysis result.

[0003] Patent Document 2 discloses an information processing system for assisting in selecting a patient who is a candidate for a clinical trial, the information processing system having a structuring processing unit that structures text information input to a predetermined screen, and a candidate processing unit that identifies a patient who is a candidate for a clinical trial using the information obtained by structuring the input text information and the information on the criteria of the clinical trial.

[0004] Patent Document 3 discloses a method of organizing medical record data according to indexed intervention events specified for each record related to a medical intervention, based on the classification of a set of medical records. The method involves extracting one or more candidate intervention events for each of a plurality of medical records, and then mapping these to a dataset (or ontology) of standard intervention event names (indexed intervention events) to identify the closest matching indexed event for each extracted intervention event. The mapping is based on classifying each extracted intervention event into a set of characterizing attributes of a particular domain or type, and then comparing these with the corresponding set of attributes for each indexed event in the dataset. Once the closest match is found, each medical record is classified according to the closest matching indexed event. The data is then aggregated based on the classification and also based on information about the user, for example, a particular specialized clinical area.

[0005] Patent Document 4 discloses a similar case search system comprising: a case management server device that stores search target cases including at least medical documents; an examination instruction input unit that inputs search input cases including at least medical documents; a feature extraction unit that extracts feature quantities from the search input cases input by the examination instruction input unit; a first search unit that searches to obtain cases from the search target cases stored in the case management server device that have feature quantities that are more similar to the feature quantities of the search input cases than a predetermined value; and a second search unit that searches to obtain medical information including medical procedures and the results of said medical procedures from the search result cases obtained as a result of the search by the first search unit.

[0006] Patent Document 5 discloses a medical support device comprising a first extraction unit, a second extraction unit, and a third extraction unit, which are a guideline search function and an output unit. The first extraction unit extracts first document information relating to medical word groups included in the patient's medical information from among multiple literature information relating to medical treatment. The second extraction unit extracts first word groups from each first word group contained in each itemized description section within the first document information based on their relevance to the medical word group. The third extraction unit extracts second word groups from each second word group contained in each itemized description section within the second document information based on their relevance to the extracted first word group and medical word group. The output unit outputs the first document information and the second document information based on the extracted first word group and the extracted second word group. [Prior art documents] [Patent Documents]

[0007] [Patent Document 1] Japanese Patent Publication No. 2023-114341 [Patent Document 2] Japanese Patent Publication No. 2022-180080 [Patent Document 3] Japanese Patent Publication No. 2021-536636 [Patent Document 4] Japanese Patent Publication No. 2015-203920 [Patent Document 5] Japanese Patent Publication No. 2023-88036 [Overview of the project] [Problems that the invention aims to solve]

[0008] While various techniques exist for extracting specific terms from medical documents such as radiology reports and electronic medical records, there is still room for improvement in obtaining information that makes medical documents easier to search.

[0009] Therefore, this disclosure aims to provide an information processing device, an information processing method, and an information processing program that can obtain information to facilitate the retrieval of medical documents. [Means for solving the problem]

[0010] To achieve the above objective, the information processing device according to the first aspect of this disclosure includes a processor which receives a medical document, extracts treatment terms from the medical document, determines the organ to be treated from the medical document, and outputs treatment information representing the treatment status from the extracted treatment terms and the determined organ.

[0011] In the information processing device according to the second aspect of this disclosure, the processor extracts terms corresponding to at least one of surgery, treatment, and a predetermined artificial object as therapeutic terms, in the information processing device according to the first aspect.

[0012] The information processing device according to the third aspect of this disclosure, in the information processing device according to the first aspect, outputs information as treatment information that includes at least one of the extracted treatment terms and the determined organs, and identifies any of the treatment states before, during, or after treatment.

[0013] The information processing device according to the fourth aspect of this disclosure, in the information processing device according to the second aspect, further adds information classifying anatomical regions, diagnostic information, and treatment types to the treatment information based on extracted treatment terms.

[0014] The information processing device according to the fifth aspect of this disclosure, in the information processing device according to the fourth aspect, has a processor that acquires information on anatomical regions and diagnostic information by extracting terms and relationships.

[0015] The information processing device according to the sixth aspect of this disclosure, in the information processing device according to the first aspect, has a processor that displays treatment information in a predetermined display method according to the organ.

[0016] An information processing device according to the seventh aspect of this disclosure, in an information processing device according to the first aspect, the processor displays treatment information by means of at least one of text, images, and tables.

[0017] The information processing device relating to the eighth aspect of this disclosure, in the information processing device relating to the first aspect, includes medical documents that have been received in the past.

[0018] An information processing device according to the ninth aspect of this disclosure, in an information processing device according to the first aspect, the processor displays at least one of the extracted therapeutic terms and the terms that were the subject of organ determination in a manner different from other terms contained in the medical document.

[0019] The information processing method relating to the tenth aspect of this disclosure involves a computer receiving a medical document, extracting treatment terms from the medical document, determining the organ to be treated from the medical document, and outputting treatment information representing the treatment status from the extracted treatment terms and the determined organ.

[0020] The information processing device according to the 11th aspect of this disclosure causes a computer to perform the following processes: receive a medical document, extract treatment terms from the medical document, determine the organ to be treated from the medical document, and output treatment information representing the treatment status from the extracted treatment terms and the determined organ. [Effects of the Invention]

[0021] According to this disclosure, it is possible to provide an information processing device, an information processing method, and an information processing program that can obtain information to facilitate the retrieval of medical documents.

Brief Description of the Drawings

[0022] [Figure 1] It is a diagram showing the schematic configuration of the information processing system according to this embodiment. [Figure 2] It is a block diagram showing the main electrical component configurations of the client terminal and the server of the information processing system according to this embodiment. [Figure 3] It is a functional block diagram showing the functional configuration of the server in the information processing system according to this embodiment. [Figure 4] It is a diagram showing the overall picture until the treatment information is output by the server of the information processing system according to this embodiment. [Figure 5] It is a diagram showing a specific configuration example of the extraction unit. [Figure 6] It is a diagram showing the probability distribution of NER labels obtained by the decoder. [Figure 7] It is a diagram showing a specific configuration example of the determination unit. [Figure 8] It is a diagram showing another specific configuration example of the determination unit. [Figure 9] It is a diagram for explaining the extraction of anatomical regions and diagnoses. [Figure 10] It is a flowchart showing an example of the processing flow performed by the server of the information processing system according to this embodiment. [Figure 11] It is a diagram showing a general-purpose personal computer.

Modes for Carrying Out the Invention

[0023] Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. Note that this embodiment does not limit the present invention. FIG. 1 is a diagram showing the schematic configuration of the information processing system according to this embodiment.

[0024] As shown in Figure 1, the information processing system 10 according to this embodiment includes a client terminal 12 and a server 14. The client terminal 12 and the server 14 are each connected to a communication line 16 and are able to communicate with each other via the communication line 16.

[0025] Examples of communication lines 16 include the Internet, LAN (Local Area Network), and WAN (Wide Area Network). While Figure 1 shows an example with multiple client terminals 12 (two in Figure 1), there may be a single client terminal 12 or three or more. Furthermore, the client terminal 12 may be a personal computer, a tablet, or a smartphone.

[0026] The information processing system 10 according to this embodiment is implemented as a computer network built in a medical institution such as a hospital that handles medical information. In Figure 1, it is shown to include a client terminal 12 and a server 14, but it is not limited to this. For example, as described in Japanese Patent Application Publication No. 2023-114341, it may further include an electronic medical record system, an examination order system, medical imaging equipment (e.g., a CT scanner or MRI scanner), an image storage server, an image interpretation report server, etc. Alternatively, the server 14 may have the functions of these devices.

[0027] Figure 2 is a block diagram showing the main electrical components of the client terminal 12 and server 14 of the information processing system 10 according to this embodiment. Since the client terminal 12 and server 14 have a typical computer configuration, the server 14 will be described as a representative example below.

[0028] Server 14 includes a CPU (Central Processing Unit) 14A as an example of a processor, ROM (Read Only Memory) 14B, RAM (Random Access Memory) 14C, storage 14D, operation unit 14E, display unit 14F, and communication interface unit 14G. The CPU 14A controls the overall operation of Server 14. ROM 14B stores various control programs and parameters in advance. RAM 14C is used as a work area when various programs are executed by the CPU 14A. Storage 14D stores various data and application programs. The operation unit 14E is used to input various information. The display unit 14F is used to display various information. The communication interface unit 14G can connect to external devices and transmits and receives various data with external devices. All of the above parts of Client Terminal 12 are electrically interconnected by a system bus 14H. In this embodiment, the server 14 uses storage 14D as the storage unit, but it is not limited to this, and other non-volatile storage units such as hard disks or flash memory may be used.

[0029] With the above configuration, the server 14 in this embodiment uses the CPU 14A to access the ROM 14B, RAM 14C, and storage 14D, acquire various data via the operation unit 14E, and display various information on the display unit 14F. The server 14 also uses the CPU 14A to control the transmission and reception of various data via the communication interface unit 14G. In this embodiment, a database (DB) 30 (see Figure 3) is constructed in the storage 14D to store image interpretation reports and treatment information representing the treatment status derived from the image interpretation reports.

[0030] In this embodiment, the server 14 performs processing to derive information from medical documents such as image interpretation reports and electronic medical records that document the results of analysis of medical images (e.g., radiographic images such as CT images, MRI images, and X-ray images) in order to make medical documents easier to search. Specifically, the server 14 performs processing to derive treatment information representing the treatment status from the medical documents as information to make medical documents easier to search.

[0031] In detail, in order to perform the process of deriving treatment information from medical documents, the CPU 14A of the server 14 loads an information processing program pre-stored in ROM 14B or storage 14D into RAM 14C and executes it, thereby realizing the function shown in Figure 3. Figure 3 is a functional block diagram showing the functional configuration of the server 14 in the information processing system 10 according to this embodiment.

[0032] As shown in Figure 3, the server 14 in the information processing system 10 according to this embodiment has the functions of a reception unit 20, an extraction unit 22, a determination unit 24, a generation unit 26, and an output unit 28.

[0033] The reception unit 20 receives medical documents such as image interpretation reports and electronic medical records from client terminals 12 operated by doctors and other medical professionals. These medical documents may include those previously received. For example, the reception unit 20 may receive medical documents from client terminals and store them in DB 30. When predetermined conditions are met, such as the amount of medical documents stored in DB 30 reaching a predetermined level, the reception unit 20 may then receive medical documents from DB 30. The following explanation will describe the case where an image interpretation report is used as an example of a medical document.

[0034] The extraction unit 22 extracts therapeutic terms from medical documents. For example, it extracts therapeutic terms from medical documents such as terms related to findings, including terms that correspond to surgery, treatment, and at least one of predetermined artificial objects such as surgical instruments or drugs.

[0035] The determination unit 24 determines the organ to be treated from the medical document. For example, it determines the treated organ (e.g., brain, esophagus, lungs, mediastinum, heart, liver, gallbladder, pancreas, spleen, adrenal gland, large intestine, small intestine, abdomen, limbs, thyroid gland, uterus, etc.) from the medical document.

[0036] The generation unit 26 generates treatment information representing the treatment status from the extracted treatment terms and the determined organs. For example, the generation unit 26 generates treatment information that includes at least one of the treatment terms extracted by the extraction unit 22 and the organs determined by the determination unit 24, and identifies the treatment status as either pre-treatment, during treatment, or post-treatment. The generation unit 26 may further add information on anatomical regions, diagnostic information, and information classifying the type of treatment to the treatment information based on the extracted treatment terms. For example, information on anatomical regions and diagnostic information are obtained by extracting terms and extracting relationships. The generation unit 26 may also add treatment classifications after classifying the type of treatment. This allows for the acquisition of detailed and uniform treatment information. Furthermore, when generating treatment information, the generation unit 26 may normalize the terms by unifying English to Japanese, unifying synonyms, etc.

[0037] The output unit 28 outputs the generated treatment information. For example, the output unit 28 outputs to DB 28 and stores it in DB 30 in association with the image interpretation report. Alternatively, the output unit 28 may output the treatment information to the client terminal 12 and display the treatment information on the display unit 12F of the client terminal 12.

[0038] The treatment information output from the output unit 28 includes treatment terms for surgical instruments, drugs, and other artificial objects, so considering it as a treatment performed improves the coverage rate when searching for image interpretation reports. Furthermore, the treatment information includes treatment terms and at least one of the organs, and represents either the pre-treatment, during treatment, or post-treatment state, allowing for the use of information more appropriate to the application.

[0039] Here, we will explain the overall process of generating treatment information with reference to Figure 4. Figure 4 is a diagram showing the overall process from the server 14 of the information processing system 10 according to this embodiment until the output of treatment information.

[0040] First, the reception unit 20 receives the image interpretation report. For example, as shown in Figure 4, we will explain an example of receiving an image interpretation report with the following content. "We compared it with the previous CT scan." I am currently undergoing chemotherapy for right lung cancer. Pre-RT for HCC in liver segment S1. Post-operative care for a left femoral fracture. Callus formation is observed. After a pelvic fracture. An artificial hip joint has been implanted. After cholecystectomy. I have a kidney stone in my right kidney.

[0041] Upon receiving the image interpretation report, the extraction unit 22 extracts treatment terms. In the case of the above image interpretation report, "during chemotherapy," "before RT," and "artificial joint" are extracted as treatment terms.

[0042] Next, the judgment unit 24 determines the organs from the image interpretation report. In the case of the above image interpretation report, it determines the organs to be "lungs," "femur," "artificial hip joint," and "gallbladder."

[0043] The generation unit 26 generates treatment information from treatment terms and organs, and the output unit 28 outputs the generated treatment information to the DB 28 and to the client terminal 12. Figure 4 shows an example in which treatment information is generated and output, including terms, organs, types, classifications, diagnoses, anatomy, and status. Specifically, in the treatment information shown in Figure 4, the terms are "during chemotherapy," "before RT (before radiation therapy)," "post-left femoral fracture (post-femoral fracture surgery)," "artificial joint," and "post-gallbladder removal." The organs corresponding to each term are "lungs," "liver," "limbs," "abdomen," and "gallbladder." The corresponding classifications are "chemotherapy," "external beam radiation," "other (unknown)," "implantation of artificial implants (surgical treatment)," and "excision / resection." The corresponding diagnoses are "lung cancer," "HCC (hepatocellular carcinoma)," and "fracture." The corresponding anatomical structures are "right lung," "liver S1," "femur," "hip joint," and "gallbladder." The corresponding states are "under treatment," "before treatment," "post-operative," "post-operative," and "post-operative." When outputting and displaying treatment information, the output unit 28 displays the treatment information using at least one of text, images, and tables. For example, Figure 4 shows an example of displaying treatment information using a table.

[0044] Furthermore, when displaying treatment information, the output unit 28 may display the treatment information using a predetermined display method depending on the organ. For example, if the organ is the abdomen, an abdominal CT image is displayed and the target area is annotated; if the organ is the lungs, an X-ray image is displayed. If the organ is the nose, only a table is displayed without an image, as shown in Figure 4. Alternatively, the target area may be annotated on a schematic.

[0045] Furthermore, when displaying treatment information, output 28 may display at least one of the extracted treatment terms and the terms used for organ determination in a manner different from other terms included in the medical document. For example, as shown in Figure 4, an example is shown in which the extracted treatment terms and other terms are displayed in a manner different from those extracted in the interpretation report by the presence or absence of underlining. Also, an example is shown in which the terms used for organ determination and other terms are displayed in a manner different from those used for organ determination by the use of text color or fill.

[0046] Treatments can be broadly categorized into surgery, radiation therapy, and drug therapy, but there are also combinations of these treatments, as well as ablation and cryotherapy.

[0047] Next, we will describe specific configuration examples of the extraction unit 22, the determination unit 24, and the generation unit 26 in the functions of server 14.

[0048] First, let's describe a specific example of the configuration of the extraction unit 22. Figure 5 shows a specific example of the configuration of the extraction unit 22.

[0049] The extraction unit 22 uses Named Entity Recognition (NER) technology to acquire term expressions and determine their type. The tasks of the extraction unit 22 include a classification task that accepts a sequence of tokens as input and predicts a label for each token in the input, and a task that distinguishes the start and end of a Named Entity (NE) using the BIO method. The BIO method is a method that identifies the start and end of a Named Entity using tags: "Begin" to indicate the start of a Named Entity, "Inside" to indicate a sequence (internal) of Named Entities, and "other" to indicate something that is not a Named Entity (everything else).

[0050] The extraction unit 22 can be configured, for example, using an encoder-decoder model. Figure 5 shows an example of a term extraction model 40 applied to the extraction unit 22. The term extraction model 40 includes an encoder 42 and a decoder 44. The encoder 42 is configured using a neural network such as BERT or LSTM (Long Short Term Memory). The encoder 42 obtains a distributed representation from the input text. The decoder 44 predicts a probability distribution for a label from the distributed representation of each token output from the encoder 42 using a fully connected layer. NER handles NER labels, which are a combination of BIO labels and NE labels.

[0051] For example, the label "B Diagnosis" shown in Figure 5 is an NER label that combines the BIO label "Begin" and the NE label "Diagnosis," and the label "I Treatment" is an NER label that combines the BIO label "Inside" and the NE label "Treatment."

[0052] Figure 6 shows an example of the probability distribution of NER labels obtained by the decoder 44. The term extraction model 40 is trained to minimize the cross-entropy of the softmax function output of the decoder 44.

[0053] Figure 7 shows a specific example of the configuration of the determination unit 24. The determination unit 24 can be configured using, for example, a natural language processing model called BERT (Bidirectional Encoder Representations from Transformers). When a sentence is input to the BERT model 46, the BERT model 46 provides output values ​​t1, t2, ...tn for each token. Note that other machine learning models, such as Recurrent Neural Networks (RNNs) or Support Vector Machines (SVMs), may also be applied, not limited to BERT.

[0054] The determination unit 24 uses these document classification techniques to determine the type of organ in each sentence within the image interpretation report. For example, Figure 7 shows an example where the document "After radiation therapy for lung cancer." is input to the BERT model 46, and the result output is "lung." When inputting, surrounding sentences (N sentences before and M sentences after) of the target sentence may also be input and judged together. For example, in the case of the sentence "After right upper lobectomy. After radiation therapy.", by considering the preceding sentence, it can be determined that "After radiation therapy." is a sentence about the lung.

[0055] Furthermore, in addition to the document classification technology described above, the determination unit 24 may also extract anatomical terms using term extraction, as shown in Figure 8, and determine the type of organ based on a pre-created anatomical hierarchical structure list 48. Alternatively, the organ may be determined in combination with a document classification technology such as BERT. Or, the organ may be determined using a machine learning model created by pre-training the anatomical hierarchical structure list 48.

[0056] Furthermore, the extraction of anatomical regions and diagnoses can be performed using the same method as described in Japanese Patent Publication No. 2023-114341. Figure 9 is a diagram illustrating the extraction of anatomical regions and diagnoses. The extraction unit 22 extracts terms related to anatomical regions, diagnoses, and treatments using term extraction, and extracts terms related to treatments using relationship extraction. In this way, by obtaining anatomical region and diagnostic information through term extraction and relationship extraction, it becomes possible to obtain information even if anatomical or diagnostic information is not included in treatment terms.

[0057] In the example in Figure 9, the terms "liver S1," "HCC," and "pre-RT" are extracted from "pre-RT for HCC in liver S1." using term extraction, and then "liver S1" is extracted as an "anatomical segment" term, "HCC" as a "diagnosis" term, and "pre-RT" as a "treatment" term using relationship extraction. Note that *1 in the figure indicates the normalized terms, and *2 indicates terms that can be extracted by term extraction and relationship extraction.

[0058] Next, we will explain the specific processing performed by the server 14 in the information processing system 10 configured according to this embodiment as described above. Figure 10 is a flowchart showing an example of the processing flow performed by the server 14 in the information processing system 10 according to this embodiment.

[0059] In step 100, the CPU 14A receives the image interpretation report and proceeds to step 102. That is, the reception unit 20 receives the image interpretation report from the client terminal 12 operated by a doctor or other medical professional. Alternatively, the reception unit 20 may receive the image interpretation report from the client terminal and store it in the DB 30, and then, when the number of image interpretation reports stored in the DB 30 reaches a predetermined amount or other predetermined conditions are met, the reception unit 20 may receive the image interpretation report from the DB 30.

[0060] In step 102, CPU 14A extracts treatment terms from the image interpretation report and proceeds to step 104. In other words, the extraction unit extracts treatment terms related to the treatment from the image interpretation report.

[0061] In step 104, the CPU 14A determines the organ to be treated from the image interpretation report and proceeds to step 106. That is, the determination unit 24 determines the organ to be treated from the image interpretation report.

[0062] In step 106, the CPU 14A generates treatment information and proceeds to step 108. Specifically, the generation unit 26 generates treatment information from the extracted treatment terms and determined organs. For example, as described above, it generates terms, organs, types, classifications, diagnoses, anatomy, and conditions as treatment information.

[0063] In step 108, the CPU 14A outputs treatment information, completing the series of processes on the server 14. Specifically, the output unit 28 stores the treatment information and the image interpretation report in DB 30, associating them. This makes it possible to easily search for the image interpretation report using the treatment information. The treatment information is also output to the client terminal 12 and displayed on the display unit 12F of the client terminal 12. This makes it possible to confirm the treatment information generated by the server 14.

[0064] While specific examples of the extraction unit 22, determination unit 24, and generation unit 26 have been described, the system is not limited to those described above. For example, treatment information may be generated using AI such as generation AI (Artificial Intelligence).

[0065] Furthermore, although the above embodiment was described as an information processing system 10 including a client terminal 12 and a server 14, as shown in Figure 11, a single device such as a general-purpose personal computer 50 equipped with a display unit 50H and an operation unit 50S such as a keyboard and mouse may also be used as the information processing system. When a personal computer 50 is used, by providing the server 14's functions to the application for managing medical documents, it becomes possible to generate treatment information and store it in association with medical information.

[0066] Furthermore, in this embodiment, each process is executed on any computer. Alternatively, any computer may execute these processes using a processor as hardware, a program as software, or a combination thereof. In that case, the processor is configured to work in cooperation with the program to execute the various processes in this embodiment, and can function as a unit or means in this embodiment. The execution order of the processes by the processor is not limited to the order described and may be changed as appropriate. Any computer may be a general-purpose computer, a computer designed for a specific purpose, a workstation, or any other system capable of executing each process.

[0067] Furthermore, the processor may be composed of one or more hardware components, and the type of hardware is not limited. For example, the processor may be composed of hardware such as a CPU (Central Processing Unit), MPU (Micro Processing Unit), FPGA (Field Programmable Gate Array) or other programmable logic devices, ASIC (Application Specific Integrated Circuit) or other dedicated circuits for executing specific processes, GPU (Graphic Processing Unit), or NPU (Neural Processing Unit). The type of hardware may also be a combination of different types of hardware. When multiple hardware components are configured to execute one or more processes of a given processor, these multiple hardware components may reside in physically separate devices or in the same device. Also, in any embodiment, the order of each process performed by the processor is not limited to the order described above and may be changed as appropriate. Hardware is composed of electrical circuits (circuitry) that combine circuit elements such as semiconductor elements.

[0068] Furthermore, the program may be firmware or software such as microcode. Alternatively, the program may be, for example, a set of program modules, each function of which may be implemented by a processor configured to perform its respective function. The program may be program code or multiple code segments stored on one or more non-temporary computer-readable media (e.g., storage media or other storage). The program may be divided and stored on multiple non-temporary computer-readable media located on physically separate devices. Program code or code segments may represent any combination of procedures, functions, subprograms, routines, subroutines, modules, software packages, classes, or instructions, data structures, or program statements. Program code or code segments may be connected to other code segments or hardware circuits by sending and receiving information, data, arguments, parameters, or memory contents.

[0069] Furthermore, although the above embodiment describes an embodiment in which the information processing program is pre-stored (installed) in ROM 14B or storage 14D, the invention is not limited to this. The information processing program may be provided in the form of a recording medium such as a CD-ROM (Compact Disc Read Only Memory), DVD-ROM (Digital Versatile Disc Read Only Memory), or USB (Universal Serial Bus) memory. Alternatively, the information processing program may be provided in the form of a download from an external device via a network.

[0070] The technology disclosed herein extends to all program products. A program product includes all forms of products for providing programs. For example, a program product includes programs provided via a network such as the Internet, and non-temporary computer-readable recording media such as CD-ROMs, DVDs, and USB memory sticks on which programs are stored.

[0071] The following additional information is disclosed regarding the embodiments described above. (Note 1) The processor comprises, We accept medical documents, From the aforementioned medical documents, treatment terms were extracted. From the aforementioned medical documents, determine the organs to be treated. An information processing device that performs processing to output treatment information representing the treatment status from the extracted treatment terms and the determined organs.

[0072] (Note 2) The processor is an information processing device according to Appendix 1, which extracts terms corresponding to at least one of surgery, treatment, and a predetermined artificial object as the treatment terms.

[0073] (Note 3) The information processing device according to Appendix 1 or Appendix 2, wherein the processor outputs information that identifies a treatment state before, during, or after treatment, including at least one of the extracted treatment terms and the determined organs, as treatment information.

[0074] (Note 4) The processor is an information processing device as described in any one of the appendices 1 to 3, which further adds information classifying anatomical regions, diagnostic information, and types of treatment to the treatment information based on the extracted treatment terms.

[0075] (Note 5) The processor is an information processing device according to Appendix 4 that acquires information on the anatomical region and diagnostic information by extracting terms and relationships.

[0076] (Note 6) The processor is an information processing device according to any one of the appendices 1 to 6, which displays the treatment information in a predetermined display method according to the organ.

[0077] (Note 7) The processor is an information processing device according to any one of Appendix 1 to 7 that displays the treatment information by at least one of text, images, and tables.

[0078] (Note 8) The aforementioned medical document is an information processing device described in any one of the appendices 1 to 8, including medical documents received in the past.

[0079] (Note 9) The processor is an information processing device according to any one of the appendices 1 to 9, which displays at least one of the extracted treatment terms and the terms that were the subject of the organ determination in a manner different from other terms contained in the medical document.

[0080] (Note 10) Computers We accept medical documents, From the aforementioned medical documents, treatment terms were extracted. From the aforementioned medical documents, determine the organs to be treated. An information processing method that performs a process to output treatment information representing the treatment status from the extracted treatment terms and the determined organs.

[0081] (Note 11) On the computer, We accept medical documents, From the aforementioned medical documents, treatment terms were extracted. From the aforementioned medical documents, determine the organs to be treated. An information processing program for executing a process that outputs treatment information representing the treatment status from the extracted treatment terms and the determined organs. [Explanation of symbols]

[0082] 10 Information Processing Systems 12 client terminals 12A, 14A CPU 12B, 14B ROM 12C, 14C RAM 12D, 14D storage 12E, 14E Operation section 12F, 14F display section 12G, 14G communication I / F section 12H, 14H System Bath 14 Servers 16 Communication lines 20 Reception Department 22 Extraction part 24 Judgment section 26 Generation part 28 Output section 30 DB 40 Term Extraction Models 42 IOS 44 Decoders 46 BERT model 48 List of Anatomical Hierarchical Structures 50 Personal Computers 50H display 50S operation section

Claims

1. The processor comprises, We accept medical documents, From the aforementioned medical documents, treatment terms were extracted. From the aforementioned medical documents, determine the organs to be treated. An information processing device that performs processing to output treatment information representing the treatment status from the extracted treatment terms and the determined organs.

2. The information processing apparatus according to claim 1, wherein the processor extracts terms corresponding to at least one of surgery, treatment, and a predetermined artificial object as the treatment terms.

3. The information processing apparatus according to claim 1, wherein the processor outputs information that identifies a treatment state, either before treatment, during treatment, or after treatment, including at least one of the extracted treatment terms and the determined organs, as treatment information.

4. The information processing device according to claim 1, wherein the processor further adds information classifying anatomical regions, diagnostic information, and types of treatment to the treatment information based on the extracted treatment terms.

5. The information processing apparatus according to claim 4, wherein the processor acquires information on the anatomical region and diagnostic information by extracting terms and relationships.

6. The information processing apparatus according to claim 1, wherein the processor displays the treatment information in a predetermined display method according to the organ.

7. The information processing apparatus according to claim 1, wherein the processor displays the treatment information by at least one of text, images, and tables.

8. The information processing device according to claim 1, wherein the medical documents include medical documents received in the past.

9. The information processing apparatus according to claim 1, wherein the processor displays at least one of the extracted treatment terms and the terms that were the subject of the organ determination in a manner different from other terms contained in the medical document.

10. Computers We accept medical documents, From the aforementioned medical documents, treatment terms were extracted. From the aforementioned medical documents, determine the organs to be treated. An information processing method that performs a process to output treatment information representing the treatment status from the extracted treatment terms and the determined organs.

11. On the computer, We accept medical documents, From the aforementioned medical documents, treatment terms were extracted. From the aforementioned medical documents, determine the organs to be treated. An information processing program for executing a process that outputs treatment information representing the treatment status from the extracted treatment terms and the determined organs.

Images