Test assist apparatus, test assist method, and test assist program

Abstract

To realize a test assist apparatus capable of predicting an interruption of a test resulting from the feelings of a patient being tested, such as uneasiness.SOLUTION: A test assist apparatus includes: an acquisition section for acquiring utterance information representing utterance content of a patient during a test performed on the patient, state information regarding the feelings of the patient during the test, and basic information of the test; an interruption prediction section for predicting a probability of interruption of the test on the patient from the utterance information, the state information, and the basic information, using a prediction model that is generated by machine learning in which samples of interruptions in past test are used as teacher data and that predicts the probability of interruption of the test; and an output section that outputs the probability of interruption.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to an inspection support device, an inspection support method, and an inspection support program. [Background technology]

[0002] Technologies for supporting medical treatment are known. One example of such a technology is described in Patent Document 1. Patent Document 1 describes a system for supporting medical treatment according to various aspects of a patient. The system described in Patent Document 1 includes an acquisition unit, an analysis unit, and a display control unit. The acquisition unit acquires patient information related to the patient, medical interview information indicating the patient's responses to medical interviews, and conversation information in which the patient's conversation is recorded. The analysis unit generates patient characteristic information indicating the psychological and social aspects of the patient through an analysis process using the patient information, the medical interview information, and the conversation information. The display control unit displays the patient's psychological and social aspects in an identifiable manner based on the patient characteristic information. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2023-071244 Summary of the Invention [Problem to be solved by the invention]

[0004] However, during examinations such as endoscopic examinations, patients may feel nervous or anxious. In such cases, the examination may be interrupted due to the patient feeling pain, etc. The technology described in Patent Document 1 has the problem of being unable to predict when the examination will be interrupted due to the patient's feelings of anxiety or the like during the examination.

[0005] The present disclosure has been made in consideration of the above-mentioned problems, and one exemplary purpose thereof is to provide a technology that can predict an interruption of an examination due to emotions such as anxiety of a patient during the examination. [Means for solving the problem]

[0006] An exemplary aspect of the present disclosure provides an examination support device that includes an acquisition means for acquiring utterance information representing the content of utterances made by a patient while an examination is being conducted on the patient, status information relating to the patient's emotions while the examination is being conducted, and basic information about the examination, an interruption prediction means for predicting the probability of examination interruption for the patient from the utterance information, the status information, and the basic information using a prediction model that predicts the probability of examination interruption, the prediction model being generated by machine learning using past examples of examination interruptions as training data, and an output means for outputting the interruption probability.

[0007] An exemplary aspect of the present disclosure provides an examination support method including: an acquisition process in which at least one processor acquires utterance information representing what a patient says while an examination is being conducted on the patient, status information relating to the patient's emotions while the examination is being conducted, and basic information about the examination; an interruption prediction process in which the at least one processor predicts the probability of examination interruption for the patient from the utterance information, the status information, and the basic information using a prediction model that predicts the probability of examination interruption, the prediction model being generated by machine learning using past examples of examination interruptions as training data; and an output process in which the at least one processor outputs the interruption probability.

[0008] An exemplary aspect of the present disclosure is an examination assistance program for causing a computer to function as an examination assistance device, and causes the computer to function as: an acquisition means for acquiring utterance information representing the content of a patient's utterances during an examination on the patient, status information relating to the patient's emotions during the examination, and basic information about the examination; an interruption prediction means for predicting the probability of examination interruption for the patient from the utterance information, the status information, and the basic information using a prediction model that predicts the probability of examination interruption, the prediction model being generated by machine learning using past examples of examination interruptions as training data; and an output means for outputting the interruption probability. [Effects of the Invention]

[0009] According to one exemplary aspect of the present disclosure, an exemplary effect is provided in that a technology can be provided that predicts that an examination will be interrupted due to emotions such as anxiety of a patient during the examination. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a block diagram illustrating a configuration of an inspection support device according to the present disclosure. [Figure 2] 1 is a flowchart showing the flow of an inspection support method according to the present disclosure. [Figure 3] 1 is a block diagram illustrating a configuration of an information processing device according to the present disclosure. [Figure 4] FIG. 2 is a diagram illustrating a functional configuration of a control unit according to the present disclosure. [Figure 5] 10A and 10B are diagrams illustrating specific examples of output information output by an output control unit according to the present disclosure. [Figure 6] 1 is a flowchart showing an example of the flow of an inspection support method according to the present disclosure. [Figure 7] 1 is a block diagram showing the configuration of a computer that functions as an inspection support device or an information processing device according to the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0011] The following are examples of embodiments of the present invention. However, the present invention is not limited to the exemplary embodiments shown below, and various modifications are possible within the scope of the claims. For example, embodiments obtained by appropriately combining the technologies (part or all of the products or methods) employed in the exemplary embodiments shown below may also be included in the scope of the present invention. Furthermore, embodiments obtained by appropriately omitting some of the technologies employed in the exemplary embodiments shown below may also be included in the scope of the present invention. Furthermore, the effects mentioned in the exemplary embodiments shown below are examples of effects expected in the exemplary embodiments, and do not define the scope of the present invention. In other words, embodiments that do not exhibit the effects mentioned in the exemplary embodiments shown below may also be included in the scope of the present invention.

[0012] First Exemplary Embodiment A first exemplary embodiment, which is an example of an embodiment of the present invention, will be described in detail with reference to the drawings. This exemplary embodiment is a basic form for each of the exemplary embodiments described below. Note that the scope of application of each technique employed in this exemplary embodiment is not limited to this exemplary embodiment. That is, each technique employed in this exemplary embodiment can also be employed in other exemplary embodiments included in the present disclosure, to the extent that no particular technical obstacles arise. Furthermore, each technique shown in the drawings referenced to explain this exemplary embodiment can also be employed in other exemplary embodiments included in the present disclosure, to the extent that no particular technical obstacles arise.

[0013] (Configuration of the inspection support device) The configuration of the test support device 1 will be described with reference to Fig. 1. Fig. 1 is a block diagram showing the configuration of the test support device 1. As shown in Fig. 1, the test support device 1 includes an acquisition unit 11, an interruption prediction unit 12, and an output unit 13.

[0014] The acquisition unit 11 acquires utterance information indicating the content of utterances made by a patient during an examination, state information relating to the patient's emotions during the examination, and basic information about the examination. The interruption prediction unit 12 predicts the interruption probability of the examination for the patient from the utterance information, the state information, and the basic information using a prediction model that predicts the interruption probability of the examination, the prediction model being generated by machine learning using past examples of examination interruptions as training data. The output unit 13 outputs the interruption probability.

[0015] (Effects of inspection support devices) As described above, the test support device 1 is configured to include an acquisition unit 11 that acquires utterance information indicating what the patient will say during the test, status information regarding the patient's emotions during the test, and basic information about the test, an interruption prediction unit 12 that predicts the probability of test interruption for the patient from the utterance information, the status information, and the basic information using a prediction model that predicts the probability of test interruption generated by machine learning using past test interruption cases as training data, and an output unit that outputs the interruption probability. Therefore, the test support device 1 has the effect of being able to predict test interruptions due to the patient's emotions, such as anxiety, during the test.

[0016] (Testing support method flow) The flow of the inspection support method S1 will be described with reference to Fig. 2. Fig. 2 is a flow diagram showing the flow of the inspection support method S1. As shown in Fig. 2, the inspection support method S1 includes an acquisition process S11, an interruption prediction process S12, and an output process S13.

[0017] In an acquisition process S11, at least one processor acquires utterance information indicating what the patient said while the test was being conducted on the patient, status information regarding the patient's emotions while the test was being conducted, and basic information about the test. In an interruption prediction process S12, the at least one processor predicts the interruption probability of the test for the patient from the utterance information, the status information, and the basic information using a prediction model that predicts the interruption probability of the test, the prediction model being generated by machine learning using past test interruption cases as training data. In an output process S13, the at least one processor outputs the interruption probability.

[0018] (Effects of inspection support methods) As described above, the examination support method S1 includes an acquisition process S11 in which at least one processor acquires utterance information indicating what the patient said during the examination, status information regarding the patient's emotions during the examination, and basic information about the examination, an interruption prediction process S12 in which the at least one processor predicts the probability of the examination being interrupted for the patient from the utterance information, the status information, and the basic information using a prediction model that predicts the probability of the examination being interrupted, the prediction model being generated by machine learning using past examples of examination interruptions as training data, and an output process S13 in which the at least one processor outputs the interruption probability. Therefore, the examination support method S1 has the effect of being able to predict the interruption of the examination due to emotions such as anxiety of the patient during the examination.

[0019] Second Exemplary Embodiment A second exemplary embodiment, which is one example of an embodiment of the present invention, will be described in detail with reference to the drawings. Components having the same functions as those described in the above exemplary embodiment will be assigned the same reference numerals, and their description will be omitted as appropriate. The scope of application of each technology employed in this exemplary embodiment is not limited to this exemplary embodiment. That is, each technology employed in this exemplary embodiment can also be employed in other exemplary embodiments included in the present disclosure, to the extent that no particular technical hindrance occurs. Furthermore, each technology shown in each drawing referenced to explain this exemplary embodiment can also be employed in other exemplary embodiments included in the present disclosure, to the extent that no particular technical hindrance occurs.

[0020] (Configuration of information processing device) The configuration of the information processing device 1A will be described with reference to Fig. 3. Fig. 3 is a block diagram showing the configuration of the information processing device 1A. The information processing device 1A includes a control unit 10A, a storage unit 20A, a communication unit 30A, an input unit 40A, and an output unit 50A.

[0021] (Communications Department) The communication unit 30A communicates with devices external to the information processing device 1A via a communication line. While the specific configuration of the communication line does not limit the present exemplary embodiment, examples of the communication line include a wireless LAN (Local Area Network), a wired LAN, a WAN (Wide Area Network), a public line network, a mobile data communication network, or a combination thereof. The communication unit 30A transmits data supplied from the control unit 10A to other devices, and supplies data received from other devices to the control unit 10A.

[0022] (Input section) The input unit 40A is configured to receive input to the information processing device 1A, and includes, for example, input devices such as a keyboard, a mouse, a touch panel, a camera, a microphone, etc. The input unit 40A may also be configured to receive data from the input devices via an interface such as a USB (Universal Serial Bus).

[0023] (output section) The output unit 50A is a component for performing output from the information processing device 1A, and includes, for example, output devices such as a display, a printer, a touch panel, a speaker, etc. The output unit 50A may also be configured to include, for example, an interface such as a USB, and to output data to the output device via the interface.

[0024] (Storage part) The storage unit 20A stores various types of information referenced by the control unit 10A. Examples of such information include medical information 201, utterance information 202, status information 203, basic information 204, interruption probability 205, and sentences 206.

[0025] (Medical Information) The medical information 201 is information relating to the patient's medical care. An example of the medical information 201 is chart information. The medical information 201 includes, for example, at least one of the patient's personal information, the patient's examination findings, and the patient's medical history information. The patient's personal information is the patient's personal information, and includes, for example, information indicating the patient's age, gender, smoking amount, etc. The patient's examination findings information is information indicating findings by a medical professional such as a doctor, and includes, for example, information obtained by the medical professional through a medical interview or visual examination. The information obtained through a medical interview or visual examination may be, for example, a sentence such as "there is pain when pressing the abdomen." The patient's medical history information is information relating to the patient's medical history, and includes, for example, information indicating the patient's medical history, the family's medical history, the patient's smoking amount, etc.

[0026] The medical information 201 may also include diagnostic images of patients. Examples of diagnostic images include at least one of X-ray images, endoscopic images, pathological images, MRI images, and CT images. The storage unit 20A stores medical information 201 for each of a plurality of patients.

[0027] (Statement information) The utterance information 202 is information representing the content of utterances made by the patient during the examination. The utterance information 202 may be, for example, audio data of the patient's utterances during the examination. In this case, the patient's utterances include, for example, complaints and questions made by the patient. The utterance information 202 may be data in text format, or may be audio data. The utterance information 202 is, for example, text representing the patient's utterances, such as "Are you okay? I'm scared. I feel pain."

[0028] (Status information) The state information 203 is information relating to the patient's emotions. As an example, the state information 203 includes information indicating at least one of the patient's facial expression, speech pattern, vital signs, and emotion analysis results during the examination. As an example, the emotion analysis is performed by the emotion analysis unit 14A, which will be described later. In other words, the state information 203 may include information indicating the analysis results of the patient's emotions performed by the emotion analysis unit 14A, which will be described later. As an example, the information indicating the emotion analysis results indicates states such as "tension" and "anxiety."

[0029] (Basic information) The basic information 204 is information related to the examination. For example, the basic information 204 includes information indicating the type of examination (lower endoscopy, etc.) and the phase of the examination (insertion of the scope). The basic information 204 may also include information indicating whether the patient has previously undergone the examination (for example, "first time," "second time," "third time," etc.).

[0030] (probability of interruption) The interruption probability 205 is the probability that the test will be interrupted (for example, 40%). The interruption probability 205 is a probability predicted by the interruption prediction unit 12A, which will be described later.

[0031] (text) Sentence 206 is a sentence that expresses to the patient at least one of the reasons for suspending the examination and advice on how to deal with the situation. An example of sentence 206 is a sentence that reads, "Since this is the patient's first examination, the patient is very anxious. In similar cases in the past, there have been cases where the patient's anxiety and tension caused the abdomen to stiffen, resulting in pain when the scope was inserted. There is a high possibility that the anxiety will be alleviated with additional explanation."

[0032] (Control unit) 4 is a diagram showing the functional configuration of the control unit 10A. The control unit 10A includes an acquisition unit 11A, an interruption prediction unit 12A, an output control unit 13A, and a sentiment analysis unit 14A. The acquisition unit 11A is an example of an acquisition means according to the present disclosure. The interruption prediction unit 12A is an example of an acquisition means, an interruption prediction means, and a sentence generation means according to the present disclosure. The output control unit 13A is an example of an output means according to the present disclosure. The sentiment analysis unit 14A is an example of a sentiment analysis means according to the present disclosure.

[0033] (Acquisition Department) The acquiring unit 11A acquires utterance information 202 representing the content of a patient's utterance while an examination is being conducted on the patient, and basic information 204 about the examination, and supplies the acquired utterance information 202 and basic information 204 to the interruption prediction unit 12A. As an example, the acquiring unit 11A may acquire the utterance information 202 and the basic information 204 by reading the utterance information 202 and the basic information 204 from a storage destination (which may be a storage device within the information processing device 1A or a storage device external to the information processing device 1A) designated by the user of the information processing device 1A. Alternatively, the acquiring unit 11A may acquire the utterance information 202 and the basic information 204 by receiving the utterance information 202 and the basic information 204 from another device via the communication unit 30A. Alternatively, the acquiring unit 11A may acquire the utterance information 202 and the basic information 204 input to the input unit 40A.

[0034] As an example, the acquisition unit 11A acquires voice data representing utterances of a patient collected during the examination, and converts the voice data into text-format utterance information 202. In this case, the acquisition unit 11A may perform speaker recognition from the voice data and generate utterance information 202 representing the content of the utterances of the patient by transcribing the utterances of each speaker.

[0035] Furthermore, the acquiring unit 11A may acquire the medical information 201 in addition to the utterance information 202 and the basic information 204. As an example, the acquiring unit 11A may acquire the medical information 201 by reading the medical information 201 from a storage location (which may be a storage device within the information processing device 1A or a storage device outside the information processing device 1A) designated by the user of the information processing device 1A. Furthermore, the acquiring unit 11A may acquire the medical information 201 by receiving the medical information 201 from another device via the communication unit 30A. Furthermore, the acquiring unit 11A may acquire the medical information 201 input to the input unit 40A.

[0036] (Sentiment Analysis Department) The emotion analysis unit 14A analyzes the emotions of the patient during the examination and generates an analysis result. For example, the emotion analysis unit 14A may analyze the emotions of the patient by analyzing at least one of the patient's voice data collected during the examination and image data captured during the examination. Here, the image data may be data representing a still image or data representing a moving image. The emotion analysis method may be, for example, a method using a pre-prepared dictionary or a method using a trained model generated by machine learning. When a trained model is used, the input of the trained model may include, for example, at least one of text, voice data, and image data. Furthermore, the output of the trained model includes information indicating the emotion classification result.

[0037] The emotion analysis unit 14A supplies the analysis result to the interruption prediction unit 12A. The emotion analysis unit 14A may also output the analysis result by writing it to a storage destination (which may be a storage device within the information processing device 1A or a storage device external to the information processing device 1A) specified by the user of the information processing device 1A. The emotion analysis unit 14A may also transmit the analysis result to another device via the communication unit 30A, or may output the analysis result to an output device such as a display.

[0038] (Interruption prediction section) The interruption prediction unit 12A acquires the state information 203. As an example, the interruption prediction unit 12A may acquire the state information 203 by reading the state information 203 from a storage location specified by the user of the information processing device 1A (which may be a storage device within the information processing device 1A or a storage device external to the information processing device 1A). Alternatively, the interruption prediction unit 12A may acquire the state information 203 by receiving the state information 203 from another device via the communication unit 30A. Alternatively, the interruption prediction unit 12A may acquire the state information 203 input to the input unit 40A.

[0039] As an example, the status information 203 includes an analysis result supplied from the emotion analysis unit 14A. The status information 203 may also include information input by a medical professional examining the patient using the input unit 40A, or information transmitted to the information processing device 1A from a communication device operated by the medical professional. In this case, the medical professional examining the patient observes the facial expression of the patient during the examination, and if the medical professional thinks that the patient is feeling nervous or anxious or does not understand the explanation, the medical professional inputs information indicating that fact.

[0040] The condition information 203 may also include information input by the patient using the input unit 40A or information transmitted from a communication device operated by the patient to the information processing device 1A. In this case, if the patient is unable to understand the explanation given by the medical staff or feels nervous or anxious about the treatment, the patient inputs information indicating that fact.

[0041] The interruption prediction unit 12A predicts an interruption probability 205 of an examination for a patient from utterance information 202, status information 203, and basic information 204 using a prediction model M1 that predicts the interruption probability of an examination. Here, the prediction model M1 may be stored in the storage unit 20A of the information processing device 1A, or may be stored in a device other than the information processing device 1A. Note that, "the prediction model M1 is stored in the storage unit 20A" means that parameters that define the prediction model M1 are stored in the storage unit 20A.

[0042] The prediction model M1 is a model generated by machine learning using past test interruption cases as training data. The training data includes, for example, multiple sets of patient statement information, condition information, and basic test information from past tests, along with a label indicating whether the test was interrupted.

[0043] The input information input by the interruption prediction unit 12A to the prediction model M1 includes, for example, at least one of patient utterance information 202 during the examination, condition information 203, and basic information 204 of the examination. The input information input by the interruption prediction unit 12A to the prediction model M1 may also include medical information 201. The output of the prediction model M1 includes an interruption probability 205.

[0044] Furthermore, the interruption prediction unit 12A uses a language model M2 generated by machine learning to generate a sentence 206 that expresses to the patient at least one of the reason for interrupting the examination and advice on how to deal with the interruption, from the basic information 204, the utterance information 202, and the status information 203. The language model M2 is, for example, a large-scale language model configured by an artificial neural network having a large number of parameters. The language model M2 may be stored in the storage unit 20A of the information processing device 1A, or may be stored in a device other than the information processing device 1A. Note that, "the language model M2 is stored in the storage unit 20A" means that parameters defining the language model M2 are stored in the storage unit 20A.

[0045] Examples of language model M2 include, but are not limited to, generative AI such as ChatGPT (Chat Generative Pre-trained Transformer) and GPT-4 (Generative Pre-trained Transformer 4), or generative AI fine-tuned using medical data.

[0046] The input information input by the interruption prediction unit 12A to the language model M2 includes at least one of utterance information 202, status information 203, and basic information 204. The input information may also include medical information 201. The input information may also include information instructing the generation of a sentence 206. For example, the information may be text such as "Please tell me the reason for interrupting the examination and advice on how to deal with it." The output information output from the language model M2 includes the sentence 206.

[0047] When the language model M2 is stored in a device other than the information processing device 1A, the interruption prediction unit 12A, for example, inputs the input information to the language model M2 by transmitting the input information to the device that stores the language model M2 via the communication unit 30A. In this case, the interruption prediction unit 12A receives information output by the language model M2 from the device via the communication unit 30A.

[0048] Furthermore, the interruption prediction unit 12A may determine whether the patient is feeling anxious by referring to the state information 203. In this case, the interruption prediction unit 12A may determine whether the patient is feeling anxious by referring to the state information 203, and may predict the interruption probability and generate the sentence 206 when it is determined that the patient is feeling anxious.

[0049] (Output control section) The output control unit 13A outputs output information 207 including an interruption probability 205 predicted by the interruption prediction unit 12A and a sentence 206. As an example, the output control unit 13A may output the interruption probability 205 and the sentence 206 by writing them to a storage destination (which may be a storage device within the information processing device 1A or a storage device external to the information processing device 1A) designated by the user of the information processing device 1A. Furthermore, the output control unit 13A may transmit the interruption probability 205 and the sentence 206 via the communication unit 30A, or may output the interruption probability 205 and the sentence 206 to an output device such as a display.

[0050] 5 is a diagram showing a specific example of an interruption probability 205 and a sentence 206 output by the output control unit 13A. As an example, as shown in FIG. 5, the output control unit 13A may cause a display device to display output information 207 including the interruption probability 205 and the sentence 206. In this case, the screen displayed on the display device includes the interruption probability 205 and the sentence 206. The screen also includes basic information 204, status information 203, and utterance information 202, which are input to the information processing device 1A. As shown in FIG. 5, the output control unit 13A may output at least one of the basic information 204, status information 203, and utterance information 202, together with the interruption probability 205 and the sentence 206.

[0051] In the example of FIG. 5, the output information 207 includes basic information 204 that the "examination content" is "first lower endoscopy. Inserting a scope." The output information 207 also includes state information 203 that the "facial expression and attitude" is "tense / anxious." The output information 207 also includes statement information 202 that the "complaint / question" is "Are you okay? I'm scared. I'm in pain."

[0052] 5, the output information 207 includes a stop probability 205 in which the "stop / continue decision" is "probability of stopping: 40%." The output information 207 also includes a sentence 206 as the "basis" that reads, "The patient is very anxious because it is the first examination. In similar cases in the past, there have been cases where the patient's anxiety and tension caused the abdomen to stiffen, resulting in pain when the scope was inserted. There is a high possibility that the anxiety will be alleviated with additional explanation."

[0053] At least one of the interruption probability 205 and the sentence 206 is used, for example, in the decision-making of a medical professional who will be performing an examination on a patient. For example, by checking the output interruption probability 205, the medical professional may decide to temporarily interrupt the examination and provide additional explanations by referring to the sentence 206 in order to alleviate the patient's anxiety.

[0054] (Testing support method flow) 6 is a flow diagram showing an example of the flow of an examination support method S1A executed by the information processing device 1A. The steps included in the flow diagram of FIG. 6 may be executed in parallel or in a different order. In step S101, the emotion analysis unit 14A analyzes the facial expression and speech content of the patient during the examination, and generates the analysis result as status information 203.

[0055] In step S102, the emotion analysis unit 14A outputs the analysis result, ie, state information 203, to an output device. As an example, the emotion analysis unit 14A may output the state information 203 to a display and cause the state information 203 to be displayed on the display.

[0056] A medical professional examining a patient checks the status information 203 displayed on the display and determines whether to predict the interruption probability 205. When predicting the interruption probability 205, the medical professional operates an operator or the like connected to the input unit 40A to input an instruction to predict the interruption probability 205 to the information processing device 1A. For example, if the output status information 203 includes at least one of information representing "tension" and information representing "anxiety," the medical professional determines to predict the interruption probability 205. On the other hand, if it is determined that there is no need to predict the interruption probability 205, the medical professional does not input a prediction instruction. For example, if the output status information 203 does not include at least one of information representing "tension" and information representing "anxiety," the medical professional determines not to predict the interruption probability 205.

[0057] In step S103, the interruption prediction unit 12A determines whether to predict the interruption probability 205. As an example, the interruption prediction unit 12A makes this determination based on whether a prediction instruction has been input by a user such as a medical professional. If it is determined that the interruption probability 205 is to be predicted, the interruption prediction unit 12A proceeds to the processing of step S104. On the other hand, if it is determined that the interruption probability 205 is not to be predicted, the interruption prediction unit 12A skips the processing of steps S104 to S109 and returns to the processing of step S101.

[0058] The determination method by the interruption prediction unit 12A in step S103 is not limited to the method described above, and the interruption prediction unit 12A may determine whether to predict the interruption probability 205 using another method. As an example, the interruption prediction unit 12A may determine whether to predict the interruption probability 205 by referring to the state information 203 generated by the emotion analysis unit 14A. In this case, as an example, the interruption prediction unit 12A may determine to predict the interruption probability 205 when the state information 203 includes at least one of information representing "tension" and information representing "anxiety." Furthermore, as an example, the interruption prediction unit 12A may determine not to predict the interruption probability 205 when the state information 203 does not include at least one of information representing "tension" and information representing "anxiety."

[0059] In step S104, the acquisition unit 11A acquires basic information 204 from the storage unit 20A. In step S105, the acquisition unit 11A acquires voice data collected during the examination. The voice data represents what the patient said during the examination. In step S106, the acquisition unit 11A performs speaker recognition processing on the voice data and transcribes the speech for each speaker, thereby generating utterance information 202 representing what the patient said. The acquisition unit 11A supplies the basic information 204 and the generated utterance information 202 to the interruption prediction unit 12A.

[0060] In step S107, the interruption prediction unit 12A inputs the basic information 204, the utterance information 202, and the state information 203 into the prediction model M1 to predict the interruption probability 205. Furthermore, in step S108, the interruption prediction unit 12A inputs the basic information 204, the utterance information 202, and the state information 203 into the language model M2 to generate a sentence 206. In step S109, the output control unit 13A outputs the interruption probability 205 and the sentence 206. Upon completing the processing of step S109, the control unit 10A returns to the processing of step S101.

[0061] (Effects of information processing devices) As described above, the information processing device 1A includes an interruption prediction unit 12A that uses a language model M2 generated by machine learning to generate sentence 206, which indicates to the patient at least one of the reason for interrupting the examination and advice on how to deal with the situation, from basic information 204, utterance information 202, and status information 203. The output control unit 13A is configured to output sentence 206 in addition to interruption probability 205. For example, a medical professional can refer to output sentence 206 and interrupt the examination to provide additional explanations to the patient, thereby reducing the patient's anxiety or tension during the examination. This can prevent, for example, an endoscopic examination in which the patient's anxiety or tension causes abdominal stiffness, resulting in pain during the insertion of the scope. In this way, the information processing device 1A achieves the effect of allowing the examination to proceed more smoothly than if the examination were to proceed without providing additional explanations.

[0062] The information processing device 1A also includes a sentiment analysis unit 14A that analyzes the emotions of the patient during the examination, and the interruption prediction unit 12A is configured to acquire status information 203 including the analysis results of the sentiment analysis unit 14A. Therefore, the information processing device 1A can perform interruption prediction that reflects the results of the emotion analysis of the patient during the examination, and by allowing a medical professional or the like to check the output interruption probability 205, they can take action such as temporarily interrupting the examination and providing additional explanations to the patient. This has the effect of, for example, allowing the examination to proceed more smoothly.

[0063] Furthermore, the information processing device 1A employs a configuration in which the acquisition unit 11A acquires voice data representing voices picked up during an examination on a patient and converts the voice data into text-format utterance information 202. Therefore, the information processing device 1A has the effect of being able to perform interruption prediction that reflects the content of the patient's utterances during the examination.

[0064] Furthermore, the information processing device 1A employs a configuration in which the interruption prediction unit 12A determines whether the patient is feeling anxious by referring to the state information 203, and if it is determined that the patient is feeling anxious, predicts the interruption probability 205. Therefore, the information processing device 1A can prevent unnecessary interruption prediction.

[0065] Furthermore, the information processing device 1A employs a configuration in which the status information 203 includes information indicating at least one of the patient's facial expression, speech style, vital signs, and emotion analysis results during the examination. Therefore, the information processing device 1A can perform interruption prediction that reflects information indicating at least one of the patient's facial expression, speech style, vital signs, and emotion analysis results during the examination.

[0066] Furthermore, the information processing device 1A employs a configuration in which the interruption probability 205 is used in the decision-making of medical personnel who perform examinations on patients. Therefore, the information processing device 1A has the effect of enabling medical personnel who perform examinations to make more appropriate decisions.

[0067] [Software implementation example] Some or all of the functions of the examination support device 1 and the information processing device 1A (hereinafter also referred to as "each of the above devices") may be realized by hardware such as an integrated circuit (IC chip), or by software.

[0068] In the latter case, each of the above devices is realized by, for example, a computer that executes instructions of a program, which is software that realizes each function. An example of such a computer (hereinafter referred to as computer C) is shown in Figure 7. Figure 7 is a block diagram showing the hardware configuration of computer C that functions as each of the above devices.

[0069] The computer C includes at least one processor C1 and at least one memory C2. The memory C2 stores a program P for causing the computer C to operate as each of the above-mentioned devices. In the computer C, the processor C1 reads and executes the program P from the memory C2, thereby realizing the functions of each of the above-mentioned devices.

[0070] The processor C1 may be, for example, a central processing unit (CPU), a graphic processing unit (GPU), a digital signal processor (DSP), a micro processing unit (MPU), a floating point number processing unit (FPU), a physics processing unit (PPU), a tensor processing unit (TPU), a quantum processor, a microcontroller, or a combination thereof. The memory C2 may be, for example, a flash memory, a hard disk drive (HDD), a solid state drive (SSD), or a combination thereof.

[0071] The computer C may further include a RAM (Random Access Memory) for expanding the program P during execution and for temporarily storing various data. The computer C may also include a communication interface for transmitting and receiving data to and from other devices. The computer C may also include an input / output interface for connecting input / output devices such as a keyboard, mouse, display, and printer.

[0072] Furthermore, the program P can be recorded on a non-transitory tangible recording medium M that can be read by the computer C. Such a recording medium M can be, for example, a tape, a disk, a card, a semiconductor memory, or a programmable logic circuit. The computer C can acquire the program P via such a recording medium M. The program P can also be transmitted via a transmission medium. Such a transmission medium can be, for example, a communication network or broadcast waves. The computer C can also acquire the program P via such a transmission medium.

[0073] Furthermore, the functions of each of the devices may be realized by a single processor provided in a single computer, by multiple processors provided in a single computer working in cooperation, or by multiple processors provided in each of multiple computers working in cooperation. Furthermore, the programs for causing each of the devices to realize the functions may be stored in a single memory provided in a single computer, or may be distributed and stored in multiple memories provided in a single computer, or may be distributed and stored in multiple memories provided in each of multiple computers.

[0074] [Appendix 1] This disclosure includes the techniques described in the following appendices. However, the present invention is not limited to the techniques described in the following appendices, and various modifications are possible within the scope of the claims.

[0075] [Appendix A] This disclosure includes the techniques described in the following appendices. However, the present invention is not limited to the techniques described in the following appendices, and various modifications are possible within the scope of the claims.

[0076] (Appendix A1) an acquisition means for acquiring utterance information representing the content of utterances made by a patient during an examination, state information relating to the patient's emotions during the examination, and basic information about the examination; an interruption prediction means for predicting the interruption probability of the test for the patient from the utterance information, the condition information, and the basic information using a prediction model for predicting the interruption probability of the test, the prediction model being generated by machine learning using past interruption examples of the test as training data; an output means for outputting the interruption probability; An inspection support device comprising:

[0077] (Appendix A2) a sentence generation means for generating a sentence expressing at least one of a reason for interrupting the examination and advice on how to deal with the interruption from the basic information, the utterance information, and the condition information by using a language model generated by machine learning, the output means outputs the sentence in addition to the interruption probability. 1. An inspection support device as described in Appendix A1.

[0078] (Appendix A3) Further comprising emotion analysis means for performing emotion analysis of the patient in the examination, the acquiring means acquires the state information including an analysis result of the emotion analyzing means. 1. An inspection support device according to claim A1 or A2.

[0079] (Appendix A4) the acquiring means acquires voice data representing voices collected during the examination of the patient, and converts the voice data into the utterance information in text format. 10. The inspection support device according to claim 1, wherein the inspection support device is a

[0080] (Appendix A5) the interruption prediction means determines whether the patient is feeling anxious by referring to the state information, and predicts the interruption probability when it is determined that the patient is feeling anxious. 10. The inspection support device according to claim 1, wherein the inspection support device is a

[0081] (Appendix A6) The status information includes information indicating at least one of facial expression, speech pattern, vital signs, and emotion analysis results of the patient during the examination. 10. The inspection support device according to claim 1, wherein the inspection support device is a

[0082] (Appendix A7) The discontinuation probability is used to aid in the decision-making of a medical professional to perform a test on the patient. 10. The inspection support device according to claim 1, wherein the inspection support device is a

[0083] [Appendix B] This disclosure includes the techniques described in the following appendices. However, the present invention is not limited to the techniques described in the following appendices, and various modifications are possible within the scope of the claims.

[0084] (Appendix B1) an acquisition process in which at least one processor acquires utterance information representing the content of utterances made by a patient during an examination on the patient, state information relating to the patient's emotions during the examination, and basic information about the examination; an interruption prediction process in which the at least one processor predicts the interruption probability of the test for the patient from the utterance information, the condition information, and the basic information using a prediction model for predicting the interruption probability of the test, the prediction model being generated by machine learning using past interruption cases of the test as training data; an output process in which the at least one processor outputs the interruption probability; An inspection support method including:

[0085] (Appendix B2) The method further includes a sentence generation process in which the at least one processor generates a sentence expressing at least one of a reason for interrupting the examination and advice on how to deal with the interruption from the basic information, the utterance information, and the condition information using a language model generated by machine learning, In the output process, the at least one processor outputs the sentence in addition to the interruption probability. A method for assisting examinations as described in Appendix B1.

[0086] (Appendix B3) the at least one processor further includes a sentiment analysis process for performing a sentiment analysis of the patient in the test; In the acquisition process, the at least one processor acquires the state information including an analysis result of the emotion analysis process. An examination assistance method according to Appendix B1 or B2.

[0087] (Appendix B4) In the acquisition process, the at least one processor acquires voice data representing voices collected during the administration of the examination on the patient, and converts the voice data into the utterance information in text format. 10. An examination assistance method according to any one of appendices B1 to B3.

[0088] (Appendix B5) In the interruption prediction process, the at least one processor determines whether the patient is feeling anxious by referring to the state information, and predicts the interruption probability when it is determined that the patient is feeling anxious. 10. An examination assistance method according to any one of appendices B1 to B4.

[0089] (Appendix B6) The status information includes information indicating at least one of facial expression, speech pattern, vital signs, and emotion analysis results of the patient during the examination. 10. An examination assistance method according to any one of appendices B1 to B5.

[0090] (Appendix B7) The discontinuation probability is used to aid in the decision-making of a medical professional to perform a test on the patient. 10. An examination assistance method according to any one of appendices B1 to B6.

[0091] [Appendix C] This disclosure includes the techniques described in the following appendices. However, the present invention is not limited to the techniques described in the following appendices, and various modifications are possible within the scope of the claims.

[0092] (Appendix C1) A program for causing a computer to function as an inspection support device, The computer an acquisition means for acquiring utterance information representing the content of utterances made by a patient during an examination, state information relating to the patient's emotions during the examination, and basic information about the examination; an interruption prediction means for predicting the interruption probability of the test for the patient from the utterance information, the condition information, and the basic information using a prediction model for predicting the interruption probability of the test, the prediction model being generated by machine learning using past interruption examples of the test as training data; an output means for outputting the interruption probability; An inspection support program to function as a

[0093] (Appendix C2) The computer further functioning as a sentence generation means for generating a sentence expressing at least one of the reason for interrupting the examination and advice on how to deal with the interruption from the basic information, the utterance information, and the condition information, using a language model generated by machine learning; the output means outputs the sentence in addition to the interruption probability. The inspection assistance program described in Appendix C1.

[0094] (Appendix C3) The computer further functioning as emotion analysis means for analyzing the emotion of the patient in the examination; the acquiring means acquires the state information including an analysis result of the emotion analyzing means. An inspection support program according to appendix C1 or C2.

[0095] (Appendix C4) the acquiring means acquires voice data representing voices collected during the examination of the patient, and converts the voice data into the utterance information in text format. 1. The inspection assistance program according to any one of appendices C1 to C3.

[0096] (Appendix C5) the interruption prediction means determines whether the patient is feeling anxious by referring to the state information, and predicts the interruption probability when it is determined that the patient is feeling anxious. 1. The inspection assistance program according to any one of appendices C1 to C4.

[0097] (Appendix C6) The status information includes information indicating at least one of facial expression, speech pattern, vital signs, and emotion analysis results of the patient during the examination. 10. The inspection assistance program according to any one of appendices C1 to C5.

[0098] (Appendix C7) The discontinuation probability is used to aid in the decision-making of a medical professional to perform a test on the patient. 10. The inspection assistance program according to any one of appendices C1 to C6.

[0099] [Appendix D] This disclosure includes the techniques described in the following appendices. However, the present invention is not limited to the techniques described in the following appendices, and various modifications are possible within the scope of the claims.

[0100] (Appendix D1) at least one processor, an acquisition process for acquiring utterance information representing the content of a patient's utterances during an examination, state information regarding the patient's emotions during the examination, and basic information about the examination; an interruption prediction process for predicting the interruption probability of the test for the patient from the utterance information, the condition information, and the basic information using a prediction model for predicting the interruption probability of the test, the prediction model being generated by machine learning using past examples of interruptions of the test as training data; an output process for outputting the interruption probability; An inspection support device that performs the above.

[0101] The test support device may further include a memory, and the memory may store a program for causing the at least one processor to execute each of the processes.

[0102] (Appendix D2) the at least one processor: further executing a sentence generation process for generating a sentence expressing at least one of a reason for interrupting the examination and advice on how to deal with the interruption from the basic information, the utterance information, and the condition information, using a language model generated by machine learning; In the output process, the at least one processor outputs the sentence in addition to the interruption probability. 10. The inspection support device according to claim D1.

[0103] (Appendix D3) the at least one processor: further performing a sentiment analysis process for analyzing the sentiment of the patient in the test; In the acquisition process, the at least one processor acquires the state information including an analysis result of the emotion analysis process. The inspection support device according to appendix D1 or D2.

[0104] (Appendix D4) In the acquisition process, the at least one processor acquires voice data representing voices collected during the administration of the examination on the patient, and converts the voice data into the utterance information in text format. An inspection support device according to any one of appendices D1 to D3.

[0105] (Appendix D5) In the interruption prediction process, the at least one processor determines whether the patient is feeling anxious by referring to the state information, and predicts the interruption probability when it is determined that the patient is feeling anxious. An inspection support device according to any one of appendices D1 to D4.

[0106] (Appendix D6) The status information includes information indicating at least one of facial expression, speech pattern, vital signs, and emotion analysis results of the patient during the examination. An inspection support device according to any one of appendices D1 to D5.

[0107] (Appendix D7) The discontinuation probability is used to aid in the decision-making of a medical professional to perform a test on the patient. An inspection support device according to any one of appendices D1 to D6.

[0108] [Appendix E] This disclosure includes the techniques described in the following appendices. However, the present invention is not limited to the techniques described in the following appendices, and various modifications are possible within the scope of the claims.

[0109] (Appendix E1) A program for causing a computer to function as an inspection support device, The computer, an acquisition process for acquiring utterance information representing the content of a patient's utterances during an examination, state information regarding the patient's emotions during the examination, and basic information about the examination; an interruption prediction process for predicting the interruption probability of the test for the patient from the utterance information, the condition information, and the basic information using a prediction model for predicting the interruption probability of the test, the prediction model being generated by machine learning using past examples of interruptions of the test as training data; an output process for outputting the interruption probability; A non-transitory recording medium on which an inspection support program for executing the above is recorded. [Explanation of symbols]

[0110] 1. Inspection support equipment 1A Information processing equipment 11, 11A Acquisition Department 12, 12A Interruption Prediction Section 13, 50A output section 13A Output control section 14A Sentiment Analysis Department

Claims

1. an acquisition means for acquiring utterance information representing the content of utterances made by a patient during an examination, state information relating to the patient's emotions during the examination, and basic information about the examination; an interruption prediction means for predicting the interruption probability of the test for the patient from the utterance information, the condition information, and the basic information using a prediction model for predicting the interruption probability of the test, the prediction model being generated by machine learning using past interruption examples of the test as training data; an output means for outputting the interruption probability; An inspection support device comprising:

2. a sentence generation means for generating a sentence expressing at least one of a reason for interrupting the examination and advice on how to deal with the interruption from the basic information, the utterance information, and the condition information by using a language model generated by machine learning, the output means outputs the sentence in addition to the interruption probability. The inspection support device according to claim 1 .

3. Further comprising emotion analysis means for performing emotion analysis of the patient in the examination, the acquiring means acquires the state information including an analysis result of the emotion analyzing means. The inspection support device according to claim 1 or 2.

4. the acquiring means acquires voice data representing voices collected during the examination of the patient, and converts the voice data into the utterance information in text format. The inspection support device according to claim 1 or 2.

5. the interruption prediction means determines whether the patient is feeling anxious by referring to the state information, and predicts the interruption probability when it is determined that the patient is feeling anxious. The inspection support device according to claim 1 or 2.

6. The status information includes information indicating at least one of facial expression, speech pattern, vital signs, and emotion analysis results of the patient during the examination. The inspection support device according to claim 1 or 2.

7. The discontinuation probability is used to aid in the decision-making of a medical professional to perform a test on the patient. The inspection support device according to claim 1 or 2.

8. an acquisition process in which at least one processor acquires utterance information indicating the content of utterances made by the patient during the administration of the test, state information relating to the patient's emotions during the administration of the test, and basic information about the test; an interruption prediction process in which the at least one processor predicts the interruption probability of the test for the patient from the utterance information, the status information, and the basic information using a prediction model for predicting the interruption probability of the test, the prediction model being generated by machine learning using past interruption cases of the test as training data; an output process in which the at least one processor outputs the interruption probability; An inspection support method including:

9. An examination assistance program for causing a computer to function as an examination assistance device, the program comprising: an acquisition means for acquiring utterance information representing the content of utterances made by a patient during an examination, state information relating to the patient's emotions during the examination, and basic information about the examination; an interruption prediction means for predicting the interruption probability of the test for the patient from the utterance information, the condition information, and the basic information using a prediction model for predicting the interruption probability of the test, the prediction model being generated by machine learning using past interruption examples of the test as training data; an output means for outputting the interruption probability; An inspection support program to function as a

Images