Computer program, information processing device, information processing method, and learning model generation method

Abstract

The invention provides a computer program, an information processing device, an information processing method, and a learning model generation method capable of providing an appropriate coping method. A computer program causes a computer to execute a process for acquiring pain-related information relating to pain of a patient, inputting the acquired pain-related information to a learning model that outputs a result of evaluating pain when the pain-related information has been input, and acquiring the result of evaluating pain of the patient. On the basis of the acquired evaluation result of the pain, response information for response to the pain is generated, and the generated response information is output.

Description

Technical Field

[0001] The present invention relates to a computer program, an information processing device, an information processing method, and a learning model generating method. Background Art

[0002] Patent document 1 discloses the following diagnosis and treatment information management system, which has multiple treatment department servers that provide diagnosis and treatment information stored in the databases of multiple treatment departments within a medical institution, and a specific disease treatment unified server that obtains specific disease diagnosis and treatment information from the treatment department servers and provides unified specific disease diagnosis and treatment information from a unified database. By being able to refer to the diagnosis and treatment information of specific diseases such as cancer in all therapies that combine surgery, radiotherapy, chemotherapy and palliative care, and registered related information on a wide range of specific diseases, the progress of treatment can be grasped in a highly real-time manner.

[0003] Patent Document 1: Japanese Patent Application Publication No. 2010-3135

[0004] Pain caused by diseases such as cancer is directly related to the patient's quality of life (QOL). It is often difficult for patients to accurately convey their pain to doctors. In addition, since patients' symptoms vary, there is no general method to derive appropriate pain treatment, making it difficult for doctors to determine appropriate pain treatment. In addition, although pain treatment is performed during the doctor's examination, patients need to endure the pain even if the symptoms change during periods other than the examination. Summary of the invention

[0005] The present invention is completed in view of such a situation, and its purpose is to provide a computer program, an information processing device, an information processing method, and a learning model generation method that can provide an appropriate coping method. Specifically, in addition to the period of diagnosis and treatment, the appropriate coping method required at the time is provided at an appropriate time based on the information when the patient feels pain.

[0006] (1) The computer program of the present invention causes a computer to perform the following processing: obtaining pain-related information related to a patient's pain, inputting the obtained pain-related information into a learning model that outputs a pain evaluation result when pain-related information is input, so as to obtain an evaluation result of the patient's pain, generating coping information for coping with the pain based on the obtained pain evaluation result, and outputting the generated coping information.

[0007] Here, in the present invention, regarding the embodiment,

[0008] (2) In the computer program of (1) above, preferably, the pain-related information includes at least one of an evaluation index for evaluating pain, vital data, medication information, and physical condition.

[0009] (3) The computer program of (1) or (2) above preferably causes the computer to perform the following processing: obtaining medical information related to the diagnosis and treatment of the patient, and then inputting the obtained medical information into the learning model that outputs the evaluation result of pain when the medical information is input, so as to obtain the evaluation result of the pain of the patient.

[0010] (4) In any one of the computer programs (1) to (3) above, the medical information preferably includes at least one of diagnosis information, examination information, treatment information, prescription information, and disease prognosis prediction information.

[0011] (5) Any one of the computer programs (1) to (4) above preferably causes a computer to perform the following processing: obtaining literature information related to pain treatment, and then inputting the obtained literature information into the learning model that outputs a pain evaluation result when the literature information related to pain treatment is input, so as to obtain an evaluation result of the patient's pain.

[0012] (6) In any one of the computer programs (1) to (5) above, the pain evaluation result preferably includes the course of pain experienced by the patient from the past to the future.

[0013] (7) Any of the computer programs described in (1) to (6) above preferably causes a computer to execute the following processing: receiving a condition of the patient as a result of implementing the countermeasure information, and recommending a doctor's examination based on the received condition.

[0014] (8) Any one of the computer programs (1) to (7) above preferably causes the computer to perform the following processing: accepting the pain condition of the patient as a result of implementing pain treatment based on the response information, correcting the pain evaluation result based on the accepted pain condition, and re-learning the learning model using the corrected pain evaluation result.

[0015] (9) Any one of the computer programs (1) to (8) above preferably causes a computer to execute a process of receiving, from a doctor terminal device, an operation of correcting treatment information generated based on a result of evaluating the patient's pain.

[0016] (10) Any one of the computer programs (1) to (9) above preferably causes a computer to execute the following processing: outputting questions generated based on the evaluation results of the patient's pain to a patient terminal device, outputting questions generated based on the evaluation results of the patient's pain to a patient terminal device,.

[0017] (11) Any one of the computer programs (1) to (10) described above preferably causes a computer to execute the following processing: accepting a consultation from the patient and outputting response information to a patient terminal device based on the accepted consultation.

[0018] (12) Any one of the computer programs (1) to (11) described above preferably causes a computer to execute the following processing: receiving a prescription for medicine or contacting a doctor together with the countermeasure information.

[0019] (13) Preferably, the computer program according to any one of (1) to (12) above causes a computer to execute a process of controlling automatic administration of a drug in a drug infusion pump based on a result of the evaluation of the patient's pain.

[0020] (14) The information processing device of the present invention comprises: a first acquisition unit, which acquires pain-related information related to the patient's pain; a second acquisition unit, which inputs the acquired pain-related information into a learning model that outputs an evaluation result of pain when the pain-related information is input, so as to acquire an evaluation result of the patient's pain; a generation unit, which generates response information for responding to the pain based on the acquired pain evaluation result; and an output unit, which outputs the generated response information.

[0021] (15) The information processing method of the present invention obtains pain-related information related to the patient's pain, inputs the obtained pain-related information into a learning model that outputs a pain evaluation result when pain-related information is input, so as to obtain an evaluation result of the patient's pain, generates coping information for coping with the pain based on the obtained pain evaluation result, and outputs the generated coping information.

[0022] (16) A learning model generation method, comprising obtaining first training data, wherein the first training data includes pain-related information related to pain of multiple patients and pain evaluation results of the multiple patients, and generating a learning model based on the obtained first training data in a manner that outputs pain evaluation results when pain-related information is input.

[0023] (17) The learning model generation method of (16) above preferably obtains second training data, which also includes: medical information of multiple patients, literature information related to pain treatment, and pain evaluation results of the multiple patients. Based on the obtained second training data, the learning model is generated in a manner that outputs pain evaluation results when the medical information and literature information related to pain treatment are input.

[0024] According to the present invention, an appropriate countermeasure can be provided. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 It is a diagram showing an example of the configuration of the pain treatment support system according to the present embodiment.

[0026] Figure 2 This is a diagram showing an example of the structure of a pain treatment support device.

[0027] Figure 3 is a diagram showing information collection by means of a pain treatment assisting device.

[0028] Figure 4A This is a diagram showing an example of information in a database.

[0029] Figure 4B This is a diagram showing an example of information in a database.

[0030] Figure 4C This is a diagram showing an example of information in a database.

[0031] Figure 5 1 is a diagram showing a first example of processing for generating countermeasure information by a pain treatment support device.

[0032] Figure 6 1 is a diagram showing a second example of the processing of generating the countermeasure information by the pain treatment support device.

[0033] Figure 7 1 is a diagram showing a third example of the processing for generating countermeasure information by the pain treatment support device.

[0034] Figure 8 This is a diagram showing an example of a method for generating a learning model.

[0035] Fig. 9 This is a diagram showing a first example of response information.

[0036] Fig.10 It is a diagram showing a second example of the response information.

[0037] Fig.11 It is a diagram showing a third example of the response information.

[0038] Fig.12 It is a diagram showing a fourth example of the response information.

[0039] Fig.13 It is a diagram showing a fifth example of the response information.

[0040] Fig.14 It is a diagram showing a sixth example of the response information.

[0041] Fig.15 This is a diagram showing a seventh example of the response information.

[0042] Fig.16 It is a diagram showing an eighth example of the response information.

[0043] Fig.17 This is a diagram showing a ninth example of the response information.

[0044] Fig.18 This is a diagram showing a tenth example of the response information.

[0045] Fig.19 This is a diagram showing the eleventh example of the response information.

[0046] Fig. 20 This is a diagram showing a twelfth example of the response information.

[0047] Fig.21 This is a diagram showing the thirteenth example of the response information.

[0048] Fig. 22 This is a diagram showing an example of a response information correction screen.

[0049] Fig.23 This is a diagram showing an example of a processing sequence using a pain treatment support device.

[0050] Fig.24 This is a diagram showing an example of the generation order of the learning model. DETAILED DESCRIPTION

[0051] Hereinafter, embodiments of the present invention will be described. Figure 1 : is a diagram showing an example of the structure of the pain treatment assistance system of the present embodiment. The pain treatment assistance system as an information processing system includes a pain treatment assistance device 50 as an information processing device. The pain treatment assistance system may also include a patient terminal device 10, a device 20, an assistant terminal device 30, and a doctor terminal device 40. The patient terminal device 10, the assistant terminal device 30, and the doctor terminal device 40 are connected to the pain treatment assistance device 50 via a communication network 1. The device 20 may be configured to be connected to the patient terminal device 10 wirelessly or by wire, or may be configured to be connected to the pain treatment assistance device 50 via the communication network 1. In addition, the device 20 is not essential, and for example, it may be configured to be composed only of input from the patient terminal device 10.

[0052] The patient terminal device 10 is a terminal device carried or possessed by the patient, and the assistant terminal device 30 is a terminal device carried or possessed by assistants such as the patient's family members and caregivers. The patient terminal device 10 and the assistant terminal device 30 can be composed of a smartphone, a tablet computer, a personal computer, etc. having a display panel, an operation panel, a microphone, a speaker, etc. An application (application) for using the pain treatment assistance system is introduced into the patient terminal device 10 and the assistant terminal device 30. For example, it is assumed that the patient suffers from cancer and regularly goes to a medical institution while recuperating at home, but it is not limited to such patients. In addition, the application can be a web application or a download application.

[0053] Device 20 is a measuring device for measuring the patient's vital data, and can be a wearable terminal or a fixed device. Device 20 can measure vital data such as body temperature, heartbeat, brain wave, EDA (electrodermal activity: galvanic skin reflex). In addition, vital data is not limited to these, and any data that is considered to be related to the patient's pain caused by the disease can also be included. For example, vital data can also include blood pressure, pulse pressure, pulse, blood sugar level, weight, number of steps, activity level, etc.

[0054] The doctor terminal device 40 is a terminal device used by doctors in medical institutions, etc. The doctor terminal device 40 can be composed of a personal computer, a tablet computer, etc. with a display panel, an operation panel, etc. Medical practitioners such as health workers and nurses can also use the doctor terminal device 40 under the guidance of the doctor. An application (such as a Web application, etc.) for using the pain treatment support system is introduced into the doctor terminal device 40.

[0055] Figure 2 : is a diagram showing an example of the structure of the pain treatment auxiliary device 50. The pain treatment auxiliary device 50 includes a control unit 51 for controlling the entire device, a communication unit 52, a memory 53, a pain-related information DB 54, a diagnosis and treatment information DB 55, a response information DB 56, a document information DB 57, a response information generation unit (generation unit) 58, and a storage unit 59. The pain treatment auxiliary device 50 may also disperse the processing functions and be composed of a plurality of devices. Databases such as the pain-related information DB 54, the diagnosis and treatment information DB 55, the response information DB 56, and the document information DB 57 may be configured to be built into the pain treatment auxiliary device 50, or may be installed in an external data server. In addition, the storage unit 59 may also be installed in an external data server.

[0056] The storage unit 59 can be composed of, for example, a hard disk or a semiconductor memory, and stores a computer program 60 (program product), a learning model 61, and necessary information. The computer program 60 can be downloaded from an external device via the communication unit 52 and stored in the storage unit 59. In addition, the computer program 60 recorded in a recording medium (for example, an optically readable disk storage medium such as a CD-ROM) can be read by a recording medium reading unit and stored in the storage unit 59, or the computer program 60 can be read by a recording medium reading unit and expanded in the memory 53.

[0057] The control unit 51 is configured to be equipped with a required number of CPUs (Central Processing Units), MPUs (Micro-Processing Units), GPUs (Graphics Processing Units), etc. The control unit 51 is capable of executing the processing specified by the computer program 60. That is, the processing performed by the control unit 51 is also the processing performed by the computer program 60. The control unit 51 is capable of executing the functions of the response information generation unit 58 by executing the computer program 60. The response information generation unit 58 can be configured by hardware, can be configured to be implemented by software, or can be implemented by a combination of hardware and software. The control unit 51 is capable of performing processing using the learning model 61. In addition, the control unit 51 has the functions of a first acquisition unit, a second acquisition unit, a generation unit, and an output unit.

[0058] The communication unit 52 includes a communication module, and can exchange necessary information with the patient terminal device 10 and the doctor terminal device 40 via the communication network 1. The communication unit 52 can also exchange necessary information with the device 20.

[0059] The memory 53 can be formed of a semiconductor memory such as SRAM (Static Random Access Memory), DRAM (Dynamic Random Access Memory), or flash memory. The control unit 51 can expand the computer program 60 in the memory 53 and execute the computer program 60 .

[0060] Figure 3 5 is a diagram showing information collection by the pain treatment supporting device 50. The pain treatment supporting device 50 obtains pain-related information related to the patient's pain caused by the disease from the patient terminal device 10 and the device 20 via the communication unit 52. The pain-related information is appropriately repeatedly sent from the patient terminal device 10 and the device 20. For example, the pain-related information may be sent once during the period from the patient's last visit to the hospital to the next visit to the hospital, or may be sent multiple times depending on the length of the period. The pain-related information obtained is classified for each patient and at each acquisition time and stored in the pain-related information DB 54.

[0061] The pain treatment support device 50 also acquires medical information related to the patient's medical treatment from the doctor terminal device 40 via the communication unit 52. The acquired medical information is classified for each patient and for each medical treatment time and stored in the medical information DB 55.

[0062] Figure 4A , Figure 4B as well as Figure 4C This is a diagram showing an example of information in a database. Figure 4A An example of information in the pain-related information DB 54 is shown. Pain-related information can be classified into pain evaluation index (evaluation index for evaluating pain), vital data, medication information, and physical condition. The pain-related information sent from the patient terminal device 10 and the device 20 includes at least one of the pain evaluation index, vital data, medication information, and physical condition. In addition, the classification is an example and is not limited to Figure 4A Example.

[0063] The pain evaluation index includes the intensity of pain, the change of pain, the timing of pain, etc. The intensity of pain can be expressed in grades of 1 to 10 or 1 to 5, for example. The change of pain can be expressed, for example, by the pain gradually becoming stronger, the pain gradually becoming weaker, the stronger pain continuing, the weaker pain continuing, etc. The timing of pain indicates when the pain occurs, for example, it can be expressed by when getting up, during the day, at night, when sitting, when standing up, etc. The pain evaluation index can be sent from the patient terminal device 10 to the pain treatment auxiliary device 50 by the patient starting the application of the patient terminal device 10 and answering questions related to the intensity of pain, the change of pain, the timing of pain, etc.

[0064] The vital data include data that changes due to the response to pain, such as body temperature, heart rate, brain wave, EDA, pulse, etc. In addition, it may also include blood pressure, pulse pressure, blood sugar level, weight, number of steps, amount of activity, etc. The vital data can be acquired using the device 20.

[0065] The medication information includes the type of medication, the amount of medication, the medication period, the medication time (timing), whether medication is taken, etc. The medication information may include medications that have been taken in the past, not just medications that are currently being taken.

[0066] Physical conditions include activity level, sleep time, sleepiness, fatigue, delusions, constipation, voice, and expression, etc. It can include items that can evaluate whether there is a disorder due to pain, medicine, disease symptoms, etc.

[0067] The pain-related information includes at least one of a pain evaluation index (an evaluation index for evaluating pain), vital data, medication information, and physical condition.

[0068] By acquiring the pain-related information as described above from the patient terminal device 10 and the equipment 20 , the patient can accurately communicate the pain and symptoms he or she feels at a necessary timing and with a necessary frequency during the period from the previous examination to the next examination.

[0069] Figure 4B An example of information in the medical information DB 55 is shown. Medical information can be classified into diagnosis information, examination information, prescription information, treatment information, and disease prognosis prediction information. The medical information sent from the doctor terminal device 40 includes at least one of diagnosis information, examination information, prescription information, treatment information, and disease prognosis prediction information. In addition, the classification is an example and is not limited to Figure 4B Example.

[0070] Diagnostic information includes the results of observations during the medical examination, visual examination, palpation or percussion, electronic medical records, etc. Inspection information includes inspection result data of blood tests, urine tests, imaging tests, etc. Prescription information includes the type and amount of medicine prescribed by the doctor. In addition, it may also include the period of taking the medicine. Treatment information includes treatment methods and the period of treatment. In addition, pain treatment includes not only literal treatment but also prescriptions for medicines. Disease prognosis prediction information includes PPI (Palliative Prognostic Index). PPI is a representative indicator for predicting short-term life prognosis (weekly units), and uses a score that is the sum of the scores of PPS (Palliative Performance Scale), oral intake, edema, dyspnea at rest, and delusions. The larger the score, the shorter the predicted prognosis.

[0071] The diagnosis and treatment information includes at least one of diagnosis information, examination information, treatment information, prescription information and disease prognosis prediction information.

[0072] Figure 4C An example of information in the document information DB57 is shown. Document information can be classified into guidance and papers. Guidance is guidance related to pain treatment, for example, including guidelines indicating what kind of pain treatment is recommended for the patient's symptoms and pain. Papers are papers related to pain treatment, for example, including objective information indicating what kind of pain treatment is effective for the patient's symptoms and pain. Document information DB57 is updated appropriately to record the latest information.

[0073] Figure 5: is a diagram showing a first example of the generation process of the response information by means of the pain treatment auxiliary device 50. The control unit 51 reads the pain-related information of a specific patient from the pain-related information DB54, and inputs the pain-related information that has been read into the learning model 61. The pain-related information of a specific patient is time series data of one or more moments. For example, it may include not only the current pain-related information of the specific patient, but also the pain-related information of the past moments traced back from the present. The control unit 51 is capable of performing a vectorization operation on the patient's pain-related information to generate a pain-related information vector, and inputs the generated pain-related information vector into the learning model 61. In addition, a pain-related information vector may be generated for each of a plurality of moments. In addition, although not shown in the figure, the response information of the response information DB56 and the pain process pattern may also be input into the learning model 61.

[0074] The learning model 61 is generated (learned) to output the evaluation result of pain when pain-related information is input. The pain-related information is time series data, for example, pain-related information within a period of about one month, three months, six months or 12 months from the present. The evaluation result of pain includes the intensity (degree) of the patient's pain from the past to the future. The past period can be set to one month, three months, six months, 12 months, etc., for example. In addition, the period from the current moment to the future can also be set to one month, three months, six months, 12 months, etc. The length of the period can be predetermined or can be set to a desired period. For example, the learning model 61 can output the evaluation result of pain from the past three months to the future three months based on the pain-related information of the past three months, and can also output the evaluation result of pain from the past three months to the future three months based on the pain-related information of the past six months. In addition, the above period is an example and is not limited to these. The intensity (degree) of pain can be expressed in a quantitative level, such as 10 levels of 1 to 10 or 5 levels of 1 to 5. The larger the numerical value, the stronger the patient's pain.

[0075] The learning model 61 can use, for example, SVM (Support Vector Machine), decision tree, random forest, adaptive boosting, neural network (for example, RNN: Recurrent Neural Network, LSTM: Long Short Term Memory, Transformer, etc.), etc.

[0076] The control unit 51 reads out the treatment information (including, for example, prescription information and treatment information) and the pain progression pattern recorded in the treatment information DB 56. The control unit 51 inputs the read-out treatment information and pain progression pattern and the pain evaluation result obtained from the learning model 61 into the treatment information generating unit 58.

[0077] The response information generation unit 58 generates a pain progression pattern for the patient based on the input pain evaluation results, pain progression pattern, and response information. Specifically, based on the pain evaluation results at multiple moments, the pain evaluation results at moments between the multiple moments can be supplemented and a pain progression pattern can be generated. In addition, the response information generation unit 58 generates response information for the patient based on the input pain evaluation results and response information. The response information generation unit 58 stores the generated pain progression pattern and response information in the response information DB 56. The response information includes, for example, prescription information and treatment information. The doctor can predetermine the prescription information as needed. For example, the range of the amount of medicine to be administered can also be predetermined.

[0078] The pain progression pattern may be information indicating the temporal transition of the patient's pain level from the past to the future. The pain progression pattern can be displayed by an appropriate method such as a graphical display or a table display. Prescription information is information provided to the patient by the pain treatment support device 50 instead of a doctor, and is information related to the prescription of medicine selected according to the patient's pain condition. Treatment information is information provided to the patient by the pain treatment support device 50 instead of a doctor, and is information related to the treatment method selected according to the patient's pain condition.

[0079] The response information generation unit 58 may also generate response information in the rule base, for example, using a table indicating the correspondence between the evaluation results of pain and the response information. The table may also indicate the correspondence between the evaluation results of pain and the response information. For example, in the case where the evaluation results of pain (the course of the intensity (degree) of the patient's pain from the past to the future) increase, it is possible to establish correspondence between prescription information such as changing the medicine (response information) and administration of the medicine by means of a pump (response information). In addition, in the case where the evaluation results of pain change, it is possible to establish correspondence between the diagnosis (response information) performed by the doctor. In addition, in the case where the evaluation results of pain are stable and do not increase, it is possible to establish correspondence between response information such as the response method to maintain the status quo.

[0080] In addition, the response information generation unit 58 can be composed of a model using an algorithm obtained by machine learning, for example, SVM (support vector machine), decision tree, random forest, adaptive boosting, neural network, etc. can be used. In the case where the response information generation unit 58 is composed of a model using an algorithm obtained by machine learning, the processing with the help of the model is, for example, as follows. The model is generated to output response information when the evaluation result of pain is input. The control unit 51 can input the evaluation result of the patient's pain into the model and obtain the response information output by the model. The control unit 51 can output the obtained response information. The training data for machine learning can be collected, for example, in the following manner. Using the electronic medical records of multiple patients, etc., it is sufficient to collect data that establishes the correspondence between what kind of response method the doctor adopted when what kind of pain occurred in the patient.

[0081] As described above, the control unit 51 is able to obtain pain-related information related to the patient's pain, input the obtained pain-related information into the learning model 61 that outputs the pain evaluation result when the pain-related information is input to obtain the patient's pain evaluation result, generate response information for coping with the pain based on the obtained pain evaluation result, and output the generated response information.

[0082] Figure 6 2 is a diagram showing a second example of the processing of generating the response information by the pain treatment support device 50. Figure 5 The difference of the first example illustrated in the example is that in addition to the pain-related information, the medical information and the literature information are also input to the learning model 61. The control unit 51 reads the medical information of a specific patient from the medical information DB55, and inputs the read medical information into the learning model 61. The medical information of a specific patient is time series data of one or more moments. For example, it is not only the current medical information of a specific patient, but also the medical information of the past moments traced back from the present. The control unit 51 can generate a medical information vector by performing a vectorization operation to generate a unique vector on the medical information, and input the generated medical information vector into the learning model 61. In addition, the medical information vector can also be generated for each of multiple moments. For example, the learning model 61 can also output the evaluation results of the pain from the past three months to the future one month based on the pain-related information and medical information of the past three months, and can also output the evaluation results of the pain from the past six months to the future three months based on the pain-related information and medical information of the past six months. In addition, although not shown in the figure, the response information and the pain process pattern of the response information DB56 can also be input into the learning model 61.

[0083] In addition, the control unit 51 reads out the document information from the document information DB 57, and inputs the read document information into the learning model 61. The control unit 51 can generate a document information vector by performing a vectorization operation to generate a unique vector on the document information, and input the generated document information vector into the learning model 61. The document information, for example, only needs to include information required to establish an association between the patient's past and future pain conditions, under the condition of historical information such as the patient's symptom history, vital data history, examination history, medication history, and treatment history. For example, if there is a paper showing how the pain changes if a certain specific medicine is taken, the paper can be used as the document information. In addition, if there is a guide showing how the pain develops if a certain specific treatment is implemented, the guide can be used as the document information. In particular, in the case where the patient's pain-related information and diagnosis and treatment information are insufficient (for example, in the case of less past data), the learning model 61 can output the patient's pain evaluation result by using the document information to supplement the shortage of pain-related information and diagnosis and treatment information. By increasing the types of information input into the learning model 61, it can be expected that the accuracy of the index output by the learning model 61 will be improved. Although not shown in the figure, the response information of the response information DB 56 and the pain progression pattern may be input to the learning model 61 .

[0084] As described above, the control unit 51 may acquire medical information related to the medical treatment of the patient and input the acquired medical information into the learning model 61 that outputs the evaluation result of pain when the medical information is input, thereby acquiring the evaluation result of the pain of the patient.

[0085] Alternatively, the control unit 51 may acquire literature information related to pain treatment and input the acquired literature information into the learning model 61 that outputs a pain evaluation result when the literature information related to pain treatment is input, thereby acquiring an evaluation result of the patient's pain.

[0086] Figure 7 2 is a diagram showing a third example of the processing of generating the response information by the pain treatment support device 50. Figure 6 The second example illustrated in FIG. 1 is different in that the patient's pain-related information, medical treatment information, and literature information are input to the treatment information generating unit 58 in addition to the pain evaluation result.

[0087] The response information generating unit 58 can also generate response information in the rule base using, for example, a table representing the correspondence between the evaluation results of pain, the patient's pain-related information, diagnosis and treatment information and literature information, and the response information. The table can also represent the correspondence between the evaluation results of pain, the patient's pain-related information, diagnosis and treatment information and literature information, and the response information. For example, when the evaluation results of pain (the course of the patient's pain intensity (degree) from the past to the future) increase, and the pain based on the patient's pain-related information is relatively strong and lasts for a long time, response information such as stopping the medication and contacting the doctor can be established. In addition, when the evaluation results of pain are stable and have not increased, and there is no problem with the data of the examination results, response information of the response method to maintain the status quo can be established.

[0088] In addition, similar to the first and second examples, the response information generating unit 58 can be composed of a model using an algorithm obtained by machine learning, for example, SVM (support vector machine), decision tree, random forest, adaptive boosting, neural network, etc. can be used.

[0089] In the case where the response information generating unit 58 is composed of a model using an algorithm obtained by machine learning, the processing with the help of the model is as follows, for example. The model is generated to output response information when the evaluation result of pain, the patient's pain-related information, medical information and literature information are input. The control unit 51 can input the patient's pain evaluation result, the patient's pain-related information, medical information and literature information into the model, and obtain the response information output by the model. The control unit 51 can output the obtained pain process pattern and response information. The training data for machine learning can be collected, for example, in the following manner. Using the electronic medical records of multiple patients, etc., it is sufficient to collect corresponding data on what kind of process the patient's pain has occurred, what the patient's pain-related information and medical information are, and what kind of response method the doctor has adopted. At this time, you can also refer to the literature information.

[0090] Figure 8: is a diagram showing an example of a method for generating a learning model 61. In the following, it is assumed that the pain treatment supporting device 50 generates the learning model 61, but it can also be assumed that a learning processing device other than the pain treatment supporting device 50 generates the learning model 61, and the pain treatment supporting device 50 obtains the generated learning model 61. The control unit 51 obtains training data (second training data) including pain-related information, diagnosis and treatment information, literature information related to pain treatment, and evaluation results of the pain of multiple patients. These training data include disease course information and pain change information of multiple patients. Pain-related information, diagnosis and treatment information, and pain evaluation results are time series data, for example, including data within a period of one month, three months, six months, or 12 months. The literature information, for example, only needs to include information required to establish an association between the patient's pain and how it changes under the circumstances of historical information such as the patient's symptom history, vital data history, examination history, drug taking history, and treatment history. For example, if there is a paper that shows how pain changes when taking a certain specific drug or undergoing a specific treatment, the paper can be used as the literature information. In addition, if there is guidance indicating how pain changes if a certain specific treatment is implemented, the guidance can be used as literature information. The control unit 51 can generate a learning model 61 based on the acquired training data so that the evaluation result of pain is output when pain-related information, diagnosis and treatment information, and literature information related to pain treatment are input. For example, the learning model 61 can use training data including pain-related information, diagnosis and treatment information, and pain evaluation results for six months, and use the pain-related information, diagnosis and treatment information, and literature information for the first three months of the six months as learning input data, and use the evaluation results of pain for the six months as teacher data for learning. In this case, the learning model 61 can output the evaluation results of pain from the past three months to the future three months based on the literature information, the pain-related information, and diagnosis and treatment information for the past three months. When generating the learning model 61, the parameters of the learning model 61 can be adjusted in such a way that the evaluation result of pain output by the learning model 61 is close to the teacher data included in the training data, that is, the evaluation result of pain (refer to the reference numeral A).

[0091] In addition, Figure 8In the example, the input data for learning includes pain-related information, diagnosis and treatment information, and literature information, but for example, the input data for learning may not include at least one of the diagnosis and treatment information and the literature information. For example, the control unit 51 may also obtain training data (first training data) including pain-related information related to pain of multiple patients and evaluation results of the pain of the multiple patients, and generate a learning model 61 based on the obtained training data so that the evaluation result of the pain is output when the pain-related information is input. However, if the input data for learning includes at least one of the diagnosis and treatment information and the literature information, it is more likely that the inference accuracy of the learning model 61 will be improved.

[0092] The control unit 51 can relearn the learning model 61. That is, the control unit 51 obtains training data including the corrected pain evaluation result, and based on the obtained training data, the control unit 51 readjusts the parameters of the learning model 61 in such a way that the pain evaluation result output by the learning model 61 when pain-related information, diagnosis and treatment information, and literature information related to pain treatment are inputted is close to the corrected pain evaluation result as the teacher data (see reference symbol B).

[0093] The correction of the pain evaluation result may be performed, for example, as follows: The control unit 51 receives feedback on the result of pain treatment based on the treatment information and the pain condition of the patient, and corrects the pain evaluation result according to the received pain condition.

[0094] Next, a specific example of the countermeasure information will be described. The control unit 51 can output the countermeasure information to the patient terminal device 10. The countermeasure information is displayed on the display panel of the patient terminal device 10, and the patient can perform input operations and selection operations based on the displayed content.

[0095] Fig. 9 1 is a diagram showing a first example of the treatment information 100. The treatment information 100 shows a pattern of the course of the patient's pain. Fig. 9 In the example, the pain progression pattern is displayed as a line graph, which shows the progression of the patient's pain from the past to the future. Questions based on the pain progression pattern are displayed to the patient in the same way as a doctor asks the patient (interview). For example, a question is "Is the pain not becoming difficult to eliminate?" The patient can operate the "yes" icon 101 or the "no" icon 102 to answer the question. As a result, the patient can get into an environment that is similar to the environment in which he or she is being examined by a doctor. If the patient operates the "yes" icon 101, the following will be displayed. Fig.10 Response information shown.

[0096] Fig.10 1 is a diagram showing a second example of the treatment information 110. The treatment information 110 includes prescription information. Fig.10In the example, as prescription information, it is displayed as "Please change the medicine. Increase the amount of medicine ○○ to ×× tablets." In addition, as a doctor's advice to the patient, it is displayed as "If the pain does not improve after one hour, please open the app." The patient can get an environment like consulting a doctor by opening the app. In addition, for changing the medicine, the doctor can also decide the option of changing during the consultation. If the patient operates the "Confirm the countermeasure" icon 111, the countermeasure is displayed. Fig.10 The prescription information shown in the figure can store a table corresponding to a plurality of pain passage patterns in advance in the storage unit 59. For example, the prescription information R1, R2, R3, ... corresponding to the pain passage patterns P1, P2, P3, ... can be stored in the storage unit 59. The control unit 51 can select the prescription information corresponding to the pain passage patterns P1, P2, P3, ... from the table. Fig. 9 The pain transition pattern that is closest to the pain transition pattern of the patient shown is determined, and prescription information associated with the selected pain transition pattern is determined.

[0097] As described above, the control unit 51 can output a change in the countermeasure information to the patient terminal device 10 based on the evaluation result of the pain.

[0098] In addition, the control unit 51 can output questions generated based on the evaluation results of the patient's pain to the patient terminal device 10, and output coping information to the patient terminal device 10 according to the patient's answer to the question. As a result, the patient can obtain a coping method corresponding to the pain conditions from the past to the future, including the present, in a period other than the doctor's examination, and the patient's quality of life (QOL: Quality of life) can be improved. In this way, an appropriate coping method can be provided.

[0099] Fig.11 1 is a diagram showing a third example of the treatment information 120. The treatment information 120 shows the course of the patient's pain. Fig.11 In the example, Fig. 9 Similarly, the pain progression pattern is displayed as a line graph, and the progression of the patient's pain from the past to the future can be seen. Analysis and prescription of pain based on the pain progression pattern are displayed. For example, "The pain is getting stronger. Give the medicine in the pump." In this way, the patient's pain can be determined and the medicine in the pump can be automatically given. In addition, instructions can be sent to medical practitioners, caregivers, etc. to start the pump remotely at home, etc. In this way, the pump can also be operated without remote control.

[0100] Fig.12 1 is a diagram showing a fourth example of the countermeasure information 130. The countermeasure information 130 shows the status during the pump operation. Fig.12In the example, it is displayed as "△△ml of medicine ○× is being administered.", "The remaining amount after administration becomes ○○ml.", and "Please keep quiet during administration.", and the progress of the drug administration is displayed in a graphical form, so that the progress status can be understood at a glance.

[0101] Fig.13 1 is a diagram showing a fifth example of the treatment information 140. The treatment information 140 indicates that the administration of the medicine has been completed. Fig.13 In the example of , it is displayed as "△△ml of medicine ○× has been administered.", "The remaining amount after administration is ○○ml.", "Contact the doctor and the administration is completed.", and it is graphically displayed that the administration of the medicine has been completed.

[0102] As described above, the control unit 51 can control the automatic administration of medicine in the medicine infusion pump based on the evaluation result of the patient's pain. Thus, for example, medicine can be automatically administered according to the patient's pain condition within the range of the prescription determined by the doctor.

[0103] Fig.14 1 is a diagram showing a sixth example of the countermeasure information 150. The countermeasure information 150 includes information for confirming the countermeasure method. Fig.14 In the example, "Is there anything I would like to consult?" is displayed, and the patient's symptoms and pain conditions can be confirmed. Specifically, the "unconscious" icon 151, "unable to sleep" icon 152, "pain not relieved" icon 153, "other" icon 154, etc. are displayed, and the patient can select the icon that matches his or her own symptoms and pain conditions to operate. For example, if the patient feels that he or she is not very clear, he or she can operate the "unconscious" icon 151. In this way, the following will be displayed Fig.15 In addition, voice input or the like may be used to replace the structure in which the icons are displayed for operation.

[0104] Fig.15 1 is a diagram showing a seventh example of the countermeasure information 160. The countermeasure information 160 includes information for confirming the countermeasure method. Fig.15 In the example, "Please tell me your current condition." is displayed, and questions for determining the patient's current condition in further detail are displayed. Questions include, for example, "Please tell me your current pain on a scale of 1 to 10.", "When did the symptom begin?", etc., but are not limited to these. The patient inputs answers to the questions, and by operating the "Confirm Input" icon 161, the answers to the questions are sent to the pain treatment support device 50. Alternatively, voice input may be used.

[0105] Fig.16 1 is a diagram showing an eighth example of the response information 165. The response information 165 includes a prescription for medicine and a recommendation to contact a doctor. Fig.16In the example, it is displayed as "Please do the following.", "Please stop taking medicine ××. (Don't worry, I have obtained the doctor's permission.)", "Please contact the attending physician if there is no improvement in half a day.". As a result, the patient can stop taking medicine ×× and observe the situation for the time being. If the symptoms of "unconsciousness" improve, it can be determined that there is no need to contact the attending physician. In addition, if the patient is still unconscious even if the medication ×× is stopped, the attending physician can be contacted to receive a doctor's examination. In addition, voice output can also be used instead of displayed text. Fig.16 The response information shown can store a table that preliminarily corresponds to a plurality of answer combinations in the storage unit 59. For example, response information S1, S2, S3, ... that corresponds to the answer combinations W1, W2, W3, ... can be selected from the table by the control unit 51. Fig.15 The combination of answers shown determines the response information corresponding to the combination of answers selected.

[0106] As described above, the control unit 51 may receive the patient's condition as a result of implementing the countermeasure information and recommend a doctor's examination based on the received condition.

[0107] Fig.17 166 is a diagram showing a ninth example of the response information 166. The ninth example shows Fig.14 In the sixth example, the patient operates the "pain not relieved" icon 153. For example, Fig.17 As shown, it is displayed as "Administer ○○ medicine from the pump. (Don't worry, the doctor has approved the discontinuation of the medicine.)". If the patient operates the "Administer" icon 167, the medicine can be administered. In addition, it can also be displayed as "Today's dosage after administration is ○○ml. (Can be administered up to △△ml / day)". In this way, the patient can administer the set medicine to the pump even if the pain is not eliminated. In addition, voice output can also be used instead of displayed text.

[0108] As described above, the control unit 51 can receive consultation from the patient and output the response information to the patient terminal device 10 according to the received consultation.

[0109] Fig.18 170 is a diagram showing the tenth example of the treatment information 170. The treatment information 170 shows the course of the drug effect. If the drug effect is y and the pain is x, the relationship between the drug effect y and the pain x can be expressed as y=K / x, for example. K is a constant. In addition, the relationship is not limited to this. Fig.18In the example, the drug effect pattern is displayed as a line graph, and the patient's drug effect changes from the past to the future. Questions based on the drug effect pattern are displayed to the patient in the same way as a doctor asks the patient (interview). For example, the question is "The drug effect is starting to weaken. Change the treatment method." As a result, the patient can get the same environment as when receiving a doctor's examination. The pain treatment auxiliary device 50 can then be as described below. Fig.19 or Fig. 20 The illustrated countermeasure information is displayed on the patient terminal device 10 .

[0110] Fig.19 175 is a diagram showing an eleventh example of the response information 175. The response information 175 includes the response method after the change. Fig.19 In the example, it is displayed as "Increase the amount of medicine △△ to ×× pills." and it is displayed as "Change to this response? If possible, the medicine will be arranged." If the patient operates the "Yes" icon 176, the medicine is arranged. The arrangement of medicine can be as follows. For example, (1) delivering the prescription-based medicine to the patient's home, (2) preparing the prescription-based medicine at the pharmacy designated by the patient, (3) sending the prescription to the patient terminal device 10, etc. In addition, for the change of medicine, the doctor can also decide the change option during the consultation. In addition, when arranging medicine, the doctor's consent can also be obtained. In the case where the patient operates the "No" icon 177, the medicine is not arranged. Fig.19 The countermeasure method shown in the figure may also be a table corresponding to a plurality of drug effect passage patterns stored in the storage unit 59 in advance. For example, the countermeasures T1, T2, T3, ... are corresponding to the drug effect passage patterns M1, M2, M3, ... The control unit 51 can select the countermeasures T1, T2, T3, ... corresponding to the drug effect passage patterns M1, M2, M3, ... from the table. Fig.18 The drug effect transition pattern that is closest to the drug effect transition pattern of the displayed patient is used to determine a countermeasure method that corresponds to the selected drug effect transition pattern.

[0111] Fig. 20 180 is a diagram showing a twelfth example of the treatment information 180. The treatment information 180 includes a doctor's recommendation for treatment and a doctor's appointment. Fig. 20 In the example of , it is displayed as "In addition to taking medicine, doctor's treatment is required. Make an appointment with a doctor." The pain treatment support device 50 can advise the patient to intervene with a doctor, that is, to have a doctor's examination, when it is determined based on the patient's drug effect course pattern (pain course pattern) that the patient's condition will not improve by taking medicine alone. If the patient operates the "make doctor's appointment" icon 181, the information required for the doctor's appointment is displayed and processed.

[0112] As described above, the control unit 51 can output the change of the treatment information based on the drug efficacy of the patient to the patient terminal device 10. In addition, the control unit 51 can receive the change of the treatment information and receive the arrangement of the drug or the contact with the doctor.

[0113] Fig.21 FIG. 13 is a diagram showing a thirteenth example of the treatment information 190. The treatment information 190 shows the course of the patient's pain. Fig.21 In the example of , the pain progression pattern repeatedly produces a situation where the pain continues at ordinary times and becomes stronger or weaker according to time. In this way, when the pain progression pattern shows complex changes, for example, it is displayed as "Doctor's consultation is required. Doctor's consultation is recommended." If the patient operates the "Contact doctor" icon 191, the processing required to contact the doctor is performed.

[0114] As described above, the control unit 51 may recommend a doctor's examination based on the evaluation result of the pain.

[0115] Fig. 22 3 is a diagram showing an example of the treatment information correction screen 300. The treatment information correction screen 300 is displayed on the doctor terminal device 40 in response to a request from the doctor terminal device 40. The doctor can display the treatment information correction screen 300 on the doctor terminal device 40 and regularly observe the symptoms and pain of the patient. Fig. 22 In the example, the course of patient ×××× is displayed. The response information correction screen 300 displays the patient's pain course pattern, medical information history, treatment option correction 302, etc. The treatment option correction 302 includes response information (treatment content) generated based on the patient's pain evaluation results. By observing the patient's pain course pattern and medical information history, the doctor can determine whether it is necessary to revise the current treatment policy for the patient. If the doctor determines that the treatment policy needs to be revised, he can select the required treatment from the treatment content displayed in the treatment option correction 302. The choice of treatment includes changing the treatment, adding the treatment, deleting the treatment, etc. In addition, if the doctor determines that a consultation with the patient is necessary, he can operate the "consultation setting" icon 301 to perform the processing required for the consultation setting.

[0116] As described above, the control unit 51 can receive an operation of correcting the treatment information generated based on the evaluation result of the patient's pain from the doctor terminal device 40 .

[0117] As described above, according to this embodiment, the pain and symptoms felt by the patient on a daily basis can be captured in real time and timely, pain relief can be guided, and the patient's QOL can be improved. In addition, the patient's pain and symptoms from the past to the future can be grasped, and the generation and increase of pain can be suppressed before it occurs.

[0118] Fig.23 5 is a diagram showing an example of a processing sequence by means of the pain treatment auxiliary device 50. In the following, for convenience, the main body of the processing is described as the control unit 51. The control unit 51 obtains the patient's pain-related information (S11), and stores the obtained pain-related information in the pain-related information DB54 (database) (S12). The pain-related information can be repeatedly obtained for each patient at a necessary time. For example, it can be obtained once or multiple times during the period from the last visit to the hospital to the next visit to the hospital.

[0119] The control unit 51 acquires the patient's medical information (S13), and stores the acquired medical information in the medical information DB55 (database) (S14). The medical information can be acquired when the doctor determines that it is necessary, not only during the examination.

[0120] The control unit 51 inputs the patient's pain-related information, medical information, and literature information related to pain treatment into the learning model 61, and obtains the patient's pain evaluation result output by the learning model 61 (S15). The control unit 51 generates response information including the patient's pain progression pattern based on the patient's pain evaluation result obtained from the learning model 61 (S16). In this case, the response information may be generated based on the patient's pain-related information, medical information, and literature information.

[0121] The control unit 51 stores the generated countermeasure information in the countermeasure information DB 56 (database) ( S17 ), outputs the generated countermeasure information ( S18 ), and ends the processing.

[0122] Fig.24 is a diagram showing an example of the order of generating the learning model 61. The control unit 51 obtains training data including pain-related information, diagnosis and treatment information, pain evaluation results, and literature information related to pain treatment for a plurality of patients (S31). Based on the obtained training data, the control unit 51 generates the learning model 61 so that when the pain-related information, diagnosis and treatment information, and literature information related to pain treatment for each patient are input, the evaluation result of the pain of each patient is output (S32). The control unit 51 stores the generated learning model 61 in the storage unit 59 (S33), and ends the processing.

[0123] Description of Reference Numerals

[0124] 1…communication network; 10…patient terminal device; 20…equipment; 30…assistant terminal device; 40…doctor terminal device; 50…pain treatment assisting device; 51…control unit; 52…communication unit; 53…storage; 54…pain-related information DB; 55…medical information DB; 56…response information DB; 57…document information DB; 58…response information generating unit; 59…storage unit; 60…computer program; 61…learning model.

Claims

1. A computer program, characterized in that Causes the computer to perform the following processing: Obtain pain-related information related to the patient's pain, The pain evaluation result of the patient is obtained by inputting the acquired pain-related information into a learning model that outputs a pain evaluation result when pain-related information is input, Based on the obtained pain evaluation results, response information for coping with the pain is generated. The generated response information is output.

2. The computer program according to claim 1, characterized in that The pain-related information includes at least one of an evaluation index for evaluating pain, vital data, medication information, and physical condition.

3. The computer program according to claim 1, characterized in that Causes the computer to perform the following processing: obtaining medical information related to the medical treatment of the patient, Furthermore, the acquired medical information is input to the learning model that outputs the evaluation result of pain when medical information is input, thereby acquiring the evaluation result of the pain of the patient.

4. The computer program according to claim 3, characterized in that The diagnosis and treatment information includes at least one of diagnosis information, examination information, treatment information, prescription information and disease prognosis prediction information.

5. The computer program according to claim 1, characterized in that Causes the computer to perform the following processing: Obtain literature information related to pain treatment, Furthermore, the acquired literature information is input to the learning model that outputs a pain evaluation result when literature information related to pain treatment is input, thereby acquiring an evaluation result of the patient's pain.

6. The computer program according to any one of claims 1 to 5, characterized in that Perform the following processing: The pain assessment result includes the course of pain of the patient from the past to the future.

7. The computer program according to any one of claims 1 to 5, characterized in that Causes the computer to perform the following processing: receiving a condition of the patient as a result of implementing the response information, We recommend a doctor's consultation based on your condition.

8. The computer program according to any one of claims 1 to 5, characterized in that Causes the computer to perform the following processing: receiving the patient's pain condition as a result of implementing pain treatment based on the coping information, Modify pain assessment results based on the accepted pain status, The learning model is relearned using the corrected pain evaluation results.

9. The computer program according to any one of claims 1 to 5, characterized in that Causes the computer to perform the following processing: An operation of correcting the treatment information generated based on the evaluation result of the patient's pain is received from the doctor terminal device.

10. The computer program according to any one of claims 1 to 5, characterized in that Causes the computer to perform the following processing: Questions generated based on the patient's pain evaluation results are output to a patient terminal device, and response information is output to the patient terminal device based on the patient's answers to the questions.

11. The computer program according to any one of claims 1 to 5, characterized in that Causes the computer to perform the following processing: Accept consultation from said patient, The response information is output to the patient terminal device according to the received consultation.

12. The computer program according to any one of claims 1 to 5, characterized in that Causes the computer to perform the following processing: Receive medication arrangements or contact with a physician along with the response information.

13. The computer program according to any one of claims 1 to 5, characterized in that Causes the computer to perform the following processing: Automatic administration of medicine in the medicine infusion pump is controlled based on the evaluation result of the patient's pain.

14. An information processing device, characterized in that: have: a first acquisition unit that acquires pain-related information related to the patient's pain; a second acquisition unit that inputs the acquired pain-related information into a learning model that outputs an evaluation result of pain when pain-related information is input, thereby acquiring an evaluation result of the pain of the patient; a generating unit that generates coping information for coping with the pain based on the acquired pain evaluation result; as well as An output unit outputs the generated response information.

15. An information processing method, characterized in that: Obtain pain-related information related to the patient's pain, The pain evaluation result of the patient is obtained by inputting the acquired pain-related information into a learning model that outputs a pain evaluation result when pain-related information is input, Based on the obtained pain evaluation results, response information for coping with the pain is generated. The generated response information is output.

16. A learning model generation method, characterized in that: obtaining first training data, the first training data comprising: pain-related information related to pain of a plurality of patients, and pain evaluation results of the plurality of patients, Based on the acquired first training data, a learning model is generated so as to output an evaluation result of pain when pain-related information is input.

17. The learning model generation method according to claim 16, characterized in that: obtaining second training data, the second training data further comprising: diagnosis and treatment information of a plurality of patients, literature information related to pain treatment, and evaluation results of pain of the plurality of patients, The learning model is generated based on the acquired second training data so as to output a pain evaluation result when medical treatment information and literature information related to pain treatment are input.

Images