Processing device, processing program, processing method, and processing system

Abstract

[Problem] To provide a processing device, a processing program, a processing method, and a processing system with which it is possible to more efficiently make an assessment relating to the onset of delirium. [Solution] A processing device comprising at least one processor, wherein the at least one processor is configured so as to execute processing for: acquiring, via a communication interface, subject information indicating the state of a subject receiving medical treatment from a medical institution; acquiring the result of assessing the onset of delirium by inputting the acquired subject information into a trained assessment model used for performing assessment relating to the onset of delirium; and outputting the acquired assessment result via the communication interface.

Description

Processing device, processing program, processing method, and processing system

[0001] The present disclosure relates to a processing device, a processing program, a processing method, and a processing system for determining the onset of delirium.

[0002] Systems for managing patients hospitalized at medical institutions have been known for some time. For example, Patent Document 1 describes a "nursing support system including a server and a client, wherein the server includes a storage unit for recording nursing data of a plurality of patients, a search processing unit for searching and acquiring from the storage unit a plurality of nursing data of the patient for creating a time chart showing the patient's condition in chronological order using graphs and tables, and a transmission unit for transmitting the acquired nursing data; the client includes a receiving unit for receiving the nursing data transmitted from the transmission unit and a time chart creation unit for creating a time chart of the patient based on the received nursing data; and the search processing unit extracts nursing data of items necessary for creating graphs and tables in the time chart from a plurality of items of nursing data recorded in the storage unit."

[0003] Japanese Patent Application Laid-Open No. 2006-268613

[0004] Therefore, in light of the above-described technology, the present disclosure aims to provide, through various embodiments, a processing device, processing program, processing method, and processing system that are capable of more efficiently determining the onset of delirium.

[0005] According to one aspect of the present disclosure, there is provided a "processing device having at least one processor, wherein the at least one processor is configured to execute a process to acquire subject information indicating the condition of a subject receiving medical treatment from a medical institution via a communication interface, acquire a judgment result of the onset of delirium by inputting the acquired subject information into a trained judgment model used to make a judgment regarding the onset of delirium, and output the acquired judgment result via the communication interface."

[0006] According to one aspect of the present disclosure, there is provided a processing program that causes a computer having at least one processor to function as follows: acquire, via a communication interface, subject information indicating the condition of a subject receiving medical treatment from a medical institution; input the acquired subject information into a trained judgment model used to make a judgment regarding the onset of delirium, thereby acquiring a judgment result regarding the onset of delirium; and output the acquired judgment result via the communication interface.

[0007] According to one aspect of the present disclosure, there is provided a processing method executed by at least one processor in a computer having the at least one processor, the processing method including: a step of acquiring, via a communication interface, subject information indicating the condition of a subject receiving medical treatment from a medical institution; a step of acquiring a judgment result of the onset of delirium by inputting the acquired subject information into a trained judgment model used to make a judgment regarding the onset of delirium; and a step of outputting the acquired judgment result via the communication interface.

[0008] According to one aspect of the present disclosure, there is provided a processing system including "the processing device described above and a terminal device carried by a nurse who provides medical treatment to a subject from a medical institution, and configured to be connected to the processing device via a communication network and receive the assessment result of the onset of delirium obtained by the processing device."

[0009] According to the present disclosure, it is possible to provide a processing device, a processing program, a processing method, and a processing system that are capable of more efficiently determining the onset of delirium.

[0010] It should be noted that the above effects are merely illustrative for the sake of convenience and are not limiting. In addition to or instead of the above effects, any effect described in this disclosure or an effect obvious to a person skilled in the art may be achieved.

[0011] FIG. 1 is a block diagram showing a configuration of a processing system 1 according to an embodiment of the present disclosure. FIG. 2 is a block diagram showing a configuration of a processing device 100 according to an embodiment of the present disclosure. FIG. 3A is a diagram conceptually showing a subject management table stored in an information providing device 400 according to an embodiment of the present disclosure. FIG. 3B is a diagram conceptually showing a cause management table stored in an information providing device 400 according to an embodiment of the present disclosure. FIG. 4 is a diagram showing a processing flow executed in a processing system 1 according to an embodiment of the present disclosure. FIG. 5 is a diagram showing a processing flow executed in a model generating device 300 according to an embodiment of the present disclosure. FIG. 6 is a diagram showing a processing flow executed in a model generating device 300 according to an embodiment of the present disclosure. FIG. 7 is a diagram showing an example of a screen output from a processing device 100 according to an embodiment of the present disclosure. FIG. 8 is a diagram showing an example of a screen output from a processing device 100 according to an embodiment of the present disclosure. FIG. 9 is a diagram showing an example of a screen output from a processing device 100 according to an embodiment of the present disclosure. FIG. 10 is a diagram showing an example of a screen output from a processing device 100 according to an embodiment of the present disclosure.

[0012] 1. Overview of Processing System 1 The processing system 1 according to the present disclosure is used to acquire subject information indicating the condition of a subject undergoing medical treatment at a medical institution and output a delirium onset assessment result. In particular, the processing system 1 is used to assess the risk of future delirium onset for subjects and others hospitalized at medical institutions, and further to assess the severity of the onset cause.

[0013] Here, delirium is a type of consciousness disorder that develops primarily due to physical abnormalities such as pain, dehydration, constipation, and fever, or drug use. Delirium is a pathological condition that presents with various psychiatric symptoms, including cognitive impairment, hallucinations, delusions, and mood swings. Delirium can be classified into three types: hyperactive delirium, which results in a highly active and psychomotor agitated state such as restlessness; hypoactive delirium, which results in decreased activity due to clouding of consciousness such as drowsiness; and mixed delirium. Delirium can significantly impact not only the treatment provided by medical professionals, but also the patient and their family, as it can lead to accidents such as falls and secondary complications. In particular, delirium is said to develop in 10% to 30% of general hospitalized patients, approximately 40% of elderly patients hospitalized for non-medical reasons due to progressive cancer, and more than 40% of patients admitted to palliative care units. Prolonged hospitalization increases medical costs and places a significant mental burden on patients and their families.

[0014] In this way, it is extremely useful to determine the risk of developing delirium and the severity of the cause of the onset of delirium. Therefore, the processing system 1 makes it possible to determine the risk of developing delirium and the severity of the cause of the onset of delirium, particularly based on subject information indicating the condition of the subject.

[0015] In the present disclosure, a "subject" may be any person who receives medical treatment at a medical institution, and is not limited to only those with specific attributes. Therefore, such subjects include all types of people, such as patients, test subjects, diagnosed individuals, healthy individuals, and individuals requiring care. In particular, since delirium is frequently observed among hospitalized patients as described above, hospitalized patients are a preferred example.

[0016] Furthermore, in the present disclosure, the term "user" may refer to anyone who directly or indirectly uses the processing device 100 of the processing system 1, and is not limited to only those with a specific attribute. Therefore, such users include all types of people, such as medical professionals, the subject, and close relatives such as family members who support the subject. In particular, since delirium symptoms are common among hospitalized patients as described above, and from the perspective of providing daily medical care and long-term care to such hospitalized patients, suitable examples include nurses, caregivers, and close relatives such as the subject's family members.

[0017] Furthermore, in this disclosure, the term "healthcare professional" refers to anyone engaged in medical care and is not limited to those with specific attributes. Therefore, such healthcare professionals include all types of people, such as doctors, nurses, laboratory technicians, pharmacists, medical administrators, medical institution staff and managers, emergency personnel, medical device and equipment personnel, caregivers, nursing facility staff and managers, and staff at institutions providing medical services such as chiropractic, osteopathy, and massage. In particular, as described above, delirium symptoms are common among hospitalized patients, and nurses are a suitable example of such professionals who provide medical services to such hospitalized patients on a daily basis.

[0018] Furthermore, in this disclosure, "medical procedures" are not limited to medical procedures provided based on medical science for the treatment, diagnosis, or prevention of human diseases, but also include any pseudo-medical procedures such as chiropractic, osteopathy, massage, or nursing care. Similarly, a "medical institution" may be any institution that provides medical procedures, and includes not only medical institutions that provide such medical procedures, but also the period during which such pseudo-medical procedures are provided.

[0019] Furthermore, although terms such as "determination" are used in this disclosure, these do not necessarily mean a definitive determination by a doctor. For example, these terms naturally include a case where a user other than a doctor uses the processing system 1 to make a determination using the processing device 100. Furthermore, "determination" also includes assisting a doctor or other such person in making a definitive determination or diagnosis.

[0020] 1 is a block diagram showing a configuration of a processing system 1 according to an embodiment of the present disclosure. According to FIG. 1 , the processing system 1 includes at least a processing device 100 configured to determine the onset of delirium and a terminal device 200 configured to acquire a determination result of the onset of delirium from the processing device 100. The processing system 1 may also include an information providing device 400 configured to provide subject information indicating the state of the subject to the processing device 100, and a model generating device 300 for generating a trained determination model used when the processing device 100 determines the onset of delirium. The processing device 100, the terminal device 200, the model generating device 300, and the information providing device 400 are communicably connected to each other via at least one of a wireless network and a wired network.

[0021] 2. Configuration of the Processing Device 100 FIG. 2 is a block diagram showing the configuration of the processing device 100 according to an embodiment of the present disclosure. According to FIG. 2, the processing device 100 includes a processor 111, a memory 112, and a communication interface 113. These components are electrically connected to each other via control lines and data lines. The processing device 100 does not need to include all of the components shown in FIG. 2; some components may be omitted, or other components may be added. The processing device 100 is typically a server device, a database device, a laptop PC device, a desktop PC device, a smartphone device, or a tablet device. However, a cloud server device is preferably used from the perspective of service provision efficiency, or an on-premise server device is preferably used from the perspective of security. Furthermore, the processing device 100 does not need to perform all of its processing in a single processing device; multiple processing devices may perform the processing in a distributed manner. In such a case, the processing device 100 includes multiple processing devices that distribute the processing.

[0022] In the processing device 100, the processor 111 functions as a control unit that controls the processing device 100 or other components of the processing system 1 based on a program stored in the memory 112. Specifically, the processor 111 executes the following processes based on the program stored in the memory 112: "acquiring subject information indicating the condition of a subject receiving medical treatment from a medical institution via the communication interface 113," "acquiring a determination result of the onset of delirium by inputting the acquired subject information into a trained determination model used to make a determination regarding the onset of delirium," and "outputting the acquired determination result via the communication interface 113." The processor 111 is mainly composed of one or more CPUs, but may also be combined with a GPU, FPGA, etc. as appropriate.

[0023] The memory 112 is composed of RAM, ROM, non-volatile memory, HDD, SSD, etc., and functions as a storage unit. The memory 112 stores instructions and commands for various controls of the processing system 1 according to this embodiment as programs. Specifically, the memory 112 stores programs to be executed by the processor 111, such as "a process of acquiring, via the communication interface 113, subject information indicating the condition of a subject receiving medical treatment from a medical institution," "a process of acquiring a determination result of the onset of delirium by inputting the acquired subject information into a trained determination model used to determine the onset of delirium," and "a process of outputting the acquired determination result via the communication interface 113." In addition to the programs, the memory 112 also stores various information stored in a subject management table, a cause management table, etc., received mainly from the information providing device 400 as the processing progresses.

[0024] The communication interface 113 functions as a notification unit for transmitting and receiving various information to and from the information providing device 400 and the terminal device 200 connected via a wired or wireless network. Examples of the communication interface 113 include a wired communication connector such as USB or SCSI, a wireless communication transmitting / receiving device for broadband wireless communication such as wireless LAN, Bluetooth (registered trademark), or LTE, an infrared or other wireless communication, and various connection terminals for printed circuit boards or flexible circuit boards. The communication interface 113 receives subject information from the information providing device 400 and transmits the determination result to the terminal device 200, for example.

[0025] Although the configuration of the terminal device 200 is not specifically described, the terminal device 200 includes, for example, a processor, memory, a communication interface, an input interface, and an output interface. The terminal device 200 accepts user input instructions via the input interface and transmits various requests to the processing device 100 via the communication interface. The terminal device 200 also receives various information, such as the determination results acquired by the processing device 100, via the communication interface and outputs the information via the output interface (displaying it on a display or printing it on a printer). Examples of the terminal device 200 include laptop computers, desktop computers, smartphones, and tablet devices. As described above, delirium symptoms are common among hospitalized patients, and such terminal devices 200 are primarily used by nurses, caregivers, or close relatives of the patient, such as family members, to provide daily medical care and long-term care to such hospitalized patients. In this disclosure, the processing device 100 and the terminal device 200 are described separately, but they can naturally function as a single entity that functions as the processing device 100. In such cases, the processing device 100 will include an input interface and an output interface.

[0026] Although the configuration of the model generation device 300 for generating a trained decision model is not specifically described, the model generation device 300 includes, for example, a processor, a memory, an input interface, an output interface, and a communication interface. Examples of such devices include a laptop computer, a desktop computer, a smartphone, a tablet terminal, a server device, or a combination of these. Note that, although the processing device 100 and the model generation device 300 are described separately in this disclosure, they can also function as the processing device 100 together.

[0027] Furthermore, although the specific configuration of the information providing device 400 is not specifically described, the information providing device 400 has, for example, a processor, memory, and a communication interface, and, as necessary, includes an input interface and an output interface. Examples of such information providing devices 400 include the measuring device itself, a device for controlling the measuring device, an interview device, an electronic medical record device, a database device or server device in which information input to these devices is recorded, or a combination of these. The information providing device 400 reads out necessary information in response to a request received from the processing device 100, for example, and provides it to the processing device 100. Note that, in this disclosure, the processing device 100 and the information providing device 400 are described separately, but it is of course possible for them to function as a single device together as the processing device 100.

[0028] 3A is a diagram conceptually illustrating a subject management table stored in the information providing device 400 according to an embodiment of the present disclosure. The information stored in the subject management table is read from the information providing device 400 in accordance with the progress of processing by the processor 111 of the processing device 100, and is updated and stored in the information providing device 400 as needed.

[0029] According to FIG. 3A , the subject management table stores attribute information, measurement information, prescription drug information, evaluation information, assessment result information, nursing information, etc., in association with subject ID information. "Subject ID information" is information unique to each subject for identifying each subject. Subject ID information is generated each time a new subject is registered by a user via the terminal device 200. "Attribute information" is information regarding the attributes of each subject and is one type of subject information indicating the subject's condition. Examples of attribute information include subject name information, date of birth information, gender information, address information, height information, weight information, and medical interview information. Note that the information exemplified here is merely an example of attribute information, and any information indicating subject information can be used. Attribute information is acquired by a user entering it via an input interface on the terminal device 200, for example.

[0030] "Measurement information" refers to information measured by a measuring device and is one type of subject information indicating the subject's condition. Examples of measurement information include body temperature measured by a thermometer, heart rate (maximum and minimum values) measured by a heart rate monitor, blood pressure (maximum, minimum, and their range) measured by a sphygmomanometer, oxygen saturation (maximum, minimum, and their range) measured by a pulsoximeter, pulse measured by a pulse monitor, values ​​of white blood cells, red blood cells, hemoglobin, platelets, and hematocrit measured by a blood testing device, values ​​of pH, white blood cells, nitrite, bilirubin, ketone bodies, and the like measured by a urine analyzer, echo data measured by an ultrasound testing device, electrocardiogram data measured by an electrocardiogram testing device, and CT data measured by a CT device. Among these, values ​​of body temperature, heart rate, blood pressure, oxygen saturation, pulse, white blood cells, red blood cells, hemoglobin, platelets, and hematocrit are preferably used as they are useful for determining the onset of delirium. The information exemplified here is merely an example of measurement information, and any information indicating information about the subject can be used. The measurement information is obtained by receiving it from the measurement device via a communication interface, or by being input by any user via an input interface.

[0031] "Prescription drug information" is information about drugs prescribed to a subject or drugs administered for treatment (including medical dose narcotics), and is one type of subject information that indicates the subject's condition. In addition to the name of the drug actually prescribed, prescription drug information may also include the prescribed amount, dosage method, and dosage frequency. Furthermore, prescription drug information may include not only information about drugs currently prescribed, but also information about drugs prescribed in the past. Prescription drug information is obtained by inputting it via an input interface by any user on the terminal device 200, for example.

[0032] "Evaluation information" is information indicating the results of an evaluation of a subject regarding delirium or a delirium-related disease, and is one type of subject information indicating the subject's condition. Examples of evaluation information include the presence or absence of dementia, the presence or absence of brain substrate disease, the presence or absence of heavy alcohol consumption, and a history of delirium. The evaluation information is acquired by being input by any user via an input interface in the terminal device 200. Note that the evaluation information exemplified here is merely an example, and does not need to include all of this information; only a portion may be used, or other evaluation information may be substituted or added.

[0033] The "determination result information" is information indicating the result of the determination of the onset of delirium. The determination result information includes risk determination information indicating the result of the determination of the risk of developing delirium and cause determination information indicating the result of the determination of the level of the cause of delirium. The risk determination information may be a numerical value indicating the level of risk of developing delirium or a classification indicating the level, such as "high," "medium," "low," "level 1," "level 2," or "level 3." The cause determination information indicates the possibility that each of the causes of delirium, namely, "medium," "low," "level 1," "level 2," or "level 3," is a cause of delirium. Note that these causes are merely examples, and information identifying other symptoms may also be used. The determination result information is acquired by processing by the processing device 100. The determination result information may also include, as necessary, determination date information indicating the date on which the risk of developing delirium and the level of the cause of delirium were determined.

[0034] "Nursing information" is information showing the history of medical procedures provided at medical institutions. These procedures are primarily provided by nurses, so they are considered nursing information. However, they may also include information provided by other parties. Different nursing information is stored for each cause of delirium. For "medication," examples of nursing information include: - Whether or not medications that may cause delirium were used and their dosage; - Whether or not narcotics were used and their dosage; - Results of confirmation of consistency between the dosage and the disease causing hospitalization. For "pain," examples of nursing information include: - Confirmation of whether or not pain was present; - Pain assessment results (intensity, nature, location, etc.). For "dehydration," examples of nursing information include: - Whether or not blood tests were performed; - Confirmation of vital signs such as body temperature and heart rate; - Results of visual examination; - Water intake status and amount, and suggested drinking methods. In the case of "constipation," examples of nursing information include: - time elapsed since the last bowel movement - condition of the stool - severity of constipation based on medical interview and intestinal condition - whether laxatives have been taken and the amount thereof In the case of "fever," examples of nursing information include: - whether a blood test has been performed - results of confirmation of vital signs such as body temperature and heart rate - whether treatment such as taking antipyretics, cooling, or moisturizing has been performed Nursing information is acquired, for example, by any user inputting it via an input interface in the terminal device 200 each time a nurse provides these medical actions based on the assessment result information.

[0035] The information stored in the subject management table may be stored in the information providing device 400, or may be stored in another processing device including the processing device 100, a database device, or the like.

[0036] 3B is a diagram conceptually illustrating a cause management table stored in the information providing device 400 according to an embodiment of the present disclosure. The information stored in the cause management table is read from the information providing device 400 in accordance with the progress of processing by the processor 111 of the processing device 100, and is updated and stored in the information providing device 400 as needed.

[0037] 3B, the cause management table stores procedure information and the like in association with cause information that identifies each cause. One example of "cause information" is information that identifies "medication," "pain," "dehydration," "constipation," and "fever," which indicate the causes of the onset of delirium. That is, this information is provided in association with each cause identified as cause determination information in the determination result information. Note that the cause information exemplified here is merely an example, and does not necessarily need to include all of this information; only a portion may be used, or other cause information may be substituted or added.

[0038] The "procedure information" stores different information for each cause identified in the cause determination information. The procedure information is used to suggest medical procedures to be provided to the subject. For example, if the cause information is "drugs," examples of procedure information include information suggesting the following: · Check whether or not medications that may cause delirium have been used and the dosage; · Check whether or not narcotics have been used and the dosage; · Check the consistency between the dosage and the disease causing hospitalization; · Check with the attending physician. For example, if the cause information is "pain," examples of procedure information include information suggesting the following: · Check whether or not pain has been present; · Evaluate the pain (intensity, characteristics, location, etc.); · Consult regarding the level of treatment. For example, if the cause information is "dehydration," examples of procedure information include information suggesting the following: · Check whether or not a blood test has been performed; · Check vital signs such as body temperature and pulse rate; · Visual examination; · Check the water intake status and amount, and suggest a drinking method. Furthermore, if the cause information is "constipation," examples of procedure information include information that suggests: - Confirming the time since the last bowel movement - Confirming the condition of the stool - Determining the severity of the constipation based on the medical interview and the condition of the intestines - Determining whether a laxative has been taken and the amount thereof If the cause information is "fever," examples of procedure information include information that suggests: - Confirming whether a blood test has been performed - Confirming vital signs such as body temperature and heart rate - Confirming measures such as taking antipyretics, cooling, and moisturizing.

[0039] Note that these pieces of procedure information are merely examples, and naturally, other information may be included. Furthermore, while procedure information is stored according to each symptom in Fig. 3B, procedure information may be stored not only according to the cause but also according to the accuracy of the cause determination. In other words, in such a case, it becomes possible to select the optimal procedure according to not only the cause but also its accuracy.

[0040] The information stored in the cause management table may be stored in the information providing device 400, or may be stored in another processing device including the processing device 100, a database device, or the like.

[0041] 4. Processing Flow Executed by Processing Device 100 Fig. 4 is a diagram showing a processing flow executed by the processing device 100 according to an embodiment of the present disclosure. Specifically, Fig. 4 is a diagram showing a processing flow executed by the processor 111 of the processing device 100 by receiving, via the communication interface 113 of the processing device 100, a determination request transmitted by accepting an instruction input by a user via an input interface in the terminal device 200. This processing flow is mainly performed by the processor 111 of the processing device 100 reading and executing a program stored in the memory 112.

[0042] First, although not specifically shown in the figure, the processing flow starts by receiving, via the communication interface 113, a judgment request transmitted by accepting an instruction input by a user via the input interface of the terminal device 200 (S111).

[0043] FIG. 7 is a diagram illustrating an example of a screen output from the processing device 100 according to an embodiment of the present disclosure. Specifically, it is a diagram illustrating an example of a subject list screen 10 output to a display of the terminal device 200 via an output interface. According to FIG. 7 , the subject list screen 10 includes a collective assessment icon 11a, an individual assessment icon 11b, and a subject list area 12. The collective assessment icon 11a is an icon for requesting a collective assessment of the onset of delirium for all subjects listed in the subject list area 12 or for multiple subjects selected by accepting a user's instruction input via the input interface. That is, when an instruction input to the collective assessment icon 11a is accepted via the input interface, the processor of the terminal device 200 transmits a request for assessment to the processing device 100 via the communication interface, the request including subject ID information associated with all subjects or the selected multiple subjects and a request for assessment.

[0044] The individual assessment icon 11b is an icon for requesting a delirium onset assessment for a subject selected by receiving an instruction input from the user via the input interface. That is, when an instruction input to the individual assessment icon 11b is received via the input interface, the processor of the terminal device 200 transmits a assessment request, including subject ID information associated with the selected subject in advance, and a request for assessment, to the processing device 100 via the communication interface.

[0045] The subject list area 12 displays a list of subjects previously acquired from the subject management table. That is, the subject list area 12 includes attribute information, assessment date information, risk assessment information, cause assessment information, and care status information, associated with the subject ID information of the subject. Of these, the attribute information is information read from the attribute information, which is one of the subject information stored in the subject management table. The assessment date information is information read from the assessment result information stored in the subject management table. Specifically, the assessment date information indicates the date on which the risk of delirium onset and the cause of delirium onset were assessed, respectively, in year, month, and day format. Naturally, the date may be expressed in any format and may even include information up to the hour and minute. The risk assessment information is information read from risk assessment information stored in the subject management table and indicating the results of the assessment of the risk of delirium onset. Specifically, the risk assessment information includes a numerical value or classification indicating the degree of risk obtained as a result of the assessment. The cause determination information is stored in the subject management table and is read from the cause determination information that indicates the results of determining the degree of the cause of delirium. Specifically, the cause determination information includes information indicating the cause of delirium and, if necessary, its accuracy. The care status information is stored in the subject management table and is read from the nursing information. Specifically, the care status information includes information indicating the history and progress of whether medical treatment is being provided at the medical institution based on the nursing information.

[0046] The subject list area 12 displays the above information in a list associated with the subject ID information. The processor of the terminal device 200 can select a desired subject by accepting a user's instruction input for the row of the desired subject via the input interface. Although not specifically shown, the processor changes the display mode of the row corresponding to the selected subject (for example, by highlighting it), making it possible to distinguish between selected and unselected subjects. By accepting an instruction input for the collective judgment icon 11a or the individual judgment icon 11b as described above, the subject ID information of the selected subject is sent to the processing device 100 as a subject for judgment.

[0047] 7, the assessment date information, risk assessment information, cause assessment information, and care status information in the subject list area 12 are all displayed as "Not yet." This indicates that, as a result of referring to the relevant information in the subject management table, the process related to the assessment has not yet been carried out, and the assessment result information, nursing information, etc. have not yet been stored.

[0048] 4 , as described above, when the processor 111 of the processing device 100 receives the determination request via the communication interface 113, it reads out the subject ID information included in the determination request (S112). Then, the processor 111 transmits the read out subject ID information to the information providing device 400 via the communication interface 113.

[0049] Here, when the processor of the information providing device 400 receives the subject ID information from the processing device 100, it refers to the subject management table and reads out subject information such as attribute information, measurement information, prescription drug information, and evaluation information associated with the received subject ID information. Then, the processor of the information providing device 400 transmits the read out subject information to the processing device 100 via the communication interface.

[0050] The processor 111 of the processing device 100 acquires the subject information by receiving it transmitted via the communication interface 113 (S113). Note that, although the case where the subject information is received from the information providing device 400 installed remotely has been described here, the information providing device 400 and the processing device 100 may be configured as an integrated unit. In that case, the subject information is acquired by reading it from a subject management table stored in the memory 112 of the processing device 100.

[0051] After acquiring the subject information, the processor 111 determines the risk of developing delirium based on the acquired subject information (S114). As an example, the determination is made by using a trained risk determination model for determining the risk of developing delirium.

[0052] Here, Fig. 5 is a diagram showing a processing flow executed in the model generation device 300 according to an embodiment of the present disclosure. Specifically, Fig. 5 is a diagram showing a processing flow related to generation of a trained risk determination model used in the determination process of S114 in Fig. 4. This processing flow is mainly performed by the processor of the model generation device 300 reading and executing a program stored in memory.

[0053] 5, the processor of the model generating device 300 acquires subject information, such as attribute information, measurement information, prescription drug information, and evaluation information, previously acquired for each subject, by receiving it as training subject information from the information providing device 400 (S211). Note that the training subject information can be not only subject information acquired from actual subjects as described above, but also subject information generated by simulation.

[0054] Next, the processor of the model generating device 300 performs a process of labeling each piece of acquired training subject information with risk assessment information indicating the risk of developing delirium (S212). The labeling is performed by a medical professional such as a doctor diagnosing whether the corresponding subject has delirium based on each piece of training subject information, or by assigning a numerical value or classification indicating the degree of risk of developing delirium.

[0055] Once each training subject information and its associated risk assessment information are obtained, the processor uses them to perform machine learning of an assessment pattern (S213). For example, this machine learning is performed by providing the training subject information to a neural network composed of a combination of neurons, and repeatedly adjusting the parameters of each neuron so that the output of the neural network is the same as the risk assessment information. The processor then acquires a trained risk assessment model (e.g., neural network and parameters) (S214). This causes the processor to complete the generation of the trained risk assessment model. The acquired trained risk assessment model may be transmitted to the processing device 100 via a communication interface and stored in the memory 112 of the processing device 100. It may also be stored in the memory of the model generation device 300, another processing device, a server device, or the like.

[0056] Returning to Figure 4, the processor 111 inputs the subject information into the trained risk assessment model generated as described above, thereby obtaining risk assessment information indicating the risk of developing delirium as an output. In this way, by using the trained risk assessment model, it is possible to efficiently determine the risk of developing delirium. Note that, although the risk assessment information is obtained using the trained risk assessment model here, it may of course be obtained by other methods. For example, the processor 111 may prepare a risk management table in which subject information and risk assessment information are previously associated, and obtain the risk assessment information by referencing the risk management table based on the acquired subject information.

[0057] Next, the processor 111 refers to the acquired risk assessment information and determines whether the result of the risk assessment is "high," indicating a high risk of developing delirium (S115). If the processor 111 determines that the risk is "high," it further determines the degree of the cause of delirium based on the subject information of the subject determined to be "high" (S116). That is, this determination indicates the risk of each symptom occurring for each cause of delirium. As an example, this determination is made by using a trained cause determination model for determining the cause of delirium.

[0058] Here, Fig. 6 is a diagram showing a processing flow executed in the model generating device 300 according to an embodiment of the present disclosure. Specifically, Fig. 6 is a diagram showing a processing flow related to generation of a trained cause determination model used in the determination process of S116 in Fig. 4. This processing flow is mainly performed by the processor of the model generating device 300 reading and executing a program stored in memory. In the example of Fig. 6, such a trained cause determination model is generated in advance for each factor that can cause the onset of delirium (medications, pain, dehydration, constipation, and fever), but first, a case where the causative factor is "medications" will be described.

[0059] 6, the processor of the model generating device 300 acquires subject information, such as attribute information, measurement information, prescription drug information, and evaluation information, previously acquired for each subject, by receiving it as training subject information from the information providing device 400 (S311). Note that the training subject information can be not only subject information acquired from actual subjects as described above, but also subject information generated by simulation.

[0060] Next, the processor of the model generating device 300 performs a process of labeling each acquired piece of training subject information with cause determination information indicating whether or not a "medication" was the cause of the onset of delirium (S312). The labeling is performed by a medical professional such as a doctor determining, based on each piece of training subject information, whether or not a drug was the cause of delirium for the subject who developed delirium.

[0061] Once each training subject information and its associated cause determination information are obtained, the processor uses them to perform machine learning of a determination pattern (S313). For example, the machine learning is performed by providing the training subject information to a neural network composed of neurons, and repeatedly adjusting the parameters of each neuron so that the output of the neural network is the same as the cause determination information. The processor then acquires a trained cause determination model (e.g., neural network and parameters) for determining whether a drug is the cause (S314).

[0062] The processor also performs similar processing to label causes other than medication (pain, dehydration, constipation, and fever) and acquires trained cause determination models for determining whether pain, dehydration, constipation, and fever are each a cause. This completes the generation of trained cause determination models.

[0063] Each acquired learned cause determination model may be transmitted to the processing device 100 via a communication interface and stored in the memory 112 of the processing device 100, or may be stored in the memory of the model generation device 300, another processing device, a server device, etc.

[0064] In the example of FIG. 6 , a case where a trained cause determination model is generated and acquired for each cause has been described. However, this is not limited to this, and the presence or absence of multiple causes may be determined using a single trained cause determination model. Such a trained cause determination model is generated by a medical professional labeling a subject who has developed delirium as having one of the following causes: medication, pain, dehydration, constipation, or fever, based on each piece of training subject information. The training subject information and the cause are then input into the model generation device 300, and machine learning of the determination pattern is performed, thereby obtaining a single trained cause determination model capable of determining each cause. In this way, using a single trained cause determination model can reduce the processing load associated with generating the trained cause determination model.

[0065] Returning to FIG. 4 , the processor 111 inputs the subject information into the trained cause determination model generated as described above, thereby obtaining, as output, cause determination information indicating the degree of the cause of delirium onset. In this way, by using the trained cause determination model, it is possible to efficiently identify the cause of delirium onset. Note that, although the cause determination information is obtained using the trained cause determination model here, it may of course be obtained by other methods. For example, the processor 111 may prepare a cause determination table in which subject information and cause determination information are previously associated, and obtain the cause determination information by referencing the cause determination table based on the acquired subject information.

[0066] Next, the processor 111 refers to the cause management table based on the acquired cause determination information and identifies procedure information for proposing improvements to the cause (S117). Specifically, the processor 111 identifies causes from the cause determination information that have been determined to be "high," indicating a high probability that they will cause the onset of delirium. The processor 111 then identifies and reads out the procedure information associated with the identified cause.

[0067] The determination result of the risk of developing delirium (risk determination information) obtained in S114 of Fig. 4, the determination result of the degree of each cause of delirium onset (i.e., the possibility that it will be the main cause of the onset of delirium) obtained in S116 of Fig. 4, and the procedure information (cause determination information) corresponding thereto are transmitted, together with the subject ID information, to the information providing device 400 via the communication interface 113. The processor of the information providing device 400 that has received this information associates it with the subject ID information and stores it in the subject management table (S118).

[0068] In addition, the processor 111 transmits the assessment result information, which includes the assessment result of the risk of developing delirium (risk assessment information) obtained in S114 of Figure 4, the assessment result of the degree of each cause of delirium onset (i.e., the possibility that it will be the main cause of the onset of delirium) obtained in S116 of Figure 4, and the corresponding procedure information (cause assessment information), to the terminal device 200 that sent the assessment request via the communication interface 113 (S119).

[0069] 8 is a diagram illustrating an example of a screen output from the processing device 100 according to an embodiment of the present disclosure. Specifically, it is a diagram illustrating an example of a determination result confirmation screen 20 output to a display via an output interface in the terminal device 200. The determination result confirmation screen 20 is displayed, for example, when the processor of the terminal device 200 accepts, via an input interface, an instruction input by a user to select a row of a desired subject on the subject list screen 10 illustrated in FIG. 7 .

[0070] The assessment result confirmation screen 20 includes a subject ID area 21 containing subject ID information for identifying the subject, an attribute area 22 containing attribute information of the subject, a measurement area 23 and a measurement area 26 containing measurement information of the subject, a assessment result area 24 containing assessment result information of the subject, and a nursing area 25 containing nursing information of the subject. Specifically, the attribute area 22 reads and displays attribute information, which is one of the subject information stored in the subject management table. The measurement area 23 reads and displays vital information, such as body temperature and heart rate, which is one of the subject information stored in the subject management table. The assessment result area 24 displays risk assessment information indicating the assessment result of the risk of developing delirium and cause assessment information indicating the assessment result of each cause of delirium, which are part of the assessment result information output from the processing device 100. The nursing area 25 displays information indicating whether medical interventions to improve each cause have been provided based on the nursing information stored in the subject management table. Furthermore, in the measurement area 26, the various values ​​obtained from blood tests such as white blood cells and red blood cells are read out and displayed from the measurement information, which is one of the subject information stored in the subject management table.

[0071] Here, the nursing area 25 displays information indicating whether or not medical interventions to improve each cause have been provided, as described above, and in the example of Figure 8, all of them are displayed as "Not implemented." When the processor of the terminal device 200 receives an instruction input from the user via the input interface for the positions corresponding to "medication" and "pain" that have been determined to have a high probability of causing delirium, it outputs a proposal screen for proposing procedure information from the determination result information output from the processing device 100 to medical professionals, etc.

[0072] 9 is a diagram showing an example of a screen output from the processing device 100 according to an embodiment of the present disclosure. Specifically, it is a diagram showing an example of a proposal screen 30 output to a display via an output interface in the terminal device 200. The proposal screen 30 is displayed, for example, in the nursing area 25 of the determination result confirmation screen 20 as described above, by the processor of the terminal device 200 accepting, via the input interface, an instruction input by the user regarding a desired cause.

[0073] As shown in FIG. 9 , the screen includes information on procedures for "pain," one of the two factors determined to be likely to cause delirium: "drugs" and "pain." Specifically, the proposal screen 30 includes proposal areas 31 to 33 for suggesting medical procedures to be provided to the subject, broken down into individual steps, to a medical professional such as a nurse, and for inputting the results. The proposal area 31 includes a message saying "Verbally confirm whether or not you are in pain" and an icon for selecting the confirmation result, suggesting that the subject confirm whether or not they are in pain. The proposal area 32 includes messages saying "Please select the location of the pain," "Check whether the pain worsens with touch," and "Check whether you feel any discomfort or numbness," suggesting that the subject confirm the location and nature of the pain if they are experiencing pain, as well as input boxes and icons for inputting or selecting the respective confirmation results. The proposal area 33 includes messages saying "Check whether the pain keeps you up or wakes you up during sleep" and "Check whether the pain is so severe that you have to hold it in," suggesting that the subject confirm the intensity of the pain, as well as an icon for selecting the respective confirmation results. That is, the proposal screen 30 includes a display based on the procedure information in the cause management table.

[0074] 9 has been described using pain as an example, but different procedure information is displayed depending on each cause. The displayed procedure information is generated corresponding to the procedure information in the cause management table. Also, in the example of FIG. 9, a case has been described in which three proposal areas, proposal area 31 to proposal area 33, are included. However, the proposal areas may be one, two, or four or more depending on the procedure information, as long as they are provided corresponding to the procedure information.

[0075] Here, the proposal screen 30 includes a save icon 34 and a back icon 35 at the bottom. When the processor of the terminal device 200 accepts a user's instruction input to the save icon 34 via the input interface, it saves the information currently entered in each of the proposal areas 31 to 33 and returns to the subject list screen. Specifically, the processor transmits the information entered in each of the proposal areas 31 to 33 to the information providing device 400 via the communication interface to store it as nursing information in the subject management table. When the processor 111 of the processing device 100 accepts an information update request from the terminal device, it reads the nursing information, etc. stored in the subject management table from the information providing device 400 and transmits it to the terminal device 200 via the communication interface. Then, when the processor of the terminal device 200 receives the latest subject information via the communication interface, it controls the display of that information on the subject list screen. Note that when the processor accepts a user's instruction input to the back icon 35, it controls the display of the subject list screen without performing the above processing.

[0076] 10 is a diagram illustrating an example of a screen output from the processing device 100 according to an embodiment of the present disclosure. Specifically, it is a diagram illustrating an example of a target person list screen 10 output to a display via an output interface in the terminal device 200. The target person list screen 10 is displayed, for example, by the processor of the terminal device 200 accepting an instruction input for the save icon 34 on the proposal screen 30 as described above via the input interface.

[0077] According to Figure 10, the configuration of the screen is the same as the example shown in Figure 7. Figure 10 shows a state in which the risk of developing delirium and the degree of its cause have been determined by the processes of S114 and S116 in Figure 4, as explained in Figures 8 and 9, and medical intervention is being provided. Therefore, when focusing on the subject with subject ID information "A1," the assessment date information, risk assessment information, cause assessment information, and care status information, each of which is displayed as "not yet" in Figure 7, are now displayed with specific indications indicating the assessment date, the result of the risk assessment, the cause assessment, and that the provision of medical intervention has been completed.

[0078] Returning to FIG. 4 , the output of the determination result information in S119 allows the terminal device 200 to display a variety of corresponding information. In particular, in FIG. 8 , the determination result information output by the processing device 100 is displayed on the terminal device 200 as determination result information, allowing users, including medical professionals such as nurses, to more quickly understand the determination result of the onset of delirium and its cause. Also, in FIG. 9 , the procedure information output by the processing device 100 is displayed on the terminal device 200, allowing medical professionals such as nurses to more reliably and quickly provide the necessary medical treatment to the subject. Also, in FIG. 10 , the latest status of the determination result information, etc., is displayed in a list, allowing users to quickly understand the latest status.

[0079] This completes the processing flow.

[0080] 4, the trained risk assessment model is used in S114 to assess the risk of delirium and the degree of the cause of delirium, and the trained cause assessment model is used in S116 to assess the risk of delirium and the degree of the cause of delirium, respectively. However, it is also possible to use only one of the trained assessment models to obtain the assessment results.

[0081] In addition, in S116, the degree of the cause of delirium is determined only for subjects who are determined to have a "high" risk of developing delirium in S114. However, the degree of the cause of delirium may be determined for all subjects regardless of the degree of risk of developing delirium.

[0082] Furthermore, procedure information corresponding to only those causes determined in S117 to have a "high" possibility of causing delirium is identified. This allows causes that should be addressed with higher priority to be identified and their improvements to be implemented with priority. However, this is not limiting, and procedure information for all causes may be identified and output to the terminal device 200. In this case, the screens displayed in FIGS. 8 and 9 will display information corresponding to all procedure information.

[0083] As described above, in this embodiment, it is possible to provide a processing device, processing program, processing method, and processing system that can more efficiently determine the onset of delirium.

[0084] 9. Others In the above embodiment, the subject information for learning and the subject information used for each determination are described using the information shown in Fig. 3A as examples. However, these are merely examples, and it is also possible to use a combination of information from, for example, an MRI device, an X-ray device, an electrocardiogram device, an ultrasound diagnostic device, an endoscope device, a blood pressure monitor device, other medical record information, other medical interview information, and the like.

[0085] In the above embodiment, the medical treatment is mainly provided by a nurse. However, this is merely an example, and the medical treatment may be provided by, for example, a doctor, a laboratory technician, a pharmacist, a medical administrator, a medical institution staff member or manager, an emergency medical technician, a medical device or equipment manager, a caregiver, a nursing facility staff member or manager, a worker at an institution that provides medical treatment such as chiropractic, osteopathy, or massage, or a close relative such as a family member who supports the patient. In such a case, the terminal device 200 may be usable by any of the above-mentioned people other than a nurse.

[0086] In the above embodiment, the degree of the cause of delirium is determined (S116) only when the acquired risk determination result is "high," indicating a high risk of developing delirium (S115). However, instead of this, the degree of the cause of delirium may be determined even when the risk is "low." In other words, the determination in S115 may be omitted, and the degree of the cause of delirium may be determined in S116 in all cases.

[0087] The trained decision model described in the above embodiment is generated using a neural network or a convolutional neural network. However, the trained decision model is not limited to these, and can also be generated using machine learning techniques such as a nearest neighbor method, a decision tree, a regression tree, or a random forest.

[0088] The processes and procedures described herein can be realized not only by those explicitly described in the embodiments, but also by software, hardware, or a combination thereof. Specifically, the processes and procedures described herein can be realized by implementing logic corresponding to the processes in a medium such as an integrated circuit, volatile memory, non-volatile memory, magnetic disk, or optical storage. Furthermore, the processes and procedures described herein can be implemented as computer programs and executed by various computers, including processing devices and server devices.

[0089] Although processes and procedures described herein are described as being performed by a single device, software, component, or module, such processes or procedures may be performed by multiple devices, multiple software, multiple components, and / or multiple modules. Furthermore, although various information described herein is described as being stored in a single memory or storage unit, such information may be stored in multiple memories within a single device or multiple memories distributed across multiple devices. Furthermore, software and hardware elements described herein may be realized by integrating them into fewer components or by decomposing them into more components.

[0090] REFERENCE SIGNS LIST 1 Processing system 100 Processing device 200 Terminal device 300 Model generating device 400 Information providing device

Claims

1. A processing device having at least one processor, wherein the at least one processor is configured to execute the following processes: acquire subject information indicating the condition of a subject receiving medical treatment from a medical institution via a communication interface; acquire a judgment result of the onset of delirium by inputting the acquired subject information into a trained judgment model used to make a judgment regarding the onset of delirium; and output the acquired judgment result via the communication interface.

2. The processing device according to claim 1, wherein the trained judgment model is a trained risk judgment model used to judge the risk of developing delirium.

3. The processing device according to claim 1, wherein the judgment result is a result of judging the risk of developing delirium.

4. The processing device according to claim 1, wherein the trained judgment model is a trained cause judgment model used to judge the degree of the cause of the onset of delirium.

5. The processing device according to claim 1, wherein the judgment result is a result of judging the degree of the cause of the onset of the delirium.

6. The processing device described in claim 1, wherein the judgment result is a result of judging the risk of developing delirium by inputting the acquired subject information into a trained risk judgment model used to judge the risk of developing delirium, and of judging the degree of the cause of the onset of delirium by inputting the subject information into a trained cause judgment model used to judge the degree of the cause of the onset of delirium if the risk is judged to be high.

7. The processing device according to claim 1, wherein the at least one processor selects suggested medical treatment information to be provided to the subject depending on the result of determining the degree of the cause of the delirium.

8. The processing device according to claim 1, wherein the subject information is information obtained when the subject is admitted to the medical institution.

9. The processing device of claim 1, wherein the subject information includes at least one of attribute information indicating attributes of the subject, measurement information generated by measuring the subject's body, prescription drug information prescribed by a medical professional for the subject, and evaluation information indicating a delirium-related evaluation made for the subject.

10. The processing device according to claim 1, wherein the determination result is output to a terminal device that can be used by a user who provides medical treatment to the subject at the medical institution or is a close relative of the subject.

11. A processing program in a computer having at least one processor that causes the at least one processor to function as follows: acquire subject information indicating the condition of a subject receiving medical treatment from a medical institution via a communication interface; acquire a judgment result of the onset of delirium by inputting the acquired subject information into a trained judgment model used to make a judgment regarding the onset of delirium; and output the acquired judgment result via the communication interface.

12. A processing method executed by at least one processor in a computer having the at least one processor, comprising: a step of acquiring subject information indicating the condition of a subject receiving medical treatment from a medical institution via a communication interface; acquiring a judgment result of the onset of delirium by inputting the acquired subject information into a trained judgment model used for making a judgment regarding the onset of delirium; and a step of outputting the acquired judgment result via the communication interface.

13. A processing system comprising: a processing device as claimed in claim 1; and a terminal device carried by a nurse who provides medical treatment to a subject from a medical institution, and configured to receive the assessment result of the onset of delirium obtained by said processing device by being connected to said processing device via a communication network.

Images