Information processing device, information processing method, and program

Abstract

In an information processing device according to the present invention, a sickbed information acquisition means acquires sickbed information related to the utilization situation of sickbeds provided in a hospital. A patient information acquisition means acquires patient information related to patients in the hospital. An equipment information acquisition means acquires equipment information related to a utilization situation of equipment in the hospital. A shift information acquisition means acquires shift information related to a work shift of healthcare workers working at the hospital. A vacant bed situation prediction means predicts a vacancy situation of the sickbeds on the basis of the sickbed information and the patient information. An unacceptable patient prediction means predicts, on the basis of the patient information, the equipment information, and the shift information, unacceptable patients who cannot be accepted by the hospital. An acceptable patient information creation means creates, on the basis of the sickbed vacancy situation and the unacceptable patient information that have been predicted, acceptable patient information related to acceptable patients who can be accepted by the hospital.

Description

[Technical Field]

[0001] The present invention relates to optimizing resources in healthcare facilities. [Background technology]

[0002] When a patient is admitted to or transferred to a specific medical facility, various information from the facility, including the availability of hospital beds, is required to match the patient with the medical facility. Conventionally, the work of collecting and confirming facility information has been done over the phone by staff in the community liaison office or an organization within the hospital that has the same function. Patent Document 1 also describes a bed usage status management system that centrally manages the usage status of beds in hospitalization facilities and shares information between users. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 6908952 Summary of the Invention [Problem to be solved by the invention]

[0004] With an aging society, how to effectively utilize limited medical facility resources has become an important issue. For example, by appropriately matching patients with core hospitals, local hospitals, and clinics through regional collaboration, the resources of local medical facilities can be utilized effectively.

[0005] In matching patients with medical facilities, the conventional method of collecting and confirming information over the telephone places a heavy burden on staff, including social workers, and is inefficient. The bed utilization status management system described in Patent Document 1 can automatically collect information on bed utilization status, but even if a bed becomes available, there are cases where it cannot accept a patient due to various circumstances, and in such cases, staff still need to check by telephone or other means.

[0006] One of the purposes of the present invention is to automatically collect information on medical facilities and appropriately match patients with medical facilities, thereby making effective use of medical facility resources. [Means for solving the problem]

[0007] In order to solve the above problem, in one aspect of the present invention, an information processing device includes: a bed information acquisition means for acquiring bed information relating to the utilization status of beds in the hospital; a patient information acquisition means for acquiring patient information relating to patients of the hospital; The hospital's facilities to equipment information acquisition means for acquiring equipment information related to the equipment; a shift information acquisition means for acquiring shift information relating to work shifts of medical personnel working at the hospital; A discharge date prediction model that learns the relationship between patient information and discharge date and outputs a discharge date in response to input of patient information is used to predict the patient information acquired by the patient information acquisition means. A discharge date prediction means for predicting the discharge date of the patient; A bed availability prediction model is a model that has learned the relationship between bed information, discharge date, and bed availability, and outputs the bed availability status in response to input of bed information and discharge date. From the bed information acquired by the bed information acquisition means and the discharge date predicted by the discharge date prediction means, A bed availability prediction means for predicting the availability of hospital beds; A model that learns the relationship between patient information and equipment information and the utilization status of equipment, and outputs the utilization status of equipment in response to input of patient information and equipment information, is used to predict the utilization status of equipment from the patient information acquired by the patient information acquisition means and the equipment information acquired by the equipment information acquisition means, a facility utilization prediction means for predicting a utilization status of the facility; A patient prediction model that learns the relationship between the equipment usage status and shift information and the unacceptable patients that cannot be accepted, and outputs information on unacceptable patients in response to input of the equipment usage status and shift information, is used to calculate, from the equipment usage status predicted by the equipment usage prediction means and the shift information acquired by the shift information acquisition means, an unacceptable patient prediction means for predicting the unacceptable patient; Predicted availability of said hospital beds 、 and , predicted an acceptable patient information creating means for creating acceptable patient information regarding acceptable patients that the hospital can accept based on the information on unacceptable patients; Equipped with.

[0008] In another aspect of the present invention, an information processing method includes: Executed by an information processing device, Obtain bed information regarding the utilization status of hospital beds, obtaining patient information regarding patients at the hospital; The hospital's facilities to Obtain facility information related to Obtaining shift information regarding work shifts of medical personnel working at the hospital; A discharge date prediction model that learns the relationship between patient information and discharge date and outputs the discharge date in response to input patient information is used to predict the patient's discharge date from the acquired patient information. predicting the patient's discharge date; A bed availability prediction model that has learned the relationship between bed information, discharge date, and bed availability, and outputs the bed availability status in response to input of bed information and discharge date, is used to calculate the bed availability status from the acquired bed information and the predicted discharge date. Predicting the availability of said hospital beds; The equipment utilization prediction model is a model that has learned the relationship between patient information, equipment information, and equipment utilization status, and outputs equipment utilization status in response to input of patient information and equipment information. From the acquired patient information and acquired equipment information, Predicting the utilization status of the facility; This is a model that has learned the relationship between equipment usage status, shift information, and unacceptable patients, and the patient prediction model outputs information on unacceptable patients in response to the input of equipment usage status and shift information. From the predicted equipment usage status and the acquired shift information, predicting the unacceptable patients; Predicted availability of said hospital beds 、 and , predicted Based on the information on the unacceptable patients, acceptable patient information regarding acceptable patients that the hospital can accept is created.

[0009] In yet another aspect of the invention, a program includes: Executed by an information processing device including a computer, Obtain bed information regarding the utilization status of hospital beds, obtaining patient information regarding patients at the hospital; The hospital's facilities to Obtain facility information related to Obtaining shift information regarding work shifts of medical personnel working at the hospital; A discharge date prediction model that learns the relationship between patient information and discharge date and outputs the discharge date in response to input patient information is used to predict the patient's discharge date from the acquired patient information. predicting the patient's discharge date; A bed availability prediction model that has learned the relationship between bed information, discharge date, and bed availability, and outputs the bed availability status in response to input of bed information and discharge date, is used to calculate the bed availability status from the acquired bed information and the predicted discharge date. Predicting the availability of said hospital beds; The equipment utilization prediction model is a model that has learned the relationship between patient information, equipment information, and equipment utilization status, and outputs equipment utilization status in response to input of patient information and equipment information. From the acquired patient information and acquired equipment information, Predicting the utilization status of the facility; This is a model that has learned the relationship between equipment usage status, shift information, and unacceptable patients, and the patient prediction model outputs information on unacceptable patients in response to the input of equipment usage status and shift information. From the predicted equipment usage status and the acquired shift information, predicting the unacceptable patients; Predicted availability of said hospital beds 、 and , predicted The computer is caused to execute a process of creating acceptable patient information regarding acceptable patients that the hospital can accept, based on the information on the unacceptable patients. [Effects of the Invention]

[0010] According to the present invention, information on medical facilities is automatically collected and patients and medical facilities are appropriately matched, thereby enabling effective use of medical facility resources. [Brief explanation of the drawings]

[0011] [Figure 1] The configuration of the automatic registration system is shown. [Figure 2] 1 shows the hardware configuration of an automatic registration device. [Figure 3] 1 shows the functional configuration of an automatic registration device. [Figure 4] 10 is an example of a data configuration of hospital bed information. [Figure 5] 10 is an example of a data configuration of patient information. [Figure 6] 10 is an example of a data configuration of facility information. [Figure 7] 10 is an example of a data configuration of shift information. [Figure 8] 10 is an example of an acceptance status screen. [Figure 9] 10 is a flowchart of an automatic registration process. [Figure 10] 10 is a flowchart of a correction update process. [Figure 11] 10 shows a functional configuration of an information processing device according to a second embodiment. [Figure 12] 10 is a flowchart of processing by an information processing device according to a second embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0012] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. [First embodiment] (composition) Figure 1 shows the configuration of an automatic registration system to which the automatic registration device of the present invention is applied. The automatic registration system 100 is a system that acquires various information about a hospital and creates and registers acceptable patient information about patients that the hospital can accept (hereinafter referred to as "acceptable patients"). The automatic registration system 100 includes an automatic registration device 1, a hospital management system 20, and a terminal device 30, which are communicably connected to each other via a network 5 such as the Internet.

[0013] The automatic registration device 1 is an information processing device that processes, stores, and transmits and receives various information, and is, for example, a server device, a personal computer, or a general-purpose tablet PC (personal computer). Specifically, the automatic registration device 1 acquires information about hospitals from the hospital management system 20, and creates and registers available patient information. Then, based on the registered available patient information, the automatic registration device 1 creates and outputs an admission status screen for matching patients with hospitals.

[0014] The hospital management system 20 is made up of one or more information processing devices, and is a system that processes, stores, and transmits and receives various information related to the hospital. As will be described in detail later, the hospital management system 20 has a bed information database (hereinafter also referred to as "DB") 21, a patient information DB 22, a facility information DB 23, and a shift information DB 24.

[0015] The terminal device 30 is used by a user who matches patients with hospitals, and is, for example, an information processing device such as a wearable device such as a smartphone or mobile phone, a tablet, a PC terminal, etc. Specifically, the terminal device 30 communicates with the automatic registration device 1 to make a screen request and display an admission status screen.

[0016] 2 is a block diagram showing the hardware configuration of the automatic registration device 1. As shown in the figure, the automatic registration device 1 includes an interface 11, a processor 12, a memory 13, a recording medium 14, a display unit 15, and an input unit 16.

[0017] The interface 11 exchanges data with the hospital management system 20 and the terminal device 30 via the network 5. The interface 11 is used to receive information about the hospital from the hospital management system 20 and to send an admission status screen to the terminal device 30. The interface 11 is also used when the automatic registration device 1 exchanges data with a specific device connected by wire or wirelessly.

[0018] The processor 12 is a computer such as a CPU (Central Processing Unit), and controls the entire automatic registration device 1 by executing a prepared program. The memory 13 is composed of a ROM (Read Only Memory), a RAM (Random Access Memory), etc. The memory 13 stores the programs executed by the processor 12. The memory 13 is also used as a working memory while the processor 12 is executing various processes.

[0019] The recording medium 14 is a non-volatile, non-transitory recording medium such as a disk-shaped recording medium or semiconductor memory, and is configured to be detachable from the automatic registration device 1. The recording medium 14 records various programs executed by the processor 12. When the automatic registration device 1 executes the automatic registration process or the correction / update process, the programs recorded on the recording medium 14 are loaded into the memory 13 and executed by the processor 12.

[0020] The display unit 15 displays a predetermined screen on, for example, an LCD (Liquid Crystal Display), etc. The input unit 16 includes a keyboard, a mouse, a touch panel, etc., and is used by an operator who manages the automatic registration device 1.

[0021] 3 is a block diagram showing the functional configuration of the automatic registration device 1. Functionally, the automatic registration device 1 includes a hospital information acquisition unit 40, a discharge date prediction unit 45, a vacant bed situation prediction unit 46, a facility utilization prediction unit 47, an unacceptable patient prediction unit 48, an acceptable patient information creation unit 49, an automatic registration unit 50, an admission status screen output unit 51, a result acquisition unit 60, a correction and update unit 64, a discharge date prediction model storage unit 71, a vacant bed situation prediction model storage unit 72, a facility utilization prediction model storage unit 73, and a patient prediction model storage unit 74. The hospital information acquisition unit 40, the discharge date prediction unit 45, the vacant bed situation prediction unit 46, the facility utilization prediction unit 47, the unacceptable patient prediction unit 48, the acceptable patient information creation unit 49, the automatic registration unit 50, the admission status screen output unit 51, the result acquisition unit 60, and the correction and update unit 64 are realized by the processor 12 executing a program. In addition, the discharge date prediction model storage unit 71, the vacant bed situation prediction model storage unit 72, the facility utilization prediction model storage unit 73, and the patient prediction model storage unit 74 are realized by the memory 13.

[0022] The automatic registration device 1 creates and registers information about patients who can be admitted based on various information about the hospital acquired from the hospital management system 20. The automatic registration device 1 creates and outputs an admission status screen based on the registered information, allowing the user to easily match hospitals with patients.

[0023] The hospital management system 20 has a bed information DB21, a patient information DB22, an equipment information DB23, and a shift information DB24. The bed information DB21 stores information about hospital beds. The patient information DB22 stores information about patients who visit or are hospitalized at the hospital. The equipment information DB23 stores information about equipment owned by the hospital. Here, equipment refers not only to equipment used for examinations such as chest X-ray machines, MRI (Magnetic Resonance Imaging) machines, and CT (Computed Tomography) machines, but also to devices and instruments used for treatments such as dialysis machines, indwelling catheters, oxygen masks, ventilators, insulin injections, and anticancer drugs. The shift information DB24 stores information about the working days and times of medical personnel working at the hospital. Here, medical personnel refer to doctors, nurses, radiologists, clinical engineers, etc. who are engaged in examining and treating patients.

[0024] The hospital information acquisition unit 40 has a bed information acquisition unit 41, a patient information acquisition unit 42, a facility information acquisition unit 43, and a shift information acquisition unit 44, and acquires various information related to the hospital.

[0025] The bed information acquisition unit 41 acquires bed information related to current beds from the bed information DB 21 of the hospital management system 20. FIG. 4 shows an example of the data configuration of bed information. As shown in FIG. 4, the bed information includes information on a bed ID, date, availability, room number, and room type. The bed ID is identification information for a bed owned by the hospital. The date and availability indicate whether the bed is occupied or vacant on that date; in FIG. 4, an occupied bed is marked with "x" and an vacant bed is marked with "o". The room number is the number of the room in which the bed is located. The room type indicates the type of room, such as a single room or a four-person room. Note that the bed information may include information on availability on an hourly basis for each date, in addition to availability on a daily basis. In this way, the information included in the bed information can be set arbitrarily.

[0026] The patient information acquisition unit 42 acquires patient information about patients at the hospital from the patient information DB 22 of the hospital management system 20. FIG. 5 shows an example of the data structure of patient information. As shown in FIG. 5, the patient information includes information such as a patient ID, gender, age, disease name, severity, bed ID, and discharge date. The patient ID is identification information for patients who are outpatients or hospitalized at the hospital. The gender, age, disease name, and severity are the patient's gender, age, disease name, and severity. Here, severity indicates the patient's life prognosis or functional prognosis, and in this embodiment, it is expressed in three levels: mild "1," moderate "2," and severe "3." The bed ID is identification information for the bed occupied by the hospitalized patient, and a hyphen is used for patients who are not hospitalized. The discharge date is the discharge date for hospitalized patients, and is "undecided" for hospitalized patients and a hyphen is used for outpatients only. The patient information is not limited to the above examples, and may include, for example, the patient's surgery date, expected discharge date, medical history, risk of agitation, etc. In this way, the information contained in the patient information can be set arbitrarily.

[0027] The facility information acquisition unit 43 acquires facility information related to the hospital's facilities within a certain period from the facility information DB 23 of the hospital management system 20. In this embodiment, the certain period can be, for example, several hours, half a day, one week, ten days, one month, etc., and can be set arbitrarily. FIG. 6 shows an example of the data structure of facility information. As shown in FIG. 6, the facility information includes information on the facility ID, date, availability, facility name, disease name, and severity. The facility ID is identification information for the facility owned by the hospital. The date and availability indicate whether the facility is fully utilized or available on that date. In FIG. 6, if the facility is fully utilized due to reservations or the like, an "X" is displayed, and if the facility is available, an "O" is displayed. The facility name is the name of the device or instrument that constitutes the facility. The disease name is the name of the disease for which the facility is utilized. The severity is the severity of the patient's illness when the facility is utilized.

[0028] Specifically, in the case of chest X-ray machines and MRI machines used for examinations, multiple patients can use the machine in one day, so if the machine is reserved for all time periods, the availability status will be marked as "X". The equipment information may include information on availability not only for one day, but also for each hour of each date. Also, in the case of oxygen masks and ventilators used in treatment, there is a limit to the number available, so if all the machines are in use, the availability status will be marked as "X". The equipment information may also include information on the number of machines available for use on each date. Furthermore, the equipment information does not need to include information on the name of the disease or the severity. In this way, the information included in the equipment information can be set arbitrarily.

[0029] The shift information acquisition unit 44 acquires shift information relating to work shifts of medical personnel working at the hospital within a certain period from the shift information DB 24 of the hospital management system 20. FIG. 7 is an example of the data configuration of shift information. As shown in FIG. 7, the shift information includes information relating to staff ID, job type, severity of illness that can be handled, and work data. The staff ID is identification information of medical personnel working at the hospital. The job type is the job type of the medical personnel, such as doctor, nurse, radiologist, clinical engineer, etc. The severity of illness that can be handled is the severity of patients that the medical personnel can handle. The work data is information relating to the date and time that the medical personnel works.

[0030] Specifically, for moderately ill patients who require oxygen masks, various checks are required, such as whether the tracheal tube has come loose from the breathing circuit, making it difficult for new nurses to handle the task. Even if there are experienced nurses who can handle moderately or severely ill patients, there is a limit to the number of nurses available. For this reason, shift information includes information on the severity of patients each medical professional can handle. However, the shift information is not limited to this, and may also include information on the specialty and proficiency of each medical professional. In this way, the information included in the shift information can be set arbitrarily.

[0031] The discharge date prediction model storage unit 71 stores a discharge date prediction model that has learned the relationship between hospitalized patient information and discharge date. The learning algorithm may be any machine learning method, such as a neural network, SVM (Support Vector Machine), or logistic regression. The discharge date prediction unit 45 uses the discharge date prediction model to predict the discharge date of a specific patient based on the patient information of the patient acquired by the patient information acquisition unit 42. Specifically, the discharge date prediction unit 45 predicts the discharge date of a currently hospitalized patient.

[0032] The vacant bed situation prediction model storage unit 72 stores a vacant bed situation prediction model that has learned the relationship between bed information and discharge dates and the availability of beds. The learning algorithm may be any machine learning method, such as a neural network, SVM, or logistic regression. The vacant bed situation prediction unit 46 uses the vacant bed situation prediction model to predict the availability of beds within a certain period of time based on the bed information acquired by the bed information acquisition unit 41 and the discharge dates of currently hospitalized patients predicted by the discharge date prediction unit 45.

[0033] The predicted availability of hospital beds includes information on the date and the number of available beds, such as "three available beds on August 10th." Information may also be provided on a daily basis, such as "three available beds on August 10th," or on a predetermined time basis, such as "one available bed at 10:00 on August 10th, and three available beds at 12:00 on August 10th." The unit for predicting availability of hospital beds is not limited to these, and can be set arbitrarily, such as in units of several days or several weeks.

[0034] The facility usage prediction model storage unit 73 stores a facility usage prediction model that has learned the relationship between patient information, facility information, and facility usage. The learning algorithm may be any machine learning method, such as a neural network, SVM, or logistic regression. The facility usage prediction unit 47 uses the facility usage prediction model to predict facility usage within a certain period of time based on the patient information acquired by the patient information acquisition unit 42 and the facility information acquired by the facility information acquisition unit 43. Specifically, the facility usage prediction unit 47 predicts facility usage within a certain period of time based on the patient information, taking into account the severity of the patient who is visiting or hospitalized at the hospital, the date of surgery, and other factors, and the date and time of use of the facility.

[0035] The facility utilization prediction unit 47 may use a facility utilization prediction model that has learned the relationship between the patient information, facility information, and shift information and the facility utilization status. In this way, the facility utilization prediction unit 47 can predict the facility utilization status based on the shift information acquired by the shift information acquisition unit 44, taking into account the work shifts of medical personnel required to use the facility.

[0036] The predicted facility usage status includes information on the date, facility, and availability, such as "MRI device is available on August 10th." It may also be information on a daily basis, such as "MRI device is available on August 10th," or information on a predetermined time basis, such as "MRI device is unavailable at 10:00 on August 10th, but is available at 12:00 on August 10th." The unit for predicting facility usage status is not limited to these, and can be set arbitrarily, such as in units of several days or several weeks.

[0037] The patient prediction model storage unit 74 stores a patient prediction model that has learned the relationship between equipment usage status, shift information, and patients who cannot be admitted (also referred to as "unacceptable patients"). The learning algorithm may be any machine learning method, such as a neural network, SVM, or logistic regression. The unacceptable patient prediction unit 48 uses the patient prediction model to predict unacceptable patients based on the equipment usage status predicted by the equipment usage prediction unit 47 and the shift information acquired by the shift information acquisition unit 44. Specifically, the unacceptable patient prediction unit 48 predicts patients who cannot be admitted because the equipment required for the examination or treatment is unavailable, based on the equipment usage status. The unacceptable patient prediction unit 48 also predicts patients who cannot be admitted because there are no medical professionals available to perform the examination or treatment.

[0038] The predicted information on unacceptable patients includes the date and information on the patients who cannot be admitted, such as "patients who will use ventilators on August 10th because there are no available facilities" or "serious patients with illness name XX on August 10th because there are no medical staff available to treat them." The information on unacceptable patients includes the facilities the patients will use, and the name and severity of the patient's illness.

[0039] Furthermore, the predicted information on unacceptable patients may be information on a daily basis, such as "patients who will use ventilators on August 10th because there is no available equipment," or information on a predetermined time basis, such as "patients who will use ventilators on August 10th from 10:00 to 12:00 because there is no available equipment." The unit for predicting unacceptable patients is not limited to these, and can be set arbitrarily, such as in units of several days or several weeks.

[0040] The acceptable patient information creation unit 49 determines whether the hospital can accept newly admitted or transferred patients based on the available bed situation predicted by the available bed situation prediction unit 46 and the unacceptable patients predicted by the unacceptable patient prediction unit 48, and creates information on patients that can be accepted within a certain period as acceptable patient information. The acceptable patient information includes the date or time when patients can be accepted, the number of patients that can be accepted, and information on patients that cannot be accepted.

[0041] Specifically, if there are no available beds, the acceptable patient information creation unit 49 determines that no patients can be accepted. On the other hand, if there are available beds, the acceptable patient information creation unit 49 determines that patients who do not fall under the category of unacceptable patients can be accepted. The acceptable patient information creation unit 49 can create acceptable patient information in any unit, such as in units of several hours or one day.

[0042] The automatic registration unit 50 registers the acceptable patient information created by the acceptable patient information creation unit 49. Specifically, the automatic registration unit 50 stores the acceptable patient information in the memory 13 or the like.

[0043] The admission status screen output unit 51 creates and outputs an admission status screen that displays the date or time when the hospital can accept patients, the number of patients that can be accepted, and information about patients that cannot be accepted, based on the patient acceptance information registered by the automatic registration unit 50. Specifically, when a screen request is received from the terminal device 30, the admission status screen output unit 51 creates an admission status screen based on the patient acceptance information registered at that time, and transmits it to the terminal device 30.

[0044] Figure 8 is an example of an admission status screen. As shown in Figure 8(a), the admission status screen is formatted like a calendar, with an X mark or a number of patients displayed in the box for each date. An X mark indicates that a patient cannot be accepted on that date. On the other hand, the number of patients indicates the number of patients who can be accepted on that date. Clicking on the number of patients displays information about patients who cannot be accepted on that date, as shown in Figure 8(b). Specifically, information about patients who cannot be accepted is displayed, such as unavailable facilities and the severity of their condition that cannot be handled.

[0045] The admission status screen shown in FIG. 8 displays the admission status for one month in a calendar-like format, but the present invention is not limited to this. The admission status can be displayed for any period, such as several days or weeks, and the format can be set as desired. Also, while the admission status screen shown in FIG. 8 displays the admission status in daily units, the present invention is not limited to this. The admission status can also be displayed in any unit, such as several hours. Specifically, the period and unit of admission status can be set by the user using the terminal device 30, and information regarding the setting can be included in the screen request. In this way, by changing the period and unit for displaying the admission status, it is possible to display an admission status screen appropriate for the user, for example, in cases where a patient is considering long-term hospitalization or a patient is considering hospitalization for approximately half a day due to emergency surgery.

[0046] The result acquisition unit 60 has a patient information result acquisition unit 61 and an equipment information result acquisition unit 62, and acquires the results of patient discharge dates and equipment usage status. The patient information result acquisition unit 61 acquires discharge dates of patients who have already been discharged from the patient information DB 22 of the hospital management system 20. In addition, the equipment information result acquisition unit 62 acquires the actual usage status of equipment, rather than reservations, from the equipment information DB 23 of the hospital management system 20.

[0047] If the discharge date predicted by the discharge date prediction unit 45 or the facility usage status predicted by the facility usage prediction unit 47 is incorrect, the correction and update unit 64 appropriately corrects the registered acceptable patient information based on the results, based on the patient's discharge date and facility usage status acquired by the result acquisition unit 60. Furthermore, when the correction and update unit 64 makes a correction, it creates and accumulates additional learning data that uses the result acquired by the result acquisition unit 60 as the correct answer. Specifically, the correction and update unit 64 creates additional learning data that uses the patient's actual discharge date as the correct answer, and performs re-learning to update the discharge date prediction model. Furthermore, the correction and update unit 64 creates additional learning data that uses the actual facility usage status as the correct answer, and performs re-learning to update the facility usage prediction model. By feeding back actual results in this way, the prediction accuracy of the discharge date prediction model and the facility usage prediction model can be improved.

[0048] For ease of explanation, the hospital management system 20 has a bed information DB21, a patient information DB22, an equipment information DB23, and a shift information DB24, but the present invention is not limited to these, and the type of DB and the data structure of the DB are arbitrary as long as the hospital information acquisition unit 40 or the result acquisition unit 60 can acquire the necessary information.

[0049] (Automatic registration process) Next, we will explain the automatic registration processing by the automatic registration device 1. Figure 9 is a flowchart of the automatic registration processing by the automatic registration device 1. This processing is realized by the processor 12 shown in Figure 2 executing a program prepared in advance.

[0050] First, the automatic registration device 1 collects hospital information from the hospital management system 20 (step S101). Specifically, the automatic registration device 1 acquires from the hospital management system 20 bed information related to current hospital beds, patient information related to patients at the hospital, equipment information related to hospital equipment within a certain period of time, and shift information related to work shifts of medical personnel working at the hospital within a certain period of time.

[0051] The automatic registration device 1 predicts the discharge date of currently hospitalized patients from the acquired patient information using the discharge date prediction model (step S102).The automatic registration device 1 then predicts the availability of hospital beds within a certain period of time from the acquired hospital bed information and the predicted discharge date using the vacant bed situation prediction model (step S103).

[0052] The automatic registration device 1 also uses the facility usage prediction model to predict facility usage within a certain period based on the acquired patient information and facility information (step S104).The automatic registration device 1 then uses the patient prediction model to predict patients who cannot be admitted based on the predicted facility usage and the acquired shift information (step S105).

[0053] The automatic registration device 1 then determines whether the hospital can accept newly admitted or transferred patients based on the predicted availability of hospital beds and the unacceptable patients predicted by the unacceptable patient prediction unit 48, and creates information about patients who can be accepted within a certain period of time as acceptable patient information (step S106). The automatic registration device 1 registers the created acceptable patient information (step S107). Based on the registered acceptable patient information, the automatic registration device 1 then creates and outputs an acceptance status screen that displays the date or time when the hospital can accept patients, the number of patients it can accept, and information about patients it cannot accept (step S108). Specifically, when a screen request is received from the terminal device 30, the automatic registration device 1 creates an acceptance status screen based on the acceptable patient information registered at that time and transmits it to the terminal device 30. The user checks information about the hospital on the acceptance status screen displayed on the terminal device 30 and matches patients with hospitals. This completes the automatic registration process.

[0054] (Correction update process) Next, we will explain the correction and update processing by the automatic registration device 1. Fig. 10 is a flowchart of the correction and update processing by the automatic registration device 1. This processing is realized by the processor 12 shown in Fig. 2 executing a program prepared in advance.

[0055] First, the automatic registration device 1 acquires the patient's discharge date and facility usage status as results (step S201). Then, if the predicted patient's discharge date or facility usage status differs from the results, the automatic registration device 1 appropriately corrects the registered acceptable patient information based on the results (step S202). Furthermore, the automatic registration device 1 creates additional learning data based on the results, with the patient's actual discharge date as the correct answer, and updates the discharge date prediction model (step S203). Furthermore, the automatic registration device 1 creates additional learning data based on the results, with the actual facility usage status as the correct answer, and updates the facility usage prediction model (step S204). This completes the correction and update process.

[0056] In this embodiment, the correction and update process is performed by the automatic registration device 1, but the present invention is not limited to this, and correction of acceptable patient information and updating of the discharge date prediction model and facility usage prediction model may also be performed manually.

[0057] As described above, the automatic registration device 1 can automatically collect information on medical facilities such as hospitals and register information on patients who can be admitted within a certain period of time. The registered information can then be modified as appropriate. Furthermore, the automatic registration device 1 can output information on patients who can be admitted by the medical facility as an admission status screen based on the registered information.

[0058] The fixed period displayed on the admission status screen can be adjusted, so appropriate admission status can be displayed not only for the most recent emergency admission, but also when the user is considering arranging a transfer for, for example, one week or two weeks later. Furthermore, the admission status screen displays information about patients who cannot be admitted, such as unavailable facilities and the severity of their condition, allowing users to match patients with medical facilities that meet their facilities and severity requirements. This allows users to efficiently match patients with medical facilities, making effective use of medical facility resources.

[0059] [Second embodiment] 11 is a block diagram showing the functional configuration of an information processing device according to the second embodiment. The information processing device 80 includes a bed information acquisition means 81, a patient information acquisition means 82, a facility information acquisition means 83, a shift information acquisition means 84, a vacant bed situation prediction means 85, an unacceptable patient prediction means 86, and an acceptable patient information creation means 87.

[0060] FIG. 12 is a flowchart of the acceptable patient information creation process performed by the information processing device 80. The bed information acquisition means 81 acquires bed information related to the utilization status of hospital beds (step S801). The patient information acquisition means 82 acquires patient information related to patients at the hospital (step S802). The equipment information acquisition means acquires equipment information related to the utilization status of hospital equipment (step S803). The shift information acquisition means acquires shift information related to the work shifts of medical personnel working at the hospital (step S804). The vacant bed situation prediction means 85 predicts the vacant bed situation based on the bed information and patient information (step S805). The unacceptable patient prediction means 86 predicts unacceptable patients that the hospital cannot accept based on the patient information, equipment information, and shift information (step S806). The acceptable patient information creation means 87 creates acceptable patient information related to the acceptable patients that the hospital can accept based on the predicted vacant bed situation and unacceptable patient information (step S807).

[0061] According to the information processing device 80 of the second embodiment, it is possible to efficiently match patients with medical facilities based on the information on available patients.

[0062] Some or all of the above-described embodiments can be described as, but are not limited to, the following supplementary notes.

[0063] (Appendix 1) a bed information acquisition means for acquiring bed information relating to the utilization status of beds in the hospital; a patient information acquisition means for acquiring patient information relating to patients of the hospital; a facility information acquisition means for acquiring facility information relating to the utilization status of the facilities of the hospital; a shift information acquisition means for acquiring shift information relating to work shifts of medical staff working at the hospital; a bed availability prediction means for predicting the availability of the hospital beds based on the hospital bed information and the patient information; an unacceptable patient prediction means for predicting unacceptable patients that the hospital cannot accept based on the patient information, the facility information, and the shift information; an acceptable patient information creating means for creating acceptable patient information regarding acceptable patients that the hospital can accept based on the predicted vacancy status of hospital beds and the information on unacceptable patients; An information processing device comprising:

[0064] (Appendix 2) a discharge date prediction means for predicting a discharge date of the patient based on the patient information; The information processing device according to claim 1, wherein the bed availability prediction means predicts the availability of the beds based on the bed information and the predicted discharge date.

[0065] (Appendix 3) a facility utilization prediction means for predicting a utilization status of the facility based on the patient information and the facility information; The information processing device according to claim 1 or 2, wherein the unacceptable patient prediction means predicts the unacceptable patients based on the shift information and the predicted equipment usage status.

[0066] (Appendix 4) The patient information includes information regarding one or more of the name of the patient's disease and the severity of the disease, The facility information includes information regarding one or more of the name of a disease and the severity of the disease for which the facility is used, The shift information includes information on the severity of the medical staff that can respond, 4. The information processing device according to claim 1, wherein the unacceptable patient prediction means predicts the unacceptable patient based on one or more of the disease name and severity.

[0067] (Appendix 5) An information processing device as described in any one of appendix 1 or 4, comprising an acceptance status screen output means for creating and outputting an acceptance status screen that displays, based on the patient acceptance information, the date or date and time when the hospital can accept patients, the number of patients that can be accepted, and information on patients that cannot be accepted.

[0068] (Appendix 6) The information processing device according to claim 5, wherein the acceptance status screen displays information about the facilities used by the unacceptable patient.

[0069] (Appendix 7) the information processing device is communicably connected to a hospital management system that manages information related to the hospital, The bed information acquisition means, patient information acquisition means, equipment information acquisition means, and shift information acquisition means acquire bed information, patient information, equipment information, and shift information from the hospital management system, respectively, a result acquisition means for acquiring the patient's discharge date and the facility usage status as results from the hospital management system; and a correction means for correcting the acceptable patient information based on the result.

[0070] (Appendix 8) The discharge date prediction means predicts the discharge date of the patient using a discharge date prediction model that has been machine-learned in advance, The unacceptable patient prediction means predicts patients that the hospital cannot accept using a patient prediction model that has been machine-learned in advance, An information processing device according to claim 7, further comprising an update means for creating additional learning data in which the patient's discharge date based on the results is set as the correct answer, and additional learning data in which the equipment usage status based on the results is set as the correct answer, and updating the discharge date prediction model and the patient prediction model, respectively.

[0071] (Appendix 9) Obtain bed information regarding the utilization status of hospital beds, obtaining patient information regarding patients at the hospital; Acquire facility information regarding the utilization status of the facilities of the hospital; Obtaining shift information regarding work shifts of medical personnel working at the hospital; predicting the availability of the hospital beds based on the hospital bed information and the patient information; predicting patients that the hospital cannot accept based on the patient information, the facility information, and the shift information; An information processing method for creating acceptable patient information regarding acceptable patients that the hospital can accept based on the predicted availability of hospital beds and information on unacceptable patients.

[0072] (Appendix 10) Obtaining bed information on the utilization status of hospital beds obtaining patient information regarding patients at the hospital; Acquire facility information regarding the utilization status of the facilities of the hospital; Obtaining shift information regarding work shifts of medical personnel working at the hospital; predicting the availability of the hospital beds based on the hospital bed information and the patient information; predicting patients that the hospital cannot accept based on the patient information, the facility information, and the shift information; A recording medium having a program recorded thereon that causes a computer to execute a process of creating acceptable patient information regarding acceptable patients that the hospital can accept based on the predicted availability of hospital beds and information on unacceptable patients.

[0073] Although the present invention has been described above with reference to the embodiments and examples, the present invention is not limited to the above-described embodiments and examples. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention. [Explanation of symbols]

[0074] 1. Automatic registration device 5. Network 11 Interface 12 processors 13. Memory 14 Recording media 15 Display section 16 Input section 20 Hospital Management System 21 Hospital bed information DB 22 Patient information DB 23 Equipment information DB 24 Shift Information DB 30 Terminal Equipment 40 Hospital Information Acquisition Department 45 Discharge Date Prediction Department 46 Bed Availability Forecasting Department 47 Facility Utilization Forecasting Department 48 Unacceptable Patient Prediction Department 49 Acceptable Patient Information Creation Department 50 Automatic Registration Section 51 Acceptance status screen output section 60 Result acquisition part 64 Modification and update section

Claims

1. a bed information acquisition means for acquiring bed information relating to the utilization status of beds in the hospital; a patient information acquisition means for acquiring patient information relating to patients of the hospital; equipment information acquisition means for acquiring equipment information relating to the hospital's equipment; a shift information acquisition means for acquiring shift information relating to work shifts of medical personnel working at the hospital; a discharge date prediction means for predicting a discharge date of the patient from the patient information acquired by the patient information acquisition means, using a discharge date prediction model that is a model that has learned the relationship between patient information and a discharge date and that outputs a discharge date in response to input of patient information; a bed availability prediction means for predicting the availability of beds from the bed information acquired by the bed information acquisition means and the discharge date predicted by the discharge date prediction means, using a bed availability prediction model that has learned the relationship between bed information, discharge date, and availability of beds, and that outputs availability of beds in response to input of bed information and discharge date; an equipment usage prediction means for predicting the utilization status of the equipment from the patient information acquired by the patient information acquisition means and the equipment information acquired by the equipment information acquisition means, using an equipment utilization prediction model that has learned the relationship between patient information, equipment information, and utilization status of the equipment, and that outputs utilization status of the equipment in response to input of patient information and equipment information; an unacceptable patient prediction means for predicting the unacceptable patients based on the equipment utilization status predicted by the equipment utilization prediction means and the shift information acquired by the shift information acquisition means, using a patient prediction model that has learned the relationship between equipment utilization status, shift information, and unacceptable patients that cannot be accepted, and that outputs information on unacceptable patients in response to input of equipment utilization status and shift information; an acceptable patient information creating means for creating acceptable patient information regarding acceptable patients that the hospital can accept based on the predicted vacancy status of hospital beds and the predicted information on unacceptable patients; An information processing device comprising:

2. The information processing device described in claim 1, wherein the equipment utilization prediction means is a model that has learned the relationship between patient information, equipment information, and shift information and the utilization status of the equipment, and uses an equipment utilization prediction model that outputs the utilization status of the equipment in response to input of patient information, equipment information, and shift information to predict the utilization status of the equipment from the patient information acquired by the patient information acquisition means, the equipment information acquired by the equipment information acquisition means, and the shift information acquired by the shift information acquisition means.

3. The patient information includes information regarding one or more of the name of the patient's disease and the severity of the disease, The facility information includes information regarding one or more of the name of a disease and the severity of the disease for which the facility is used, The information processing device according to claim 1 or 2, wherein the shift information includes information on the severity of an illness that the medical staff can handle.

4. 4. An information processing device according to claim 1, further comprising an acceptance status screen output means for creating and outputting an acceptance status screen that displays, based on the patient availability information, the dates or times when the hospital can accept patients who do not fall under the category of unacceptable patients, the number of patients that can be accepted, and information on unacceptable patients.

5. An information processing device as described in Claim 4, wherein the acceptance status screen displays one or more of the disease name and severity of the unacceptable patient.

6. The information processing device according to claim 4 or 5, wherein the admission status screen displays information about facilities used by the unacceptable patient.

7. the information processing device is communicably connected to a hospital management system that manages information related to the hospital, The bed information acquisition means, patient information acquisition means, equipment information acquisition means, and shift information acquisition means acquire bed information, patient information, equipment information, and shift information from the hospital management system, respectively, a result acquisition means for acquiring the patient's discharge date and the facility usage status as results from the hospital management system; The information processing apparatus according to claim 1 , further comprising: a correction unit that corrects the acceptable patient information based on the result.

8. A discharge date prediction model update means for updating the discharge date prediction model by additionally learning the relationship between the patient information and the patient's discharge date obtained as the result; a facility utilization prediction model update means for updating the facility utilization prediction model by additionally learning the relationship between the patient information and the facility information and the utilization status of the facility acquired as a result; The information processing device according to claim 7 , comprising:

9. An information processing method executed by an information processing device, Obtain bed information regarding the utilization status of hospital beds, obtaining patient information regarding patients at the hospital; Acquire equipment information regarding the hospital's equipment; Obtaining shift information regarding work shifts of medical personnel working at the hospital; A discharge date prediction model is a model that has learned the relationship between patient information and discharge date, and outputs a discharge date in response to input of patient information. The discharge date prediction model predicts the patient's discharge date from the acquired patient information. A bed availability prediction model is a model that has learned the relationship between bed information and discharge date, and bed availability, and outputs the bed availability status in response to input of bed information and discharge date. The model predicts the bed availability status from the acquired bed information and the predicted discharge date. predicting the utilization status of the equipment from the acquired patient information and the acquired equipment information using an equipment utilization prediction model that is a model that has learned the relationship between patient information and equipment information and the utilization status of the equipment, and that outputs the utilization status of the equipment in response to the input of patient information and equipment information; A patient prediction model that learns the relationship between equipment usage status, shift information, and unacceptable patients that cannot be accepted, and outputs information on unacceptable patients in response to input of equipment usage status and shift information, is used to predict the unacceptable patients from the predicted equipment usage status and the acquired shift information, An information processing method for creating acceptable patient information regarding acceptable patients that the hospital can accept based on the predicted availability of hospital beds and the predicted information on unacceptable patients.

10. A program executed by an information processing device having a computer, Obtain bed information regarding the utilization status of hospital beds, obtaining patient information regarding patients at the hospital; Acquire equipment information regarding the hospital's equipment; Obtaining shift information regarding work shifts of medical personnel working at the hospital; A discharge date prediction model is a model that has learned the relationship between patient information and discharge date, and outputs a discharge date in response to input of patient information. The discharge date prediction model predicts the patient's discharge date from the acquired patient information. A bed availability prediction model is a model that has learned the relationship between bed information and discharge date, and bed availability, and outputs the bed availability status in response to input of bed information and discharge date. The model predicts the bed availability status from the acquired bed information and the predicted discharge date. predicting the utilization status of the equipment from the acquired patient information and the acquired equipment information using an equipment utilization prediction model that is a model that has learned the relationship between patient information and equipment information and the utilization status of the equipment, and that outputs the utilization status of the equipment in response to the input of patient information and equipment information; A patient prediction model that learns the relationship between equipment usage status, shift information, and unacceptable patients that cannot be accepted, and outputs information on unacceptable patients in response to input of equipment usage status and shift information, is used to predict the unacceptable patients from the predicted equipment usage status and the acquired shift information, A program that causes the computer to execute a process of creating acceptable patient information regarding acceptable patients that the hospital can accept based on the predicted availability of hospital beds and the predicted information on unacceptable patients.

Images