Information processing apparatus, information processing method, and program

Abstract

To provide information useful for executing the reverse introduction of a patient while preventing the deterioration of the management conditions of a hospital.SOLUTION: An information processor acquires patient information on patients receiving medical care in a target hospital and hospital management information on the management of the target hospital (step S1). An information processor extracts candidates of patients to be reversely introduced to hospitals other than a target hospital within a prescribed period on the basis of patient information and hospital management information (step S5). The information processor updates patient information and hospital management information on the assumption that the extracted patient candidates are reversely introduced (step S7). The information processor predicts a management indicator showing the management situation of the target hospital after a prescribed period based on the updated patient information and hospital management information (step S8).SELECTED DRAWING: Figure 5

Description

[Technical Field]

[0001] The present invention relates to an information processing device, an information processing method, and a program. [Background technology]

[0002] When a patient at a clinic needs specialized testing, treatment, hospitalization, etc., the clinic will refer the patient to another medical institution that has the facilities for testing, treatment, hospitalization, etc. Usually, the clinic will refer the patient to a larger medical institution. On the other hand, in medium-sized or large hospitals, once a patient's condition has stabilized, the patient is referred back to the original referring doctor, local clinic, etc.

[0003] As such, the medical institution most suitable for a patient varies depending on whether the patient's condition is acute or chronic. As a result, the medical institution where the patient is receiving treatment may not be the best suited for the patient's illness or condition. When a medical institution has many patients who are not suitable for that medical institution, medical professionals have to spend a lot of time on outpatient care. As a result, medical professionals are forced to bear a heavy burden, including excessive work.

[0004] Patent Document 1 discloses a medical information processing system that proposes treatment policies for patients in accordance with the hospital's management policy. This medical information processing system generates decision support information for medical professionals for each patient in accordance with changes in the hospital environment, in order to maximize the overall efficiency of the hospital. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] International Publication No. 2019 / 049819 Summary of the Invention [Problem to be solved by the invention]

[0006] In order to reduce the burden on outpatients, hospitals consider referring patients who are no longer suitable for treatment at the hospital to clinics, etc. It is desirable for medical professionals to select and refer appropriate patients while taking into account the patient's condition so as not to worsen the hospital's financial situation. However, Patent Document 1 does not mention the referral of patients.

[0007] The present invention has been made in consideration of the problems in the prior art described above, and aims to provide information useful for carrying out reverse patient referrals while preventing a deterioration in the hospital's financial situation. [Means for solving the problem]

[0008] In order to solve the above problem, the invention described in claim 1 is an information processing device comprising: an acquisition means for acquiring patient information of patients receiving treatment at a target hospital and hospital management information related to the management of the target hospital; an extraction means for extracting patient candidates to be referred to a hospital other than the target hospital within a specified period based on the patient information and the hospital management information; an update means for updating the patient information and the hospital management information assuming that the extracted patient candidates will be referred; and a prediction means for predicting management indicators indicating the management status of the target hospital after the specified period based on the updated patient information and the hospital management information.

[0009] The invention described in claim 2 is the information processing device described in claim 1, further comprising a receiving means for receiving designation of the management indicator and a target value for the management indicator, and a control means for repeating extraction by the extraction means, updating by the update means, and prediction by the prediction means for the designated management indicator until the value of the management indicator predicted by the prediction means reaches the designated target value.

[0010] The invention described in claim 3 is the information processing device described in claim 2, wherein the control means repeats extraction by the extraction means, update by the update means, and prediction by the prediction means while changing the way the specified period is taken.

[0011] The invention as set forth in claim 4 is the information processing device as set forth in any one of claims 1 to 3, wherein the acquisition means acquires the patient information and the hospital management information from an electronic medical record system.

[0012] The invention described in claim 5 is an information processing method including an acquisition step of acquiring patient information of patients receiving medical treatment at a target hospital and hospital management information related to the management of the target hospital; an extraction step of extracting patient candidates to be referred to a hospital other than the target hospital within a specified period based on the patient information and the hospital management information; an update step of updating the patient information and the hospital management information assuming that the extracted patient candidates will be referred; and a prediction step of predicting management indicators indicating the management status of the target hospital after the specified period based on the updated patient information and the hospital management information.

[0013] The invention described in claim 6 is a program for causing a computer to function as an acquisition means for acquiring patient information of patients receiving treatment at a target hospital and hospital management information regarding the management of the target hospital; an extraction means for extracting patient candidates to be reverse-referred to hospitals other than the target hospital within a specified period based on the patient information and the hospital management information; an update means for updating the patient information and the hospital management information assuming that the extracted patient candidates will be reverse-referred; and a prediction means for predicting management indicators that indicate the management status of the target hospital after the specified period based on the updated patient information and the hospital management information. [Effects of the Invention]

[0014] According to the present invention, it is possible to provide information useful for carrying out reverse patient referrals while preventing the deterioration of the hospital's financial situation. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a system configuration diagram of a reverse introduction support system according to a first embodiment of the present invention. [Figure 2] FIG. 10 is a diagram illustrating an example of patient information. [Figure 3] FIG. 10 is a diagram showing an example of management indicators among the hospital management information. [Figure 4] FIG. 10 is a diagram showing an example of resource information among hospital management information. [Figure 5] 10 is a flowchart showing a reverse introduction support process executed by the information processing device. [Figure 6] 10 is a flowchart showing a first management index prediction process. [Figure 7] 10 is a flowchart showing a second management index prediction process in the second embodiment. [Figure 8] 10 is a flowchart showing a third management index prediction process in the third embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0016] Hereinafter, embodiments of the present invention will be described with reference to the drawings. Advantages and features provided by the embodiments will be understood from the following detailed description and drawings. However, the scope of the present invention is not limited to the embodiments disclosed below or the examples shown in the drawings.

[0017] [First embodiment] First, a first embodiment of an information processing device, an information processing method, and a program according to the present invention will be described. FIG. 1 is a system configuration diagram of a reverse referral support system 100. The reverse referral support system 100 includes an information processing device 10, an electronic medical record system 21, an accounting system 22, an attendance management system 23, a reservation system 24, a hospital management BI system 25, and an in-hospital DB system 26. The information processing device 10 and the systems 21 to 26 are connected to each other so as to be able to communicate data via a communication network 20 such as a LAN (Local Area Network). The reverse referral support system 100 is used in a medical institution (hospital). Here, the medical institution is assumed to be larger than a predetermined size. For example, the medical institution is a medium-sized hospital or a large-sized hospital.

[0018] The information processing device 10 acquires various information from the systems 21 to 26 within the hospital. The information processing device 10 provides the user with information to support the reverse referral of patients from one hospital to another. Reverse referral refers to the referral of a patient whose condition has stabilized to the referring doctor or a local clinic. Here, the main focus is on patients receiving outpatient treatment at the hospital.

[0019] An electronic medical record system 21, an accounting system 22, an attendance management system 23, a reservation system 24, a hospital management BI system 25, an in-hospital DB system 26, etc. are existing systems within the hospital.

[0020] The electronic medical record system 21 manages information related to the electronic medical records of patients in the hospital. The information related to the electronic medical records includes medical information for each patient. The medical information includes the patient's symptoms, test results, treatment details, etc. The accounting system 22 manages accounting information within the hospital, including the hospital's income, expenditures, profit and loss, etc. The attendance management system 23 manages the working patterns, shifts, etc. of medical staff working at the hospital. The reservation system 24 manages reservations for medical examinations, tests, treatments, etc. for each patient at the hospital. The hospital management BI system 25 provides BI (Business Intelligence) tools for analyzing hospital management and streamlining operations. The hospital DB system 26 has a DB (DataBase) that stores various types of information in the hospital and manages the various types of information.

[0021] The information processing device 10 includes a control unit 11, an operation unit 12, a display unit 13, a communication unit 14, a storage unit 15, a database 16, and the like. The control unit 11 includes a CPU (Central Processing Unit), RAM (Random Access Memory), etc. The control unit 11 comprehensively controls the processing operations of each unit of the information processing device 10. Specifically, the CPU reads out various programs stored in the storage unit 15 and loads the read programs into the RAM. The CPU performs various processes in cooperation with the programs.

[0022] The operation unit 12 includes a keyboard, a mouse, etc. The keyboard includes cursor keys, character input keys, various function keys, etc. The operation unit 12 outputs operation signals input by key operations on the keyboard or mouse operations to the control unit 11. The operation unit 12 may include a touch screen configured integrally with the display unit 13. In this case, the operation unit 12 outputs operation signals to the control unit 11 according to the position of the touch operation on the touch screen.

[0023] The display unit 13 includes an LCD (Liquid Crystal Display) etc. The display unit 13 displays various screens according to instructions of a display signal input from the control unit 11.

[0024] The communication unit 14 is configured by a network interface, etc. The communication unit 14 transmits and receives data to and from external devices connected via a communication network 20 such as a LAN (Local Area Network).

[0025] The storage unit 15 is a storage device configured by an HDD (Hard Disk Drive), an SSD (Solid State Drive), a non-volatile semiconductor memory, etc. The storage unit 15 stores various programs, and parameters and data required to execute the various programs.

[0026] The database 16 is a database for managing various information acquired from the systems 21 to 26 and the like.

[0027] The control unit 11 acquires various types of information from each of the systems 21 to 26, etc., via the communication unit 14. For example, the control unit 11 acquires patient information and hospital management information from each of the systems 21 to 26, etc. The patient information is information about patients receiving medical treatment at the hospital. The hospital management information is information about the management of the hospital. The control unit 11 does not have to acquire the information managed in each of the systems 21 to 26, etc., via the communication network 20. For example, the control unit 11 may import the information managed in each of the systems 21 to 26, etc., as a CSV file.

[0028] An example of patient information is shown in Figure 2. Figure 2 lists the various information items included in the patient information and the sources of the various information. The sources indicate from which systems the control unit 11 obtains the various information. The "re-examination period for existing patients" is the period from the date of the second consultation to the date of the most recent appointment, with the first consultation being the first visit or a consultation that has been held for a certain period of time or more being considered as the first consultation. The "existing patient's visit route" is information indicating the route by which the patient visited the hospital. The "existing patient's visit route" is classified into, for example, referral outpatient, non-referral outpatient, emergency outpatient, emergency, etc. The "timing at which an existing outpatient can be referred back" is the date of their next appointment. "Timing of discharge for existing hospitalized patients" is the planned discharge date.

[0029] 3 and 4 show examples of hospital management information. 3 shows various information items and sources of management indicators, which are part of the hospital management information. Management indicators are information that indicates the management status of a hospital. Management indicators can be specified as criteria for determining whether or not a target value is reached. "Number of patients referred for their first consultation" is the number of patients who received a referral from another hospital. "Number of patients who visited for the first time without a referral" is the number of patients who visited for the first time without a referral from another hospital. "Number of emergency outpatients" is the number of patients who visited the emergency outpatient clinic. "Number of patients requesting emergency admission" is the number of patients who requested emergency admission. The "emergency response rate" is the ratio of the "number of patients accepted for emergency care" to the "number of patients requesting emergency care." The "reverse referral rate" is the ratio of the "number of reverse referred patients" to the "sum of the number of first-time patients and the number of repeat patients." The "reverse referral rate" is usually expressed in per mille. The "number of patients proposed for reverse referral" is the number of patients for whom a reverse referral was proposed using the reverse referral support system 100 or the like. The "reverse referral success rate" is the ratio of the "number of patients for whom reverse referral was successful" to the "number of patients for whom reverse referral was proposed." The "hospitalization rate by combination of disease and hospital visit route" is the ratio of the "number of hospitalized patients" to the "number of visiting patients" for the combination of the relevant disease and hospital visit route. The "surgery rate by combination of disease and hospital visit route" is the ratio of the "number of patients who underwent surgery" to the "number of patients who visited the hospital" for the combination of the relevant disease and hospital visit route.

[0030] Figure 4 shows the various information items and sources of resource information, which is part of hospital management information. Resource information is categorized into "facilities," "doctors," "nurses and paramedicals," and "overall." "Bed turnover time" is the average time a patient remains hospitalized per bed.

[0031] The control unit 11 (acquisition means) acquires patient information of patients receiving medical treatment at a target hospital and hospital management information related to the management of the target hospital. Here, the target hospital is a hospital that uses the reverse referral support system 100. For example, the control unit 11 acquires at least a portion of the patient information and hospital management information from the electronic medical record system 21.

[0032] The control unit 11 (extraction means) extracts candidates for patients to be referred back to hospitals other than the target hospital within a predetermined period based on the patient information and hospital management information. The control unit 11 (updating means) updates the patient information and hospital management information, assuming that the extracted patient candidates will be reverse-referred. The control unit 11 (prediction means) predicts management indicators that indicate the management status of the target hospital after a predetermined period of time based on the updated patient information and hospital management information.

[0033] The control unit 11 (accepting means) accepts the designation of a management indicator and a target value for the management indicator. The target value may be the upper limit value or the lower limit value of the management indicator. The target value may also be a range including the upper limit value and the lower limit value.

[0034] The control unit 11 (control means) repeats extraction by the extraction means, update by the update means, and prediction by the prediction means for the designated management index until the value of the management index predicted by the prediction means reaches the target value. The control unit 11 repeats extraction by the extraction means, update by the update means, and prediction by the prediction means while changing how the predetermined period is determined. For example, the control unit 11 sets the predetermined period to "one month from the present" and extracts candidates for patients to be reverse-referred, updates patient information and hospital management information, and predicts management indicators. Here, if the value of the management indicator has not reached the target value, the control unit 11 changes the predetermined period to "between one month from now and two months from now," and extracts candidates for patients to be reverse-referred, updates patient information and hospital management information, and predicts management indicators.

[0035] Next, the operation of the reverse introduction support system 100 will be described. FIG. 5 is a flowchart showing the reverse introduction support process executed by the information processing device 10.

[0036] The control unit 11 acquires patient information and hospital management information from the electronic medical record system 21, accounting system 22, attendance management system 23, reservation system 24, hospital management BI system 25, hospital DB system 26, etc. via the communication unit 14 (step S1). The control unit 11 stores the acquired patient information and hospital management information in the database 16. The control unit 11 may automatically import various pieces of information from the systems 21 to 26 within the hospital. In this case, the control unit 11 appropriately converts the various pieces of information into a format suitable for the information processing device 10 and imports the information into the information processing device 10. Alternatively, the user may manually set the various pieces of information to be imported, and the control unit 11 may acquire the set various pieces of information from the systems 21 to 26. Furthermore, the user may manually change the information (each value) imported into the information processing device 10.

[0037] Next, the control unit 11 accepts designation of management indicators to be used as targets (judgment items) and target values ​​of the management indicators (step S2) through operation by the user from the operation unit 12. The user designates the management indicators and target values ​​of the management indicators via the operation unit 12.

[0038] In the first embodiment, the "reverse referral rate" is used as the target management indicator. The reverse referral rate is calculated by the following formula (1).

[0039]

number

[0040] Next, the control unit 11 sets a target period to be used for prediction (step S3). Here, the control unit 11 sets the target period to one month.

[0041] The control unit 11 calculates a score for reverse referral for patients who have outpatient appointments during the target period (one month from the present) (step S4). For example, the control unit 11 determines patients who have outpatient appointments during the target period based on various information acquired from the electronic medical record system 21, the appointment system 24, etc. Hereinafter, the "score for reverse referral" will be referred to as the "reverse referral score." The reverse referral score is a score that indicates the degree to which reverse referral of a patient is recommended.

[0042] For example, the control unit 11 calculates the reverse referral score based on at least one of information on revenue from medical treatment of patients and information indicating the ease of reverse referral. For example, the return on investment (ROI) is used as information regarding revenue from patient care. ROI is the ratio of profit to costs related to patient care. The lower the ROI value, the higher the reverse referral score. Information indicating the ease of reverse referral, for example, can be the distance from the patient's home to the reverse referral hospital, the severity of the patient's illness, etc. Generally, the closer the distance from the patient's home to the reverse referral hospital, the easier it is for a doctor to reverse refer the patient. Also, the less severe the patient's illness, the easier it is for a doctor to reverse refer the patient. The higher the ease of reverse referral value, the higher the reverse referral score.

[0043] The control unit 11 extracts candidates for patients to be reverse-referred to other hospitals within a target period (one month from the present time) (reverse-referred patient candidates) based on the reverse-referral score of each target patient (step S5). Specifically, the control unit 11 extracts N patients as reverse-referred patient candidates in descending order of the reverse-referral score. Here, N is a predetermined value that can be changed arbitrarily. However, the control unit 11 excludes patients whose reverse referral scores do not exceed the level at which reverse referral is possible from the reverse referral patient candidates, even if the patient is among the top N patients in the reverse referral score ranking. In other words, the control unit 11 keeps patients whose reverse referral scores are too low and who should still be treated at this hospital at this hospital.

[0044] The control unit 11 outputs a list of the extracted reverse referral patient candidates (step S6). For example, the control unit 11 displays the list of reverse referral patient candidates on the display unit 13. The control unit 11 may also transmit data of the list of reverse referral patient candidates to an external device or cause a printer to print the list of reverse referral patient candidates.

[0045] Next, the control unit 11 updates the patient information and hospital management information in the database 16, assuming that the extracted reverse referral patient candidates will be reverse referred to another hospital within the target period (step S7). The control unit 11 updates the patient information of the reverse referral patient candidates to "reverse referred". For example, the control unit 11 changes the flag corresponding to each piece of patient information of the reverse referral patient candidates to "reverse referred". The control unit 11 assumes that a reverse referral was proposed for the reverse referral patient candidates at the first consultation within the target period, and that there are no further appointments for treatment.

[0046] Next, the control unit 11 performs a management index prediction process (step S8). The management index prediction process is a process for predicting management indexes after a target period based on updated patient information and hospital management information. Specifically, the control unit 11 predicts the reverse referral ratio one month from the present time.

[0047] In the first embodiment, in step S8, the control unit 11 performs the first management index prediction process shown in FIG. The control unit 11 predicts the number of return visit patients for the target period (one month from the present time) based on the updated patient information and hospital management information (step S21). The patient information and hospital management information used here may be the information listed in Figures 2 to 4 or other information.

[0048] For example, the control unit 11 predicts the number of return visit patients within one month from the present time using a demand prediction method, such as the moving average method, exponential smoothing method, regression analysis method, or weighted moving average method. When using the moving average method, the exponential smoothing method, or the weighted moving average method, the control unit 11 predicts the number of re-examination patients for the target period based on past performance (time series data on the number of re-examination patients). In the simplest example of prediction, the control unit 11 may predict the number of re-examination patients for the target period from the number of re-examination patients for the same month as the prediction target month in the previous year, or the number of re-examination patients for the most recent month. It is believed that there is a correlation between a patient's illness and the period required for medical treatment (period of outpatient visits) or frequency of medical treatment. Therefore, when using regression analysis, for example, the control unit 11 predicts the timing of outpatient visits based on the illness of each existing patient, and uses the predicted timing of outpatient visits to predict the number of re-examination patients.

[0049] Alternatively, the control unit 11 generates a prediction model by machine learning using patient information and hospital management information at the reference time as explanatory variables and the number of revisiting patients within one month from the reference time as a target variable. Using the prediction model, the control unit 11 predicts the number of revisiting patients within one month from the current time using the patient information and hospital management information as input data.

[0050] The control unit 11 may further predict the number of re-examination patients in more detail using information such as the re-examination period for each existing patient, the disease of each existing patient, the route each existing patient takes to visit the hospital (referral outpatient clinic, emergency outpatient clinic, emergency), the timing when each existing outpatient becomes eligible for reverse referral, the timing when each existing inpatient is discharged, the reverse referral rate, the number of patients proposed for reverse referral, and the success rate of reverse referral. Here, for the reverse referral rate, the number of patients proposed for reverse referral, and the reverse referral success rate, it is desirable to use information from a past period that is similar to the period of the predicted "number of re-examination patients." For example, information from the same month as the target month of the prediction in the previous year, or information from the most recent month, etc., is used.

[0051] Next, the control unit 11 predicts the number of first-time patients for the target period (one month from the present time) based on the updated patient information and hospital management information (step S22). The patient information and hospital management information used here may be the information listed in Figures 2 to 4, or other information. First-time patients are classified into one of referral / no referral / emergency outpatient / emergency transport.

[0052] For example, the control unit 11 predicts the number of first-time patients for one month from the present time using a demand prediction method. Demand prediction methods that can be used include the moving average method, exponential smoothing method, regression analysis method, and weighted moving average method. Details of each method are the same as those for predicting the number of repeat visit patients.

[0053] Alternatively, the control unit 11 generates a prediction model by machine learning using patient information and hospital management information at the reference time as explanatory variables and the number of first-time patients within one month from the reference time as a response variable. Using the prediction model, the control unit 11 predicts the number of first-time patients within one month from the current time using the patient information and hospital management information as input data.

[0054] The control unit 11 may further use information such as the number of referred first-time patients, the number of first-time patients without referral, the number of emergency outpatient patients, the number of patients requesting emergency admission, and the emergency response rate to predict the number of first-time patients in more detail. The number of patients who will be "transported to emergency care" is calculated by multiplying the "number of patients requesting emergency admission" by the "emergency response rate." Therefore, if there are fluctuations in the ratio of referrals / no referrals / emergency outpatients / emergency transports due to, for example, the season, etc., it is desirable for the control unit 11 to predict the number of first-time patients taking this information into consideration. It is desirable to use information from a past period similar to the period for which the "number of first-time patients" is predicted as information to be used for the prediction. For example, information from the same month as the target month of the prediction in the previous year, or information from the most recent month, etc. is used. Note that while actual values ​​are expected to provide more accurate predictions, if actual values ​​are not available, estimated values ​​may be used for the prediction.

[0055] In steps S21 and S22, the control unit 11 predicts the number of returning patients and the number of first-time patients so as not to exceed the capacity of the hospital's resources (see the resource information in FIG. 4). Of the hospital resources, the facilities include the number of examination rooms, examination room usage time, number of hospital beds, bed rotation time, number of operating rooms, usage time of operating rooms, number of testing facilities, usage time of testing facilities, etc. Of the hospital resources, the doctors include the number of doctors, the number of outpatients each doctor is responsible for, the time each doctor spends tending to outpatients, the number of surgeries each doctor is responsible for, the time each doctor spends tending to surgeries, and the working hours of each doctor. Of the hospital resources, the nurses or paramedical staff include the number of nurses, the number of patients each doctor is responsible for, and the working hours of each doctor.

[0056] Next, the control unit 11 calculates the reverse referral rate after the target period (one month from the present time) according to the above formula (1) (step S23). The numbers of return patients and first-time patients are calculated using the values ​​predicted in steps S21 and S22. The number of reverse referral patients is calculated using the number of reverse referral patient candidates extracted in step S5. This completes the first management index forecasting process.

[0057] In the first management index forecasting process, the control unit 11 sums up the separately predicted numbers of return patients and first-time patients. Alternatively, the control unit 11 may simultaneously forecast the number of outpatients, which is the sum of the numbers of return patients and first-time patients. In addition, in the first management index forecasting process, the order of the processes in step S21 and step S22 may be reversed.

[0058] 5, the control unit 11 outputs the predicted value of the management indicator (reverse introduction rate) after the target period (step S9). For example, the control unit 11 causes the display unit 13 to display the predicted value of the management indicator.

[0059] Next, the control unit 11 determines whether or not the value of the predicted management index (reverse introduction rate) has reached the target value (step S10). If the predicted value of the management index has not reached the target value (step S10; NO), the control unit 11 determines whether the execution of the processes of steps S3 to S9 has reached a predetermined number of times (step S11).

[0060] If the execution of the processes of steps S3 to S9 is less than the predetermined number of times (step S11; NO), the process returns to step S3. In step S3, the control unit 11 sets the target period to the next month and repeats the process. In step S4, the control unit 11 calculates a reverse referral score for patients who have outpatient appointments during the target period (from one month to two months later). In step S5, the control unit 11 extracts patient candidates (reverse referral patient candidates) to be reverse referred to other hospitals during the target period based on the reverse referral score of each target patient. In step S6, the control unit 11 outputs a list of the extracted reverse referral patient candidates. In step S7, the control unit 11 updates the patient information and hospital management information, assuming that the extracted reverse referral patient candidates will be reverse referred to other hospitals. In step S8, the control unit 11 predicts management indicators after the target period based on the updated patient information and hospital management information. In step S9, the control unit 11 outputs predicted values ​​of management indicators after the target period.

[0061] In step S10, if the value of the predicted management index (reverse introduction rate) reaches the target value (step S10; YES), the reverse introduction support process ends. In step S11, if the execution of the processes of steps S3 to S9 reaches a predetermined number of times (step S11; YES), the reverse introduction support process ends. Note that, if the control unit 11 has repeated the processes of steps S3 to S9 a predetermined number of times but the value of the management indicator has not reached the target value, it may notify that the value of the management indicator has not reached the target value.

[0062] When a potential reverse referral patient visits the hospital for an outpatient appointment, a doctor or other healthcare professional will propose a reverse referral to the patient. If the patient agrees to the reverse referral, no further appointments will be made for this patient. Even if a healthcare professional proposes a reverse referral, there may be cases where the patient declines and continues with a follow-up visit.

[0063] As described above, according to the first embodiment, the control unit 11 of the information processing device 10 extracts candidate patients to be referred to a hospital other than the target hospital within a predetermined period based on patient information and hospital management information. The control unit 11 updates the patient information and hospital management information, assuming that the extracted candidate patients will be referred. The control unit 11 predicts management indicators indicating the management status of the target hospital after a predetermined period based on the updated patient information and hospital management information. Therefore, the control unit 11 can provide information useful for carrying out patient referrals while preventing a deterioration in the hospital's management status. A user can consider the extracted candidate patients as patients who should be referred and evaluate the future management status of the target hospital based on the predicted management indicators. Referring patients to other hospitals reduces congestion at the hospital and reduces the workload of medical professionals.

[0064] The control unit 11 also accepts the designation of management indicators and target values ​​for the management indicators. The control unit 11 repeats the extraction of reverse-referred patient candidates, updating patient information and hospital management information, and predicting management indicators for the designated management indicators until the predicted management indicator values ​​reach the target values. Thus, the control unit 11 can extract reverse-referred patient candidates, aiming for the target values ​​designated for the management indicators.

[0065] Furthermore, the control unit 11 can extract reverse-referred patient candidates by changing how the predetermined period is determined so that the value of the management index reaches the target value.

[0066] Furthermore, the control unit 11 acquires patient information and hospital management information from the electronic medical record system 21 and the like, so that existing systems within the hospital can be used.

[0067] In particular, in the first embodiment, the control unit 11 can provide useful and objective information for carrying out the reverse referral of patients by using the "reverse referral rate" as a management index.

[0068] [Second embodiment] Next, a second embodiment to which the present invention is applied will be described. The reverse introduction support system of the second embodiment has the same configuration as the reverse introduction support system 100 shown in the first embodiment. Therefore, the same components as those in the first embodiment are designated by the same reference numerals, and illustrations and explanations thereof are omitted. The configuration and processing characteristic of the second embodiment will be explained below.

[0069] In the second embodiment, the reverse introduction support process (see FIG. 5) is similar. Only the parts of the second embodiment that are different from the first embodiment will be described. In the second embodiment, "medical fees" are used as the target management index.

[0070] In step S8, the control unit 11 predicts medical fees for the target period (one month from the present) based on the updated patient information and hospital management information. Specifically, the control unit 11 performs the second management index prediction process shown in FIG.

[0071] The control unit 11 predicts medical fees for each existing patient for the target period (one month from the present time) based on the updated patient information and hospital management information (step S31). The patient information and hospital management information used here may be the information listed in Figures 2 to 4, or other information. Medical fees vary greatly depending on whether or not a patient is hospitalized or undergoes surgery. Standard treatments are determined based on the diagnosis (disease) or symptoms. Therefore, the control unit 11 can predict how much medical fees will be earned in the future based on the diagnosis (disease) or symptoms of the patient.

[0072] For example, the control unit 11 predicts medical fees for each existing patient for one month from the present time using a demand forecasting method, such as the moving average method, exponential smoothing method, regression analysis method, or weighted moving average method. When using the moving average method, exponential smoothing method, or weighted moving average method, the control unit 11 predicts the medical fees for each existing patient in the target period based on past performance (time series data of medical fees for each existing patient). In the simplest example of prediction, the control unit 11 may predict the medical fees for each existing patient in the target period from the medical fees for each existing patient in the same month as the target prediction month in the previous year, or the medical fees for each existing patient in the most recent month. It is believed that there is a correlation between a patient's illness and the period required for medical treatment (period of outpatient visits) or frequency of medical treatment. Therefore, when using regression analysis, for example, the control unit 11 predicts the timing of outpatient visits based on the illness of each existing patient, and uses the predicted timing of outpatient visits to predict medical fees for each existing patient.

[0073] Alternatively, the control unit 11 generates a prediction model through machine learning using patient information and hospital management information at the reference time as explanatory variables and medical fees for each existing patient for one month from the reference time as a target variable. Using the prediction model, the control unit 11 predicts medical fees for each existing patient for one month from the current time using the patient information and hospital management information as input data.

[0074] The control unit 11 may further use information such as the medical fees obtained from each existing patient, the medical department of each existing patient, the diagnosis of each existing patient, the test status of each existing patient, the symptoms of each existing patient, and the medical history of each existing patient to predict or calculate the medical fees for each existing patient in more detail. The medical history of each existing patient includes the history of outpatient visits, hospitalizations, status, or route of visits of each existing patient. The status is information such as whether the patient is currently outpatient or hospitalized.

[0075] Next, the control unit 11 predicts medical fees for new patients for the target period (one month from the present time) based on the updated patient information and hospital management information (step S32). The patient information and hospital management information used here may be the information listed in Figures 2 to 4, or other information.

[0076] For example, the control unit 11 predicts medical fees from new patients for one month from the present time using a demand prediction method. Demand prediction methods that can be used include the moving average method, exponential smoothing method, regression analysis method, and weighted moving average method. Details of each method are the same as those for predicting medical fees from existing patients.

[0077] Alternatively, the control unit 11 generates a prediction model through machine learning using patient information and hospital management information at the reference time as explanatory variables and medical fees from new patients within one month from the reference time as a target variable. Using the prediction model, the control unit 11 predicts medical fees from new patients within one month from the current time using the patient information and hospital management information as input data.

[0078] The control unit 11 may further predict or calculate medical fees for new patients in more detail using explanatory variables for estimating the number of new patients, explanatory variables for estimating the income from each new patient, and information for calculating medical fees. Explanatory variables for estimating the number of new patients include the number of patients by disease, the number of patients by visit route, and the emergency response rate. The number of patients by visit route includes the number of first-time patients with referrals, the number of first-time patients without referrals, the number of emergency outpatient patients, and the number of patients requesting emergency care. Explanatory variables for estimating income from each new patient include the hospitalization rate for each combination of disease and visit route, the surgery rate for each combination of disease and visit route, etc. In the case of emergency transport, a high proportion of patients require hospitalization or surgery, so using the visit route improves the accuracy of predictions. Information for calculating medical fees includes the medical fees for hospitalization for each combination of disease and visit route, the medical fees for surgery for each combination of disease and visit route, and the medical fees for outpatient care for each combination of disease and visit route.

[0079] In steps S31 and S32, the control unit 11 predicts medical fees for each existing patient and new patient so as not to exceed the resource capacity of the hospital (see the resource information in FIG. 4).

[0080] Next, the control unit 11 adds up the medical fees for each existing patient and the medical fees for new patients to calculate the medical fees for the target period (one month from the present) (step S33). The values ​​predicted in steps S31 and S32 are used for the medical fees for each existing patient and the medical fees for new patients. This completes the second management index forecasting process.

[0081] In the second management index forecasting process, the control unit 11 summed up the separately predicted medical fees for existing patients and medical fees for new patients. Alternatively, the control unit 11 may simultaneously forecast the total of the medical fees for existing patients and medical fees for new patients. In the second management index forecasting process, the order of the processes in steps S31 and S32 may be reversed.

[0082] In step S10, the control unit 11 determines whether or not the value of the predicted management index (medical fee) has reached the target value.

[0083] As described above, according to the second embodiment, the control unit 11 of the information processing device 10 can provide information useful for carrying out reverse patient referrals while preventing the deterioration of the hospital's business situation, as in the first embodiment. In particular, in the second embodiment, the control unit 11 can provide useful and objective information for carrying out reverse patient referrals by using "medical fees" as a management index.

[0084] [Third embodiment] Next, a third embodiment to which the present invention is applied will be described. The reverse introduction support system of the third embodiment has the same configuration as the reverse introduction support system 100 shown in the first embodiment. Therefore, the same components as those in the first embodiment are designated by the same reference numerals, and illustrations and explanations thereof are omitted. Below, the configuration and processing characteristic of the third embodiment will be explained.

[0085] In the third embodiment, the reverse introduction support process (see FIG. 5) is similar. Only the parts of the third embodiment that are different from the first embodiment will be described. In the third embodiment, the "outpatient attendance time of a doctor" is used as a management index.

[0086] In step S8, the control unit 11 predicts the outpatient attendance time of doctors after the target period (one month from the present time) based on the updated patient information and hospital management information. Specifically, the control unit 11 performs the third management index prediction process shown in FIG.

[0087] The control unit 11 predicts the outpatient response time for return patients during the target period (one month from the present time) based on the updated patient information and hospital management information (step S41).

[0088] For example, the control unit 11 predicts the outpatient response time for returning patients for one month from the present time using a demand forecasting method, such as the moving average method, exponential smoothing method, regression analysis method, or weighted moving average method. When the moving average method, exponential smoothing method, or weighted moving average method is used, the control unit 11 predicts the outpatient response time for return patients during the target period based on past performance (time series data of outpatient response time for return patients). In the simplest example of prediction, the control unit 11 may predict the outpatient response time for return patients during the target period from the outpatient response time for return patients during the same month as the prediction target month in the previous year, or the outpatient response time for return patients during the most recent month. When using regression analysis, the control unit 11 predicts outpatient response times for returning patients during a target period using the already scheduled outpatient times, the medical departments of each existing patient, the diagnosis details of each existing patient, the test status of each existing patient, the symptoms of each existing patient, and the medical history of each existing patient. The medical history of each existing patient includes hospital visit history, hospitalization history, status, and route of arrival at the hospital.

[0089] Alternatively, the control unit 11 generates a prediction model by machine learning using patient information and hospital management information at the reference time as explanatory variables and outpatient response times for return patients for one month from the reference time as objective variables. Using the prediction model, the control unit 11 predicts outpatient response times for return patients for one month from the current time using the patient information and hospital management information as input data.

[0090] The patient information and hospital management information, which are considered as explanatory variables, include already scheduled outpatient times, the medical department of each existing patient, the diagnosis of each existing patient, the test status of each existing patient, the symptoms of each existing patient, the medical history of each existing patient, etc. The medical history of each existing patient includes the history of outpatient visits, hospitalization history, status, route of arrival at the hospital, etc.

[0091] Next, the control unit 11 predicts the outpatient response time for new patients during the target period (one month from the present time) based on the updated patient information and hospital management information (step S42).

[0092] For example, the control unit 11 predicts the outpatient response time for new patients for one month from the present time using a demand forecasting method, such as the moving average method, exponential smoothing method, regression analysis method, or weighted moving average method. When the moving average method, the exponential smoothing method, or the weighted moving average method is used, the control unit 11 predicts the outpatient attendance time for first-time patients in the target period based on past performance (time series data of outpatient attendance time for first-time patients). In the simplest example of prediction, the control unit 11 may predict the outpatient attendance time for first-time patients in the target period from the outpatient attendance time for first-time patients in the same month as the prediction target month in the previous year, or the outpatient attendance time for first-time patients in the most recent month. When regression analysis is used, the control unit 11 predicts outpatient response times for first-time patients during a target period using explanatory variables for estimating the number of first-time patients and information for calculating outpatient response times for first-time patients. Explanatory variables for estimating the number of first-time patients include the number of patients by disease, the number of patients by arrival route, and the emergency response rate. The number of patients by arrival route includes the number of first-time patients with referrals, the number of first-time patients without referrals, the number of emergency outpatient patients, and the number of patients requesting emergency admission. Information for calculating outpatient response times for first-time patients includes outpatient response times for each combination of disease and arrival route.

[0093] Alternatively, the control unit 11 generates a prediction model by machine learning using patient information and hospital management information at the reference time as explanatory variables and outpatient response times for first-time patients for one month from the reference time as objective variables. Using the prediction model, the control unit 11 predicts outpatient response times for first-time patients for one month from the current time using the patient information and hospital management information as input data.

[0094] The patient information and hospital management information that are used as explanatory variables include explanatory variables for estimating the number of first-time patients, information for calculating outpatient response times for first-time patients, etc. Explanatory variables for estimating the number of first-time patients include the number of patients by disease, the number of patients by arrival route, and emergency response rates. The number of patients by arrival route includes the number of first-time patients with referrals, the number of first-time patients without referrals, the number of emergency outpatient patients, and the number of patients requesting emergency admission. Information for calculating outpatient response times for first-time patients includes outpatient response times for each combination of disease and arrival route.

[0095] Next, the control unit 11 adds up the outpatient attendance time for return patients and the outpatient attendance time for first-time patients to calculate the outpatient attendance time of the doctor after the target period (one month from the present) (step S43). For the outpatient attendance time for return patients and the outpatient attendance time for first-time patients, the values ​​predicted in steps S41 and S42 are used. This completes the third management index forecasting process.

[0096] In the third management index prediction process, the control unit 11 sums up the outpatient care time for return patients and the outpatient care time for first-time patients, which were predicted separately. Alternatively, the control unit 11 may predict the sum of the outpatient care time for return patients and the outpatient care time for first-time patients at the same time. In addition, in the third management index forecasting process, the order of the processes in steps S41 and S42 may be reversed.

[0097] In step S10, the control unit 11 determines whether the value of the predicted management index (the time spent by doctors attending outpatient clinics) has reached the target value.

[0098] As described above, according to the third embodiment, the control unit 11 of the information processing device 10 can provide information useful for carrying out reverse patient referrals while preventing the deterioration of the hospital's business situation, as in the first embodiment. In particular, in the third embodiment, the control unit 11 can provide useful and objective information for carrying out reverse patient referrals by using "doctors' outpatient hours" as a management index.

[0099] The descriptions in the above embodiments are examples of the information processing device, information processing method, and program according to the present invention, and are not limited to these. The detailed configuration and detailed operation of each part constituting the device can also be changed as appropriate within the scope of the present invention.

[0100] Regarding the management indicators for which target values ​​are set, the first embodiment uses "reverse referral rate," the second embodiment uses "medical fees," and the third embodiment uses "doctors' outpatient response time" as examples, but target values ​​may also be set for other management indicators. For example, target values ​​may be set for income (medical fees, etc.), expenses (labor costs, pharmaceutical costs, etc.), and profits. Target values ​​may also be set for the number of patients, the number of outpatients, the number of inpatients, the number of repeat patients, the hospitalization rate, the number of patients requesting emergency admission, the emergency response rate, the number of first-time outpatient patients, the referral rate, the number of referrals, the number of reverse referrals, the reverse referral rate, and the reverse referral success rate. Target values ​​may also be set for resource capacity and resource sufficiency rate.

[0101] In each of the above embodiments, the case where a target value is set for one management indicator has been described, but a target value may be set for a plurality of management indicators.

[0102] In the above embodiments, the target period is set to "one month," but the period is not limited to this. Furthermore, each piece of information used in the processing may be information about the entire hospital, or information about a specific unit such as a medical department.

[0103] 5, the target management indicators may be set in advance. Furthermore, in the reverse referral support process, after executing step S1, the control unit 11 may first predict management indicators after a predetermined period of time using current information (step S8). Then, the control unit 11 may specify target values ​​(part of step S2), extract reverse referral patient candidates (steps S4 and S5), and update patient information and hospital management information (step S7).

[0104] In addition, in the reverse referral support processing, the control unit 11 may have the user select some of the reverse referral patient candidates extracted in step S5, and perform subsequent processing assuming that the selected reverse referral patient candidates will be reverse referred.

[0105] Furthermore, the method for calculating the reverse referral score is not limited to the above example. For example, profits from treating patients, income from treating patients, etc. may be used as information regarding revenue from treating patients. Furthermore, the ease of accepting a proposal, etc. may be used as information indicating the ease of reverse referral.

[0106] In each of the above embodiments, the processing executed by the information processing device 10 may be performed by a plurality of devices in cooperation with each other. Furthermore, instead of the operation unit 12 and the display unit 13 of the information processing device 10, an operation unit and a display unit of an external device that can access the information processing device 10 may be used. For example, the control unit 11 of the information processing device 10 may execute processing in response to an operation by a doctor from the operation unit of the external device, and may cause the processing result to be displayed on the display unit of the external device.

[0107] In each of the above embodiments, a program for causing the information processing device 10 to realize each function is stored in the storage unit 15. Alternatively, software for causing the information processing device 10 to realize each function may be provided in the form of SaaS (Software as a Service) from a computer device on the side of an external service provider via the Internet. For example, a configuration may be adopted in which each process is performed on a cloud server accessed by the information processing device 10 via the Internet, and the process result is returned from the server to the information processing device 10.

[0108] In the above-described embodiments, the systems 21 to 26 listed as sources of various information acquired by the information processing device 10 are merely examples and do not limit the present invention.

[0109] The computer-readable medium for storing the program for executing each process is not limited to the above examples. A carrier wave may also be used as a medium for providing program data via a communication line.

[0110] The above-disclosed embodiments are for the purpose of explanation and example only, and are not intended to be limiting. The scope of the present invention should be interpreted by the claims. [Explanation of symbols]

[0111] 10. Information processing equipment 11 Control section 12 Control section 13 Display section 14 Communications Department 15 Storage section 16 Databases 20. Communication Networks 21 Electronic Medical Record System 22 Accounting System 23 Attendance management system 24 Reservation System 25 Hospital Management BI System 26 Hospital DB System 100 Reverse introduction support system

Claims

1. an acquisition means for acquiring patient information of patients receiving medical treatment at the target hospital and hospital management information relating to the management of the target hospital; an extraction means for extracting patient candidates to be referred to a hospital other than the target hospital within a predetermined period based on the patient information and the hospital management information; an updating means for updating the patient information and the hospital management information on the assumption that the extracted patient candidate will be referred back; a prediction means for predicting a management indicator indicating the management status of the target hospital after the predetermined period based on the updated patient information and the updated hospital management information; An information processing device comprising:

2. a receiving means for receiving the management index and a target value for the management index; a control means for repeating extraction by the extraction means, updating by the update means, and prediction by the prediction means for the specified management indicator until the value of the management indicator predicted by the prediction means reaches the specified target value; Further provided with The information processing device according to claim 1 .

3. the control means repeats the extraction by the extraction means, the update by the update means, and the prediction by the prediction means while changing the way in which the predetermined period is determined; The information processing device according to claim 2 .

4. the acquiring means acquires the patient information and the hospital management information from an electronic medical record system. The information processing device according to claim 1 .

5. an acquisition step of acquiring patient information of patients receiving medical treatment at the target hospital and hospital management information relating to the management of the target hospital; an extraction step of extracting patient candidates to be referred to a hospital other than the target hospital within a predetermined period based on the patient information and the hospital management information; an updating step of updating the patient information and the hospital management information assuming that the extracted patient candidate will be reverse-referred; a prediction step of predicting a management indicator indicating the management status of the target hospital after the predetermined period based on the updated patient information and the updated hospital management information; An information processing method including:

6. Computer, An acquisition means for acquiring patient information of patients receiving medical treatment at the target hospital and hospital management information relating to the management of the target hospital; an extraction means for extracting patient candidates to be reverse-referred to a hospital other than the target hospital within a predetermined period based on the patient information and the hospital management information; an updating means for updating the patient information and the hospital management information on the assumption that the extracted patient candidate will be reverse-referred; a prediction means for predicting a management indicator indicating the management status of the target hospital after the predetermined period based on the updated patient information and the updated hospital management information; A program to function as a

Images