A program with bed management functions that supports medical professionals in selecting medical resources and patients

Abstract

When deciding which medical treatments and procedures to provide to patients from among the hospital's medical resources, a computer is used to predict how patients will use medical resources, and by systemizing the medical resource decisions, the hospital aims to optimize its profits by making resource use more efficient and profitable. [Solution] Patient information and information on available medical resources that can be provided to patients by medical institutions are stored, and a prediction of the medical resources required by the patient is calculated based on the patient information as predicted patient resource information, and the predicted patient resource information is matched with the available medical resource information (S707). The matching results are presented to medical professionals, and input from the medical professionals is accepted. The predicted patient resource information is changed to planned (decided) patient resource information (S710), allowing the patient to be selected and accepted, and medical resources to be provided to the patient.

Description

[Technical Field]

[0001] The present invention relates to a program (information processing device and method) used in a hospital bed management system of a medical institution, and in particular to assist medical personnel in determining medical resources and patients. [Background technology]

[0002] The current state of hospital management in Japan is not good, with unprofitable hospitals prioritizing policy-based medical care and research, public hospitals that are unable to escape from a deficit, and private hospitals that are difficult to manage because they must survive under the same conditions as public hospitals, even if they have excellent management skills.

[0003] The most important thing for stable and improved management is to improve profitability, and to achieve this, it is necessary to make effective use of medical resources while controlling expenses and eliminating waste. Medical resources are diverse, and include physical resources such as hospital beds and examination rooms, human resources such as medical professionals like doctors, nurses, medical technicians, and administrative staff, hard resources such as medical equipment like CT scans and MRI scans (especially expensive medical equipment), and soft resources such as medical supplies and pharmaceuticals.

[0004] It is also important to provide medical resources that are suitable for hospital management and to optimize the selection of patients who receive these resources. If this medical resource information and patient information can be systematized and managed, and medical resources can be efficiently selected and allocated to patients who need them, it will contribute to improving the operational efficiency of hospital management. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] WO2018 / 084166 publication (paragraph

[0026]

[0052] )

[0006] Patent Document 1 describes a technology for optimizing the use of medical institution resources, and attempts to reduce the probability of readmission as a measure to optimize and minimize medical institution resources. In particular, in order to reduce negative income for medical institutions, the number of readmissions within 30 days is reduced through medical intervention. For medical intervention, requirements such as a first prediction medical institution and a second prediction medical institution are defined, and it is decided which treatment should be administered to the patient at the medical institution (including home care).

[0007] In other words, although it is beneficial in that it will lead to a reduction in public medical expenses by reducing readmissions and in that it will allow multiple medical institutions to share limited medical resources, there is no disclosure of the process from prediction, planning, to decision-making, or of the aspects of profit optimization and medical resource utilization at a particular medical institution, or even patient selection.

[0008] Doctors, nurses, and other medical professionals are required to have the skills to select and administer the necessary medical resources to patients while managing the availability and remaining amount of medical resources at medical institutions.In addition, while it is of utmost importance to provide existing medical resources to patients who need them, there is no system in place to help medical institutions determine which patients should receive the most optimal allocation of medical resources from a management perspective. Summary of the Invention [Problem to be solved by the invention]

[0009] The present invention has been made in light of these issues, and aims to provide a hospital bed management tool (program, information processing device (system of collaboration between devices), method) for optimizing hospital profits by systematizing management-based medical resource decisions to increase the efficiency and profitability of resource use, while placing emphasis on computer-based predictions of patient use of medical resources when deciding on the treatment and medical procedures to be provided to patients from among the medical resources possessed by the hospital, depending on the patient. [Means for solving the problem]

[0010] In order to solve the above problems, the program of the present invention has the following main features.

[0011] (1) A program for operating a computer having a processor and a memory, wherein the memory stores a database, and the database stores patient information and available medical resource information that can be provided to patients by medical institutions. The program has the following functions: calculates a prediction of medical resources required for a patient based on the input patient information as patient utilization predicted resource information; matches the patient utilization predicted resource information with the available medical resource information and presents it to medical professionals; and accepts input from medical professionals and changes the patient utilization predicted resource information to one or more of patient utilization planned resource information that plans the medical resources required by the patient or patient utilization determination resource information that determines the medical resources required by the patient. One aspect of this program includes updating the remaining available medical resource information after determining the patient's planned resource use information or the patient's decided resource use information, and continuing the next matching process.

[0012] According to the present invention, patient information and available medical resource information for a patient are stored. Alternatively, timely updated patient information is also stored. Based on the patient's medical condition, disease, and other factors included in the patient information, a computer predicts medical resources to calculate patient utilization prediction resource information. That is, the computer first predicts the medical resources needed by the patient. Second, the computer matches the patient utilization prediction resource information with the available medical resource information to determine whether the resource information matches, mismatches, or is similar. If matching or similar resource information is found, the patient utilization prediction resource information is changed to one or more of planned patient utilization resource information or determined patient utilization resource information, triggered by a selection by a medical professional who refers to the matching results. That is, the system changes the "predicted" status to "planned" or "determined," and the provision of the medical resource to the patient is scheduled or determined. Alternatively, if the "predicted" status is not changed, the medical resource is not provided to the patient. This contributes to supporting the operation of the bed management tool from a management perspective by presenting to doctors and others, when making their selection, which patient to allocate the computer-predicted medical resources to in terms of management and management efficiency. It is also possible to change this perspective to that of community medicine. In one form of this program, the above medical resource information is linked and recorded with clinical outcomes recorded in electronic medical records, PROs (patient reported outcomes) answered through patient questionnaires, and QALYs, making it possible to create judgment formulas for making the most effective use of limited resources in communities and hospitals from a clinical and outcome perspective.

[0013] The database stores hospital bed data, facility standard information, etc., and the program has the function of calculating one or more of the required medical resources and / or patient-specific management indicators from the information of one or more patients using DPC information, hospital bed data, facility standards, patient data, potential inpatients, and medical resource information.

[0014] (2) The database stores the medical institution's past DPC information or prescription information, and the patient utilization prediction resource information is calculated based on the patient's past DPC information or prescription information.

[0015] According to the present invention, in addition to (1), the database stores past DPC information or medical receipt information of medical institutions, and the patient resource utilization prediction information is calculated based on the past DPC information or medical receipt information of the patient, so it is possible to calculate the patient resource utilization prediction information based on information such as the treatment history of the patient and the appropriate payment amount obtained from the past DPC information or medical receipt information. For example, this is useful for predicting medical resources such as whether an examination should be performed using an endoscope or PET.

[0016] (3) The database stores electronic medical record information, and the program has the function of extracting and outputting information into DPC information based on the electronic medical record information, and the DPC information includes consent or non-consent information regarding the secondary use of personal information output from the electronic medical record information.

[0017] According to this invention, DPC information or medical claim information from multiple hospitals can be collected and used to optimize hospital bed utilization as part of a regional medical plan. However, collecting all medical claim information may lead to resistance from each hospital to collecting the information. Therefore, this study also includes implementing a method to automatically mask, modify, or omit some information to enable its provision. DPC information and medical claim information are payment information submitted to the payment fund once a month, so they are updated approximately once a month. Electronic medical record data, on the other hand, is recorded by medical professionals every time a patient is examined, so they are updated at least once a day during hospitalization. Furthermore, image data and data analyzing these images are typically updated in real time. This study takes advantage of the ease of outputting and anonymizing DPC information and medical claim information, which are updated and finalized approximately once a month, to link more real-time information to this information, manage it, and use it for analysis. Furthermore, there are differences in the quality and degree of structuring of this information. Because DPC is payment information, it is structured with strictly standardized terminology and is highly accurate data. On the other hand, information in electronic medical records is insufficiently structured. Real-time information may be of low quality. This information is evaluated comprehensively, but by linking other information to the high-quality DPC information, which is the most structured and has been evaluated by many people, it is possible to improve the accuracy of predictions.

[0018] (4) The change is made by changing the prediction to a schedule to accommodate the patient's choice.

[0019] According to the present invention, when a medical professional inputs a change from "prediction" to "plan" or "decision," the computer accepts the patient's selection, and the information on the resources that the patient is expected to use is scheduled to be provided to the patient, and the patient's hospital bed acceptance is decided. According to the present invention, by recording a log of cases where a medical professional does not manually change a computer-generated prediction into a schedule and the reasons for doing so, it is useful for identifying issues and solutions when a prediction based on machine learning or the like is rejected, contributing to improving the performance of machine learning. Alternatively, by visualizing the reasons why a medical professional rejected an AI prediction, it is useful for managing medical professionals. Furthermore, by implementing operations such as requiring approval from a supervisor when changing matching results, it is possible to increase compliance with operating standards. It is also possible to use machine learning not only for prediction but also for matching, and the recorded reason information can be used to improve matching performance.

[0020] (5) When making such changes, if the forecast is not changed to the plan, a log and / or the reason shall be recorded.

[0021] According to the present invention, by recording a log of cases where medical professionals did not manually change the schedule based on a computer prediction and the reasons for doing so, it is useful for identifying issues and solutions when an AI prediction is not adopted, and contributes to improving the performance of AI-based machine learning.Also, by visualizing the reasons why medical professionals decided not to adopt an AI prediction, it is useful for managing medical professionals.

[0022] (6) The medical resource information includes single-function resources and multi-function resources, and the multi-function resources are defined as a set of interchangeable single-function resources. For example, a single-function resource would be a simple bed (a bed used only for specific patient care or treatment) or a nurse with actual experience in one medical department, while a multi-function resource would be a mixed bed (a bed that can treat patients from multiple medical departments), and a multi-function resource would be a nurse who rotates between multiple medical departments and is able to treat a variety of patients.Physicians who also see mixed wards and doctors who can perform multiple surgeries are also considered multi-function resources.

[0023] According to this invention, medical resource information includes simple and mixed beds, operating rooms, and skilled nurses, as well as resource increases resulting from medical administrative assistants and digital transformation tools. By comprehensively categorizing these resources into single-function and multi-function resources and defining multi-function resources as a set of interchangeable single-function resources, the allocation of complex resources can be simplified and resource management can be systematically and efficiently managed. While physician resources are valuable, the allocation of medical administrative assistants and the purchase of digital transformation tools can improve physician work efficiency, ultimately increasing the resources available at medical institutions. One aspect of this program also calculates and presents the increase in resources, enabling accurate estimation by increasing available resources with assistance.

[0024] (7) The decision is made with reference to selection support information obtained by linking the patient utilization forecast resource information with the available medical resource information. (8) The selection support information is at least one of the following: sales calculated from one or more of the prescription information, DPC information, and facility standard information stored in the database; expenses required to provide the medical resources required by the patient; and profits calculated by dividing expenses by sales. (9) In making the decision, reference is made to one or more forecast information of the sales forecast, the expenditure forecast, and the profit forecast.

[0025] Selection support information (including management indicator information) is income and expenditure data calculated by dividing the expenditure required to provide patients with the medical resources they need from the income, including receipts, calculated from data including DPC information and facility standard information stored in the database, and / or calculation results from past income and expenditure data based on past management indicator information. DPC information is information submitted by medical institutions to the payment fund, and is specifically information recorded in Form 1, Form 3, Form 4, E File, F File, D File, Outpatient E File, and Outpatient F File. Specifically, DPC information includes the following information: The first is information about each facility, such as the facility name and facility code. The second is information about each patient, such as date of birth, gender, height, weight, smoking index, pregnant woman information, newborn information, and elderly information. The third is information about each hospitalization for each patient, including the main illness, the illness that led to hospitalization, the illness that required the most medical resources, ICD10 code, modifier code, department that treated the illness that required the most medical resources, reason for hospitalization, purpose and progress of treatment, previous discharge, readmission survey, re-transfer survey, date of admission, payload, date of admission to the ward, date of admission, route of admission, whether or not referred from another hospital, whether or not admitted from the outpatient department of the hospital, whether or not admitted for planned or emergency medical care, whether or not transported by ambulance, whether or not self-harm or suicide attempt occurred, whether or not overdose occurred, date of discharge, destination of discharge, outcome at the time of discharge, whether or not home medical care was provided after discharge , whether or not there were repeated short-term hospitalizations (chemotherapy, radiotherapy, etc.), whether or not a clinical trial was conducted, whether or not the patient was admitted to a general ward that was the subject of the survey, whether or not the patient was admitted to a psychiatric ward, whether or not the patient was admitted to other wards, whether or not the patient had pressure ulcers, whether or not the patient had pressure ulcers at the time of admission, usage of medical resources, gestational age at the time of admission, birth weight, gestational age at birth, for the illness or injury that required the most medical resources, diagnostic information (comorbidities, sequelae, intractable diseases, etc.), anesthesia (intravenous anesthesia, spinal anesthesia, etc.), primary or recurrent cancer, TNM classification of cancer, whether or not chemotherapy was administered for cancer, severity of pneumonia, angina pectoris, patient information on chronic ischemic heart disease, modified Rankin Scale at the time of discharge, time of onset of heart failure, systolic blood pressure, heart rate, cardiac rhythm, dementia-friendly shared living care (group home), elderly day service center, whether or not the illness or injury that required the most medical resources was cured or improved, whether or not it was in remission, whether or not it remained unchanged, whether or not it worsened, information on death or death due to other causes, information on medications used, prescription details, and test details. In particular, the information on the drugs used, prescription details, and test details recorded in the EF file includes information on the drug resources and test resources actually used, making it useful for predicting drug resources and test resources.Regarding drug resource information, by adding information not included in the DPC information shown below, such as the prescribing physician, the prescribing physician's supervising physician, and the patient's attending physician, it is possible to clarify the decision maker for administering drug resources.

[0026] This invention improves hospital resource management efficiency by adding to each patient's DPC information information not originally included in the DPC information: the specific ward used, the specific nurse in charge, the nurse's patient experience, the attending physician, the attending physician's patient experience, ward clinical path information, information included in the electronic medical record template, electronic medical record progress notes, electronic medical record summary information, the contents of the electronic medical record profile section, electronic medical questionnaire information, consent / non-consent information regarding personal information, each medical institution's bed information, the prescribing physician, the prescribing physician's supervising physician, the patient's attending physician, resource information, image information, information converted from image information into text, hospital employee survey results, employee health check data, and communication frequency and sentiment analysis of employee chats. In particular, the information included in the template for the admission of an electronic medical record by the Admission and Discharge Support Center is useful for predicting the length of hospital stay. It also includes information on medical fee surcharges, which is useful for predicting management indicators. Information entered into the electronic medical questionnaire by the patient is also useful. Typically, patients are asked to fill out an electronic medical questionnaire once a morning while hospitalized. This allows for structured collection of information about their discharge wishes and changes in their physical condition, improving prediction accuracy. Furthermore, hospital employee survey information can be collected, including employee motivation, work status, dissatisfaction, willingness to implement work style reforms, and understanding of inspection procedures, which is effective for human resource management. Furthermore, by introducing employee chat systems, employee motivation can be assessed based on the frequency of communication and sentiment analysis of conversations, and this information can be used for resource management. Process mining based on this information can be used to perform detailed analysis of hospital workflows and resource usage, identifying continuous improvement measures to improve operational efficiency and the quality of patient care. Process mining technology can visualize operational procedures and resource consumption patterns in each hospital department, identifying wasteful processes and excess or insufficient resources.This analysis supports data-driven decision-making for optimizing operations and utilizing resources more effectively, enabling measures to improve the quality of patient care and reduce staff burden. Furthermore, waterfall charts can be used to visually display performance against targets for ward and operating room utilization rates, allowing for real-time monitoring and analysis of resource usage. Waterfall charts are ideal for clearly illustrating which components account for a large percentage of resources and which factors have the greatest impact on changes over time. Using these charts, the causes of low utilization rates or resource shortages over a specific period can be quickly identified and corrective measures implemented. For example, if a ward's utilization rate is low on a particular day or time, the causes can be analyzed and optimal data-driven improvements, such as adjusting staff allocation or patient admission and discharge schedules, can be implemented. It is also possible to search for similar patients based on patient information, and use the medical fee claim information and DPC information of those patients as reference information to assign medical fee claim information, DPC information, and management indicators to the currently viewed patient. At this time, it is also possible to specify the extent of similarity, present patients with good management indicators from the information of similar patients, and use that information as reference to assign medical fee claim information and DPC information to the currently viewed patient.

[0027] (10) The medical resource prediction is made by using one or more of the following information stored in the database: past prescription information, DPC information, facility standard information, clinical path information, bed utilization information, nurse information in charge, and surgery time; or one or more of the patient’s disease name, surgery name, DPC information, prescription information, clinical path, and electronic medical record template information, to predict one or more of the number of bed days, type of bed stay, surgery time, required nursing time, required nursing skills, sales, expenses, and profits. (11) The program makes the prediction using one or more of the patient's past prescription information, DPC information, facility standard information, and clinical path information stored in the database. (12) The program predicts one or more of sales, expenses, and profits using one or more of the patient's past prescription information, DPC information, facility standard information, and electronic medical record template information stored in the database.

[0028] (13) For the calculation of the above prediction, statistics are calculated by aggregating the past number of bed days, type of bed, operation time, primary doctor, primary nursing skill, sales, expenditures, and profits of patients whose disease name or the disease name with the most resources matches. "Statistics" are numerical indicators that represent the characteristics of data, and include the mean, median, mode, quantile, variance, and standard deviation. These are used to understand the central tendency, variance, and distribution of data. (14) To calculate the prediction, a similarity search is performed to obtain information on past patients, aggregate sales, expenses, and profits, and calculate statistics. Similarity search is the process of locating specific information within data or documents. Types of similarity search include full-text search, logical search, vector search, semantic search, match search, and regular expression search, each of which uses different algorithms and techniques to efficiently retrieve information. As a further form of search, when using progress notes and summary information from electronic medical records, multiple pathologies and symptoms are typically described in a single article. However, generative AI can be used to separate each pathology and related findings / test findings. Furthermore, test findings can be described by test name, adjective, findings, and location (e.g., CT = 2cm * hemorrhage @ brain). Using a large-scale multimodal model (LMM), it is possible to generate text by dividing image data into test names, adjectives, findings, and areas, and by searching this output as a single block, it is possible to search for cases with similar test findings.In addition, it is possible to implement a system that searches for the underlying pathology based on the above-mentioned "separately described information" to determine what causative pathology is present in cases with similar test findings, which is ultimately effective in naming DPC diseases.

[0029] (15) A machine learning model is trained for the calculation of the prediction, and the trained predictive machine learning model is used. According to the present invention, vector search maps data into a high-dimensional vector space and searches for information based on similarity, requiring multiple searches. Meanwhile, semantic search allows a search engine to understand the user's intent and query, rather than simply searching for keyword matches, and provides highly relevant information. For example, it is possible to extract and search for only abnormal findings. Regarding reference information, it is possible to search for similar patients in the past based on patient information, and use the medical fee claim information and DPC information of those patients as reference information to assign medical fee claim information, DPC information, and management indicators to the currently viewed patient. In this case, it is possible to specify the extent of similarity, obtain highly specific or highly sensitive reference information, select patients with good management indicators from that, and assign medical fee claim information and DPC information to the currently viewed patient from that patient's information.

[0030] (16) When calculating the information on available medical resources, the program analyzes image information captured inside one or more facilities, such as operating rooms, ICUs, or wards, converts it into category information, and works in conjunction with a function to evaluate the utilization rate of hospital beds or the degree of occupancy. (17) When calculating the information on available medical resources, the program performs image analysis (OCR processing) on ​​image information captured from one or more of the monitor information in the operating room, the monitor information in the ICU, and the monitor information in the ward, and works in conjunction with a function to evaluate the patient's vital signs. Image analysis includes classification, expression extraction using large multimodal models, clustering, time series analysis, object detection, person tracking, image classification, segmentation, OCR (optical character recognition), etc. By combining these methods, it is possible to determine whether a bed is available, how far a surgery is progressing, whether a patient is in the operating room, and how many nurses are assigned to the operating room or ward, thereby enabling a multifaceted evaluation of the utilization of medical resources and the efficiency of staffing.

[0031] According to the present invention, real-time information can be obtained through image analysis, and by evaluating the utilization status of hospital beds, the degree of occupancy, and the vital signs of patients, it contributes to more efficient hospital bed management.

[0032] In one embodiment of the program, when calculating the available medical resource information, the program has the function of extracting and outputting profile information / template information from electronic medical records as DPC information, and the function of periodically extracting, outputting, and saving the DPC information with an output time. As a result, it is possible to use as input for machine learning how an individual's DPC information has been entered, modified, and changed over time. As a result, machine learning can learn how the hospital manages and operates the DPC information, thereby improving prediction performance. In fact, this can improve prediction performance. In another embodiment, the DPC information can contain an anonymized hash ID obtained by hashing the patient ID as a seed. Information not included in the DPC information can also be assigned an anonymized hash ID by hashing the patient ID as a seed in a similar manner, and this anonymized hash ID can be used to link the DPC information to information not included in the DPC information. In fact, this can reduce the effort required to link information from which the patient ID has been removed. In another embodiment, the output of the DPC information can be added to group information and used in machine learning. Specifically, the drug information contained in the EF file includes drugs with various dosages and uses, but it is possible to assign group information to the products, such as "infusion drugs," "hypertension drugs," or "amlodipine (including multiple uses)," and then perform machine learning using this group information. In fact, doing this can improve prediction performance.

[0033] According to the present invention, DPC information and medical receipt information are payment information submitted to the payment fund once a month, and therefore are typically completed approximately once a month. On the other hand, electronic medical record data is recorded each time a medical professional examines a patient, and therefore is typically updated at least once a day during hospitalization. Furthermore, image data and data derived from image analysis of those images are typically updated in real time. Another feature of the present invention is the use of information with different output frequencies. Furthermore, DPC information and medical receipt information are matched and standardized, facilitating output, anonymization, and understanding of operations at each hospital. Because the information is standardized, implementation costs at each hospital can be reduced. Taking advantage of this, electronic medical record information and image analysis information can be linked to DPC information, enabling predictions based on real-time conditions. Furthermore, real-timeness is paramount for predictions; if a patient has already been discharged by the time a prediction is made, the prediction becomes meaningless. To address this issue, one aspect of the present invention allows DPC information to be periodically output and analyzed, and simultaneously linked to other real-time information, enabling year-by-year and time-series changes to be observed. By combining this function with a log of medical professionals' responses to matching and a record of the reasons for changes, it becomes possible to hold efficient retrospective meetings. Using waterfall and process mining, which are effective in improving the judgment abilities of medical professionals, AI makes improvements based on feedback.

[0034] (19) When calculating the information on available medical resources, the program has the function of aggregating and outputting either DPC information or prescription information from multiple hospitals based on search (query) information, and the function of not displaying aggregated values ​​below a threshold as specific numerical values ​​when aggregating and displaying the aggregated values.

[0035] According to this invention, by collecting and aggregating DPC information or medical insurance claim information from multiple hospitals, this information can be used to optimize hospital bed utilization as part of a regional medical plan. Furthermore, since collecting all medical insurance claim information may lead to resistance from each hospital to collecting this information, this invention also includes the implementation of a method that enables the provision of information by automatically masking, correcting, or omitting some information, i.e., by incorporating a hiding function.

[0036] (20) The program causes the processor to execute the following steps: a first step of replacing multi-function resources with one or more replaceable single-function resources to create a single-function resource dataset, a second step of predicting required medical resources for hospitalized patient candidates who require hospitalization based on the patient information, a third step of calculating required medical resources for each hospitalized patient candidate from among the hospitalized patient candidates, and a fourth step of identifying patients to be hospitalized based on the single-function resource dataset, the required medical resources for hospitalized patients, and the required medical resources, a fifth step of calculating patient-specific management indicators (selection support information) for the hospitalized patients, and a sixth step of displaying the patient-specific management indicators (selection support information) and accepting patient selection.

[0037] According to the present invention, the first step (creation of a single-function resource dataset) is effective in building a system that can handle multiple diseases. The second step (prediction of medical resources required for hospitalized patients) predicts the medical resources required for hospitalized patients, and the third step (calculation of medical resources required for each hospitalized patient candidate) calculates the medical resources required for hospitalized patients.

[0038] In the fourth step (identifying hospitalized patients), hospitalized patients are identified by performing a matching process using various information on the single-function resource dataset obtained in the first step, the medical resources required for hospitalized patients obtained in the second step, and the required medical resources obtained in the third step, and hospitalized patients that fit the remaining resources of the medical institution are presented. In addition, in the fifth step (calculation of management indicators by patient), management indicators are calculated for the hospitalized patients identified in the fourth step, and are linked to the management indicators for each patient, so that the relationship between the hospitalized patients and the management indicators is clearly presented at a glance, which will assist doctors and others in selecting hospitalized patients in the sixth step and will help doctors and others make decisions based on computer-generated resource predictions. [Effects of the Invention]

[0039] The program (information processing device and method) of the present invention has the effect of providing a hospital bed management system for optimizing the profits of medical institutions and efficiently supporting medical personnel in selecting medical resources and patients. [Brief explanation of the drawings]

[0040] [Figure 1] 1 is a diagram showing the overall configuration of a system according to an embodiment of the present invention; [Figure 2] FIG. 2 is a block diagram showing an example of the functional configuration of a server. [Figure 3] FIG. 1 is a diagram for explaining an overview of a hospital bed management system according to an embodiment of the present invention. [Figure 4] A diagram showing a patient placement status table for each hospital bed. [Figure 5] A diagram showing the relationship between medical resources and patients. [Figure 6] FIG. 1 is a diagram showing the relationship between patient data and management indicators and other information. [Figure 7] 10 is a flowchart showing a processing procedure of the hospital bed management system according to the present embodiment. BEST MODE FOR CARRYING OUT THE INVENTION

[0041] <System configuration> 1 is a diagram showing the overall configuration of a system 1 according to an embodiment of the present invention. In this system 1, a hospital-side terminal 10 and an external server 20 are connected via a wired / wireless network 80 such as the Internet. The server 20 is a server that functions as a web server (including a cloud server), and exchanges information with the terminal 10 via web pages. A web browser for viewing web pages is installed on the terminal 10, but a dedicated application for receiving services from the server 20 may also be installed, allowing the web pages to be viewed using the dedicated application.

[0042] Terminal 10 is a device operated by medical staff (doctors, nurses, laboratory technicians, office staff, assistants, etc.) at a medical institution, and is communicatively connected to server 20 via network 80. Terminal 10 is connected to network 80 by communicating with communication devices such as a wireless base station 81 compatible with various communication standards such as LTE, and a wireless LAN router compatible with IEEE or wireless LAN standards. Terminal 10 includes a communication IF 12, an input device 13, an output device 14, memory 15, a storage unit 16, and a processor 19. Terminal 10 may be a desktop or laptop PC, or a portable terminal such as a tablet or smartphone.

[0043] The communication IF 12 is an interface through which the terminal 10 communicates with external devices to input and output signals. The input device 13 is an input device (such as a keyboard, a touch panel, a touch pad, or a pointing device such as a mouse) for receiving input operations from a user. The output device 14 is an output device (such as a display or a speaker) for presenting information to a user. The memory 15 is for temporarily storing programs, data processed by the programs, etc., and is, for example, a volatile memory such as a DRAM. The storage unit 16 is a storage device for saving data, such as a flash memory or a HDD. The processor 19 is hardware for executing an instruction set written in a program, and is composed of an arithmetic unit, registers, peripheral circuits, etc.

[0044] The server 20 is managed by an administrator of the system 1 according to the embodiment of the present invention, and changes to the stored content, such as corrections, additions, and deletions of information, are made as appropriate by medical professionals who are users of the terminals 10. The server 20 may also have the functionality of an electronic medical record device, allowing medical professionals at medical facilities to view the input items and input content of the electronic medical record via a terminal device (not shown) and correct or add to the input content. The server 20 also accepts editing operations for the electronic medical record template and electronic questionnaire performed by the medical professionals via this terminal device, and corrects, adds, or deletes the stored content based on these editing operations.

[0045] The server 20 is a computer connected to a network 80 and includes a communication IF 22 , an input / output IF 23 , a memory 25 , a storage 26 , and a processor 29 .

[0046] The communication IF is an interface for inputting and outputting signals so that the server 20 can communicate with external devices. The input / output IF 23 functions as an interface with an input device for receiving input operations from a user and an output device for presenting information to the user. The memory 25 is for temporarily storing programs and data processed by the programs, etc., and is a volatile memory such as a DRAM. The storage 26 is a storage device for saving data, such as a flash memory or HDD. The processor 29 is hardware for executing an instruction set written in a program, and is composed of an arithmetic unit, registers, peripheral circuits, etc.

[0047] <Functional configuration of server 20> 2 is a block diagram showing an example of the functional configuration of server 20. Server 20 includes communication means 220, an input device 230, an output device 240, an audio processing unit 270 connected to a microphone 271 and a speaker 272, storage means 280, and control means 290, and each block is electrically connected by a bus or the like.

[0048] The communication means 220 performs modulation / demodulation processing and the like to enable the server 20 to communicate with other devices, performs transmission processing on signals calculated by the control means 290, and transmits the signals to external devices. The communication means 220 performs reception processing on signals received from the outside, and outputs the signals to the control means 290. In this way, the communication means 220 interprets commands or input contents and provides them to each means, and also functions as an interface that interprets various display commands issued from the storage means 280 and controls output.

[0049] The input device 230 is a device through which a user operating the server 20 inputs instructions or information, and may be a keyboard, mouse, reader, or touch-sensitive device. The input device 230 converts instructions input by the user into electrical signals and outputs the electrical signals to the control means 290. The input device 230 also includes a receiving port that receives electrical signals input from an external input device.

[0050] The output device 240 is a device such as a display 241 of an LCD or organic EL display for presenting information to a user who operates the server 20. The display 241 displays data according to the control content of the control means 290.

[0051] The audio processing unit 270 performs digital-to-analog conversion processing of the audio signal. It converts the signal provided from the microphone 271 into a digital signal and provides the converted signal to the control means 290. The audio processing unit 270 also provides the audio signal to the speaker 272. The audio processing unit 270 is realized by a processor for audio processing, and the microphone 271 accepts audio input and provides an audio signal corresponding to the audio input to the audio processing unit 270. The speaker 272 converts the audio signal provided from the audio processing unit 270 into audio and outputs the audio to an external device connected to the server 20.

[0052] The storage means 280 is realized by a memory (RAM) 25 and a storage 26 such as a disk device (floppy disk, hard disk, optical magnetic disk, etc.), and stores data, programs, etc. used by the server 20. The storage means 280 stores the application program of this system as well as data on facility standards, electronic medical records, DPC / receipts, hospital beds, patients, available medical resources (single-function resources, multi-function resources), predicted adoption / rejection logs / reasons, and clinical paths.

[0053] The control means 290 is realized by the processor 29 reading an application program stored in the storage means 280 and executing instructions included in the application program. The control means 290 also controls the operations of the server 20 and the terminal 10, and operates in accordance with the application program, thereby fulfilling the functions of an input operation reception unit, a transmission / reception unit, a data processing unit, a display control unit, a matching processing unit, a multi-function resource single-function allocation processing unit, a patient utilization prediction / required resource processing unit, a medical resource remaining amount calculation processing unit, and a selection support / management index calculation processing unit.

[0054] The input operation reception unit performs processing for receiving instructions or information input from the input device 230. Specifically, it receives information based on instructions input from a keyboard, a mouse, or the like. The input operation reception unit also receives voice instructions input from the microphone 271. Specifically, for example, it receives a voice signal input from the microphone 271 and converted into a digital signal by the voice processing unit 270. It also analyzes the received voice signal to extract a predetermined noun, thereby acquiring instructions from the user.

[0055] The transmitting / receiving unit performs processing for transmitting and receiving data according to a communication protocol by the server 20. Specifically, for example, the transmitting / receiving unit transmits content input by a user to the server 20 and receives information about the user from the server 20.

[0056] The data processing unit performs calculations on data that the server 20 has received as input in accordance with an application program, and outputs the calculation results to the memory 25 or the like.

[0057] The presentation control unit controls the output device 240 to present the information provided from the server 20 to the user. Specifically, for example, the presentation control unit causes the information transmitted from the server 20 to be displayed on the display 241. The presentation control unit also causes the information transmitted from the server 20 to be output from the speaker 272.

[0058] <Details of the hospital bed management system> Figure 3 is a diagram for explaining an overview of the hospital bed management system according to this embodiment, where (A) manages hospital beds for ICU patients / HCU patients, and (B) manages hospital beds for gastrointestinal patients / cardiovascular patients. The list of patients who are candidates for admission shows the predicted management indicators for each patient (profit = sales - cost) as selection support information.

[0059] In other words, in the example of Figure 3(A), if the ICU / HCU can accommodate 20 admissions, and based on the available medical resource information, 10 can be admitted to the ICU and 10 to the HCU, and 8 ICU patients are following clinical paths, 8 HCU patients are following clinical paths, and 1 doctor is following a schedule, the system predicts that 5 ICU patients will be admitted on the first day, 4 on the second day, 2 on the third day, and 1 on the fourth day and thereafter (total number of patients), while the doctor's schedule is to admit 2 ICU patients on the first day, 4 on the second day, 1 on the third day, and 1 on the fourth day and thereafter (total number of patients), and the decision on which patients to admit is made based on the management indicator forecast. In this case, the patient to be admitted is decided based on the list of candidate patients to be admitted, while referring to the patient-specific management indicator forecast for each patient. In addition, in the example of Figure 3(B), if it is possible to admit patients to 6 gastrointestinal beds, 6 cardiology beds, and 5 mixed beds, and based on the medical resource information available, 10 gastrointestinal patients and 10 cardiology patients can be admitted, and 8 gastrointestinal patients and 8 cardiology patients are following clinical paths, and 1 is following a doctor's schedule, the system predicts that 5 gastrointestinal patients will be admitted on the first day, 4 on the second day, 2 on the third day, and 1 on the fourth day or later (total number of patients), while the doctor's schedule is to admit 2 on the first day, 4 on the second day, 1 on the third day, and 1 on the fourth day or later (total number of patients), and the decision on which patient to admit to which bed is based on the management indicator prediction. Furthermore, while the system predicts that three cardiovascular patients will be admitted on the first day, four on the second day, two on the third day, and one on the fourth day or later (total number), the doctor's plan is to admit two on the first day, four on the second day, two on the third day, and one on the fourth day or later (total number). The system then decides which patients to admit to which beds based on the management indicator forecast. In this case, the system determines which patients to admit based on the list of potential patients for admission, while referencing the management indicator forecast for each patient. For example, if gastrointestinal patients 1, 2, and 3 and cardiovascular patients 1 and 2 are given priority, cardiovascular patient 3, who has a poor management indicator forecast, is excluded from the system as a patient to be admitted, and efforts are made to collaborate with other medical institutions. FIG. 3 shows an example of management indicators, in which forecast profits, forecast sales, costs, and forecast bed occupancy are recorded in a table, and at least one of these items can be displayed in a list.

[0060] Figure 4 shows a patient allocation table for each hospital bed, showing the results of calculations on which beds patients (P01 to P15) should be allocated to in order to use hospital beds efficiently. Here, for each day's prediction, a computer calculates the number of days the patient will stay in bed based on DPC information, etc., and allocates the bed. The schedule for each day is decided by a doctor based on the computer's prediction. The bed utilization status for the next day and beyond is shown by combining the computer's prediction and the doctor's schedule. At this time, if a bed is expected to be available, the bed into which the patient will be admitted is decided by selecting the patient with the best management index from among the candidate inpatients. When using a clinical path, the schedule is decided for several days in advance.

[0061] In the example of Figure 4(A), patient P14 is placed in the hospital bed for hospitalization 01 on days when there is a vacant bed for patient P01 (dashed block), patient P15 is placed in the hospital bed for hospitalization 02 on days when there is a vacant bed for patient P02 (dashed block), patient P12 is placed next to patient P05 in the hospital bed for hospitalization 05 (dashed block), and patient P06 is not placed on days when there is a vacant bed for patient P06 (dashed block). The patient to be placed is determined by extracting it from the list shown in Figure 4(B) (a list that combines patient data, bed admission predictions, and management indicators).

[0062] Figures 5 and 6 show the data structure underlying the list shown in Figure 4(B). Figure 5 shows the relationship between medical resources (diseases, available hospital beds, and used / unused status) and patients, and Figure 6 shows the relationship between patient data (patient name, gender, age, occupation, expected hospital bed, desired bed, desired timing, etc.) and management indicators (sales, cost, profit, profit rate) and other information (priority, category, availability of hospitalization on weekends). The input information for the input items is entered directly by medical professionals using the input device 13, 230, or data entered using the input device 13 is acquired by the server 20 via the network 80. For convenience, the black-colored cells in Figures 5 and 6 highlight patients P14, P15, and P12 as potential patients for hospitalization before admission, and these patients are placed in available resources in Figure 4(A).

[0063] As shown in Figure 5, the predicted 〇 / planned 〇 (dashed block B1) for patient P01 means that the computer predicts that the patient will need to stay in bed for a certain period of time, and the doctor has already scheduled it, so the patient will continue to stay in bed to secure medical resources. There is a possibility that the doctor will later cancel the resource and change the schedule from 〇 to ​​-, but normally this resource will be used for patient P01. The reason why patient P09 is predicted as 0 / planned as - (dashed block part B2) is that the computer predicts that the patient will need to stay in bed for a certain period of time, but the plan does not yet determine whether the patient will continue to stay in bed. After this, the doctor may approve the patient's stay in bed, and the plan may change from - to 0. If the plan is - instead of the predicted 0, the log and reason are recorded in the prediction acceptance / rejection log / reason data 288. The reason why patient P12 is predicted - / planned ◯ (dashed block part B3) is that the computer prediction may indicate that the patient does not need to be discharged / admitted, but the hospital's clinical pathway expects the patient to continue to stay in bed. In such cases, the log and reason may be recorded in the prediction acceptance / rejection log / reason data 288.

[0064] In other words, the agreement / inconsistency between the computer prediction and the doctor's schedule is the result of the doctor's judgment on whether or not a patient needs to stay in bed, and if the hospitalization prediction is not approved, it is saved as not being scheduled. The authority to approve the prediction and change it to a schedule can be a medical professional or a medical assistant directly under the doctor.

[0065] As shown in Figure 6, in addition to a list of patient data that is always available and linked to management indicators, other information (priority, category, availability of hospitalization on weekends) is also available to a limited extent, and when doctors and others make schedule decisions, the order and sorting of the display can be determined based on this other information.

[0066] Medical resources include physical resources such as bed types (simple beds, mixed beds), operating rooms, and examination rooms, as well as human resources such as skilled nurses and doctors, and the available medical resources are calculated based on the operating situation on the day. Also, pre-admission beds are temporary beds for patients who are temporarily admitted from a list of candidate patients before they are officially admitted.

[0067] 7 is a flowchart showing the processing procedure of the hospital bed management system according to this embodiment. In this system, a control means 290 performs processing of each processing unit using a server 20 connected to a communication line such as the Internet.

[0068] First, a definition process is performed to define multifunctional medical resources as a collection of single-function medical resources (step SA701). The definition process performed by the multifunctional resource single-function allocation processor 296 refers to the resource data stored in the single-function resource data 286 and the multifunctional resource data 287, and the AI ​​performs optimal allocation and definition based on past definition examples and cases. The AI ​​learning model is stored as an example of linking the single-function resource data 286 and the multifunctional resource data 287, and is updated by the AI ​​through machine learning using the prediction acceptance / rejection log / reason data 288.

[0069] Next, a set of available single-function resources is calculated (step SA702). If the single-function resource obtained as a result of the definition process performed by the multifunctional resource single-function allocation processing unit 296 is available for provision, a possible flag of "1" is set, and if it is not available, a not possible flag of "0" is set. The availability of the resource at the medical institution is determined by referring to the DPC information 283 and the hospital bed data 284.

[0070] Next, available medical resources are selected (step SA703). For single-function resources flagged "1" by the multi-function resource single-function allocation processor 296, available medical resources are selected from physical resources, human resources, and the like. The remaining medical resource calculation processor 298 also analyzes image information captured inside one or more facilities, such as operating rooms, ICUs, and wards, converting it into category information and evaluating the availability and availability of medical resources by assessing the utilization status of hospital beds or the degree of overcrowding. This also contributes to the selection of available medical resources. Furthermore, image analysis to evaluate the patient's vital signs and AI to calculate and predict the future remaining available medical resources also contribute to the calculation of available medical resource information in real time. This allows medical personnel to check available medical resource information in real time, which helps determine whether to accept a patient after the medical resources required by the patient have been determined.

[0071] The processing content of the multifunctional resource single-function allocation processing unit 296 in steps SA701 to SA703 is executed as task A processing of a program that defines multifunctional resources as a set of single-function resources and presents them as available medical resources.

[0072] Meanwhile, task B processing is executed separately / in parallel with task A processing. First, patient data is input to patient data 285 in storage means 280 (step SB701). The patient data is stored as patient data 285 by acquiring input information from input device 13 of terminal 10 or patient data stored in storage unit 16. As patient data, information such as patient name, sex, age, occupation, expected hospital bed, desired bed, desired time, etc., as shown in FIG. 6, is stored.

[0073] Next, for the patient in the input / acquired patient data, a determination is made as to whether a clinical pathway (CP) is required (step SB702). If a clinical pathway is required, the clinical pathway is entered (step SB704). If a clinical pathway is not required, the medical resources required for the patient are predicted and patient utilization prediction resources are calculated (step SB703). The patient utilization prediction / schedule / decision resource processing unit 297 calculates the medical resources required for the patient by referencing the electronic medical record data 282, DPC / receipt 283, etc. For prediction, the past number of hospital bed days, type of hospital bed, operation time, primary physician, primary nursing skill, sales, expenses, and profits of patients matching the disease name or the disease name with the most medical resource input are compiled, and statistics are calculated to make a prediction. For the prediction calculation, a similarity search is performed using semantic search and vector search to obtain information on past patients, and sales, expenses, and profits are compiled to calculate statistics.

[0074] In the CP judgment (step SB702), the computer makes a priority judgment on the clinical path information by referring to information from the electronic medical record data 282, AI prediction information based on DPC information, or information pre-registered as clinical path data 288, or a doctor or other person makes the judgment directly.

[0075] Next, the medical resources required by the patient are determined (step SB705). This is performed by the patient utilization prediction / schedule / determined resource processing unit 297, which determines the medical resources required by the patient by referencing the patient data 285 and electronic medical record data 282 when the predicted patient utilization resources required are calculated (step SB703) or a technical path is input (step SB704). Alternatively, when CP determination is not required, the calculated predicted patient utilization resources may be determined as the medical resources required by the patient.

[0076] The electronic medical record data 282 includes an electronic medical record template, and the input items and input contents of the electronic medical record template include medical receipt information, DPC information, facility standard information, and clinical path information. The profile information of the electronic medical record can be extracted and output as DPC information.

[0077] The processing content of the patient necessary medical resource calculation processing unit performed in steps SB701 to SB705 is executed as task B processing for linking a patient with the medical resources required by the patient.

[0078] The execution results of both tasks are obtained by processing tasks A and B, and a matching process is performed between them (step S707). Matching is performed by a data processing unit or the like, and the computer determines whether the medical resources available to the medical institution (task A) match the medical resources required by the patient (task B) (step S708). If the result of the determination is that the available medical resources match the medical resources required by the patient, the matching is determined to be successful, and processing may be performed to link the medical resources required by the patient with management indicators. The selection support / management indicator calculation processing unit 299 calculates selection support information (management indicators) when providing the medical resources required by the patient.

[0079] If it is determined in step S708 that the available medical resources and the patient-required medical resources do not match, the matching process (step S707) is executed again to substitute similar medical resources. For example, if the available medical resources do not match but there are substitute human resources, the data processing unit, etc. performs the substitution and matching, and determines that the match is possible.

[0080] Next, the selection support / management index calculation processing unit 299 updates the selection support information and management indexes in response to successful matching with the patient-needed medical resource information generated in step S705, and the doctor or other person refers to the result of the linking process between the matching result and the selection support information (management index), changes the patient-usage predicted resources to the patient-usage planned resources, and schedules the patient's admission (step S710). As a result, the patient-usage planned resources are scheduled (step S710), the patient selection and prediction → schedule change process is completed, and this subroutine ends.

[0081] The results of linking the medical resources required by the patient from among the medical resources available to the selection support information (management indicators) are visualized by displaying them on an output device 240 such as a display 241, and await acceptance of the selection by a doctor or other such person. Once a selection is made, the computer determines the status of the prediction as scheduled and decides to accept the patient's selection (step S711), and then ends this subroutine.

[0082] On the other hand, if it is determined in step S709 that the patient is not acceptable, the system records a log of the refusal and prompts the medical staff to enter the reason for the refusal (step S711), after which the subroutine ends. [Industrial Applicability]

[0083] The present invention is useful for contributing to the optimization of profits of medical institutions and for supporting medical professionals in selecting patients and medical resources from the perspective of improving management efficiency.

[0084] [Appendix A1] 1. A method implemented by a computer having a processor and a memory, comprising: The memory stores a database, The database stores patient information and information on available medical resources that can be provided to patients by medical institutions, The program includes a step of calculating predicted medical resources required for the patient as patient utilization predicted resource information based on the input patient information; a step of matching the patient utilization prediction resource information with the available medical resource information and presenting the matching result to a medical professional; and receiving input from a medical professional and making a change from the predicted patient utilization resource information to one or more of planned patient utilization resource information or determined patient utilization resource information. [Appendix A2] The database stores past DPC information or receipt information of medical institutions, The method described in Appendix A1, characterized in that the patient utilization prediction resource information is calculated based on the patient's past DPC information or prescription information. [Appendix A3] The database stores electronic medical record information, The program has a function of extracting and outputting information into DPC information based on electronic medical record information, The method according to appendices A1 and A2, wherein the DPC information includes consent or non-consent information regarding secondary use of personal information output from electronic medical record information. [Appendix A4] The method according to any one of claims A1 to A3, wherein the change is made by changing the prediction into a schedule, thereby allowing the patient's choice to be accepted. [Appendix A5] When the prediction is not changed to a plan in response to a change in notes A1 to A3, the method is characterized by having the system perform one or more of the following: recording a log; or requesting a medical professional to input a reason and recording the response. [Appendix A6] A method characterized in that the available medical resource information of Supplements A1 to A3 includes single-function resources and multi-function resources, and the multi-function resources are defined as a set of one or more interchangeable single-function resources. [Appendix A7] A method characterized in that the determination of Supplementary Notes A1 to A3 is made by referring to selection support information obtained by linking the patient utilization predicted resource information with the available medical resource information. [Appendix A8] A method characterized in that the selection support information in Appendix A7 is at least one of sales calculated from one or more of prescription information, DPC information, and facility standard information stored in the database, expenses required to provide the medical resources required by the patient, and profit obtained by dividing expenses by sales. [Appendix A9] A method characterized in that the determination in Appendix A7 refers to one or more forecast information of the sales forecast, the expenditure forecast, and the profit forecast. [Appendix A10] The medical resource predictions in the appendices A1 to A3 are: One or more of the following information stored in the database: past prescription information, DPC information, facility standard information, clinical path information, hospital bed usage information, nurse information, and surgery time; Or, one or more of the following information: the patient's disease name, surgery name, DPC information, receipt information, clinical path, electronic medical record template information, The method is characterized by using the above to predict one or more of the number of bed days, type of bed, operation time, required nursing time, required nursing skills, sales, expenses, and profits. [Appendix A11] The method of Appendix A10 is characterized in that the prediction is made using one or more of the patient's past prescription information, DPC information, facility standard information, and clinical path information stored in the database. [Appendix A12] The method of Appendix A10 is characterized by predicting one or more of sales, expenses, and profits using one or more of past prescription information, DPC information, facility standard information, and electronic medical record template information of patients who have previously used medical resources at the medical institution, which are stored in the database. [Appendix A13] For the calculation of the prediction in Appendix A10, a method for calculating statistics by aggregating the number of days spent in a hospital bed in the past, the type of hospital bed, the duration of surgery, the primary doctor, the primary nursing skill, sales, expenses, and profits of patients who have used resources at a medical institution in the past and whose disease name matches either the name of the disease that has received the most resources. [Appendix A14] A method for calculating the prediction in Appendix A10, characterized in that a search is performed using a similarity search on patients who have used resources at the medical institution in the past to obtain information on past patients, and sales, expenses, and profits are aggregated to calculate statistics. [Appendix A15] A method characterized in that, for calculating the prediction in Appendix A10, a machine learning model is trained using resource usage information of patients who have previously used resources at a medical institution, and the trained predictive machine learning model is used. [Appendix A16] When calculating the available medical resource information in Supplementary Notes A1 to A3, A method characterized by analyzing image information captured inside one or more facilities, such as operating rooms, ICUs, or hospital wards (converting it into category information) and linking it to a function that evaluates the utilization of hospital beds or the degree of occupancy of people. [Appendix A17] When calculating the available medical resource information in Supplementary Notes A1 to A3, A method characterized by performing OCR on image information captured from one or more of the following monitor information: operating room monitor information, ICU monitor information, and ward monitor information, and linking this to a function for evaluating a patient's vital signs. [Appendix A18] When calculating the available medical resource information in Supplementary Notes A1 to A3, A method characterized by having a function to extract and output profile information from an electronic medical record as DPC information, and a function to periodically assign an output time to the DPC information and extract and output it. [Appendix A19] When calculating the available medical resource information in Supplementary Notes A1 to A3, Based on search query information, it has the function of aggregating and outputting either DPC information or receipt information from multiple hospitals, A method characterized by having a function of not displaying aggregated values ​​that are below a threshold as specific numerical values ​​during aggregation. [Appendix A20] The processor of the appendix A1 to A19, a first step of replacing a multi-function resource with one or more substitutable single-function resources to create a single-function resource dataset; A second step of predicting the medical resources required for a candidate patient who needs to be admitted to a hospital based on the patient information; A third step of calculating the required medical resources for each of the hospitalized patient candidates from the hospitalized patient candidates; a fourth step of identifying an admitted patient from the single-function resource data set, the admitted patient's required medical resources, and the required medical resources; How to make it run.

[0085] The term "computer" below is synonymous with "information processing device" and also refers to a "system" formed by the cooperation of computers. [Appendix B1] A computer comprising a processor and a memory, The memory stores a database, The database stores patient information and information on available medical resources that can be provided to patients by medical institutions, The program has a function of calculating predicted medical resources required for a patient as patient utilization predicted resource information based on the input patient information; a function of matching the patient utilization prediction resource information with the available medical resource information and presenting the matching result to a medical professional; A computer that executes a program having the function of accepting input from a medical professional and changing the patient utilization predicted resource information to one or more of patient utilization planned resource information or patient utilization determined resource information. [Appendix B2] The database stores past DPC information or receipt information of medical institutions, A computer that executes the program described in Appendix B1, which has the function of calculating the patient utilization prediction resource information based on the patient's past DPC information or prescription information. [Appendix B3] The database stores electronic medical record information, The program has a function of extracting and outputting information into DPC information based on electronic medical record information, The computer according to appendix B1 or B2, wherein the DPC information includes consent or non-consent information regarding secondary use of personal information output from electronic medical record information. [Appendix B4] The computer is characterized in that the change in the appendices B1 to B3 is made by changing the prediction into a schedule to accommodate a patient's choice. [Appendix B5] When the prediction is not changed to a plan in response to a change in any of the appendices B1 to B3, the computer performs one or more of the following: recording a log; or requesting a medical professional to input a reason and recording the response. [Appendix B6] A computer characterized in that the available medical resource information of Supplementary Notes B1 to B3 includes single-function resources and multi-function resources, and the multi-function resources are defined as a set of one or more replaceable single-function resources. [Appendix B7] A computer characterized in that the decision of Supplementary Notes B1 to B3 is made by referring to selection support information obtained by linking the patient utilization predicted resource information with the available medical resource information. [Appendix B8] A computer characterized in that the selection support information in Appendix B6 is at least one of sales calculated from one or more of prescription information, DPC information, and facility standard information stored in the database, expenses required to provide the medical resources required by the patient, and profit obtained by dividing expenses by sales. [Appendix B9] A computer characterized in that, when making the decision in Addendum B7, it refers to one or more forecast information of the sales forecast, the expenditure forecast, and the profit forecast. [Appendix B10] The medical resource predictions in Supplementary Notes B1 to B3 include: One or more of the following information stored in the database: past prescription information, DPC information, facility standard information, clinical path information, hospital bed usage information, nurse information, and surgery time; Or, one or more of the following information: the patient's disease name, surgery name, DPC information, receipt information, clinical path, electronic medical record template information, The computer is characterized by using the above to predict one or more of the following: length of stay in bed, type of stay in bed, surgery time, required nursing time, required nursing skills, sales, expenses, and profits. [Appendix B11] The computer of Appendix B10 is characterized in that it makes the prediction using one or more of the patient's past prescription information, DPC information, facility standard information, and clinical path information stored in the database. [Appendix B12] The computer of Appendix B10 is characterized by predicting one or more of sales, expenses, and profits using one or more of prescription information, DPC information, facility standard information, and electronic medical record template information of patients who have previously used medical resources at the medical institution, which are stored in the database. [Appendix B13] For the calculation of the prediction in Appendix B10, a computer that calculates statistics by aggregating the number of days spent in a hospital bed in the past, the type of hospital bed, the duration of surgery, the primary doctor, the primary nursing skill, sales, expenses, and profits of patients who have used resources at a medical institution in the past and whose disease name matches either the name of the disease that has received the most resources. [Appendix B14] A computer characterized by performing a search using a similarity search for patients who have used resources at a medical institution in the past to obtain information on past patients, aggregating sales, expenses, and profits, and calculating statistics for the calculation of the prediction in Appendix B10. [Appendix B15] A computer characterized by training a machine learning model using resource usage information of patients who have previously used resources at a medical institution for calculating the prediction in Appendix B10, and using the trained predictive machine learning model. [Appendix B16] When calculating the available medical resource information in Supplementary Notes B1 to B3, A computer that is characterized by its ability to analyze image information captured inside one or more facilities, such as operating rooms, ICUs, or hospital wards (converting it into category information) and to evaluate the utilization of hospital beds or the degree of occupancy. [Appendix B17] When calculating the available medical resource information in Supplementary Notes B1 to B3, A computer characterized by its ability to analyze (OCR) image information captured from one or more of the following monitor information: operating room monitor information, ICU monitor information, and ward monitor information, and to work in conjunction with a function to evaluate a patient's vital signs. [Appendix B18] When calculating the available medical resource information in Supplementary Notes B1 to B3, A computer having a function to extract profile information from an electronic medical record as DPC information and output it, and a function to periodically assign an output time to the DPC information and extract and output it. [Appendix B19] When calculating the available medical resource information in Supplementary Notes B1 to B3, Based on search query information, it has the function of aggregating and outputting either DPC information or receipt information from multiple hospitals, A computer characterized by having a function of not displaying aggregated values ​​that are below a threshold as specific numerical values ​​when aggregating. [Appendix B20] The processor of the appendices B1 to B19 is a first step of replacing a multi-function resource with one or more substitutable single-function resources to create a single-function resource dataset; A second step of predicting the medical resources required for a candidate patient who needs to be admitted to a hospital based on the patient information; A third step of calculating the required medical resources for each of the hospitalized patient candidates from the hospitalized patient candidates; a fourth step of identifying an admitted patient from the single-function resource data set, the admitted patient's required medical resources, and the required medical resources; A computer that runs [Explanation of symbols]

[0086] 10: Terminal (13: Input device, 14: Output device, 15: Memory, 16: Storage unit, 19: Processor) 20: Server (25: Memory, 26: Storage, 29: Processor) 80: Internet network, 81: wireless base station

Claims

1. A program for operating a computer having a processor and a memory, The memory stores a database, The database stores patient information and information on available medical resources that can be provided to patients by medical institutions, The program has a function of calculating predicted medical resources required for a patient as patient utilization predicted resource information based on the input patient information; a function of matching the patient utilization prediction resource information with the available medical resource information and presenting the matching result to a medical professional; A program characterized by having a function of accepting input from a medical professional and changing the patient utilization predicted resource information to one or more of patient utilization planned resource information or patient utilization determined resource information.

2. The database stores past DPC information or receipt information of medical institutions, 2. The program according to claim 1, wherein the patient utilization prediction resource information is calculated based on the patient's past DPC information or prescription information.

3. The database stores electronic medical record information, The program has a function of outputting information to DPC information based on electronic medical record information, 3. The program according to claim 1, wherein the DPC information includes consent or non-consent information regarding secondary use of personal information output from electronic medical record information.

4. 3. The program according to claim 1, wherein the change is made by changing the prediction that uses the patient-usage predicted resource information as patient-usage planned resource information into a schedule to accept the patient's selection.

5. The program according to claim 1 or 2, characterized in that, when the change is made, if the prediction that uses the patient utilization predicted resource information as the patient utilization planned resource information is not changed to the plan, the program performs one or more of the following: recording a log, or asking a medical professional to input a reason and recording the response.

6. 3. The program according to claim 1, wherein the available medical resource information includes single-function resources and multi-function resources, and the multi-function resources are defined as a set of one or more replaceable single-function resources.

7. 3. The program according to claim 1, wherein the medical resources required by a patient are determined by referring to selection support information obtained by linking the patient-usage predicted resource information with the available medical resource information.

8. The program described in claim 7, characterized in that the selection support information is at least one of sales calculated from one or more of prescription information, DPC information, and facility standard information stored in the database, expenses required to provide the medical resources needed by the patient, and profits calculated by dividing expenses by sales.

9. 9. The program according to claim 8, wherein the determination of the medical resources required for the patient is made by referring to one or more forecast information of the sales forecast, the expenditure forecast, and the profit forecast.

10. The prediction of medical resources is based on one or more pieces of information stored in the database, such as past receipt information, DPC information, facility standard information, clinical path information, hospital bed utilization information, nurse information, and surgery time. Or, one or more of the patient's disease name, surgery name, DPC information, receipt information, clinical path information, and electronic medical record template information, The program according to claim 1 or 2, characterized in that by using the program, one or more of the following is predicted: length of stay in bed, type of stay in bed, surgery time, required nursing time, required nursing skills, sales, expenses, and profits.

11. The program is characterized in that the prediction is made using one or more of the patient's past prescription information, DPC information, facility standard information, and clinical path information stored in the database, Presenting clinical path information as the selection support information; The program described in claim 7, characterized in that it accepts input from medical professionals and changes the patient usage predicted resource information in one go to one or more of patient usage planned resource information or patient usage determined resource information based on clinical path information.

12. The program of claim 10, characterized in that the program predicts one or more of sales, expenses, and profits using one or more of prescription information, DPC information, facility standard information, and electronic medical record template information of patients who have previously used medical resources at the medical institution, which are stored in the database.

13. The program of claim 10, wherein for calculating the prediction, statistics are calculated by aggregating the number of days spent in a bed, type of bed, operation time, primary doctor, primary nursing skill, sales, expenditures, and profits of patients who have used resources at a medical institution in the past and whose disease name matches either the name of the disease that has invested the most resources.

14. The program according to claim 10, characterized in that, for calculating the prediction, a search is performed using a similarity search for patients who have used resources at the medical institution in the past to obtain information on past patients, and sales, expenses, and profits are compiled to calculate statistics.

15. The program of claim 10, characterized in that for the calculation of the prediction, a machine learning model is trained using resource usage information of patients who have previously used resources at a medical institution, and the trained predictive machine learning model is used.

16. The program, when calculating the available medical resource information, The program according to claim 1 or 2, characterized in that it is linked to a function for analyzing image information captured inside one or more facilities, such as an operating room, an ICU, or a hospital ward, and evaluating the utilization status of hospital beds or the degree of occupancy of people.

17. The program, when calculating the available medical resource information, 3. The program according to claim 1, further comprising a function for obtaining vital signs of a patient by performing OCR on image information captured from one or more of the monitor information in the operating room, the monitor information in the ICU, and the monitor information in the ward.

18. The program, when calculating the available medical resource information, 3. The program according to claim 1, further comprising a function for extracting profile information from an electronic medical record and outputting it as DPC information, and a function for periodically outputting the DPC information with an output time.

19. The program, when calculating the available medical resource information, A function to aggregate and output either DPC information or receipt information from multiple hospitals based on search query information, 3. The program according to claim 1, further comprising a function of not displaying a total value that is less than a threshold value as a specific numerical value during the calculation.

20. The program according to claim 1 or 2, wherein the processor: a first step of replacing a multi-function resource with one or more substitutable single-function resources to create a single-function resource data set; A second step of predicting the required medical resources for a candidate patient who needs to be admitted to a hospital based on the patient information; A third step of calculating the required medical resources for each of the hospitalized patient candidates from among the hospitalized patient candidates; a fourth step of identifying an admitted patient from the single-function resource data set, the admitted patient's required medical resources, and the required medical resources; A program that executes.

Images