A hospital management support system, hospital management support method, program, and recording medium containing the program, which visualize the hospital's management status and support the decision-making process for allocating medical resources.

Abstract

In hospital management, traditional methods made it difficult to identify the causes of resource surpluses or shortages, or declines in revenue. However, by understanding the profitability and workload of each clinical department / group and optimizing resource allocation, we can improve management efficiency and maintain the quality of medical services. [Solution] The present invention provides a hospital management support system that visualizes the status of hospital management and supports efficient resource allocation based on data. It includes a profit simulation means 295 that manages the revenue and workload of each clinical department / clinical group and calculates the profit for each medical resource, and an alert processing means 293 that detects and notifies of abnormalities in profitability and workload. The profit simulation means 295 has the function of analyzing the resource allocation and profitability of each clinical department / clinical group and predicting changes in profit when resources are moved, thereby enabling revenue improvement through efficient reallocation of resources and visualizing measures to improve hospital management.

Description

Technical Field

[0001] The present invention relates to a hospital management support system that visualizes the operating conditions of a hospital and supports decision-making regarding the allocation of medical resources such as doctors, nurses, hospital beds, operating rooms, etc. More specifically, it relates to a hospital management support tool (system, program, method) that integrally manages revenue information and medical resource information, dynamically calculates and updates management indicators for visualization, and supports the formulation of management improvement measures and the consideration of resource reallocation in real time. The present invention is not limited to the medical field and is also applicable to the allocation of business operation resources such as airport operation, manufacturing, accommodation and retail, call centers, data centers, etc.

Background Art

[0002] Conventionally, in hospital management, in order to grasp the profitability and cost structure of each medical department, basic indicators related to hospital management (for example, hospital bed occupancy rate, average length of stay, patient unit price, profit rate, etc.) are analyzed, and a system that aggregates and analyzes various management indicators such as sales, expenses, number of patients, occupancy rate, etc. is used.

[0003] Patent Document 1 enables extremely easy comparison with other hospitals and comparison between medical department sections within the same hospital by performing evaluations based on RMP (medical revenue per yen of labor cost) and RIP (capital invested per yen of labor cost). RMP contributes to numerical improvement by achieving high revenue with low labor costs, and RIP contributes to numerical improvement by efficiently utilizing capital (medical departments with high capital efficiency and medical departments that require facility investment) with low labor costs.

[0004] Non-Patent Document 1 discloses a method of numerically quantifying some aspects of the functions of a hospital from viewpoints such as "functionality", "profitability", "productivity", "safety", etc., organizing the indicators of each medical department and section, and performing management analysis.

Prior Art Documents

Patent Documents

[0005] [Patent Document 1] Japanese Patent Publication No. 2010-218448

[0006] [Non-Patent Document 1] Yumiko Utsu, Nursing BUSiNESS Autumn 2021 Special Issue, Reference Number "Nursing Managers Who Control Data Control Ward Management: Solving Human, Material, and Financial Problems! An Introduction to Data Analysis and Utilization", No. 214, 1st Edition, Medica Publishing Co., Ltd., November 10, 2021, pp. 68-72, 91-95, 130-135. [Overview of the project] [Problems that the invention aims to solve]

[0007] However, while the granular patient analysis and indicators (RMP and RIP) disclosed in Patent Document 1 are desirable as means of indirectly achieving both quality and profitability of medical services from the standpoint of profitability and cost efficiency, they do not directly improve profit volatility through the efficiency of medical resources. In other words, it is expected that appropriate resource allocation while maintaining the quality of medical care will increase patient satisfaction and have a positive impact on revenue through an increase in repeat patients and referred patients. Furthermore, the efficiency of resources will have ripple effects not only on specific medical departments or patients, but on the operation of the entire hospital. For example, by optimizing hospital beds, medical equipment, and treatment spaces, it is expected that the speed and responsiveness of treatment will be improved in all medical departments while keeping costs down and increasing revenue.

[0008] Furthermore, the technology disclosed in Non-Patent Document 1 is limited to the calculation and comparative analysis of static management indicators based primarily on past performance data, and does not provide a mechanism for dynamically changing the allocation of medical resources (number of doctors, nurses, hospital beds, operating rooms, etc.) to predict and evaluate management effects. Therefore, when managers and others consider reallocating or increasing / decreasing medical resources, it is difficult to grasp changes in indicators immediately, and it has not yet reached the point of supporting real-time decisions on optimal resource allocation.

[0009] Furthermore, many conventional systems lacked an interactive user interface capable of simultaneously handling resource changes across multiple clinical departments, requiring manual comparison of multiple scenarios. This prevented real-time visualization and comparison of the impact of resource allocation changes on the overall management, hindering the acceleration of decision-making.

[0010] Furthermore, while focusing on granular patient analysis and metrics (RMP and RIP) may yield temporary revenue improvements, resource efficiency alone cannot be expected to lead to medium- to long-term stability for the hospital as a whole. Optimizing resource allocation and improving or reducing bottlenecks that result in unprofitable operations and unnecessary costs is expected to lead to long-term stability and improved profitability for the hospital. In particular, efficient resource allocation reduces the burden on healthcare professionals. For example, if the bed occupancy rate is appropriate, the workload of patient care is distributed, easing the burden on doctors and nurses and making it easier to provide high-quality medical care. This also contributes to lower turnover rates and improved morale among healthcare professionals.

[0011] Furthermore, by optimizing resource utilization, unnecessary costs can be reduced, enabling more strategic investments. Proper use of medical equipment and treatment spaces reduces equipment maintenance and replacement costs, making it easier to reinvest in necessary resources and introduce new medical technologies.

[0012] To address these challenges, the objective of this invention is to support decision-making regarding the allocation of medical resources while visualizing the state of hospital management. In other words, the system associates management information such as sales and costs with resource data such as the number of doctors, nurses, hospital beds, operating rooms, examination rooms, and medical equipment, calculates management indicator data for each medical resource, and outputs this as a unit management indicator normalized to the unit resource level. Furthermore, in response to resource changes made by the user, the system recalculates the management indicator data in real time and immediately visualizes and outputs changes in the management situation, including the recalculated results, thereby providing a hospital management support system that allows managers to intuitively and quantitatively grasp the overall management efficiency and appropriateness of resource allocation for the hospital. [Means for solving the problem]

[0013] (1A) A hospital management support tool for visualizing the status of hospital management. This tool (system, program, method) visualizes the hospital's management status using a dashboard format displayed on a screen. This allows managers and administrators to quickly and quantitatively grasp the performance of each clinical department and clinical group, the usage of medical resources, profitability, and workload. Furthermore, management indicators for each medical resource are updated in real time during visualization, allowing for a constant understanding of the latest management situation. (1B) A hospital management support tool to assist in decision-making regarding the allocation of medical resources. This tool recalculates management indicator data based on user actions or AI-driven changes to medical resources, and visualizes these changes in real time. This allows managers and others to immediately understand the impact of resource increases or decreases on revenue and efficiency, enabling them to make resource reallocation and optimization decisions based on objective data.

[0014] The differences between general company management and hospital management lie in the revenue structure, cost management methods, and unique constraints on the scope of operations. <Differences in revenue structure> Hospitals have limited revenue potential because their income is determined by the medical fee system, preventing them from freely setting prices. While general companies can freely adjust the prices and content of their services to increase profits, hospitals must devise ways to maximize profits within the system. Since they cannot individually charge for consumables such as bandages and gauze used by patients, and their revenue depends on medical fees, it is essential for hospitals to devise ways to reduce the costs of consumables and equipment. <Cost control constraints> Treatment costs include direct costs such as pharmaceuticals, tests, and labor, but reducing these costs can easily impact patient safety and the quality of medical services. Because simple cost reduction is difficult, the focus was on efficient resource allocation without waste. Furthermore, indirect cost reductions are required through inventory management of pharmaceuticals, medical devices, and consumables, as well as workload leveling. This requires not just reducing the workload, but managing resources to distribute the workload while maintaining high-quality medical services. <Managing workload and human resources> The number of medical professionals, such as doctors and nurses, is limited, leading to risks of overwork due to long working hours and high turnover rates. Effective management improvements emphasize the efficient allocation of personnel and the appropriate distribution of workload. Furthermore, it's not simply a matter of reducing the workload; resource management is required to distribute the workload while maintaining high-quality medical services. <Balancing patient satisfaction and profitability> While general businesses can adjust customer service costs to balance profitability, hospitals prioritize patient safety and quality of care. Therefore, they must optimize operating costs while maintaining patient satisfaction. Reducing patient response times and improving the efficiency of medical care contribute to increased revenue, but these must be done in a way that does not compromise patient convenience or satisfaction, thus maintaining a balance between the quality of medical care and profitability. <Legal and ethical constraints> Hospital management is subject to strict regulations on medical fees and medical procedures, and unlike general companies, the degree of freedom to increase profits is limited. Therefore, management strategies must be based not only on profit maximization, but also on legal compliance and ethical considerations. Furthermore, hospitals are highly public institutions, and their mission is not only to generate profits, but also to meet the healthcare needs of the community and ensure the quality of medical care. Therefore, it is necessary to manage hospitals sustainably while balancing profit and public interest. This invention proposes hospital management improvements that take these aspects into consideration, emphasizing the importance of efficient resource allocation, optimization of workload, reduction of indirect costs, and improvement of patient satisfaction. These improvements involve data-driven analysis and adjustments, including effective resource utilization, identification and improvement of bottlenecks, and presentation of profit improvement measures through simulations.

[0015] In this invention, management information, management indicator data, and unit management indicators are linked as a three-layer structure for evaluating and simulating hospital management. Specifically, it consists of (a) "management information" as a basic data layer, (b) "management indicator data" as a calculation and analysis layer, and (c) "unit management indicators" as a visualization and comparison layer. The technical feature of this structure is that it allows for the quantitative calculation and recalculation of management effects in response to changes and reallocations of medical resources, and enables real-time visualization.

[0016] Medical service provision slots: Provision slots that manage the time slots, locations, and assigned resources for outpatient, inpatient, surgery, procedures, examinations, and therapies as a whole. Target patient demand: Demand indicators including the number of waiting patients, the number of appointments, the number of unscheduled appointments, and the number of patients awaiting referral acceptance. Medical equipment: This refers to equipment used for diagnosis, treatment, and monitoring (CT scanners, MRI scanners, endoscopes, radiation therapy equipment, monitors, etc.). Operational resources include personnel, equipment, facilities, time slots, and inventory; service slots are units of time, location, and assigned resources for service provision; and demand includes reservations, orders, visitor traffic, etc.

[0017] "Management information" refers to basic performance data related to hospital management, and mainly consists of information on accounting, medical treatment, operations, and personnel. Specifically, it includes medical treatment reimbursement points, DPC comprehensive evaluation points, patient unit price, pharmaceutical costs, material costs, labor costs, fixed costs, equipment maintenance costs, hospital bed occupancy rate, number of surgeries, average length of hospital stay, working hours of doctors and nurses, operating hours of operating rooms, etc. These are primary data that comprehensively represent sales, costs, efficiency, and resource status, and are stored in the storage means 280 of the server 20 and used as input variables for calculating "management index data". "Management index data" is analysis data obtained by calculating "management information" such as sales and costs in association with the quantity or operating hours of medical resources (doctors, nurses, hospital beds, operating rooms, inspection equipment, treatment equipment, etc.). The management index data is calculated based on at least sales and costs, and if necessary, is calculated based on management information such as medical treatment reimbursement points, pharmaceutical price margin, material cost margin, hospital bed occupancy rate, average length of hospital stay, number of surgeries, etc. These data are classified by categories such as revenue system, cost system, efficiency system, profitability system, productivity system, etc., and are used as intermediate data that quantitatively shows the management performance of each medical resource. That is, it is analyzed data derived from "management information" and serves as the basis for simulation and visualization processing. That is, "management index data" is not just simple financial records or statistical aggregations, but a group of numerical data that calculates important management indicators such as profitability, cost efficiency, and profit rate with the input quantity or operating status of each medical resource as variables, and functions as the basic data for simulation processing and visualization processing.

[0018] "Unit management index" is a value obtained by normalizing "management index data" by medical resource unit (one doctor, one hospital bed, one operating room, one hour, etc.), and is normalized data that enables comparison between different medical departments or hospitals. "Unit management index" expresses the profitability, efficiency, occupancy rate, etc. per resource unit on a common scale, facilitating comparison by medical department, time series, and with other hospitals. It can quantitatively compare and evaluate the differences in business efficiency between medical departments and the differences in resource utilization between hospitals. By tracking over time, the effectiveness of management improvement measures and the validity of resource redistribution can be continuously evaluated.

[0019] Conventional management evaluations merely provide a general overview of the state of each clinical department based on abstract categories such as "functionality, profitability, productivity, and safety" as shown in Non-Patent Document 1. This type of classification presents a conceptual framework but does not disclose specific computer-processable methods. Therefore, abstract classification alone does not allow for the derivation of technical means to quantitatively predict the expected benefits of resource reallocation or increase / decrease and to immediately reflect them on the UI. Unlike conventional abstract classifications, the "management indicator data" of the present invention is specifically implemented in a three-tiered structure: management information → management indicator data → unit management indicators.

[0020] In other words, (1) Correspondence calculation: Management information such as profit, cost, bed occupancy rate, number of surgeries, and average length of hospital stay are linked to the quantity or hours of medical resources in a one-to-one or many-to-one manner, and calculated indicator values ​​(management indicator data) are generated for each clinical department. (2) Unit normalization: The generated indicators are normalized to common units such as one doctor, one nurse, one hospital bed, one operating room, and one hour, to obtain "unit management indicators" that can be compared between different medical departments and hospitals. (3) Dynamic updates: When resource quantities or time change due to user operations or AI suggestions, they are recalculated and visualized in real time, enabling immediate decision-making. These specific configurations (1) to (3) are technical means (operations, data structures, UI control) that cannot be achieved through abstract classification.

[0021] Furthermore, according to the present invention, (a) Resource operations (increasing staff, reallocating, moving hospital beds, adjusting surgical slots, etc.) are combined with mathematical updates. (b) Unit management indicators enable fair comparisons that eliminate differences in departmental size, (c) Bottleneck processing automates the comparison of reference values ​​and prioritization. As a result, it goes beyond simply displaying abstract "good / bad" ratings and can instantly and quantitatively show "how much profit changes when certain unit resources are moved, in what quantities, and to where." This is a management simulation capability that cannot be achieved with mere classification systems.

[0022] (1C-1) Benefit management database. (1C-2) Resource management database. The revenue management database calculates and records sales, costs, and profits, accumulating data such as sales figures and profit margins, which are then used for revenue analysis and business improvement. The resource management database registers medical resources (personnel, equipment, medical devices, hospital beds, etc.) assigned to each clinical department or clinical group, allowing for the calculation of workload and resource utilization, and supporting efficient resource allocation. Furthermore, by utilizing a patient database that records data such as each patient's medical history, age, gender, disease, treatment details, and number of visits, it is possible to analyze patient trends and understand the usage and repeat visit rates of specific medical departments. In addition, by utilizing a cost management database that records direct costs (personnel costs, pharmaceutical costs, examination costs, equipment maintenance costs, etc.) and indirect costs related to the operation of each medical department and medical group, the balance between revenue and costs can be calculated and the profit margin of each medical department can be evaluated. This data is used as basic data for measures to reduce costs and improve profitability. Furthermore, by utilizing a work schedule database that records the shifts, work schedules, and appointment status of each medical department and staff, it is used to equalize staff utilization rates and workload, preventing excessive burden on staff and wasted resources, thereby streamlining the scheduling of hospital beds and equipment. In addition, by utilizing an inventory management database that records the inventory status of pharmaceuticals, consumables, medical equipment, etc., and manages usage frequency and replenishment timing, it is possible to ensure that necessary supplies are supplied appropriately without shortages, contributing to cost reduction and improved operational efficiency. Furthermore, by utilizing an equipment management database that manages data such as the operating rate, frequency of use, maintenance history, and lifespan of equipment and medical devices used in each clinical department, it is possible to use this data to efficiently operate equipment and formulate appropriate maintenance plans, thereby maximizing the operating rate while minimizing the risk of operational downtime due to equipment failure or lifespan. In addition, by utilizing an external factors database that covers external factors such as seasonal information such as influenza outbreaks, the local infectious disease situation, and social and economic impacts (legal revisions, economic indicators), it is possible to adjust hospital operations and optimize resource allocation based on external factors, enabling responses that can predict fluctuations in the number of patients and revenue. Specifically, resources include one or more of the following resource data: number of waiting patients, number of patients, number of doctors, number of nurses, number of medical office assistants, number of nursing assistants, number of hospital beds, number of operating rooms, number of surgical slots, number of surgical materials, number of drugs, number of anesthesiologists, number of available working hours for anesthesiologists, and working hours for each clinical department.

[0023] Furthermore, by incorporating a data collection function into the profit indicator calculation module (=profit simulation module / means), these databases enable efficient simulations by collecting only the necessary information in real time for simulations related to revenue and resource allocation. The revenue data collection function of the profit indicator calculation module (profit simulation module / means) identifies the data to be collected by selecting and prioritizing revenue, costs, resource utilization, patient numbers, and patient data such as patient groups. A trigger function is provided to automatically collect data when the simulation is run or when the data is updated, ensuring that the latest data is always reflected. At that time, a data integrity check is performed to confirm that the collected data does not contain missing values ​​or outliers. If there are anomalies, they are not reflected in the simulation, or if abnormally high costs or revenues are included, the data is automatically corrected or supplemented as needed.

[0024] (1D) Based on revenue data (management information) and allocated resource data for each clinical department or clinical group, management indicators and unit management indicators are calculated for each resource unit. Alternatively, the profit increase is calculated by moving medical resources from a clinical department with fewer management indicators / unit management indicators to a clinical department with more. Or, based on the revenue data (management information) and allocated resource data of each clinical department or clinical group, unit management indicators are calculated for each resource, and based on the said unit management indicators, the profit fluctuations resulting from resource movement or resource expansion between clinical departments or clinical groups are simulated.

[0025] Comparing unit profits involves comparing the calculated unit management indicators across each clinical department or group to identify departments with low and high unit profits. This allows for prediction of how overall profits would change if medical resources were shifted from departments with low profit efficiency to those with high profit efficiency. Alternatively, it predicts profit changes if resources were increased in departments with high profit efficiency.

[0026] "Management indicators" and "unit management indicators" are used to evaluate profitability for each resource unit (doctors, nurses, hospital beds, examination rooms, etc.). Specifically, they are used to calculate profit for each resource allocated to each clinical department or clinical group. Profit per resource is calculated by determining the profit per resource unit (e.g., 1 doctor, 1 hour of doctor work, 1 hospital bed, 1 hospital bed per day, 1 hour of anesthesiologist work, 1 slot of anesthesiologist work, 1 operating room surgery slot, etc.). The profit score is calculated by scoring how much profit is generated for each resource. By using "management indicators" and "unit management indicators," the overall profit change when resource allocation is changed between clinical departments or clinical groups can be calculated.

[0027] (1E) A function that, when the quantity or number of hours corresponding to medical resources is changed, recalculates management indicator data and unit management indicators based on the changed quantity or number of hours, and visualizes and outputs the changes in management indicators based on the recalculation results in real time.

[0028] Changes to medical resources include both manual input by the user on a terminal and automatic determination by one or more of the following: a trained model, rule-based inference, an optimization solver, or heuristics. In the case of manual operation, managers or other personnel change resource quantities or operating hours, such as the number of doctors, nurses, hospital beds, and operating rooms, using sliders, numerical input fields, or buttons on the terminal. In the case of automatic determination, historical data such as past management indicator data, workload scores, profitability scores, patient number trends, seasonal fluctuations, and work shift history are used as input, and a trained model or optimization solver analyzes this data to estimate the optimal resource allocation. The estimation results are reflected as change inputs via control means, and the management indicator data and unit management indicators are recalculated.

[0029] The processor (control means) recalculates the management indicator data based on these modified data and recalculates the unit management indicators. The display control means is configured to instantly visualize the direction of increase or decrease in profit and efficiency based on the recalculation results, so that users can intuitively grasp the nature of the changes.

[0030] Resource data and management indicator data provided by other hospitals may be obtained from regional medical collaboration networks or publicly available government databases (e.g., DPC databases). The comparison results will generate multidimensional indicators including management efficiency (profit margin, patient cost per patient, productivity, etc.) and resource utilization (bed occupancy rate, staff utilization rate, etc.), and the differences will be visualized using graphs, heatmaps, etc. "Derivation" is not merely "calculation (calculation)," but represents a broad concept that includes analytical and comparative processing as described below. • A process that calculates an evaluation value by combining multiple variables such as sales, costs, and resource counts. • Extracting results through correspondence and comparative analysis of data from our own hospital and other hospitals. • Statistical and logical difference analysis using AI and algorithms (e.g., deviation, efficiency index, etc.)

[0031] The "reference value" is dynamically updated per resource based on past performance values, average values, or target values ​​set by the administrator, and the system calculates this value through the reference value setting process (S503). The "average value of other hospitals" is a benchmark value obtained by statistically aggregating management indicator data and resource data of other hospitals obtained through the process of claim 4, and is calculated per clinical department or occupation. "Efficiency" = management indicator data ÷ medical resources (quantity or hours), and is the degree of resource utilization based on "management indicator data" or "unit management indicators".

[0032] (2) Management indicators are calculated based on one or more management indicator data from sales, costs, patient numbers, and revenue, using one or more of the following: DPC information, claims information, and drug price difference / material cost difference. (3) Changes in the number or hours of medical resources are made by moving resources between clinical departments or clinical groups, or by adding resources that have been allocated to each clinical department or clinical group. Furthermore, the management indicator data may be calculated not only from DPC, but also from data based on comprehensive evaluation systems such as DRG, AP-DRG, MS-DRG, or performance-based evaluation systems.

[0033] Resource movement simulations involve moving unit resources (e.g., one doctor, one hour of doctor work, one hospital bed, one hospital bed per day, one hour of anesthesiologist work, one anesthesiologist shift, one operating room surgery slot, etc.) from less profitable departments to more efficient ones over a predetermined period. For example, it estimates how much overall revenue would increase by allocating physician staffing and equipment utilization to departments with high unit profits.

[0034] Profit increase forecasts calculate the expected increase in profit due to resource relocation or resource expansion. It quantifies how much profit improves when medical resources are reallocated due to changes, and proposes the optimal resource allocation along with numerical information. Specifically, the predicted increase in profit is calculated as: Predicted Increase in Profit = Unit Profit of the Relocating Department × Amount of Resources Relocated - Unit Profit of the Original Department × Amount of Resources Relocated. This calculation allows for changing simulation conditions as needed, enabling the experimentation of resource changes in different patterns.

[0035] Furthermore, it is possible to flexibly select the method of resource movement according to management efficiency and the needs of each clinical department. Moving (unit) resources permanently or only for a predetermined period can lead to stable management of the entire hospital and efficient resource utilization. When there is a long-term imbalance in the profitability or workload of clinical departments, or when concentrating resources in highly profitable departments to improve long-term profits, permanent resource reallocation is preferable for departments with high utilization of equipment or clinical space, or departments that require personnel with specific skills. On the other hand, when it is necessary to respond to seasonal or temporary demands, such as during influenza outbreaks or when there is a demand for specific treatments, or when introducing new medical services or treatments, it is preferable to move resources only for a predetermined period. In addition, it is possible to combine permanent and temporary movements, and by taking measures such as flexibly responding to fluctuations in demand in line with the growth of clinical departments or changes in the external environment, preventing resource waste and excessive staff burden by allocating necessary resources without excess or deficiency, and switching to permanent allocation if the effect of moving resources for a predetermined period is confirmed and stable results are obtained, it is possible to select as appropriate according to the situation in order to improve the efficiency of hospital management and maximize profits while maintaining the quality of patient services.

[0036] Furthermore, moving or adding resources over a predetermined period enables dynamic simulations, which have a different significance from static simulations based on data accumulation. This allows for greater flexibility in responding to real-world changes and improved simulation accuracy. Moving resources over a predetermined period allows for real-time collection of data on actual work conditions, fluctuations in patient numbers, and impacts on revenue. Dynamically obtaining data makes it easier to identify discrepancies between the effects predicted by static simulations and actual data. Moving or adding resources over a predetermined period is advantageous because it allows for rapid hypothesis testing. The revenue effects and workload reduction effects of increasing resources in a specific clinical department can be verified in a short period, allowing for confirmation of whether the hypothesis is correct. Based on the verification results, it is helpful in deciding whether to implement permanent resource reallocation or try other measures.

[0037] The resource management database may be in either a list format in which the number of doctors, nurses, hospital beds, operating rooms, anesthesiologists, available working hours for anesthesiologists, or working hours for each medical department are registered as resource data, or in a table format in which medical resources for doctors, nurses, hospital beds, operating rooms, anesthesiologists, and each medical department, along with their numerical information (number and hours), are registered. Furthermore, "complex resources" refer to a data structure in which two or more medical resources with different characteristics are linked by a common identifier or management key, and configured to be aggregated or analyzed as the same operational unit. It refers to a unit in which multiple medical resources (doctors, nurses, hospital beds, operating rooms, examination rooms, medical equipment (testing equipment, treatment equipment, etc.)) operate in relation to each other. For example, a surgical slot is a slot that can only be established when the resources of "doctor," "anesthesiologist," "nurse," "operating room," "anesthesia equipment," and "surgical materials" are all operating simultaneously, and it is positioned as a "slot" that manages these together. Similarly, examination slots, inpatient slots, ICU slots, rehabilitation slots, emergency admission slots, drug therapy slots, etc., are also treated as complex resource units composed of combinations of the operation of multiple types of medical resources. The system registers these complex resources in a resource management database and makes it possible to calculate the utilization rate, profitability, and bottleneck situation at the slot level. Management indicators may be calculated using medical resources such as equipment-related resources, staff-related resources, facility-related resources, other resources, external resources, patient service-related resources, and IT-related resources. Equipment-related resources include the number of diagnostic devices (e.g., MRI, CT, ultrasound equipment), the number of therapeutic devices (e.g., radiation therapy equipment, laser therapy equipment), the number of testing devices (e.g., blood testing equipment, electrocardiogram monitors, endoscopes), and the number of pharmaceutical inventory (e.g., specific drug inventory or stock levels). Staff-related resources include the number of rehabilitation staff (physical therapists, occupational therapists), pharmacists, radiologic technologists, clinical laboratory technologists, administrative staff, and counselors / social workers. Facility-related resources include the number of examination rooms, testing rooms, waiting room capacity, intensive care unit (ICU) beds, emergency response equipment, rehabilitation facility equipment, and treatment rooms. Other resources include the number of ambulances and means of transportation, the number of patient-only parking spaces, the number of mobility devices such as beds and stretchers, the available hours for each resource (e.g., operating hours of examination rooms and testing rooms, usage times for specific medical equipment), and the number of infection control facilities (e.g., disinfection equipment, inventory of personal protective equipment). External resources include the number of partner facilities (other hospitals, nursing homes, specialized medical facilities, etc.) and the number of external specialists (the number of specialists who can provide cooperation from outside the hospital). Patient service-related resources include the number of private / multi-bed rooms for patients, the number of services provided to patients (e.g., interpretation services, nutritional counseling), and telemedicine equipment (equipment for online consultations and remote monitoring). IT-related resources include the number of operational electronic medical record systems, data server capacity, and security devices (firewalls, antivirus equipment). These medical resources fall within the scope of the present invention or its equivalents.

[0038] In particular, regarding the placement of medical office assistants, the bottleneck can be calculated by incorporating the perspective of how much the physician's productivity will increase as a result of their placement into the calculation formula. It is said that 30% of a physician's work involves administrative tasks, and if half of that time can be dedicated to directing medical office assistants to complete the administrative tasks, then a productivity improvement of 17% can be expected (1 / (1-0.3 / 2) = 1.17). Similarly, regarding nursing assistants and licensed practical nurses, it is said that 30% of a nurse's work involves paperwork and patient care such as patient transport, and if half of that time can be dedicated to directing nursing assistants and licensed practical nurses to complete nursing tasks, then a bottleneck reduction effect of 17% can be achieved (1 / (1-0.3 / 2) = 1.17).

[0039] (4) The simulation results of the resource relocation or resource expansion will be used as budgeting data for hospital management in the following period and beyond. (5) The simulation results of resource relocation or resource expansion are managed in a plan vs. actual manner. (6) Calculate the productivity improvement of physicians or nurses by adding medical office assistants and nursing assistants, and simulate the management indicators of the increased resources. (7) The system has a function to register the number of potential additional resources that can be added, and a function to calculate potential additional profit or potential additional sales based on the number of potential additional resources that can be added. (8) The resource management database has a function to visualize whether there are any limitations on other resources when simulating either an increase or replacement of one or more resources, and at the same time has a function to visualize a list of measures to resolve resource limitations. The resource management database 283A has the function of registering not only the current number of each medical resource, but also the upper limit of the number of resources that can be added in the future through expansion or recruitment (potential additional number). For example, the number of doctors is registered as "currently 10, potential additional number 3," and the number of hospital beds is registered as "currently 50, potential additional number 10." When the system runs simulations involving resource reallocation or expansion, it can refer to this potential additional number and impose constraints to ensure that the amount of change set by the user does not exceed the upper limit. Furthermore, for scenarios that assume the potential additional number, it calculates the corresponding change in profit and displays this as potential additional profit or potential additional sales. This allows managers to quantitatively compare the cost-effectiveness of additional investments and supports decision-making regarding resource expansion. Potential additional profit ΔP=(U×ΔR)-C Potential additional sales ΔS = (U × ΔR) U: Unit Management Indicator (Profit per unit of resource) ΔR: Number of additional resources (within the range of the potential number of additional resources that can be added) C: Cost of additional resources U: Average sales per unit resource

[0040] <Use as budget formulation material> Based on the simulation results of resource relocation and expansion, this can be used as budgeting material for hospital management in subsequent periods. <Application to budget management> Budget and actual performance are managed based on simulation results of resource relocation and expansion. This allows for a comparison of business plans with actual performance and identification of discrepancies. <Productivity Improvement Simulation> This system calculates the productivity improvement effect of adding medical office assistants and nursing assistants on doctors and nurses, and simulates how the increased resources will impact management indicators. This simulation function allows for a quantitative evaluation of how adding medical office assistants and nursing assistants will improve efficiency and productivity in actual medical settings, and predicts the business improvement effects of increased resources. <Registration of potential additional slots> The resource management database has a function to register the potential number of additional resources that can be added, and uses this data to calculate potential additional profits and sales. <Visualizing resource limitations and listing solutions> The resource management database has a function that visualizes whether there are limitations on other resources when simulating resource increases or replacements, and displays a list of measures to resolve those limitations. These features enable the hospital management support system to utilize simulation results in management decisions and planning, supporting optimal resource utilization and productivity improvement.

[0041] (9) Visualize the bed occupancy rate for hospital beds, which are part of the aforementioned resources, and enable simulations of an increase in the number of patients using hospital beds and an improvement in the average cost per patient. This invention visualizes the bed occupancy rate and performs simulations for optimizing bed utilization in order to evaluate the efficient use of hospital beds, which are a part of the resources. The bed occupancy rate is calculated based on the utilization status of each bed (utilization rate, number of empty beds, etc.), and based on this occupancy rate, it simulates how much the number of patients that can be accepted will increase if the number of beds is increased or patient admissions and discharges are accelerated. This allows for a simulation of profit improvement when the price per patient is increased when bed utilization is maximized. For example, it estimates how much the price per patient can be increased by improving the length of hospital stay and the content of medical care. As a result, the profit simulation is reflected, and the occupancy rate, patient increase prediction, and price increase simulation results obtained from the bed occupancy rate management module are reflected in the profit simulation to calculate the overall profit improvement effect of the hospital.

[0042] Furthermore, the present invention performs resource reallocation and revenue forecasting using the profit simulation means (295) described later.

[0043] (10) The present invention has a function to promote early hospitalization and discharge of patients, and a function to allow medical personnel to input the reasons for such admission and discharge. Reasons for requiring early admission or discharge include medical reasons based on the patient's recovery status or changes in treatment plan, the possibility of home care where appropriate care can be received at home after discharge, the severity of the hospital bed shortage and whether early discharge is desirable, and the patient's or family's wishes for early discharge. Healthcare professionals will be able to input the reasons for admission or discharge using a selection format (e.g., a dropdown menu or checkboxes) or free-text format, and will also be able to input detailed information and supplementary comments as needed.

[0044] Furthermore, the present invention visualizes and simulates the hospital bed occupancy rate using the resource management DB283C and profit simulation means (295) described later.

[0045] (11) Visualize the resources that are bottlenecks in the hospital's equipment and other fixed costs, and support proposals for improving the allocation of those resources. (12) If the bottleneck is either the number of patients or the number of patients on the waiting list, display a list of measures to increase the number of patients and calculate the cost-effectiveness of one or more of these measures. This invention provides functions to visualize areas within a hospital where equipment and other fixed costs are bottlenecks (obstacles to management and operations) and to propose improvements to their allocation. It includes functions for visualizing bottleneck resources, simulating resource allocation optimization, evaluating fixed costs, predicting resource utilization and analyzing demand, and monitoring the results of improvement proposals. This improves the utilization of fixed cost resources, reduces overall hospital operating costs, and enables a stable supply of necessary resources. If the bottleneck is related to the number of patients or the number of patients on the waiting list, a function has been added that displays a list of measures to increase the number of patients and calculates the cost-effectiveness of each measure. This allows for the selection of efficient measures to increase the number of patients and supports decisions aimed at expanding revenue.

[0046] (13) The system proposes the placement of multiple medical office assistants and includes functions to support the operation of multiple operating rooms.

[0047] The resources to be targeted are those with high fixed costs, such as operating rooms, hospital beds, medical equipment, waiting rooms, and specialized medical equipment. These resources are selected based on their utilization status (uptime, frequency of use, waiting time) and maintenance costs collected from a database. Resources with low or excessive uptime, or those with low or very high usage frequency, tend to be concentrated in specific departments or tasks, potentially disrupting other operations. Long waiting times for resource use indicate insufficient supply relative to demand. Resources with very high maintenance or operating costs should be reviewed. Resources with abnormally low uptime or extremely uneven usage should be identified and included as potential bottlenecks. Time-series data should be analyzed, and resources showing significant changes in utilization trends should be included as potential bottlenecks. Furthermore, if a particular resource is linked to others, a bottleneck in one resource can affect overall operations, so resource interrelationship analysis should also be conducted. For example, in cases where the uptime of operating rooms and physicians are linked, a bottleneck in either will reduce surgical efficiency, so both should be identified. Since there are various reasons for bottlenecks, we will create a list of potential bottlenecks and prioritize them. The resources extracted using the above indicators will then be listed and prioritized based on utilization rate, cost, frequency of use, and waiting time. Improvement proposals will be presented starting with the highest priority items, and reallocation, distribution of utilization rates, and introduction of additional resources will be suggested as needed.

[0048] Bottleneck calculation differs from averages in that it only shows the overall trend and is not suitable for identifying areas where the load is particularly concentrated (e.g., specific time periods or specific equipment), as it identifies specific departments or equipment prone to delays, rather than the overall load. Bottlenecks identify points in the data where the load is locally high, allowing attention to be paid to abnormal data that deviates significantly from the average. Furthermore, visualizing bottlenecks makes it possible to prioritize resource allocation to areas that require improvement, enabling measures to be taken starting with the areas with the greatest impact, even with limited budgets and personnel.

[0049] Furthermore, the fixed cost utilization optimization function of the present invention is supported by the bottleneck processing unit 295A, described later, in detecting bottleneck fixed cost resources and proposing improvements.

[0050] (14) The system includes a score generation function that converts the workload and profitability of each clinical department and clinical department group into a score, and a visualization function that visualizes the score. (15) Periodically record the changes in the workload score and profitability score generated by the score generation function, and record the history of changes in order to grasp the trends in workload and profitability for each medical department. (16) Based on the fluctuation trends in workload and profitability obtained from the recording of the fluctuation history, the system is equipped with a notification function that notifies medical administrators when (significant) fluctuations such as excessive workload or decreased profits are detected for each medical department.

[0051] According to the present invention, the score generation function includes a scoring function that converts the workload and profitability of each clinical department / clinical group into a score, and a visualization function that visualizes the generated scores on a dashboard or graph. As a result, the performance of each clinical department is quantified, and resource allocation and profitability can be grasped at a glance. By scoring, complex data such as workload and profitability are made easier to understand, and the performance of each clinical department can be quickly grasped. In addition, the scored indicators make it easy to compare between clinical departments. That is, it is possible to compare the workload and profitability of different clinical departments or clinical groups, analyze differences in resource allocation and efficiency between clinical departments, and help identify areas that need improvement or areas where resources should be prioritized. Furthermore, by scoring and recording regularly, the effects of improvement measures can be tracked in concrete numbers, and by evaluating the fluctuations in scores, the success of the measures and the need for further improvement can be judged. Moreover, by regularly monitoring scores, risks such as imbalances in workload and declines in profitability can be detected early. By issuing warnings when scores fall below the standard value or when sudden fluctuations occur, efforts can be made to detect management risks early, and it contributes to maintaining management stability through prompt response.

[0052] Furthermore, the fluctuation history recording function periodically records fluctuations in the workload score and profitability score generated by the score generation function. This can be used to understand long-term fluctuation trends in workload and profitability for each medical department, enabling analysis of improvement effects and changes in resource demand, which is useful for management decisions.

[0053] Furthermore, the notification function, based on fluctuation trends in workload and profitability obtained from the record of fluctuation history, automatically notifies medical managers if significant fluctuations such as excessive workload or decreased profits are detected in a particular medical department. This allows for immediate countermeasures and helps reduce business risks.

[0054] Furthermore, this invention corresponds to the score evaluation unit 295A described later and is related to functions related to the conversion and visualization of scores for workload and profitability. In addition, the fluctuation history recording function periodically records fluctuations in workload and profitability scores using the data storage area 283 described later and stores them in the data storage area. In addition, the notification function corresponds to the alert processing means 293 and notification means 250 described later and is related to the function of notifying medical managers when an anomaly in workload or profitability is detected.

[0055] (17) The profit indicator calculation function periodically monitors and updates one or more of the following outcomes for each clinical department or clinical group based on the simulation results: revenue improvement rate, reduction in workload, improvement in bed occupancy rate, reduction in patient response time, and cost reduction rate. According to this invention, the effects of management improvements can be continuously monitored as one or more outcomes, including revenue improvement rate, reduction in workload, improvement in bed occupancy rate, reduction in patient response time, and cost reduction rate, enabling more accurate management decisions. Furthermore, by combining multiple indicators, it is possible to improve overall management performance, which is difficult to see with a single indicator, and to provide measures that can be expected to have a greater synergistic effect. By taking into account not only economic indicators such as revenue and costs, but also operational indicators such as workload and patient response time, it is possible to derive strategic and sustainable improvement proposals that are not biased towards short-term profits.

[0056] This invention visualizes the profitability of each patient group, making it possible to identify high-revenue patient groups and low-revenue patient groups with high costs. This allows for the strengthening of services and measures tailored to each group, facilitating efficient countermeasures and the development of strategies for optimal allocation of management resources. When low-revenue groups are identified, the cause may be related to the content of medical treatment, patient care, or insufficient equipment. Visualization highlights these problems, allowing for appropriate service improvements and potentially increasing patient satisfaction. Furthermore, for high-revenue patient groups, further service improvements can lead to an increase in repeat patients. In addition, based on the profitability of each patient group, it becomes easier to plan the efficient allocation of resources (doctors, nurses, equipment, etc.) between departments and medical groups. By increasing the capacity for medical care for high-revenue groups, revenue can be increased, supporting efficient operations.

[0057] (20) The revenue management database is capable of calculating profits by adding drug price profits and material cost profits to the DPC profit for each patient, and the results of calculating modules for grouping patients are registered for each clinical department or clinical group within the hospital, and the profit indicator calculation module has a function to visualize the profit margin for each patient group.

[0058] The revenue management database has a function to calculate the profit for each patient by adding the profit margin on drug prices and material costs to the profit margin on the DPC (Diagnosis Procedure Combination) system. It also groups patients according to specific criteria, calculates the profit for each group, and registers this information for each clinical department or clinical group within the hospital. Furthermore, the profit indicator calculation module has a function to visualize the profit margin for each patient group, making it easier to understand the profitability of each clinical department or clinical group. In particular, for profits including drug price differences, the system calculates the average using a statistically sufficient number of patients, allowing for the evaluation of revenue stability and profitability.

[0059] (21) The system has a function to input text requesting doctors to input the target number of patients, a function to register the times when healthcare professionals are most likely to receive phone calls, and a function to notify healthcare professionals by speaking the text information aloud during the aforementioned times when they are most likely to receive calls.

[0060] This system includes a function to generate text requests for doctors to input their target patient numbers. It also has a function to register times when healthcare professionals are most likely to receive phone calls, and can notify healthcare professionals by speaking the request text information aloud at the registered times. Furthermore, it incorporates a function to send reminders by phone as needed to ensure that target patient numbers are entered correctly each month, as well as a chat-based reminder function, efficiently supporting reminders using both chat and phone. This series of functions ensures that healthcare professionals can reliably input their target numbers, supporting efforts toward achieving those goals. [Effects of the Invention]

[0061] The present invention aims to efficiently utilize resources within a hospital and simultaneously achieve sound management and improved quality of medical services. In particular, it comprehensively evaluates multiple indicators such as workload, profitability, bed occupancy rate, and cost reduction, and derives improvement plans through simulation, thereby enabling managers to make quick and sustainable data-driven decisions. Furthermore, it supports the early identification of resource surpluses or shortages and bottlenecks through the visualization and notification functions of each indicator, thereby optimizing the overall management efficiency and service quality of the hospital.

[0062] Furthermore, the present invention dynamically links management information and medical resource information, and when the quantity or operating status of resources changes, it can immediately recalculate relevant management indicators and visualize the results in real time. This allows managers and others to instantly grasp the impact of changes in resource allocation on revenue and costs and consider the optimal allocation strategy. Furthermore, by comparing indicators from multiple clinical departments within the hospital on the same screen, or by comparing them with data obtained from other hospitals, it is possible to quantitatively grasp differences in management efficiency. Compared to conventional static analysis, this allows for more objective and strategic management decision-making. Furthermore, by evaluating the capacity of healthcare professionals and analyzing complex resources, it is possible to optimize human and material resources, thereby achieving both reduced burden on healthcare settings and improved service quality. [Brief explanation of the drawing]

[0063] [Figure 1] A diagram showing the network configuration of a hospital management support system according to an embodiment of the present invention. [Figure 2] A block diagram showing an example of the system configuration of a hospital management support system. [Figure 3] A block diagram showing an example of the functional configuration of Server 20. [Figure 4] A follow chart showing the processing procedure executed by the program of the hospital management support system according to an embodiment of the present invention. [Figure 5] A follow-up chart illustrating the process for resolving bottlenecks. [Figure 6] A diagram illustrating the before and after of the simulation. [Figure 7] A diagram illustrating the surgical procedure flow in a hospital. [Figure 8] This figure shows an example of a visualization screen for comparing medical departments. [Figure 9] This diagram shows an example of a visualization screen comparing hospitals with other hospitals. [Figure 10] This figure shows an example of a visualization screen for bottleneck warnings. [Best Mode for Carrying Out the Invention]

[0064] Figure 1 shows the network configuration centered on the hospital management support system 2. It is connected to in-hospital terminals 1 (such as PCs and tablet devices) and in-hospital medical systems 3 (for example, electronic medical record systems, accounting systems, and DPC systems) via telecommunication lines, using communication networks such as the Internet, intranet, and in-hospital LAN. The hospital management support system 2 is networked to allow access to medical systems 3 when performing analysis by referencing data recorded within those systems.

[0065] Figure 2 is a block diagram showing an example of the system configuration of the server 20 of the hospital management support system 2 and other equipment. The hospital management support system 2 analyzes and evaluates management information and medical resource information using the server 20, and controls the display to visualize the results as the status of hospital management to in-hospital terminals 10 and 30.

[0066] Server 20 is the core computing device of the hospital management support system 2 of the present invention, and includes a communication interface 22, an input / output interface 23, memory 25, storage 26, and a processor 29. Communication IF22 is an interface for data communication with external devices (in-hospital terminals 10, 30, medical system 3, etc.). Input / Output IF23 is an interface for sending and receiving operation signals and control signals related to visualization output from the user or other systems. Memory 25 is a work area that temporarily stores programs executed by the processor 29 and the data to be processed by them, and is configured as volatile memory such as DRAM. Storage 26 is a storage device for long-term data retention, consisting of, for example, flash memory or a hard disk drive, and stores the following database: (a) A revenue management database in which management information such as sales and costs is registered, (b) A resource management database that registers medical resources such as the number of doctors, nurses, and hospital beds. The processor 29 is hardware for executing the instruction set described in the program, and is composed of an arithmetic unit, registers, peripheral circuits, etc. It executes the above program to calculate management indicator data by associating management information with medical resource information, normalizes the management indicator data to generate unit management indicators, and recalculates these indicators in response to changes in resources and outputs them for visualization.

[0067] The in-hospital terminals 10 and 30 are connected to the server 20 via the network 80 and have display means for visualizing the status of hospital management analyzed and evaluated by the server 20. They also have visual and audible display and notification means for providing real-time notifications when significant changes occur in the management indicators or resource utilization status being monitored. The in-hospital terminal 10 is connected to the network 80 by communicating with communication devices such as a wireless base station 81 that supports various communication standards such as LTE and Wi-Fi (IEEE802.11), and a wireless LAN router that supports IEEE and wireless LAN standards. The in-hospital terminal 10 includes a communication IF 12, an input device 13, an output device 14, a memory 15, a storage unit 16, and a processor 19. The in-hospital terminal 10 is a desktop or laptop PC, while the in-hospital terminal 30 is a mobile terminal such as a tablet or smartphone.

[0068] Communication IF12 is an interface for the in-hospital terminal 10 to communicate with the server 20 and input / output signals. Input device 13 is an input device (keyboard, touch panel, touchpad, mouse, or other pointing device) for receiving user input for management simulation operations (resource changes, comparison selection, graph switching, etc.). Output device 14 is an output device (display device or speaker) for displaying or outputting audio management indicators, resource allocation results, bottleneck warnings, etc. transmitted from the server 20. The memory 15 and storage unit 16 store programs and data necessary for display control and user interface processing, and the processor 19 executes these programs to generate a visualization output screen, perform real-time updates, and control notifications.

[0069] <Functional configuration of Server 20> Figure 3 is a block diagram showing an example of the functional configuration of server 20. Server 20 is electrically connected by a bus to a communication means 220, an input device 230, a display device 240, a storage means 280, a control means 290, an input means 291, a display control means 292, an alert processing means 293, a user IF 294, and a profit simulation means 295.

[0070] The following database is stored in the storage device 280. (a) Revenue management database 283B: Management information including sales and costs. (b) Resource management database 283C: Medical resources such as the number of doctors, nurses, hospital beds, and operating rooms. (c) Comparative Analysis Database: This database stores resource data and management indicator data from other hospitals or from past periods, and stores data for relative evaluation of management efficiency using comparative analysis methods. (d) Capacity database: This database stores data for calculating a capacity index using a capacity analysis tool, registering the number of patients assigned to each medical professional, such as doctors and nurses, the number of hours worked, the number of cases assisted, etc. (e) Simulation results database: Stores simulation results such as resource changes, reallocation proposals, profit fluctuations, and cost reduction effects, allowing users to compare them with past simulation history. (f) Alert History Database: Records alert history and countermeasures for bottleneck detection, excessive workload, and declining profitability, enabling tracking of the effectiveness of business improvements. (g) Master database: Holds master information that is used in common with other databases, such as medical department codes, medical procedure codes, facility codes, and cost categories. These databases are managed on a departmental or group basis as needed, and the processor (control means 290) refers to them to calculate management indicator data and unit management indicators.

[0071] The control means 290 has the function of executing a program to calculate management indicator data by associating management information with the quantity or time of medical resources, and then normalizing this data by resource unit to generate unit management indicators. Furthermore, if the quantity or time of medical resources is changed by the user or the generating AI, the control means recalculates the management indicator data to reflect the change and outputs the updated results in real time.

[0072] The display control means 292 has the function of visualizing and outputting management indicator data for each clinical department or clinical group, unit management indicators, comparison results with other hospitals, etc. The comparison results are displayed by color-coding or numerically representing differences in sales, costs, resource utilization efficiency, etc., so that users can intuitively grasp resource surpluses or shortages or decreased efficiency.

[0073] The bottleneck processing unit 295B of the profit simulation means 295 detects a medical department or group that falls below a standard value based on the comparison results of management indicator data or unit management indicators, and assigns bottleneck information (flags or warning information) to the corresponding items in the resource management DB 283C. The bottleneck information is displayed by the display control means 292, which highlights the relevant resource items on the screen with colors or icons, so that managers can grasp the bottleneck at a glance.

[0074] The score evaluation unit 295C of the profit simulation means 295 calculates the healthcare worker capacity index and generates a resource reallocation plan by performing a correlation analysis with unit management indicators. The Healthcare Worker Capacity Index is an indicator that quantifies the balance between workload and resource supply. It is calculated by combining input variables (measured values): number of patients, assigned time, number of procedures, number of people, and output (calculated result): capacity index, to determine whether the current workload is excessive or insufficient compared to the resource supply. For doctors: Number of patients under their care ÷ Number of doctors For nurses: Total number of patients ÷ Number of nurses For anesthesiologists: Number of surgeries ÷ Number of anesthesiologists For medical technologists: Number of tests ÷ Number of medical technologists A high value indicates excessive load (bottleneck), while a low value indicates ample capacity (resource surplus). The capacity index is not used in isolation, but rather in correlation analysis with other unit management indicators.

[0075] The comparative analysis unit 295D of the profit simulation means 295 correlates resource and management data of other hospitals with the data of the own hospital, performs comparative calculations, quantifies the relative efficiency difference, and outputs a visualized output.

[0076] In addition, the auxiliary analysis unit 295E has the function of correcting management indicator data by taking DPC information, claims information, drug price difference profit, or material cost difference profit as input, and also plays an auxiliary analysis role in enabling potential profit simulations based on potentially additional resources and interactive operation of reallocation proposals through a user interface.

[0077] The communication means 220 performs modulation and demodulation processing for the server 20 to communicate with user terminals 10 and 30, processes the signal calculated by the control means 290 for transmission, and transmits it to external devices and equipment. The communication means 220 processes the signal received from the outside and outputs it to the control means 290. In this way, the communication means 220 interprets commands or input content and provides them to each means, and also functions as an interface that interprets various display commands issued from the storage means 280 and performs output control.

[0078] The input device 230 is a device used by an administrator to input instructions or information to operate the server 20 as needed, and may be a keyboard, mouse, reader, or touch-sensitive device. The input device 230 also converts the instructions input by the administrator into electrical signals and outputs the electrical signals to the control means 290. The input device 230 also includes a receiving port that accepts electrical signals input from external input devices. The display means 240 is a display device such as an LCD or organic EL that presents information to an administrator who operates the server 20 as needed. The display 241 can display data corresponding to the control content of the control means 290 and can check the communication status between the server 20 and other external devices 10, 30.

[0079] The storage means 280 is implemented by memory (RAM) 25 and storage 26 such as a disk device (floppy disk, hard disk, or magneto-optical disk, etc.) and stores data, programs, etc. used by the server 20. The storage means 280 stores the application program 282 of this system, as well as data for the work area 281, data storage area 283, and screen definition storage area 284.

[0080] The work area 281 is a region that is secured when the system is started and where various data input and output by the system are temporarily stored. The data storage area 283 is a region where data temporarily stored in the work area 281 is semi-permanently stored through write control when a save request is made. The screen definition area 284 is a region where screen definition information for various screens to be output and displayed on the in-hospital terminals 10 and 30 is stored in advance, and includes format information for the screen settings to be displayed by the display control means 292.

[0081] The data storage area 283 includes an evaluation basis DB 283A, which stores information that forms the basis of the evaluation used by the profit simulation means 295.

[0082] Evaluation Base DB283A is a database that stores information indicating the status of hospital management in terms of items and numerical values. It includes information such as hospital beds and their occupancy rates, patients and patient costs, in-bed patients and length of stay, fixed cost items and their amounts, and doctors and administrative assistants and their working hours, working days, and compensation amounts. Resource Management DB283C is a database that stores information indicating the status of hospital management in terms of items and numerical values ​​or allocation frequencies. For facilities that directly affect revenue, such as operating rooms and waiting rooms, it includes information such as operating room occupancy rates, number of surgeries, revenue, waiting time, and number of medical staff allocated, as well as the number of waiting room users, waiting time, and the status of provision of revenue-related services.

[0083] Here, allocation frequency refers to the frequency and number of resources (doctors, nurses, medical equipment, etc.) allocated to a specific facility or resource, numerically indicating how much resources are allocated to facilities that need them and how frequently those resources are used. Staff allocation frequency represents the frequency of the number of doctors and nurses assigned to a facility (for example, an operating room). If "2 doctors and 3 nurses" are assigned to an operating room in the morning, the staff allocation frequency for the operating room in the morning is recorded as "2 doctors, 3 nurses." Equipment allocation frequency shows how often medical equipment and treatment spaces are used in which facilities. For example, the allocation frequency for a CT scanner might be recorded as "Operating room: 3 times a week, Emergency room: 2 times a week," allowing us to understand which facilities use the equipment frequently and helping to optimize allocation. Bed allocation frequency represents the occupancy and patient utilization frequency of hospital beds, indicating the occupancy rate of the beds. If a waiting room's frequency of use is "used by an average of 10 people per day," this can serve as a basis for deciding whether to increase, decrease, or reallocate hospital beds. By introducing the concept of frequency of use, even for resources that are difficult to quantify intuitively, it becomes possible to manage resource allocation within the hospital more precisely and to concretize and visualize improvement measures aimed at improving operational efficiency.

[0084] The revenue management DB283B is a database that stores management information such as sales and profits for each clinical department or clinical group within the hospital. This database registers management indicator data such as sales, costs, profits, and patient numbers on a departmental or clinical group basis. This data is used as basic information for evaluating profitability, and the processor (control means 290) calculates management indicator data by associating it with the quantity or time of medical resources.

[0085] The revenue management DB283B can also include the following detailed information: (a) Medical cost data: Direct costs such as drug costs, examination costs, and surgery costs, as well as indirect costs such as personnel costs and equipment usage costs, are recorded and used for revenue-cost balance analysis. (b) Patient-related data: Register the number of patients, visits, hospitalizations, repeat visitor rates, etc., and analyze the relationship between patient trends and revenue fluctuations. (c) Hospitalization efficiency data: The average length of stay and bed turnover rate are registered to evaluate bed utilization efficiency. (d) Unit price data: Register the unit price for medical services or the unit price per patient (average revenue per person) and use it to identify and strengthen high-revenue medical services, departments, and medical groups. (e) Time-related data: Record average treatment time and staff working hours and use them to evaluate profitability per hour. (f) Reservation-related data: The number of reservations, cancellation rate, and unfulfilled reservation rate will be registered and used to implement measures to improve the utilization rate of medical departments with a high rate of cancellations and unfulfilled reservations. (g) Revenue data by type of medical service: Revenue data for specific treatments, procedures, or tests is registered and used to analyze the most profitable types of medical services. (h) Seasonal and trend data: Seasonal fluctuations or annual trends are registered and used to optimize resource allocation according to revenue trends at specific times. By analyzing the interrelationships of this data, we can identify management challenges and support the development of simulations for improving profitability and strategies for reallocating resources.

[0086] The control means 290 is configured such that various processes, including the input means 291, display control means 292, alert processing means 293, user IF 294, and profit simulation means 295, are implemented by a processor. The processor is one or more processors. At least one processor is typically a microprocessor such as a CPU (Central Processing Unit), but may be other types of processors such as a GPU (Graphics Processing Unit). At least one processor may be single-core or multi-core. Furthermore, at least one processor may be a broad-sense processor such as a hardware circuit that performs some or all of the processing (e.g., an FPGA (Field-Programmable Gate Array) or ASIC (Application Specific Integrated Circuit)).

[0087] The display control means 292 controls the display of the results of the evaluation and simulation of the management status by this system on the in-hospital terminals 10 and 30. Key indicators such as sales, profits, resource utilization rates, workload, and profit margins for each clinical department and clinical group are displayed in a dashboard format for easy viewing. Anomalies in key indicators (for example, clinical departments with excessively high workloads or declining profitability) are highlighted using color coding and icons. The simulation results are displayed in graph formats such as line graphs, bar graphs, and pie charts, showing the impact of changes in profits when resources are increased or decreased, and the impact of changes in the number of patients and profit margins for each patient group on revenue, over time, aiding in intuitive understanding. A dashboard is provided for simultaneously comparing multiple simulation results, such as changes in profits due to resource reallocation and changes in bed occupancy rates, helping to consider the optimal strategy while comparing different patterns. Different simulation conditions can also be manually adjusted using interactive formats such as sliders and checkboxes. In addition to checkboxes, the interactive format accepts drag-and-drop, pull-down menus, and natural language input, and can reproduce and display the simulation history based on the operation log.

[0088] The alert processing means 293 has the function of notifying medical managers when significant fluctuations such as excessive workload or decreased profits are detected in the fluctuation trends of workload and profitability obtained by the fluctuation history recording module, and issues a command to warn on the displays and speakers of the in-hospital terminals 10 and 30. Alternatively, immediate notifications may be sent to managers via email or SMS. Furthermore, as a preventative measure for business improvement, by having the AI ​​detect significant fluctuations early, preventative measures can be taken before they develop into serious business risks.

[0089] User interface 294 performs processing that enables functions such as receiving user operations and commands from in-hospital terminals 10 and 30 via keyboard input or voice input, and creating a layout that is easy for the user to view based on the screen format information in the screen definition area 284.

[0090] The profit simulation means 295 has the function of predicting and calculating the business effects corresponding to changes or reallocations of medical resources by referring to the information in each database of the data storage area 283. As described above, the means 295 is equipped with a resource reallocation unit 295A, a bottleneck processing unit 295B, a score evaluation unit 295C, a comparative analysis unit 295D, and an auxiliary analysis unit 295E, and has the following functions: a function to calculate the profit increase that will result from moving or adding resources; a function to calculate simulations of an increase in the number of patients using hospital beds and an improvement in the average patient cost based on the bed occupancy rate; a function to calculate simulations of an increase in the number of patients and an improvement in the average patient cost by promoting early admission and discharge of patients; a function to calculate simulations of resource improvements that are bottlenecks due to hospital facilities and other fixed costs; a function to propose the placement of multiple medical office assistants and calculate simulations of the operation of multiple operating rooms; a function to convert the workload and profitability of each clinical department and clinical department group into scores and calculate simulations using score values; a function to periodically record fluctuations in workload scores and profitability scores and calculate fluctuation trends in workload and profitability for each clinical department; and a function to calculate the profit margin for each patient group and group them by clinical department or clinical group. In other words, the profit simulation means 295 has a complex function of performing various simulations in hospital management aimed at maximizing revenue and optimizing workload through the efficient allocation of medical resources, and providing data for management improvement.

[0091] This simulation provides data-driven insights into specific directions for business improvement, supporting managers in making quick, data-driven decisions. It also maximizes revenue and reduces workload through efficient resource allocation (resource movement, resource expansion). Furthermore, it supports medium- to long-term business strategies, enabling the setting of medium- to long-term business goals through trend analysis and evaluation of their achievement. For example, it can be integrated with a function to output simulation results for use as budgeting data in hospital management in subsequent years.

[0092] The profit increase simulation through resource relocation simulates the increase in profits obtained when resources are reallocated between medical departments, based on each database in the data storage area 283. For example, it calculates how much overall revenue improves when personnel or hospital beds are moved from a low-profit medical department to a high-profit medical department, or when resources are increased in a high-profit medical department.

[0093] The bed occupancy rate-based patient number and average patient revenue increase simulation uses bed occupancy rate data to simulate changes in revenue due to an increase in the number of patients or an increase in average patient revenue. For example, it calculates the increase in revenue when accommodating more patients through efficient use of beds, and the change in profit when the average patient revenue is increased. In this process, the profit margin for each patient group is calculated and registered for each clinical department or clinical group within the hospital, and the profit simulation module visualizes the profit margin for each patient group.

[0094] The simulation for increasing the number of patients and improving the average revenue per patient by promoting early admission and discharge aims to increase profitability by improving the turnover rate of hospital beds through earlier admission and discharge of patients. For example, it predicts the change in revenue that can be obtained by increasing the number of patients that can be accommodated as bed utilization becomes more efficient by accelerating admission and discharge. In this simulation as well, the profit margin for each patient group is taken into consideration.

[0095] Revenue simulations based on proposed improvements to fixed cost resources simulate changes in revenue when fixed cost resources such as equipment are acting as a bottleneck. For example, they calculate the effects of cost reductions and revenue increases expected from rearranging equipment or improving its utilization efficiency.

[0096] The simulation for optimizing medical office support and operating room operations simulates the revenue and efficiency improvements that can be achieved by optimizing the placement of medical office support staff and supporting the operation of multiple operating rooms. For example, it analyzes the potential for increased revenue through reduced workload for doctors and improved operating room utilization rates.

[0097] The simulation of workload and profitability scores for each clinical department and clinical group scores the workload and profitability of each department and clinical group, and calculates the change in scores after resource reallocation and the implementation of measures. For example, it provides simulation results that show increased profitability by adjusting the balance of workload.

[0098] The recording and trend calculation of workload and profitability scores involves periodically recording fluctuations in these scores, analyzing trends for each clinical department, and evaluating the long-term improvement effects. For example, it calculates how workload and profitability fluctuations have changed over a long period and predicts the sustainability of management improvements.

[0099] Figure 4 is a flowchart showing various processing procedures executed by the application program of the hospital management support system according to an embodiment of the present invention. This system supports management improvement based on the optimal allocation of medical resources through data collection, evaluation, simulation, and visualization output.

[0100] <Data collection and update processing> This system connects to various terminals and medical systems (electronic medical record system, accounting system, DPC system, etc.) within the hospital via communication IF22 when server 20 is started. Furthermore, initial setup is performed by loading various data such as the evaluation basis DB 283A, revenue management DB 283B, and resource management DB 283C from the data storage area 283 of the storage means 280, and deploying the necessary initial data into memory (step S401). Subsequently, the latest sales, costs, resource utilization rates, and other data are acquired via the communication means 220 and updated in real time (step S402). The need for updates is controlled based on the data's expiration date and frequency of fluctuation. An AI-powered expiration date setting function dynamically adjusts the expiration date according to data stability, learning and optimizing based on past data fluctuation trends. This ensures both timeliness and efficiency by applying shorter update cycles to frequently fluctuating data and longer cycles to stable data. The AI ​​dynamically adjusts the optimal expiration date based on past data fluctuation patterns and evaluation accuracy. Historical data fluctuation analysis is performed over time to evaluate the frequency and stability of fluctuations. A shorter expiration date is used for frequently fluctuating data, and a longer expiration date for less fluctuating data. Trend detection is performed, and the AI ​​uses anomaly detection algorithms and trend analysis to evaluate the data's stability. Trends and anomalies are identified based on whether revenue data fluctuates weekly or remains stable monthly.

[0101] <Assessment of workload and profitability: Score calculation and trend evaluation> Next, the score evaluation unit 295C generates workload scores and profitability scores for each clinical department or clinical group (step S403). The workload score is calculated by standardizing and weighting workload-related indicators such as staff working hours, number of consultations (including surgeries and examinations), number of assigned patients, bed occupancy rate, and complexity of medical treatment. The profitability score is calculated by standardizing indicators such as sales, costs, average patient spending, profit margin, and profitability per hour. These scores are recorded over time, and trend analysis is used to evaluate long-term improvement effects. Furthermore, revenue fluctuations due to seasonality and external factors are corrected using predictive models, and comparisons between medical departments can be made using the levelized scores. Furthermore, when calculating the profitability score, adjustments and seasonal factors may be made. If the impact of seasonality differs by medical department, a predictive model may be used to adjust for seasonality and smooth out fluctuations in the profitability score. By evaluating and managing this as a score that allows for a quick overview of workload and profitability, it becomes possible to improve management and resource allocation by enabling comparisons not only between individual medical departments but also across the entire hospital or with other hospitals.

[0102] <Generating management indicator data and conducting profit simulations> The control means 290 refers to the revenue management DB 283B and the resource management DB 283C, calculates management indicator data by associating management information with the quantity or number of hours of medical resources, and normalizes it as a unit management indicator (step S404). The profit simulation means 295 predicts the impact of changes, transfers, and expansions of medical resources based on these unit management indicators. The resource reallocation unit 295A calculates the profit increase effect due to resource transfers between clinical departments, and the bottleneck processing unit 295B detects decreases in utilization rate and cost efficiency and generates improvement plans (step S405). Furthermore, multiple simulation modes are available, including improvements to profitability by patient group, bed occupancy rates, fixed cost resources, and optimization of medical office support and operating room operations. Furthermore, the simulation can also be performed on profits and related factors such as bed occupancy rates and medical expense resources. Alternatively, the profit margin for each patient group, which is a group of patients, can be calculated for each clinical department or clinical group within the hospital, and the patients can be grouped and simulated. As a resource reallocation simulation, the profit simulation means 295 calculates the resource unit profit for each clinical department and simulates the increase in profit due to resource movement. As a bed occupancy rate simulation, simulations are performed to improve the average patient cost and increase the number of patients based on the bed occupancy rate. As an optimization of fixed cost resources, the bottleneck processing unit detects bottlenecks in equipment utilization and performs improvement simulations.

[0103] Furthermore, the profit simulation means 295 may automatically generate resource reallocation proposals using a trained model. By training the AI ​​model with past simulation history, actual business results, and resource utilization rate data, it predicts patterns of resource increases and decreases that contribute to revenue improvement. For example, by learning past measures that improved profit margins, it can automatically propose a "staff increase proposal" or a "reallocation proposal" when similar conditions are automatically detected. This allows for the presentation of automated simulation results in addition to manual operation.

[0104] <Alert processing> The alert processing means 293 monitors sudden or significant fluctuations in workload and profitability, and if these exceed a threshold, it displays an alert on the in-hospital terminals 10 and 30, or notifies the manager via email or SMS on their mobile device (step S405).

[0105] <Display, Visualization, and Interactive Operation> The display control means 292 integrates management indicator data, scores, simulation results, and alert information to visualize the management status of each clinical department and clinical group in a dashboard format (step S407). Furthermore, the display control means 292 may visualize profit forecasts based on potentially additional resources. For example, the number of medical professionals expected to apply or unused operating rooms and hospital beds are modeled as potential additional resources, and the change in revenue when these are virtually added is simulated. The system can evaluate future expansion scenarios by using the number of possible additions as an input parameter and displaying the potential additional profit as a predicted value in a graph. The displayed information is presented visually in various formats such as line graphs, bar graphs, and heatmaps, allowing users to grasp the differences in revenue structure and resource efficiency for each medical department at a glance. User IF294 receives input from the hospital terminal in response to user input operations, allows for changes to simulation conditions and resource allocation proposals, and immediately reflects the recalculation of results. Furthermore, the profit simulation means 295 compares the history of executed simulations with actual business data and performs a comparison of planned and actual results to form a continuous improvement cycle.

[0106] Figure 5 is a follow-up chart showing the bottleneck processing procedure implemented by the hospital management support system. This process quantitatively analyzes resource utilization and workload, dynamically sets baseline values ​​manually or using AI, identifies potential bottlenecks, and then performs improvement simulations and visualizes the results.

[0107] <Data collection (S501)> The control means 290 acquires resource utilization rates, workload, equipment utilization rates, and fixed cost information for each clinical department or clinical group from the evaluation basis DB 283A, revenue management DB 283B, and resource management DB 283C. Furthermore, it acquires fixed cost resource-related data such as equipment utilization rates, maintenance costs, operating hours, and material costs, and stores them as integrated analysis target data.

[0108] <Resource utilization analysis processing (S502)> The control means 290 analyzes the utilization rate, usage frequency, and load distribution of each resource based on the acquired data. By calculating the occupancy rates of operating rooms, medical equipment, and hospital beds, and evaluating the workload of staff such as doctors and nurses, as well as the number of patients they are responsible for, we identify and visualize imbalances in over- and under-occupancy. This allows us to conduct a basic analysis to identify potential resource bottlenecks that are hindering management efficiency.

[0109] <Setting reference values ​​(S503)> The bottleneck processing unit 295B sets a baseline value for the utilization rate or workload of each resource. The baseline value may be set manually as a fixed value, or it may be configured to be dynamically adjusted by AI. The AI ​​learns from past operational history, seasonal variations, infectious disease outbreak data, economic indicators, etc., and dynamically corrects the baseline value using time series models such as LSTM (Long Short-Term Memory) or SARIMA (Seasonal ARIMA). Furthermore, to analyze the impact of external factors, extrinsic analysis models such as XGBOOST and Random Forest are used to optimize the baseline values ​​according to social and seasonal fluctuations. For example, adjustments can be made such as setting a higher hospital bed occupancy rate baseline in winter and a lower profitability baseline during periods of economic downturn. Furthermore, bottleneck thresholds are set for each resource, with a threshold value for what constitutes a bottleneck (e.g., utilization rate below 80%, excessive concentration of usage on a specific resource). If a resource's utilization rate or usage frequency exceeds this threshold, it is flagged as a potential bottleneck. The threshold values ​​can also be adjusted based on factors such as seasonality and social phenomena, and the system may be designed so that AI automatically sets the bottleneck thresholds. In this case, in addition to data from each department within the hospital (utilization rate, number of patients, waiting time, revenue, etc.), data from various external data sources such as seasonal data (influenza outbreaks, climate change, seasonal events) and social factor data (economic conditions, infectious disease outbreaks, etc.) can be integrated to acquire data. Changes in seasonality and social factors can be constructed as long-term time-series data, allowing for the extraction of resource usage trends for each season or during specific event periods. As a time-series forecasting model, the AI ​​model can learn resource utilization patterns by using time-series analysis models such as LSTM (Long Short-Term Memory) and SARIMA (Seasonal ARIMA) to predict how seasonal and social factors affect resource usage trends. As a factor analysis model, in cases where resource utilization fluctuates based on external factors (e.g., epidemics or economic fluctuations), models such as XGBOOST and Random Forest, which incorporate external variables that can respond to changes in seasonal and social factors into the forecasting model, can be used to measure the impact of these variables and reflect them in setting baseline values. Dynamic adjustment of baseline values ​​can also be performed by setting different bottleneck baseline values ​​for each season and factor. For example, the baseline value for hospital bed occupancy rate can be raised during winter influenza outbreaks, and the revenue baseline can be adjusted when a deterioration in the economic situation is predicted. In addition, methods for resolving bottlenecks can be managed as a checklist and used as input to a large-scale language model, which can then be displayed as advice.

[0110] <Comparison with reference values ​​(S504) · Identification of potential bottlenecks (S505)> After setting a threshold value for determining a bottleneck (step S503), the set threshold value is compared with the measured value of each resource, and if it exceeds or falls below the threshold, it is extracted as a bottleneck candidate. Resources that exceed that threshold are identified as bottleneck candidates (step S505). The identified bottlenecks are managed as a bottleneck list and categorized by resource, such as facilities, equipment, personnel, and hospital beds. Prioritization is calculated based on impact (contribution to revenue) and the degree of uneven distribution of workload, and the bottlenecks are sorted in order of their management importance. Identifying bottleneck resources involves prioritizing a list of facilities with excessively low utilization rates, such as operating rooms and waiting rooms, or clinical departments where staff are overloaded. Prioritizing these resources based on their impact can then be sorted and visualized.

[0111] Furthermore, to quantify the workload of healthcare professionals, a system for calculating a capacity index may be adopted. The capacity index is calculated as a normalized score by weighting each element, using the actual working hours, number of patients assigned, and workload indicators (such as the number of surgical assistance procedures and the number of medical records) for each profession as input variables. For example, the physician capacity index can be calculated as (working hours × number of patients assigned) / average workload standard value, and the nurse capacity index as (number of surgical assistance procedures + number of nursing records) / number of staff. By using this index, it is possible to quantitatively grasp the workload imbalances between professions.

[0112] Furthermore, some resources are interconnected and can be treated not only as single resources, but also as composite resources combining multiple resources, such as the number of hospital beds and operating rooms, or the number of examination slots and outpatient appointment slots. The system analyzes the correlations between these composite resources and estimates and visualizes, for example, "the impact of increased operating room occupancy on hospital bed occupancy" or "the contribution of examination room occupancy to outpatient revenue." This allows for the simultaneous identification of not only individual bottlenecks but also interconnected resource constraints.

[0113] <Improvement proposals based on simulation (S506)> The profit simulation means 295 simulates and generates multiple improvement scenarios for resolving the identified bottleneck resource. For example, the scenarios may include adding medical office support, reallocating the number of hospital beds, changing or increasing / decreasing operating room operations, adding equipment or adjusting operating hours, and accelerating patient admission and discharge. For each scenario, the profit increase rate, cost reduction effect, and workload fluctuation rate after resource reallocation are calculated, and the improvement effect is quantitatively calculated to present the most effective improvement plan for resolving the bottleneck.

[0114] <Evaluation and prioritization of improvement proposals (S507)> The score evaluation unit 295C evaluates the effectiveness of the improvement plan using the workload score and the profitability score. The scores are normalized to a range of 1 to 100 points. The workload score is calculated based on factors such as staff working hours, number of consultations, and number of patients, while the profitability score is calculated based on factors such as profitability, cost efficiency, and profit margin per unit. A weighted average score is calculated for each improvement proposal, and the most effective scenario is presented as the priority option. Furthermore, by comparing the current score with past data, the trend of score fluctuations can be analyzed, and the sustainability of improvement in the medium to long term can be evaluated.

[0115] <Visualization display and alert notification (S508)> The display control means 292 visualizes and outputs improvement suggestions and potential bottlenecks on the dashboard. The display intuitively presents resource utilization, workload, and profitability scores using graphs and color coding. When the alert processing means 293 detects a resource that is in high need of improvement, it sends a warning notification to the in-hospital terminals 10, 30 or the management terminal. Furthermore, methods for resolving bottlenecks can be stored in a checklist format, input into a large-scale language model (LLM) to automatically generate improvement suggestions, and then displayed alongside the dashboard.

[0116] The specific method for converting scores involves quantifying the workload and profitability of each clinical department and clinical group. <Calculation of workload score> • The workload is calculated based on indicators such as the number of patients per medical department, consultation time, number of consultations, working hours of doctors and nurses, and the complexity of medical treatment. • Standardize factors such as the number of consultations and working hours, calculate the deviation from the mean, and determine the score. The score is then normalized to a range of 1 to 100. • If a specific indicator significantly impacts the workload (e.g., a medical department with a large number of patients), weight each indicator accordingly. For example, assign a weight of 40% to the number of patients, 30% to working hours, and 30% to the number of consultations. <Calculation of Profitability Score> • The revenue of a medical department is calculated as medical fees (unit price) x number of consultations. Expenses include personnel costs, medical supplies costs, and equipment maintenance costs. • Evaluate the profitability of each medical department by dividing revenue by expenses. This profit margin is then used to create a score, which is standardized for comparison with other medical departments. • Convert scores into a 100-point scale or a 5-point rating system, making the profitability of each medical department immediately apparent. For example, a score of 100 would be assigned to a profitability rate of 20% or higher, and a score of 50 to a profitability rate of 5% or lower, creating a hierarchical system. <Regular score updates and trend analysis> • Scores fluctuate depending on business and revenue performance, so scores are recalculated monthly and quarterly to maintain the most up-to-date scores. By recording the history of score fluctuations, we can analyze how the workload and profitability of each clinical department change over time. This allows us to predict the occurrence of risks such as increased workload and decreased profitability. <Overall Score> • The workload score and profitability score are combined and weighted to create a total score. For example, if the workload score is 60 points and the profitability score is 80 points, the workload score is weighted 40% and the profitability score 60%, resulting in a total score of 70 points. • Using a comprehensive score allows for a holistic evaluation of each medical department, making it easier to compare with other departments.

[0117] Quantitative evaluation using score values ​​is useful for assessing the effectiveness of resource relocation or resource expansion. By comparing changes in workload scores and profitability scores for each clinical department or clinical group before and after resource relocation, it becomes possible to measure the extent to which resource relocation has affected operational efficiency and profitability. Setting target scores according to the purpose of resource relocation and comparing them with actual results clarifies the degree of target achievement and contributes to budget management. Resource expansion serves as an indicator of whether the workload score for the entire clinical department or clinical group has decreased, i.e., whether operational efficiency has improved. Furthermore, the profitability score can be used to evaluate how much new revenue has increased as a result of resource expansion, or whether there has been an improvement in the number of patients or the average patient spending. By regularly evaluating the effects of resource relocation or expansion with scores and building a PDCA cycle that plans the next resource allocation based on the results, continuous management improvement becomes possible.

[0118] Figure 6 illustrates the before-and-after of the hospital room profit simulation. (A) shows the profit simulation by medical department, (B) shows the additional profit for each medical department, (C) shows the results of the hospital room relocation simulation, and (D) shows the total profit before and after the simulation. This specifically evaluates how the relocation of resources (hospital rooms) affects the profitability of each medical department.

[0119] Figure 6(A) shows the monthly profit per patient room for each medical department (internal medicine, general surgery, ophthalmology, and otolaryngology), visualizing the differences in profitability among the departments. The total profit with the current patient room layout is 1,600 million yen, but after a simulation of revising the patient room layout, the total profit is expected to increase to 1,700 million yen, an increase of 100 million yen. In the simulation, the profit simulation module calculates the breakdown by medical department and the AI ​​generates resource movements or resource additions that will increase profits. In other words, the profit changes for each medical department will be as follows. Internal Medicine: Reducing the number of patient rooms by one resulted in a decrease in profit from 200 million yen to 180 million yen (-20 million yen). General Surgery: There is no change in the number of patient rooms, and profits remain unchanged at 1,000 million yen. Ophthalmology: By increasing the number of patient rooms by one, profits increased from 360 million yen to 480 million yen (+120 million yen). ENT (Ear, Nose, and Throat): No changes in the number of patient rooms or profits. This simulation demonstrates that increasing the number of ophthalmology wards, in particular, can increase overall profits. The increased profits resulting from the revised layout are visually shown, and resource allocation can be optimized for each medical department. The increase or decrease in the number of hospital beds is based on the hospital bed occupancy rate (not shown) calculated by the hospital bed occupancy rate management module. The hospital bed occupancy rate management module then performs a simulation of room relocation based on the current number of rooms and the number of additional rooms that can be added, calculated from the maximum number of rooms that can be physically accommodated. While there is no change in the number of hospital rooms as a whole hospital, an increase in profits can be expected due to resource changes between clinical departments. Furthermore, a clinical group refers to a team formed by collaboration between various clinical departments, or a group formed by gathering doctors and medical professionals selected from various clinical departments.

[0120] Figure 6(B) shows the potential benefits that increases or decreases in resources can bring to each department by indicating the amount of additional profit each department can generate. Based on the additional profit, it is reasonable to focus on ophthalmology. Ophthalmology has a high profit per patient room (Figure 6(C)), and the additional profit from increasing the number of patient rooms is also larger than in other departments, so it is expected to have an effect on increasing profitability. The simulation results show that adding one patient room to ophthalmology is expected to increase profits by 120 million yen, which is a higher revenue-generating effect than in other departments.

[0121] Figure 6(D) visualizes the change in total profit after resource reallocation through simulation. While the total profit before resource movement was 1,600 million yen, reallocating resources (particularly increasing the number of ophthalmology rooms by one and decreasing the number of internal medicine rooms by one) results in a total profit of 1,700 million yen after simulation, indicating an expected increase in profit of 100 million yen. This result demonstrates that resource reallocation improves the overall revenue of the hospital and visually illustrates the profitability improvement achieved by concentrating resources in specific medical departments.

[0122] Figure 7 is a diagram illustrating the hospital's surgical flow, showing information related to surgery, such as the name of the surgery, the scheduled admission date, preoperative examinations, the surgeon, discontinuation of medications, surgical instruments, the date of surgery, anesthesiology consultations, obtaining and type of consent forms, and other restrictions. This information is a crucial factor in resource allocation and scheduling in the simulation of the present invention, as described below. These elements function as basic data to enable appropriate resource allocation and schedule adjustments through simulation, and this basic data is stored in a database within the hospital management support system 2 or a database within the medical system 3. The patient management database stores basic information related to surgery and hospitalization, such as the scheduled admission date, preoperative examinations, surgery date, surgeon, and scheduled anesthesiology consultations for each patient. The resource management database stores information on hospital beds, operating rooms, surgical instruments, and medications, and manages the utilization and reservation status of each resource. This database allows for optimal resource allocation based on the simulation. The medical procedure database stores information on the status of consent form acquisition, the type of consent form, and other restrictions. This allows for management of whether necessary procedures have been completed before surgery and reflects this in the simulation. As a schedule management database, it stores schedule information related to surgeries and hospitalizations, ensuring smooth coordination of resources and appointments. This optimizes the scheduling of surgeries and examinations to avoid overlapping with other patients. Through these databases, the hospital management support system can comprehensively manage the status of each clinical department and patient, enabling resource allocation and scheduling based on simulations. Furthermore, by updating and synchronizing data, simulations are always conducted based on the latest information.

[0123] • Name of surgery and surgeon The required resources vary depending on the type of surgery and the qualifications and skills of the surgeon performing it, which affects the appropriate allocation of resources. • Scheduled date of hospitalization and date of surgery These dates directly impact resource scheduling and are crucial factors in optimizing the allocation of hospital beds and operating rooms. • Pre-operative examination and anesthesiology consultation By allocating resources at the appropriate time to patients who require these preparations, we help ensure that surgery proceeds smoothly. • Discontinue medication If discontinuation of certain medications is necessary, the pre-operative preparation period will differ, which will affect resource planning. • Types of surgical instruments and consent forms Securing the necessary surgical instruments and preparing consent forms are essential for performing the surgery, and it is important to track resource allocation and document preparation status through simulations.

[0124] The profit indicator calculation module of the present invention comprehensively manages resources within a hospital and quantitatively evaluates the extent to which each resource contributes to business results. Specifically, it incorporates a wide range of data related to clinical operations, such as "number of waiting patients, number of patients, number of doctors, number of nurses, number of medical office assistants, number of nursing assistants, number of hospital beds, number of operating rooms, number of surgical slots, number of surgical materials, number of drugs, number of anesthesiologists, available working hours for anesthesiologists, and working hours by clinical department," and analyzes this data in correspondence with revenue data at the clinical department or clinical group level. This module calculates management indicators such as profit margins, cost efficiency, and utilization rates for each resource unit and normalizes them as unit management indicators. This makes it possible to visualize which resources are contributing to increased profitability or are incurring excessive costs, and can be used to review resource allocation and prioritize improvement measures. Therefore, this module constitutes a core function that supports data-driven decision-making in hospital management and maximizes the use of limited medical resources to simultaneously improve profitability and operational efficiency. [Example 1]

[0125] <Figure 8-10> Figures 8-10 are explanatory diagrams that allow for an intuitive understanding of bottlenecks by job type and medical department, and enable immediate visualization of the management effects of resource allocation and increases / decreases. This makes it possible to comprehensively support the reallocation of medical resources, the decision of whether or not to increase staffing, and the formulation of management strategies, including comparisons with other hospitals.

[0126] Figure 8 (simulation screen for simultaneous adjustment of surgical slots for multiple clinical departments) is a diagram showing a management simulation user interface that can simultaneously adjust surgical slots for multiple clinical departments, according to one embodiment of the present invention. This diagram shows the processing content corresponding to "the process of calculating management indicator data by associating management information with the quantity or number of hours of medical resources and calculating unit management indicators" and "the provision of an interactive visualization user interface". The system's processor acquires resource information such as gross profit, unit gross profit (gross profit / slot), current number of surgical slots, and number of waiting patients for each clinical department, including otolaryngology, general surgery, and ophthalmology, and recalculates these in real time based on user input. On the screen, the number of surgical slots for each medical department can be adjusted using sliders or ± buttons, and the system searches for the optimal allocation while ensuring that the total number of surgical slots does not exceed a constraint value (e.g., 7.5 slots or less). The cell being manipulated is highlighted in light yellow, and the change in gross profit is calculated in real time. When profit increases, the cell background is displayed in green, and when it decreases, it is displayed in red, allowing users to visually grasp the direction of change. This UI configuration, which allows for cross-functional manipulation of allocations across multiple medical departments, enables administrators to instantly evaluate the optimal allocation while taking into account the constraints of the entire hospital.

[0127] Figure 9 (Capacity Simulation Screen during Nurse Bottleneck) shows the capacity simulation results when nurses or nurse anesthesiologists are the bottleneck. This diagram shows the processing content corresponding to "bottleneck detection," "calculation and correlation analysis of healthcare worker capacity index," and "efficiency visualization through comparison with other hospital data." The system's processor acquires input data such as the number of nurses, the number of surgical assistance tasks per nurse, the number of patients assigned to each nurse, and the application status, and calculates a capacity index. If, based on comparisons with other hospitals, the number of patients per person in the same profession is lower than in other hospitals, that profession will be identified as a bottleneck. If a bottleneck is identified, both scenarios are generated and compared: (a) a scenario in which staffing is increased when applications are received, and (b) a scenario in which the workload per person is increased. In the simulation table, cells that are subject to change (number of people / number of patients) are surrounded by a gray border and highlighted in blue when changed. The rightmost column shows the increase in cost and the increase in gross profit side by side, and the profit increase due to bottleneck improvement is displayed with a green background. For example, adding one anesthesiologist nurse would increase the overall gross profit of the operating room by 4.2 million yen, quantitatively demonstrating the effectiveness of resource enhancement. In this way, managers can rationally select the optimal strategy for increasing staff and reallocating tasks by considering application status and data from other hospitals.

[0128] Figure 10 (Simulation screen for cost increase when there is no bottleneck) shows a cost increase scenario when anesthesiologists are not the bottleneck. This diagram shows the processing content corresponding to "resource surplus / shortage detection" and "simulation processing to quantify the effect of adding non-bottleneck resources." The processor retrieves data on the number of anesthesiologists, the number of patients they handle, and comparative data with other hospitals, and calculates a capacity index. If it is determined that anesthesiologists are not a bottleneck, an increase in gross profit due to increased staffing cannot be expected, so the gross profit for the entire operating room will be recalculated to reflect the cost of increasing staffing. As shown in the figure, increasing the number of anesthesiologists resulted in a decrease of 20 million yen in gross profit, clearly demonstrating that increasing staff is detrimental from a business perspective. Non-bottleneck areas are highlighted with a light blue background, and comparison data from other hospitals is displayed in the lower section. In this way, the system quantitatively determines the effect of increasing staff based on whether or not a bottleneck exists, supporting resource management that minimizes business risks. [Example 2]

[0129] The calculation structure of "management indicator data" and "unit management indicators" is shown below as a conceptual model. Here, management indicator data is the result of analysis calculated by correlating management information (sales, costs, etc.) with medical resources (personnel, equipment, time, etc.), and unit management indicators are normalized by resource units for each medical department and occupation. The "management indicator data" in this invention is fundamentally different from the abstract management evaluation classifications such as "functionality, profitability, productivity, and safety" shown in the conventional Non-Patent Literature 1. The classification in Non-Patent Literature 1 merely organizes the characteristics of medical departments and the hospital as a whole into qualitative categories such as "good" and "problems," and does not explicitly show the mathematical correspondence or causal structure between each evaluation item. Therefore, it is not possible to quantitatively estimate how sales, costs, and profits will change when resource quantities or operating hours are changed, and it is insufficient as a means of dynamically verifying management improvement measures. In contrast, the "management indicator data" of the present invention is constructed as a numerical data model that clearly correlates management information and medical resource information. That is, "revenue elements" such as medical fee points, patient unit price, drug price difference profit, and material cost difference, and "cost / operation elements" such as personnel costs, fixed costs, occupancy rate, and average length of hospital stay are combined in units of medical resources such as the number of doctors, nurses, hospital beds, and operating rooms. Management indicator data = f(management information, medical resources) This is a set of structured data that can be numerically derived in the form of [this]. This management indicator data is not merely an evaluation category, but forms the basis of calculation specifications that define how profits and costs are recalculated when the quantity or duration of resources changes. Furthermore, management indicator data is normalized for each medical resource to generate "unit management indicators," enabling quantitative comparisons and simulations between medical departments and with other hospitals. Therefore, while Non-Patent Document 1 remains a conceptual analytical framework, the management indicator data of the present invention has a qualitatively different technical system in that it specifically includes (a) a data structure that explicitly associates management information and resource information, (b) a calculation model that can be sequentially recalculated in response to resource modification operations, and (c) control means for visualizing the quantified results in real time. Thus, the "management indicator data" of the present invention is defined as a new data model that goes beyond conventional abstract classification systems and realizes the structuring, quantification, and dynamic updating of management information.

[0130] <Calculation model for management indicator data> In clinical department d, Revenue-d: Data related to sales (medical fee points, drug price difference profit, material cost difference profit, etc.) Cost-d: Cost data including labor costs, fixed costs, material costs, outsourcing costs, etc. R: Number of surgical slots, m: Number of doctors, b: Number of hospital beds, L: Average length of stay, etc. Let this be the input variable. Based on these inputs, the control means 290 uses the following relational expression: We calculate management indicator data (profit, profitability, and efficiency) for each medical department. Business performance indicator data (Profit-d) = Sales data (Revenue-d) - Cost data (Cost-d) In other words, Profit-d represents the revenue structure of medical department d, while Revenue-d and Cost-d depend on multiple resource variables such as r, m, b, and L, respectively. This Profit-d is a set of numerical data calculated by associating management information with the quantity and duration of resources. <Calculation model for unit management indicators> Unit management indicators are values ​​that normalize the above management indicator data on a resource-by-resource basis, enabling comparisons between different medical departments and with other hospitals. For example, it is calculated as follows: Profit per physician: UP - doctor - d = Profit - d ÷ Number of physicians (m) Profit per hospital bed: UP - bed - d = Profit - d ÷ Number of hospital beds (b) Profit per surgical slot: UP-OR-d = Profit-d ÷ Number of surgical slots (r) These "UP (Unit Profit)" metrics are indicators that show management efficiency on a resource-by-resource basis. This enables the comparison of productivity across different resources, such as doctors, hospital beds, and operating rooms, on the same scale. <Real-time Recalculation and Visualization Processing> When the user increases or decreases, for example, the number of doctors (Δm), the number of hospital beds (Δb), and the number of operating room slots (Δr) on the terminal, the control means 290 recalculates Profit-d and UP- using the changed resource quantity as an input. The display control means 292 immediately visualizes the recalculation result, and intuitively outputs the direction of change and the degree of influence, such as displaying the profit increase direction in green and the profit decrease direction in red. In this way, in the present invention, a series of processes of "resource change operation → arithmetic processing → normalization → immediate visualization" operate in联动, enabling an operation-integrated dynamic management simulation that could not be achieved in an abstract classification system.

[0131] The abstract classification of the conventional Non-Patent Document 1 only presents an evaluation framework and does not disclose or suggest specific technical means such as (i) numerical association with resource quantity and time, (ii) unit normalization, and (iii) recalculation and simulation with operation linkage. It cannot be said that those skilled in the art can self-evidently reach the configuration of the present invention from the abstract classification, and since the implementation requirements (data design, arithmetic specification, UI control) are also qualitatively different, the difference between the present invention and the prior art is clear.

Example 3

[0132] <Change by AI> The change of medical resources may be automatically determined by a learned model. The learned model refers to an artificial intelligence (AI) model that has learned past management index data, resource allocation data, and the corresponding revenue results or efficiency scores. The AI model is constructed using machine learning techniques such as neural networks, gradient boosting trees (XGBoost), or linear regression models. After learning, the model receives, as inputs, the sales, costs, resource utilization rates, etc. of each current medical department or medical group, and generates, as an output, an estimated value of the resource change amount ΔR (number of doctors, number of hospital beds, number of operating room slots, etc.). The control means 290 automatically determines the direction and quantity of increase or decrease of medical resources by referring to the output results of the AI ​​model, and recalculates the management indicator data and unit management indicators based on the results. This allows the trained model to autonomously suggest the optimal resource allocation based on historical data, without requiring manual intervention from the user. For example, if the model outputs "add one operating room," "add two nurses," or "reduce internal medicine beds by three," the system recalculates the management indicators based on that output and immediately displays the predicted revenue changes on the visualization screen.

[0133] The trained model is built based on historical business data and resource allocation history. The training data used will include revenue, costs, profits, number of medical resources, bed occupancy rate, average length of stay, number of surgeries for each medical department, and management performance data corresponding to changes in these factors. The model learns the correlation between the amount of resources contained in this data and profit or efficiency scores, and, given the current medical resource configuration as input, estimates the amount of resource increase or decrease (ΔR) or the expected change in profit as output. Machine learning algorithms such as linear regression, gradient boosting trees, or neural networks can be used for training. The trained model uses the trained parameters to estimate the optimal allocation of resources in each clinical department or clinical group, and the control means 290 automatically generates resource change proposals. This enables the automatic presentation of allocation proposals based on past data by AI without requiring any input operations from the user, thereby speeding up and improving the accuracy of management decisions. [Example 4]

[0134] <Regional Healthcare Reorganization Support System> The hospital management support system of the present invention can be used to support the promotion of regional medical care plans and the consideration of hospital bed reallocation. For example, in formulating medical plans at the prefectural level, hospital management support systems located on servers or in a cloud environment at multiple medical institutions within the region are linked to aggregate and compare management indicator data and unit management indicators for each hospital on a regional basis. This allows for the analysis of resource utilization efficiency, such as bed occupancy rates, length of stay, number of doctors and nurses, and number of surgeries, on a unified scale for each region.

[0135] For example, by comparing unit management indicators (profit per bed, average length of stay, occupancy rate, etc.) for acute care beds and rehabilitation beds, it is possible to run simulations recommending the conversion of acute care beds to rehabilitation or chronic care beds in areas where profitability and hospitalization efficiency are declining. Furthermore, by visualizing workload and profitability scores across multiple hospitals, it is possible to numerically grasp the uneven distribution of medical resources within a region. This allows for the early detection of issues such as an oversupply or shortage of medical personnel in specific regions, prolonged surgical waiting lists, and limitations in emergency acceptance capacity, enabling administrative bodies and regional medical liaison offices to formulate evidence-based adjustment policies.

[0136] Furthermore, this system can be linked with prefectural medical planning systems to input future population projections and changes in disease structure (e.g., increase in chronic diseases due to aging, decrease in emergency medical demand, etc.) as variables, predict medical demand 5 to 10 years into the future, and then simulate the optimal distribution of hospital bed functions. This configuration makes it possible to consider hospital relocation and medical area redefinition with objective and quantitative evidence when promoting regional medical reorganization. [Example 5]

[0137] <Policy and Administrative Analysis Platform for Differentiating Hospital Bed Functions> The system of the present invention can be configured to link with public medical databases such as DPC data, claims data, and healthcare professional statistics data, and to perform functional differentiation evaluations at the regional or hospital group level. For example, the system retrieves admission and discharge numbers, length of stay, and medical fee points from the DPC database, and obtains cost information such as drug costs, testing costs, and material costs from claims data to automatically generate Profit-d and unit management indicators for each hospital. At this time, the control means 290 constructs a network model in which each medical institution within the same region is a node and the patient's transfer route is an edge, and quantifies the overlapping functions and referral relationships between hospitals and outputs them to the display control means 292.

[0138] Based on this data, the government can simulate the overall healthcare delivery system in the region and numerically predict the impact of policy changes (e.g., reduction of acute care beds, strengthening of rehabilitation care) on total medical expenses and occupancy rates. On the other hand, healthcare institutions can strategically redesign their resource allocation to align with policy guidelines and regional needs. For example, for medical departments whose profitability is declining under the DPC comprehensive evaluation system, we can support the conversion of hospital bed functions by estimating scenarios in which resources are reallocated to high-profit medical departments. This allows both government agencies and hospitals to discuss using common numerical indicators, enabling a shift from traditional intuitive and empirical policy decisions to data-driven policy formulation and management optimization. Therefore, the present invention also has extremely high practical value as an administrative analysis platform for regional healthcare reorganization and hospital bed function differentiation policies. [Example 6]

[0139] (Line, equipment, and setup changes) In the manufacturing operations optimization system, resources include the number of production lines, equipment, workers, setup time, and maintenance slots, while demand is expressed as product-specific order volume and delivery date. Unit management indicators include marginal profit per line hour, work-in-progress (WIP), and delay penalties. Throughput, inventory, and on-time delivery rates are recalculated in conjunction with UI adjustments to line allocation, shifts, and setup sequences. Setup constraints and common fixture conflicts are managed using constraint graphs, and alternative batching and resequencing options are presented. [Example 7]

[0140] Accommodation and Retail (Guest Room Staff / Cleaning / Cashier / Overbooking) As a lodging and retail operations support system, resources are represented by the number of rooms, cleaning crew slots, front desk staff, number of POS registers, etc., while demand is represented by the number of reservations, arrival time distribution, and customer traffic. Cancellations and unfulfilled guests are modeled probabilistically, and overbooking and staff reallocation are optimized within the range that meets service levels (maximum waiting time / complaint rate). Unit management indicators are normalized by gross profit per room per hour or sales per register per hour, and occupancy rate, stay / waiting time, and gross profit are recalculated in conjunction with UI operations. [Industrial applicability]

[0141] This invention relates to a management support system that provides management support for hospitals and medical institutions, particularly for visualizing and proposing improvements to profitability, efficiency, and workload at the departmental level. It is extremely useful in the field of healthcare management because it can simultaneously achieve optimization of resource allocation across the entire hospital, improvement of the cost structure, and enhancement of patient care capabilities.

[0142] Furthermore, the technology of this invention can be applied not only to hospital management but also to any field where it is necessary to quantitatively understand the operational efficiency of medical resources and the cost of providing services, such as nursing homes, health checkup centers, and pharmacy chains. It can also be easily extended to AI simulations using management indicator data and benchmark comparisons with other facilities, and can therefore be used as an analytical platform for optimizing the entire regional medical network and for medical policy formulation.

[0143] Furthermore, this invention has extremely high industrial applicability as a foundational technology that enables management and administrative departments of medical institutions to intuitively grasp the effects of management measures, thereby achieving both improved operational efficiency and enhanced quality of medical services.

[0144] 1: In-hospital terminals 2: Hospital management support system 3: Medical system 10,30: In-hospital 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

[0145] The program of the present invention can be installed in computer terminals having computer functions such as CPU, memory, and storage, as well as mobile devices such as smartphones, tablets, and wearable devices, digital home appliances such as smart TVs, smart speakers, and smart home appliances, recording media such as USB memory, SD cards, hard disk drives (HDDs) / solid state drives (SSDs), dedicated equipment and terminals such as POS terminals, vending machines, ATMs, and medical equipment, and game consoles (home and portable). When this program is installed in medical equipment, it may be linked with the hospital's electronic health record (EHR / EMR) system.

Claims

1. A hospital management support system that visualizes the status of hospital management while supporting decision-making regarding the allocation of medical resources, The system comprises memory and a processor that executes a program stored in the memory, The aforementioned memory is managed on a departmental or clinical group basis. (a) A revenue management database that registers management information including at least sales and costs, and (b) A resource management database in which one or more of the following medical resources are registered as resource data: physicians, nurses, hospital beds, operating rooms, examination rooms, and medical equipment, and the quantity or operating hours corresponding to said medical resource. It is stored there, The processor executes the program, (1) A process of referring to the revenue management database and the resource management database, associating the management information with the quantity or hours of medical resources, calculating management indicator data for each medical resource, normalizing the management indicator data based on the quantity or hours corresponding to the medical resource, and calculating a unit management indicator, and (2) When the quantity or number of hours corresponding to medical resources is changed, the management indicator data and unit management indicators are recalculated based on the changed quantity or number of hours, and the changes in management indicators based on the results of the recalculation are visualized and output in real time. A hospital management support system characterized by achieving the following:

2. A hospital management support system according to claim 1, The hospital management support system is characterized in that the aforementioned changes are automatically determined by one or more of the following: a trained model, rule-based inference, an optimization solver, or a heuristic.

3. A hospital management support system according to claim 1, The aforementioned visualization output is a hospital management support system characterized by displaying management indicator data corresponding to a medical department or medical group selected by the user, along with management indicator data for other medical departments or medical groups, on the same screen.

4. A hospital management support system according to claim 1, The aforementioned processor, We acquire resource data and management indicator data provided by other hospitals. The items in the acquired data that correspond to a specific medical department or medical group are then mapped to the corresponding items of the hospital stored in the memory. Based on the sales, costs, and medical resources of both parties, comparative results including management efficiency or resource utilization will be derived. A hospital management support system characterized by implementing a process that quantifies and visualizes the differences between medical departments or medical groups based on the aforementioned comparison results.

5. A hospital management support system according to claim 4, The aforementioned processor, Based on the above comparison results, (i) Medical resources belonging to a medical department or medical group that fall below the standard value, (ii) Medical resources that are less efficient than the average of other hospitals, Detect at least one of the following: Based on the detected results, a flag or warning information indicating a bottleneck is added to the corresponding item in the resource management database. A hospital management support system characterized by implementing a process that visually highlights the flag or warning display based on the warning information on the screen.

6. A hospital management support system according to claim 1, The aforementioned processor, Regarding healthcare professionals, including physicians, nurses, pharmacists, clinical laboratory technicians, and radiological technologists, The healthcare worker capacity index is calculated based on at least one of the following: the number of patients each healthcare worker is responsible for, the number of hours they are assigned, or the number of surgeries / procedures they assist in, and the number of healthcare workers assigned to a clinical department or clinical group. Based on the analysis results obtained by analyzing the correlation between the healthcare worker capacity index and the aforementioned unit management indicators, resource reallocation measures including an increase in the number of patients under their care or an increase in the number of healthcare workers are estimated. A hospital management support system characterized by presenting the resource reallocation strategy and the estimation results in the visualization output.

7. A hospital management support system according to claim 1, The hospital management support system is characterized in that the resource data includes one composite resource from among surgical slots, examination slots, inpatient slots, ICU slots, rehabilitation slots, outpatient slots, emergency admission slots, and drug therapy slots, which are configured by associating two or more of the aforementioned medical resources.

8. A hospital management support system according to claim 1, The hospital management support system is characterized in that the aforementioned management indicator data is calculated based on at least one of the following: Diagnosis Procedure Combination (DPC) information, claims information, drug price difference profit, or material cost difference profit.

9. A hospital management support system according to claim 1, The aforementioned resource management database has a function to register the potential number of additional resources that can be added for each medical resource. A hospital management support system characterized by calculating potential additional profit or potential additional sales based on the potential number of additional resources that can be added, in response to proposals for increasing or reallocating medical resources.

10. A hospital management support system according to claim 1, In the visualization output, Based on user input, the system displays detailed simulation results of proposed expansion or reallocation of selected medical resources. A hospital management support system characterized by providing a user interface that allows adjustment of the amount or target of changes to resources in response to a proposal for increasing or reallocating medical resources.

11. A program for causing a computer to function as a hospital management support system according to any one of claims 1 to 10.

12. A method for supporting hospital management that is performed by a hospital management support system according to any one of claims 1 to 10.

13. A recording medium in which the program according to claim 11 is recorded in a way that is readable by a computer.

Images