JP4552099B2 - Hospital user number prediction system - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to a system for predicting the number of hospital users for supporting a business establishment plan for a medical facility.
[0002]
[Background Art and Problems to be Solved by the Invention]
Conventionally, in business establishment plans for medical facilities, predictions are made according to the administrative divisions of the municipalities or the medical sphere, so it is impossible to grasp and predict the accurate population distribution due to the size of the area. It was. In addition, the population, the number of patients, and the number of users of the hospital are manually performed in independent systems.
[0003]
Furthermore, each system has the following problems.
Future population prediction model Predictions based on administrative divisions, estimations based on past population changes, and rate of increase / decrease rate, so the predicted values vary widely, so it is not accurate to predict facility users.
The national value is used for the patient number prediction model treatment rate data, and the treatment characteristics of each region are not reflected. In addition, it did not correspond to the prediction by medical subject necessary for business planning of medical facilities.
Since the straight line distance is used as the distance data between the corresponding area and the hospital, the terrain characteristics such as public transportation, road network and river are not considered.
[0004]
The present invention solves the above-described conventional problems, and provides a hospital user number prediction system capable of predicting the future number of patients to be used in a target hospital in consideration of regional characteristics and topographic characteristics. For the purpose.
[0005]
[Means for Solving the Problems]
In order to achieve the above object, the system for predicting the number of hospital users according to the present invention partitions the reference population in the primary mesh A, the reference population of the secondary mesh B that partitions the primary mesh A, and the secondary mesh B. Reference population that stores reference population data of at least the third mesh among the reference population data based on the national census composed of the reference population of the tertiary mesh and the reference population of the fourth mesh that divides the tertiary mesh with a large population Data storage means, target hospital for predicting the number of users and target area input means for inputting a plurality of secondary meshes of the target area , and a hospital for inputting the number of beds, positions, and distance parameters of all hospitals in the target area Population prediction data comprising information input means and future birth rate, future survival rate, and future movement rate data is stored, and the population prediction data and the reference population data are stored. Population prediction means for obtaining and outputting future predicted population data below the third mesh of the target area input to the target area input means by the cohort factor method based on the reference population data stored in the data storage means ; The patient number prediction means for storing the treatment rate data comprising the treatment population for a population of 100,000, and obtaining and outputting the predicted patient number data from the treatment rate data and the predicted population data output from the population prediction means, and the target as gravity data between the hospital and the third mesh, said the distance r _N between mesh by the position and location of the target hospitals all hospitals of the hospital information within the target area that has been input to the input means (1 to N) The distance r between the tertiary mesh and the mesh by the position of the target hospital with respect to the sum Σ (m _N / r _N β) of the value r _N β multiplied by the distance parameter β divided by the number of bets m _n The distance parameter beta values m _n / r _n ratio _{β (m n / r n β} ) with a value obtained by dividing the number of bets m _n with r _n beta of multiplying / sigma seeking (m _N / r _N β) in _n And calculating the future predicted number of users of the target hospital based on the predicted gravity data output from the gravity data calculating means, the predicted patient number data output from the patient number predicting means , and the gravity data output from the gravity data calculating means. And a means for predicting the number of users to output .
[0006]
DETAILED DESCRIPTION OF THE INVENTION
Hereinafter, embodiments of the present invention will be described with reference to the drawings. FIG. 1 is a system configuration diagram showing an embodiment of a hospital user number prediction system according to the present invention.
[0007]
The system of the present invention includes a reference population input means 1, a target area input means 2, a hospital information input means 3, a population prediction system (population prediction means) 4, a patient number prediction system (patient number prediction means) 5, and the hospital gravity model. (Gravity data calculation means) 6, user number prediction system (user number prediction means) 7, and predicted user number output means 8.
[0008]
The reference population input means 1 stores reference population data (issued as a CD-ROM) based on the latest national census. As shown in FIG. 2, the reference population data includes a reference population in the primary mesh A divided into longitudes of 1 ° and latitudes of 40 ′, and 8 × 8 (about 10 km square) in the primary mesh A. The reference population of the secondary mesh B partitioned into two, the reference population of the tertiary mesh partitioned into 10 × 10 (about 1 km square) and the secondary mesh with a large population of 2 × 2 (about 0.2 mm). It is composed of a 4th-order mesh reference population divided into 5km square.
[0009]
The population prediction system 4 receives a reference population of at least the third mesh or less of the reference population input means 1 and the target area input means 2 inputs area information for the number of users of the hospital concerned. . This is because the maximum number of secondary meshes in the target area of the hospital is set to 9, and a 3 × 3, 2 × 3, and 3 × 2 secondary mesh area is set according to the population distribution. A secondary mesh code is input. For example, in FIG. 2, if the hospital is located in the secondary mesh Tachikawa 43 and the target area is set as 3 × 3, Ome 52, Tokorozawa 53, Shiki 54, Kichijoji 44, Mizoguchi 34, Musashifuchu 33, Hachioji 32, The area surrounded by Haijima 42 is the target area.
[0010]
In the population prediction system 4, the reference population of the 3rd mesh or 4th mesh of the target area, the future birth rate (data by prefecture) published as a CD-ROM by the Health and Welfare Statistics Association, the future survival rate (by prefecture) Data), future migration rate (data by prefecture) and future fertility ratio (uniform nationwide) based on the cohort factor method, as shown in FIG. 3, 0-4 years, ... 80-84 years , Predicted population data 7 by gender is output every 85 years old and every 5 years old. This data is output as prediction data after 5 years, 10 years, up to 25 years, and every 5 years.
[0011]
Next, the patient number prediction system 5 will be described. There are patient surveys by the Ministry of Health, Labor and Welfare as data on the number of existing patients, treatment rate data by wound and disease classification × age, treatment rate data by wound and disease classification by prefecture, and treatment rate data by age group by prefecture. Is published. From these three types of data, as shown in FIG. 4, data on the treatment rate (treatment population for a population of 100,000) by prefecture, treatment subject × age is created. Based on this treatment rate and the predicted population data 9, predicted patient number data 10 is output.
[0012]
On the other hand, the target area information input by the target area input unit 2 and the hospital information input by the hospital information input unit 3 are input to the hospital gravity model 6. The hospital information consists of target area map data, hospital data (name, number of beds, position), bridge data (name, position), and distance parameters (river, ie “shortest” substantial distance considering the bridge) β. Yes. And the said hospital gravity model 6 calculates the gravity data 11 of the said hospital from these input information. The gravity data 11 represents the gravity between the hospital and the target area (third mesh), that is, the suction force. The distance between all the hospitals (1 to N) in the target area and the mesh is represented by r _N , When the number of beds is m _N , the gravity of the hospital n is (m _n / r _n β) / Σ (m _N / r _N β). Here, gravity near 0 means that most people do not go to the hospital, and gravity close to 1 means that most people go to the hospital.
[0013]
FIG. 5 shows an example of gravity data between the hospital and the tertiary mesh in the target area where the number of secondary meshes is 3 × 2. In the figure, ◎ indicates the position of the hospital, and the dotted line indicates the position of the river. You can see that gravity data fluctuate across the river.
[0014]
Then, in the user number prediction system 7, the predicted patient number data 10 and the gravity data 11 are multiplied to output the number of users of the hospital and output together with the map data as shown in FIG. 6. The detailed output includes the predicted number of patients in the target area (total, outpatient outpatient, by gender, age, by medical subject) and the predicted number of hospital users (total, outpatient outpatient, by gender, by age, By medical subject).
[0015]
【The invention's effect】
As is clear from the above description, according to the present invention, the future number of patients to be used in the target hospital can be predicted in consideration of regional characteristics and topographic characteristics, from 5 years to a maximum of 25 years later. It is possible to predict the transition of the number of patients and propose an appropriate hospital facility scale. Moreover, when considering the relocation of facilities, it is possible to examine whether the number of patients will increase relative to the current value, and where the number of patients will increase. Furthermore, by simulating the current facility demand, it is possible to evaluate the hospital from the viewpoint of selecting the facility of the patient, whether the number of patients originally expected is satisfied.
[Brief description of the drawings]
FIG. 1 is a system configuration diagram showing an embodiment of a hospital user number prediction system according to the present invention.
FIG. 2 is a diagram for explaining a target area of reference population data.
FIG. 3 is a diagram for explaining predicted population data.
FIG. 4 is a diagram for explaining treatment rate data by age.
FIG. 5 is a diagram showing an example of gravity data.
FIG. 6 is a diagram for explaining the predicted number of users in the hospital.

Claims (1)

The reference population in the primary mesh A, the reference population of the secondary mesh B that partitions the primary mesh A, the reference population of the tertiary mesh that partitions the secondary mesh B, and the fourth that partitions the tertiary mesh with a large population Reference population data storage means for storing reference population data of at least a third mesh or less among reference population data based on a national census composed of mesh reference populations ;
Target area input means for inputting a plurality of secondary meshes of the target hospital and target area for predicting the number of users ,
Hospital information input means for inputting the number of beds, positions, and distance parameters of all hospitals in the target area ;
Population prediction data comprising data on future birth rate, future survival rate, and future movement rate is stored, and the cohort factor is based on the population prediction data and the reference population data stored in the reference population data storage means Population prediction means for obtaining and outputting future predicted population data below the third mesh of the target area input to the target area input means by the method ,
Storing the treatment rate data comprising the treatment population for a population of 100,000, and obtaining and outputting the predicted patient number data from the treatment rate data and the predicted population data output from the population prediction unit ;
As gravity data between the target hospital and the tertiary mesh, the distance r _N between the meshes based on the positions of all the hospitals (1 to N) in the target area and the positions of the target hospitals input to the hospital information input means distance r _n between the mesh by the distance to the parameter value obtained by multiplying the beta r _n total value obtained by dividing the number of bets m _n with _{β Σ (m n / r n} β), 3 mesh with the position of the target hospital the distance parameter ratio of the values divided by the number of bets m _n in beta obtained by multiplying the value _{r n β m n / r n} β (m n / r n β) / Σ seeking (m _n / r _n β) in Gravity data calculation means to output ;
A user number predicting means for obtaining and outputting a future predicted user number of the target hospital based on the predicted patient number data output from the patient number predicting means and the gravity data output from the gravity data calculating means; ,
A system for predicting the number of hospital users characterized by comprising:

Images