CN107368699A - A kind of hospital admission rate Forecasting Methodology based on existing consultation rate information - Google Patents
A kind of hospital admission rate Forecasting Methodology based on existing consultation rate information Download PDFInfo
- Publication number
- CN107368699A CN107368699A CN201710862694.3A CN201710862694A CN107368699A CN 107368699 A CN107368699 A CN 107368699A CN 201710862694 A CN201710862694 A CN 201710862694A CN 107368699 A CN107368699 A CN 107368699A
- Authority
- CN
- China
- Prior art keywords
- rate
- consultation rate
- consultation
- month
- date
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Medical Treatment And Welfare Office Work (AREA)
Abstract
A kind of hospital admission rate Forecasting Methodology based on existing consultation rate information, is characterized in that, comprises the following steps：A, hospital's first half of the year consultation rate monthly, or daily consultation rate, or the consultation rate of the first five years are counted, establish respectively month, date and time respectively with patient numbers' array；B, consultation rate predictor formula is determined according to first half of the year consultation rate monthly and corresponding month, daily consultation rate and corresponding date, annual consultation rate and corresponding time respectively；C, by month to be predicted second half year, or the date to be predicted, or the time to be predicted substitutes into the consultation rate that consultation rate predictor formula obtains the month, the date or the time, medical worker and medical material is reasonably distributed according to consultation rate, so that it is guaranteed that medical patient is timely diagnosed.
Description
Technical field：
The present invention relates to electronic engineering message area, and in particular to a kind of hospital admission rate based on existing consultation rate information
Forecasting Methodology.
Background technology：
Hospital outpatient is the most place of patient numbers, and medical quantity every year, monthly even daily differs, and
Hospitals at Present registers personnel and medical personnel's quantity for seeing and treating patients is changeless mostly, can not make the personnel of registering, medical matters people
Member or the quantity of medical material are matched well with the quantity of medical patient, are often occurred certain day, certain month or certain year
Consultation rate is higher, and the personnel that register, medical worker or medical material quantity are relatively fewer, medical patient can not be carried out timely
Diagnosis；Or occur certain day, certain month or certain year consultation rate it is relatively low, and the personnel that register, medical worker or medical material quantity phase
To more, the waste of medical worker and medical material is caused, so, if certain year, the consultation rate of even certain day certain month can be predicted
Certain year, the medical worker of even certain day certain month and the quantity of medical material are carried out reasonably arranging with deposit to be very necessary
's.
The content of the invention：
It is an object of the invention to provide a kind of hospital admission rate Forecasting Methodology based on existing consultation rate information, pass through this
Method can be predicted to the consultation rate of certain year, even certain day certain month, obtain medical worker and medical material according to consultation rate
To rational distribution, so that it is guaranteed that medical patient is timely diagnosed.
The hospital admission rate Forecasting Methodology based on existing consultation rate information of the present invention, it is used to achieve the above object
Technical scheme is, comprises the following steps：
Step a, the consultation rate of hospital's first half of the year monthly is counted, establishes month and patient numbers' array；
Step b, according to first half of the year consultation rate monthly and corresponding month, consultation rate predictor formula is determined：
Y=a1x2+a2x+a3
In formula, y is of that month consultation rate, and x is month, a1、a2、a3For coefficient；
Using month x and consultation rate y as known quantity, by fitting, a is calculated1、a2And a3；
Step c, the month to be predicted second half year is substituted into the consultation rate that consultation rate predictor formula obtains the month；
With month x, a1、a2And a3For known quantity, y is calculated.
As a further improvement on the present invention, described to be fitted to fitting of a polynomial, described multinomial is quadratic polynomial.
The hospital admission rate Forecasting Methodology based on existing consultation rate information of the present invention, can also be used to achieve the above object
Following technical scheme：
Comprise the following steps：
Step a, hospital's first half of the year daily consultation rate, building maths modec and patient numbers' array are counted；
Step b, according to the first half of the year daily consultation rate and corresponding date, consultation rate predictor formula is determined：
Y=a1x+a2
In formula, y is the consultation rate on the same day, and x is the date, a1、a2For coefficient；
Using date x and consultation rate y as known quantity, by fitting, a is calculated1And a2；
Step c, the date substitution consultation rate predictor formula that the second half year to be predicted is obtained to the consultation rate on the date；
With date x, a1And a2For known quantity, y is calculated.
As a further improvement on the present invention, described to be fitted to fitting of a polynomial, described multinomial is an order polynomial.
The hospital admission rate Forecasting Methodology based on existing consultation rate information of the present invention, can also be used to achieve the above object
Following technical scheme：
Comprise the following steps：
Step a, the consultation rate of hospital's the first five years is counted, establishes time and patient numbers' array；
Step b, according to annual consultation rate and corresponding time, consultation rate predictor formula is determined：
Y=a1x3+a2x2+a3x+a4
In formula, y is consultation rate then, and x is the time, a1、a2、a3And a4For coefficient；
Using time x and consultation rate y as known quantity, by fitting, a is calculated1、a2、a3And a4；
Step c, time substitution consultation rate predictor formula to be predicted is obtained to the consultation rate in the time；
With time x, a1、a2、a3And a4For known quantity, y is calculated.
As a further improvement on the present invention, described to be fitted to fitting of a polynomial, described multinomial is cubic polynomial.
The beneficial effects of the invention are as follows：The present invention establishes out month and patient by counting the consultation rate of the first half of the year monthly
Number array, then according to first half of the year consultation rate monthly and determine consultation rate predictor formula in corresponding month, finally will under
Substitute into month to be predicted half a year in consultation rate predictor formula and obtain the consultation rate in the month；Count the first half of the year daily medical
Rate, and date and patient numbers' array are established out, then determined just according to the first half of the year daily consultation rate and corresponding date
Rate predictor formula is examined, the date to be predicted is finally substituted into consultation rate predictor formula to the consultation rate for obtaining the date；Before statistics
Several years annual consultation rates, and time and patient numbers' array are established out, then according to annual consultation rate and corresponding time
Consultation rate predictor formula is determined, finally the time to be predicted is substituted into consultation rate predictor formula and obtains the medical of the time
Rate.
By three of the above technical scheme can to hospital year consultation rate, moon consultation rate and day consultation rate be predicted,
By the consultation rate quantity of prediction come the quantity of the quantity for the doctor that arranges to see and treat patients accordingly, medical article and medicine equipment, help
In coordinating the job placement of medical worker of seeing and treating patients, doctor and medical material is set rationally to be utilized, so that it is guaranteed that patient can obtain
To timely diagnosing.
Brief description of the drawings：
Fig. 1 is the derivation of equation programme diagram of embodiment one.
Embodiment：
Embodiment one
The hospital admission rate Forecasting Methodology based on existing consultation rate information of the present embodiment, for predicting certain month medical
Rate, below by taking No.1 Hospital Attached to Harbin Medical Univ.'s (hereinafter referred to as breathing out the First Academy of medical university) as an example, the present embodiment is carried out detailed
Describe in detail bright：
The present embodiment comprises the following steps：
Step a, statistics breathes out the consultation rate of medical university in January, 2016 to June monthly, and consultation rate monthly is shown in Table 1
1 2016 years 1-6 month consultation rate detail lists of table
Data in table 1 establish month and patient numbers' array；
Step b, according to first half of the year consultation rate monthly and corresponding month, consultation rate predictor formula is determined：
Y=a1x2+a2x+a3 (1)
In formula, y is of that month consultation rate, and x is month, a1、a2、a3For coefficient；
Using month x and consultation rate y as known quantity, it is fitted by quadratic polynomial, calculates a1=-0.113, a2=
1.084、a3=0.832.
The present embodiment is specifically emulated on Matlab r2012b softwares, and simulated program is as follows：
close all
clear all
clc
X0=[1 2345 6]；Month known to %
Y0=[1.67 2.58 3.44 3.42 2.78 3.63]；% patient populations
A1=polyfit (x0, y0,2)；% is fitted conic section
X=[7 8]；% months to be predicted
Y=a1 (1) * x.^2+a1 (2) * x.^1+a1 (3) * x.^0% patient populations to be predicted
Program operation result is as shown in Figure 1.
Step c, the month to be predicted second half year is substituted into the consultation rate that consultation rate predictor formula obtains the month, with month
x、a1、a2And a3For known quantity, y is calculated.
Below by taking in July, 2016 as an example, substitute into formula (1) and obtain formula (2)
Y=a172+a27+a3 (2)
The a that step b is obtained afterwards1、a2And a3Numerical value substitute into formula (2), obtain the people of consultation rate y=2.9080 ten thousand in July.
Again by taking part of in August, 2016 as an example, substitute into formula (1) and obtain formula (3)
Y=a182+a28+a3 (3)
The a that step b is obtained afterwards1、a2And a3Numerical value substitute into formula (3), obtain August part consultation rate y=2.3046 ten thousand
People.The actual consultation rate of in July, 2016 and August is shown in Table 2.
Table in July, 2 2016 and August consultation rate detail list
As can be seen here, can be seen that by table 2, the July predicted according to the Forecasting Methodology of the present embodiment and August part are just
The actual consultation rate that rate is examined with July and August part is consistent, and its error is extremely small, in tolerance interval, therefore can be neglected not
Meter, this Forecasting Methodology are feasible.
Embodiment two
The hospital admission rate Forecasting Methodology based on existing consultation rate information of the present embodiment, for predicting the medical of one day
Rate,
It comprises the following steps：
Step a, hospital's first half of the year daily consultation rate, building maths modec and patient numbers' array are counted；
Step b, according to the first half of the year daily consultation rate and corresponding date, consultation rate predictor formula is determined：
Y=a1x+a2
In formula, y is the consultation rate on the same day, and x is the date, a1、a2For coefficient；
Using date x and consultation rate y as known quantity, by fitting, a is calculated1And a2；
Step c, the date substitution consultation rate predictor formula that the second half year to be predicted is obtained to the consultation rate on the date；
With date x, a1And a2For known quantity, y is calculated.
Described to be fitted to fitting of a polynomial, described multinomial is an order polynomial.
Embodiment three
The hospital admission rate Forecasting Methodology based on existing consultation rate information of the present embodiment, for predicting certain year medical
Rate, comprise the following steps：
Step a, the consultation rate of hospital's the first five years is counted, establishes time and patient numbers' array；
Step b, according to annual consultation rate and corresponding time, consultation rate predictor formula is determined：
Y=a1x3+a2x2+a3x+a4
In formula, y is consultation rate then, and x is the time, a1、a2、a3And a4For coefficient；
Using time x and consultation rate y as known quantity, by fitting, a is calculated1、a2、a3And a4；
Step c, the time that will be predicted substitutes into the consultation rate that consultation rate predictor formula obtains the time；
With time x, a1、a2、a3And a4For known quantity, y is calculated.
Described to be fitted to fitting of a polynomial, described multinomial is cubic polynomial.
Consultation rate predictor formula in embodiment two and embodiment three to ask for mode identical with embodiment one, herein no longer
The process asked for is repeated.
Claims (6)
1. a kind of hospital admission rate Forecasting Methodology based on existing consultation rate information, it is characterised in that comprise the following steps：
Step a, the consultation rate of hospital's first half of the year monthly is counted, establishes month and patient numbers' array；
Step b, according to first half of the year consultation rate monthly and corresponding month, consultation rate predictor formula is determined：
Y=a1x2+a2x+a3
In formula, y is of that month consultation rate, and x is month, a1、a2、a3For coefficient；
Using month x and consultation rate y as known quantity, by fitting, a is calculated1、a2And a3；
Step c, the month substitution consultation rate predictor formula that the second half year to be predicted is obtained to the consultation rate in the month；
With month x, a1、a2And a3For known quantity, y is calculated.
2. the hospital admission rate Forecasting Methodology according to claim 1 based on existing consultation rate information, it is characterised in that institute
State and be fitted to fitting of a polynomial, described multinomial is quadratic polynomial.
3. a kind of hospital admission rate Forecasting Methodology based on existing consultation rate information, it is characterised in that comprise the following steps：
Step a, hospital's first half of the year daily consultation rate, building maths modec and patient numbers' array are counted；
Step b, according to the first half of the year daily consultation rate and corresponding date, consultation rate predictor formula is determined：
Y=a1x+a2
In formula, y is the consultation rate on the same day, and x is the date, a1、a2For coefficient；
Using date x and consultation rate y as known quantity, by fitting, a is calculated1And a2；
Step c, the date to be predicted second half year is substituted into the consultation rate that consultation rate predictor formula obtains the date；
With date x, a1And a2For known quantity, y is calculated.
4. the hospital admission rate Forecasting Methodology according to claim 3 based on existing consultation rate information, it is characterised in that institute
State and be fitted to fitting of a polynomial, described multinomial is an order polynomial.
5. a kind of hospital admission rate Forecasting Methodology based on existing consultation rate information, it is characterised in that comprise the following steps：
Step a, the consultation rate of hospital's the first five years is counted, establishes time and patient numbers' array；
Step b, according to annual consultation rate and corresponding time, consultation rate predictor formula is determined：
Y=a1x3+a2x2+a3x+a4
In formula, y is consultation rate then, and x is the time, a1、a2、a3And a4For coefficient；
Using time x and consultation rate y as known quantity, by fitting, a is calculated1、a2、a3And a4；
Step c, the time that will be predicted substitutes into the consultation rate that consultation rate predictor formula obtains the time；
With time x, a1、a2、a3And a4For known quantity, y is calculated.
6. the hospital admission rate Forecasting Methodology according to claim 5 based on existing consultation rate information, it is characterised in that institute
State and be fitted to fitting of a polynomial, described multinomial is cubic polynomial.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710862694.3A CN107368699A (en) | 2017-09-19 | 2017-09-19 | A kind of hospital admission rate Forecasting Methodology based on existing consultation rate information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710862694.3A CN107368699A (en) | 2017-09-19 | 2017-09-19 | A kind of hospital admission rate Forecasting Methodology based on existing consultation rate information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107368699A true CN107368699A (en) | 2017-11-21 |
Family
ID=60302506
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710862694.3A Pending CN107368699A (en) | 2017-09-19 | 2017-09-19 | A kind of hospital admission rate Forecasting Methodology based on existing consultation rate information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107368699A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108877905A (en) * | 2018-06-12 | 2018-11-23 | 中南大学 | A kind of medical amount prediction technique of the hospital outpatient based on Xgboost frame |
| CN109919755A (en) * | 2019-02-15 | 2019-06-21 | 中国银行股份有限公司 | Mobile banking's dot data processing method, server and system |
| CN110097957A (en) * | 2019-04-22 | 2019-08-06 | 安徽晶奇网络科技股份有限公司 | A kind of hospital management analysis system based on big data |
| CN115083615A (en) * | 2022-07-20 | 2022-09-20 | 之江实验室 | Method and device for chain type parallel statistics of number of patients in multi-center treatment |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104952024A (en) * | 2015-06-19 | 2015-09-30 | 孟桂林 | Method for predicting emergency treatment visiting amount and hospital management system |
| CN106202847A (en) * | 2015-04-30 | 2016-12-07 | 青岛海信医疗设备股份有限公司 | A kind of medical Forecasting Methodology |
| CN106932361A (en) * | 2017-03-21 | 2017-07-07 | 江苏省农业科学院 | The method for building up of Peach fruits maturity forecast model |
-
2017
- 2017-09-19 CN CN201710862694.3A patent/CN107368699A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106202847A (en) * | 2015-04-30 | 2016-12-07 | 青岛海信医疗设备股份有限公司 | A kind of medical Forecasting Methodology |
| CN104952024A (en) * | 2015-06-19 | 2015-09-30 | 孟桂林 | Method for predicting emergency treatment visiting amount and hospital management system |
| CN106932361A (en) * | 2017-03-21 | 2017-07-07 | 江苏省农业科学院 | The method for building up of Peach fruits maturity forecast model |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108877905A (en) * | 2018-06-12 | 2018-11-23 | 中南大学 | A kind of medical amount prediction technique of the hospital outpatient based on Xgboost frame |
| CN108877905B (en) * | 2018-06-12 | 2020-11-10 | 中南大学 | Hospital outpatient quantity prediction method based on Xgboost framework |
| CN109919755A (en) * | 2019-02-15 | 2019-06-21 | 中国银行股份有限公司 | Mobile banking's dot data processing method, server and system |
| CN110097957A (en) * | 2019-04-22 | 2019-08-06 | 安徽晶奇网络科技股份有限公司 | A kind of hospital management analysis system based on big data |
| CN110097957B (en) * | 2019-04-22 | 2023-07-11 | 安徽晶奇网络科技股份有限公司 | Hospital management analysis system based on big data |
| CN115083615A (en) * | 2022-07-20 | 2022-09-20 | 之江实验室 | Method and device for chain type parallel statistics of number of patients in multi-center treatment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107368699A (en) | A kind of hospital admission rate Forecasting Methodology based on existing consultation rate information | |
| Vanbrabant et al. | Quality of input data in emergency department simulations: Framework and assessment techniques | |
| CA2848742C (en) | System and method for collaborative healthcare | |
| Wouters | Essential national health research in developing countries: health‐care financing and the quality of care | |
| Auconi et al. | Prediction of Class III treatment outcomes through orthodontic data mining | |
| Hess et al. | Perspectives of quality care in cancer treatment: a review of the literature | |
| Martens et al. | The effect of computer reminders on GPs’ prescribing behaviour: a cluster-randomised trial | |
| Alpert et al. | Impact of oncology drug shortages on chemotherapy treatment | |
| US20120157793A1 (en) | Medication intake analyzer | |
| US20110066445A1 (en) | Systems, apparatus, and methods for advanced payment tracking for healthcare claims | |
| CN110033838A (en) | A kind of triple logic verification systems of medical data and its method of calibration | |
| US20130262132A1 (en) | Methods, apparatuses and computer program products for facilitating real-time metrics impacting behavior of individuals to optimize performance | |
| US11966374B2 (en) | Medical clinical data quality analysis system based on big data | |
| Edwards et al. | Pragmatics: Operations research survey and computer simulation of waiting times in two medical outpatient clinic structures | |
| Pines et al. | The effect of operational stressors on emergency department clinician scheduling and patient throughput | |
| CN105894223A (en) | Medical consumable and medicine stock monitoring method | |
| Wu et al. | A simulation study of outpatient scheduling with multiple providers and a single device | |
| Dunnick et al. | Quality—a radiology imperative: report of the 2006 Intersociety Conference | |
| CN114613478A (en) | Emergency nursing intelligent management system | |
| CN108806764A (en) | Medical case examines interrogation tracing system of hearing a case | |
| Morikawa et al. | Effectiveness of a computerized clinical decision support system for prevention of glucocorticoid-induced osteoporosis | |
| Coberly | Medicare's Post-Acute Care Payment: An Updated Review of the Issues and Policy Proposals | |
| Tikoo et al. | Global scenario of Medical Device vigilance system | |
| Finkler et al. | The cost effects of protocol systems: the marginal cost-average cost dichotomy | |
| US20230290491A1 (en) | System and methods for digitally enhancing medical imaging current procedural terminology codes |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171121 |