A Study on Birth Prediction and BCG Vaccine Demand Prediction using ARIMA Analysis

Kim, Keun Won; Li, Guozhong; Park, Seong Taek; Ko, Mi Hyun

doi:10.17485/ijst/2016/v9i24/96151

Cited by 4 publications

(2 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Authors in [7] utilized ARIMA and Back-Propagation Neural Networks (BPNN) to forecast the annual vaccine demand of a specific vaccine. Similarly, researcher in [8] use ARIMA analysis in predicting vaccine demand in advance through analysis of progress of birth of newborn babies in Korea, while [9] use Artificial Neural Network (ANN) to expose the trend and proposing the forecasting model for monthly pentavalent infant immunization coverage and [10] use ARIMA and Neural Network to propose computer-based forecast model to build a decision support system aiming to forecast the annual vaccine demand for specific vaccines of Taiwan. However, none of them are focused on forecasting measles immunization coverage and provided three-year forecasts.…”

Section: Introductionmentioning

confidence: 99%

Forecasting Measles Immunization Coverage Using ARIMA Model

Alegado¹,

Tumibay²

2019

JCC

View full text Add to dashboard Cite

This study aimed to find a model to forecast monthly measles immunization coverage using Autoregressive Integrated Moving Average (ARIMA). The monthly registered data for measles immunization coverage from January 2014 to December 2018 were used for the development of the model. The best model with the smallest Normalized Bayesian Information Criterion (BIC) of 8.673 is ARIMA (0, 1, 0). ARIMA (0, 1, 0) was used to forecast the monthly measles immunization coverage for the next 36 months from January 2018 to December 2020. The results obtained prove that this model can be used for forecasting future immunization coverage and will help decision-makers to establish strategies, priorities, and proper use of immunization resources.

show abstract

Section: Introductionmentioning

confidence: 99%

Forecasting Measles Immunization Coverage Using ARIMA Model

Alegado¹,

Tumibay²

2019

JCC

View full text Add to dashboard Cite

show abstract

“…The study contains examples of constructing regression models to determine the number of people who were discharged from hospitals in a calendar year based on historical data. Work [8] contains the results of predicting the need for vaccine for vaccination against tuberculosis based on forecasting fertility. Forecasting was carried out on the basis of the Box-Jenkins model based on time series analysis.…”

Section: Research Of Existing Solution Of the Problemmentioning

confidence: 99%

Development of elements of the concept of determining the future demand for medical services based on the results of analysis of data of different nature

Mulesa¹,

Snytyuk²,

Melnyk³

et al. 2020

TAPR

View full text Add to dashboard Cite

Planning and organizing the functioning of health care institutions is a priority area of activity of their founders. The purpose of such management activities is to ensure the timeliness, quality and completeness of medical services provided to the clients of the institution. At the same time, an important step is to predict the needs for medical services in future periods of time. Forecasting should be carried out taking into account the socio-demographic, medical and behavioral characteristics of persons -potential consumers of medical services and the characteristics of the population structure of the territory in which the medical institution operates. Thus, the object of research is the processes that arise during the analysis of operational and retrospective statistical, medical and social, expert and other data to determine the forecast values of the levels of demand for certain medical services. The results of the analysis should become the basis for making management decisions on planning and organizing the activities of health care institutions in future periods.In the course of the research, a systematic approach, methods of mathematical modeling and other general scientific methods were used.The research result is a developed method for forecasting the demand for medical services in future periods of time. The method consists in the implementation of four sequential stages of the analysis of the initial data. In this case, it becomes necessary to solve the problems of clustering, classification, identification and forecasting. The accu racy of the predicted values depends on the choice of methods and algorithms for solving the problems posed and on the completeness of the initial data. As a result of applying the method, it is possible to obtain:-аdivision of persons -potential consumers of medical services into groups in accordance with their sociodemographic portraits, medical data and behavioral characteristics;-relationship between the number of educated groups and the demand for various medical services; -predicted values of the number of groups, as well as the demand for medical services.The results can serve as a basis for making managerial decisions on organizing the activities of medical institutions in future periods of time.

show abstract