Cargando…
Hypertension and Diabetes in Akatsi South District, Ghana: Modeling and Forecasting
BACKGROUND: The rising incidence of hypertension and diabetes calls for a global response. Hypertension and diabetes will rise in Ghana as the population ages, urbanization increases, and people lead unhealthy lives. Our goal was to create a time series algorithm that effectively predicts future inc...
Autores principales: | , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Hindawi
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8850043/ https://www.ncbi.nlm.nih.gov/pubmed/35187174 http://dx.doi.org/10.1155/2022/9690964 |
_version_ | 1784652526380908544 |
---|---|
author | Asante, Dorothy O. Walker, Anita N. Seidu, Theodora A. Kpogo, Senam A. Zou, Jianjun |
author_facet | Asante, Dorothy O. Walker, Anita N. Seidu, Theodora A. Kpogo, Senam A. Zou, Jianjun |
author_sort | Asante, Dorothy O. |
collection | PubMed |
description | BACKGROUND: The rising incidence of hypertension and diabetes calls for a global response. Hypertension and diabetes will rise in Ghana as the population ages, urbanization increases, and people lead unhealthy lives. Our goal was to create a time series algorithm that effectively predicts future increases to help preventative medicine and health care intervention strategies by preparing health care practitioners to control health problems. METHODS: Data on hypertension and diabetes from January 2016 to December 2020 were obtained from three health facilities. To detect patterns and predict data from a particular time series, three forecasting algorithms (SARIMAX (seasonal autoregressive integrated moving average with exogenous components), ARIMA (autoregressive integrated moving average), and LSTM (long short-term memory networks)) were implemented. We assessed the model's ability to perform by calculating the root mean square error (RMSE), mean absolute error (MAE), mean square error (MSE), and mean absolute percentage error (MAPE). RESULTS: The RMSE, MSE, MAE, and MAPE for ARIMA (5, 2, 4), SARIMAX (1, 1, 1) × (1, 1, 1, 7), and LSTM was 28, 769.02, 22, and 7%, 67, 4473, 56, and 14%, and 36, 1307, 27, and 8.6%, respectively. We chose ARIMA (5, 2, 4) as a more suitable model due to its lower error metrics when compared to the others. CONCLUSION: All models had promising predictability and predicted a rise in the number of cases in the future, and this was essential for administrative and management planning. For appropriate and efficient strategic planning and control, the prognosis was useful enough than would have been possible without it. |
format | Online Article Text |
id | pubmed-8850043 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Hindawi |
record_format | MEDLINE/PubMed |
spelling | pubmed-88500432022-02-17 Hypertension and Diabetes in Akatsi South District, Ghana: Modeling and Forecasting Asante, Dorothy O. Walker, Anita N. Seidu, Theodora A. Kpogo, Senam A. Zou, Jianjun Biomed Res Int Research Article BACKGROUND: The rising incidence of hypertension and diabetes calls for a global response. Hypertension and diabetes will rise in Ghana as the population ages, urbanization increases, and people lead unhealthy lives. Our goal was to create a time series algorithm that effectively predicts future increases to help preventative medicine and health care intervention strategies by preparing health care practitioners to control health problems. METHODS: Data on hypertension and diabetes from January 2016 to December 2020 were obtained from three health facilities. To detect patterns and predict data from a particular time series, three forecasting algorithms (SARIMAX (seasonal autoregressive integrated moving average with exogenous components), ARIMA (autoregressive integrated moving average), and LSTM (long short-term memory networks)) were implemented. We assessed the model's ability to perform by calculating the root mean square error (RMSE), mean absolute error (MAE), mean square error (MSE), and mean absolute percentage error (MAPE). RESULTS: The RMSE, MSE, MAE, and MAPE for ARIMA (5, 2, 4), SARIMAX (1, 1, 1) × (1, 1, 1, 7), and LSTM was 28, 769.02, 22, and 7%, 67, 4473, 56, and 14%, and 36, 1307, 27, and 8.6%, respectively. We chose ARIMA (5, 2, 4) as a more suitable model due to its lower error metrics when compared to the others. CONCLUSION: All models had promising predictability and predicted a rise in the number of cases in the future, and this was essential for administrative and management planning. For appropriate and efficient strategic planning and control, the prognosis was useful enough than would have been possible without it. Hindawi 2022-02-09 /pmc/articles/PMC8850043/ /pubmed/35187174 http://dx.doi.org/10.1155/2022/9690964 Text en Copyright © 2022 Dorothy O. Asante et al. https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. |
spellingShingle | Research Article Asante, Dorothy O. Walker, Anita N. Seidu, Theodora A. Kpogo, Senam A. Zou, Jianjun Hypertension and Diabetes in Akatsi South District, Ghana: Modeling and Forecasting |
title | Hypertension and Diabetes in Akatsi South District, Ghana: Modeling and Forecasting |
title_full | Hypertension and Diabetes in Akatsi South District, Ghana: Modeling and Forecasting |
title_fullStr | Hypertension and Diabetes in Akatsi South District, Ghana: Modeling and Forecasting |
title_full_unstemmed | Hypertension and Diabetes in Akatsi South District, Ghana: Modeling and Forecasting |
title_short | Hypertension and Diabetes in Akatsi South District, Ghana: Modeling and Forecasting |
title_sort | hypertension and diabetes in akatsi south district, ghana: modeling and forecasting |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8850043/ https://www.ncbi.nlm.nih.gov/pubmed/35187174 http://dx.doi.org/10.1155/2022/9690964 |
work_keys_str_mv | AT asantedorothyo hypertensionanddiabetesinakatsisouthdistrictghanamodelingandforecasting AT walkeranitan hypertensionanddiabetesinakatsisouthdistrictghanamodelingandforecasting AT seidutheodoraa hypertensionanddiabetesinakatsisouthdistrictghanamodelingandforecasting AT kpogosenama hypertensionanddiabetesinakatsisouthdistrictghanamodelingandforecasting AT zoujianjun hypertensionanddiabetesinakatsisouthdistrictghanamodelingandforecasting |