Time series forecasting for tuberculosis incidence employing neural network models

Alvaro David Orjuela-Cañón; Andres Leonardo Jutinico; Mario Enrique Duarte González; Carlos Enrique Awad García; Erika Vergara; María Angélica Palencia

doi:10.1016/j.heliyon.2022.e09897

Time series forecasting for tuberculosis incidence employing neural network models

Título traducido de la contribución: Predicción de series temporales de la incidencia de la tuberculosis mediante modelos de redes neuronales

Alvaro David Orjuela-Cañón, Andres Leonardo Jutinico, Mario Enrique Duarte González, Carlos Enrique Awad García, Erika Vergara, María Angélica Palencia

Producción científica: Contribución a una revista › Artículo › revisión exhaustiva

2 Citas (Scopus)

Resumen

Todos los esfuerzos encaminados a detener la expansión de la Tuberculosis son importantes para la lucha de los programas nacionales contra esta enfermedad. Diferentes herramientas computacionales han sido propuestas con el fin de diseñar nuevas estrategias que permitan manejar pacientes potenciales y así proporcionar el tratamiento correcto. En este trabajo se utilizaron redes neuronales artificiales para el pronóstico de series de tiempo, las cuales fueron entrenadas con información de casos reportados obtenida de la institución nacional de vigilancia en Colombia. Se propusieron tres modelos neuronales con el fin de determinar el mejor de acuerdo a su desempeño en el pronóstico. La primera aproximación empleó un modelo autorregresivo no lineal, la segunda propuesta utilizó una red neuronal recurrente y la tercera propuesta se basó en funciones de base radial. Los resultados se presentan en términos del porcentaje medio de error, lo que indica que los modelos basados en métodos tradicionales muestran un mejor rendimiento que los conexionistas. Estos modelos contribuyen a obtener información dinámica sobre la incidencia, lo que supone una ayuda adicional para que las autoridades sanitarias propongan más estrategias para controlar la propagación de la enfermedad.

Título traducido de la contribución	Predicción de series temporales de la incidencia de la tuberculosis mediante modelos de redes neuronales
Idioma original	Inglés estadounidense
Número de artículo	e09897
Publicación	Heliyon
Volumen	8
N.º	7
DOI	https://doi.org/10.1016/j.heliyon.2022.e09897
Estado	Publicada - jul. 2022

Áreas temáticas de ASJC Scopus

General

ODS de las Naciones Unidas

Este resultado contribuye a los siguientes Objetivos de Desarrollo Sostenible

Acceder al documento

10.1016/j.heliyon.2022.e09897

Otros archivos y enlaces

Citar esto

@article{45f04e87342e4f24a82b65987321c4ed,

title = "Time series forecasting for tuberculosis incidence employing neural network models",

abstract = "Every effort aimed at stopping the expansion of Tuberculosis is important to national programs' struggle to combat this disease. Different computational tools have been proposed in order to design new strategies that allow managing potential patients and thus providing the correct treatment. In this work, artificial neural networks were used for time series forecasting, which were trained with information on reported cases obtained from the national vigilance institution in Colombia. Three neural models were proposed in order to determine the best one according to their forecasting performance. The first approach employed a nonlinear autoregressive model, the second proposal used a recurrent neural network, and the third proposal was based on radial basis functions. The results are presented in terms of the mean average percentage error, which indicates that the models based on traditional methods show better performance compared to connectionist ones. These models contribute to obtaining dynamic information about incidence, thus providing extra-help for health authorities to propose more strategies to control the disease's spread.",

author = "Orjuela-Ca{\~n}{\'o}n, {Alvaro David} and Jutinico, {Andres Leonardo} and {Duarte Gonz{\'a}lez}, {Mario Enrique} and {Awad Garc{\'i}a}, {Carlos Enrique} and Erika Vergara and Palencia, {Mar{\'i}a Ang{\'e}lica}",

note = "Publisher Copyright: {\textcopyright} 2022 The Author(s)",

year = "2022",

month = jul,

doi = "10.1016/j.heliyon.2022.e09897",

language = "English (US)",

volume = "8",

journal = "Heliyon",

issn = "2405-8440",

publisher = "Elsevier BV",

number = "7",

}

TY - JOUR

T1 - Time series forecasting for tuberculosis incidence employing neural network models

AU - Orjuela-Cañón, Alvaro David

AU - Jutinico, Andres Leonardo

AU - Duarte González, Mario Enrique

AU - Awad García, Carlos Enrique

AU - Vergara, Erika

AU - Palencia, María Angélica

PY - 2022/7

Y1 - 2022/7

N2 - Every effort aimed at stopping the expansion of Tuberculosis is important to national programs' struggle to combat this disease. Different computational tools have been proposed in order to design new strategies that allow managing potential patients and thus providing the correct treatment. In this work, artificial neural networks were used for time series forecasting, which were trained with information on reported cases obtained from the national vigilance institution in Colombia. Three neural models were proposed in order to determine the best one according to their forecasting performance. The first approach employed a nonlinear autoregressive model, the second proposal used a recurrent neural network, and the third proposal was based on radial basis functions. The results are presented in terms of the mean average percentage error, which indicates that the models based on traditional methods show better performance compared to connectionist ones. These models contribute to obtaining dynamic information about incidence, thus providing extra-help for health authorities to propose more strategies to control the disease's spread.

AB - Every effort aimed at stopping the expansion of Tuberculosis is important to national programs' struggle to combat this disease. Different computational tools have been proposed in order to design new strategies that allow managing potential patients and thus providing the correct treatment. In this work, artificial neural networks were used for time series forecasting, which were trained with information on reported cases obtained from the national vigilance institution in Colombia. Three neural models were proposed in order to determine the best one according to their forecasting performance. The first approach employed a nonlinear autoregressive model, the second proposal used a recurrent neural network, and the third proposal was based on radial basis functions. The results are presented in terms of the mean average percentage error, which indicates that the models based on traditional methods show better performance compared to connectionist ones. These models contribute to obtaining dynamic information about incidence, thus providing extra-help for health authorities to propose more strategies to control the disease's spread.

UR - http://www.scopus.com/inward/record.url?scp=85134490408&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85134490408&partnerID=8YFLogxK

U2 - 10.1016/j.heliyon.2022.e09897

DO - 10.1016/j.heliyon.2022.e09897

M3 - Article

C2 - 35865994

AN - SCOPUS:85134490408

SN - 2405-8440

VL - 8

JO - Heliyon

JF - Heliyon

IS - 7

M1 - e09897

ER -

Time series forecasting for tuberculosis incidence employing neural network models

Resumen

Áreas temáticas de ASJC Scopus

ODS de las Naciones Unidas

Acceder al documento

Otros archivos y enlaces

Huella

Citar esto