Analysis of Models to Estimate Morbidity Rates of Respiratory Diseases Through Deep Learning
Authors:
- Liliane Moreira NeryLNLiliane Moreira Nery
- Nícholas de Paula NicomedesNNNícholas de Paula Nicomedes
- Pedro Cesar Madureira de Godoy CamargoPCPedro Cesar Madureira de Godoy Camargo
- Sidney Alves de OuteiroSOSidney Alves de Outeiro
- Leopoldo André Dutra Lusquino FilhoLFLeopoldo André Dutra Lusquino Filho
- Claudio Miceli de FariasCFClaudio Miceli de Farias
- Darllan Collins da Cunha e SilvaDSDarllan Collins da Cunha e Silva
Open Access
- 19 March 2026
- journal article
- Published by Wiley in Tropical Medicine & International Health
- Vol. 31 (6) , 742-753
Abstract
Respiratory diseases remain a challenge in Brazil due to socioeconomic inequalities and environmental risks that intensify population vulnerability. This study compared XGBoost with a deep learning model using stacked Gated Recurrent Units (GRU), trained with morbidity data from respiratory diseases and exogenous variables such as per capita GDP, population density, urbanisation index and greenhouse gas emissions (1999–2023). These data were normalised and temporally disaggregated using synthetic data to refine time‐series granularity. Results showed regional heterogeneity: the GRU achieved superior performance in Porto Alegre ( R 2 = 0.529), São Paulo ( R 2 = 0.518) and São Luís ( R 2 = 0.313), while XGBoost showed mostly negative R 2 values. These findings demonstrate the potential of recurrent neural networks to capture temporal dependencies in health data and support morbidity forecasting. By anticipating fluctuations, such models can guide resource allocation and inform evidence‐based policies. The study underscores the value of integrating socioeconomic and environmental indicators into predictive frameworks and positions deep learning as a promising tool for precision public health in unequal contexts.Keywords
Funding Information
- Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (001)
- Conselho Nacional de Desenvolvimento Científico e Tecnológico (444734/2023‐6)
This publication has 29 references indexed in Scilit:
- Data Augmentation techniques in time series domain: a survey and taxonomyNeural Computing and Applications, 2023
- Popular deep learning algorithms for disease prediction: a reviewCluster Computing, 2022
- Health impacts of wildfire-related air pollution in Brazil: a nationwide study of more than 2 million hospital admissions between 2008 and 2018Nature Communications, 2021
- Comparing COVID-19 risk factors in Brazil using machine learning: the importance of socioeconomic, demographic and structural factorsScientific Reports, 2021
- Data Augmentation for Short-Term Time Series Prediction with Deep Learning2021
- Times-series data augmentation and deep learning for construction equipment activity recognitionAdvanced Engineering Informatics, 2019
- Deep learning for time series classification: a reviewData Mining and Knowledge Discovery, 2019
- A novel artificial intelligence approach based on Multi-layer Perceptron Neural Network and Biogeography-based Optimization for predicting coefficient of consolidation of soilCATENA, 2019
- State-of-the-art in artificial neural network applications: A surveyHeliyon, 2018
- Skills, systems and supports: An Aboriginal Community Controlled Health Service (Apunipima) approach to building health promotion evaluation capacity of staffHealth Promotion Journal of Australia, 2018