A comparative analysis of classical and machine learning methods for forecasting TB/HIV co-infection
Authors:
Open Access
- 16 August 2024
- journal article
- research article
- Published by Springer Nature in Scientific Reports
- Vol. 14 (1) , 1-14
Abstract
TB/HIV coinfection poses a complex public health challenge. Accurate forecasting of future trends is essential for efficient resource allocation and intervention strategy development. This study compares classical statistical and machine learning models to predict TB/HIV coinfection cases stratified by gender and the general populations. We analyzed time series data using exponential smoothing and ARIMA to establish the baseline trend and seasonality. Subsequently, machine learning models (SVR, XGBoost, LSTM, CNN, GRU, CNN-GRU, and CNN-LSTM) were employed to capture the complex dynamics and inherent non-linearities of TB/HIV coinfection data. Performance metrics (MSE, MAE, sMAPE) and the Diebold-Mariano test were used to evaluate the model performance. Results revealed that Deep Learning models, particularly Bidirectional LSTM and CNN-LSTM, significantly outperformed classical methods. This demonstrates the effectiveness of Deep Learning for modeling TB/HIV coinfection time series and generating more accurate forecasts.Keywords
All Related Versions
Funding Information
- Fundação de Amparo à Pesquisa do Estado de Mato Grosso , Brasil (000087/2023, 000087/2023, 000087/2023, 000087/2023, 000087/2023, 000087/2023, 000087/2023, 000087/2023, 000087/2023)
- Conselho Nacional de Desenvolvimento Científico e Tecnológico (445458/2023-2, 445458/2023-2, 445458/2023-2, 445458/2023-2, 445458/2023-2, 445458/2023-2, 445458/2023-2, 445458/2023-2, 445458/2023-2)
This publication has 44 references indexed in Scilit:
- Mean Absolute Percentage Error for regression modelsNeurocomputing, 2016
- A review of copula models for economic time seriesJournal of Multivariate Analysis, 2012
- Hybridization of autoregressive integrated moving average (ARIMA) with probabilistic neural networks (PNNs)Computers & Industrial Engineering, 2012
- Another look at measures of forecast accuracyInternational Journal of Forecasting, 2006
- Autocovariance functions of series and of their transformsJournal of Econometrics, 2005
- Introduction to Time Series and Forecasting2002
- Global Burden of TuberculosisJAMA, 1999
- Support-vector networksMachine Learning, 1995
- Accuracy measures: theoretical and practical concernsInternational Journal of Forecasting, 1993
- Testing the null hypothesis of stationarity against the alternative of a unit rootJournal of Econometrics, 1992