Federal Institute of Education, Science and Technology of Mato Grosso, Department of Computer Science, Campus Barra do Garças, Barra do Garças, Mato Grosso, Brazil.
Department of Health Sciences, Barra do Garças, Campus Araguaia, Federal University of Mato Grosso, Cuiabá, Mato Grosso, Brazil.
Sci Rep. 2024 Aug 16;14(1):18991. doi: 10.1038/s41598-024-69580-4.
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.
结核/艾滋病双重感染构成了复杂的公共卫生挑战。准确预测未来趋势对于高效资源配置和干预策略制定至关重要。本研究比较了经典统计学和机器学习模型，以预测按性别和普通人群分层的结核/艾滋病双重感染病例。我们使用指数平滑法和 ARIMA 分析时间序列数据，以建立基线趋势和季节性。随后，采用机器学习模型（SVR、XGBoost、LSTM、CNN、GRU、CNN-GRU 和 CNN-LSTM）来捕捉结核/艾滋病双重感染数据的复杂动态和固有非线性。使用均方误差（MSE）、平均绝对误差（MAE）和标准化平均百分比误差（sMAPE）以及迪博尔德-马里亚诺检验来评估模型性能。结果表明，深度学习模型，特别是双向 LSTM 和 CNN-LSTM，显著优于经典方法。这证明了深度学习在结核/艾滋病双重感染时间序列建模和生成更准确预测方面的有效性。
