ChatGPT-Assisted Deep Learning Models for Influenza-Like Illness Prediction in Mainland China (Preprint)
Wudi wei · 2025
BACKGROUND Background While deep learning shows potential for influenza forecasting, implementation complexity persists. Large language models like ChatGPT enable automated code generation and model optimization, potentially lowering technical barriers in epidemiological research. OBJECTIVE To evaluate the effectiveness of deep learning models in predicting Influenza-Like Illness (ILI) positive rates in Mainland China and explore the utility of ChatGPT as a development assistant in model construction and optimization. METHODS ILI positive rate data spanning from 2014 to 2024 were obtained from the Chinese CDC database. Five deep learning architectures, Long Short-Term Memory (LSTM), Neural Basis Expansion Analysis for Time Series (N-BEATS), Transformer, Temporal Fusion Transformer (TFT), and Time-series Dense Encoder (TiDE), were implemented with ChatGPT's assistance for code generation, debugging, and optimization. Models were trained on data from 2014 to 2023 and evaluated on 2024 data (weeks 1-39) using Mean Squared Error (MSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE) metrics. RESULTS ILI cases in China exhibited clear seasonal patterns withwinter peaks and summer troughs, showing marked fluctuations during 2020-2022. TIDE demonstrated superior performance nationally (MAE = 5.551, MSE = 43.976, MAPE = 72.413%) and in southern China (MAE = 7.554, MSE = 89.708, MAPE = 74.475%). Northern region predictions were challenging across all models, with TIDE still performing best (MAE = 4.131, MSE = 28.922) despite high percentage errors (MAPE > 400%). ChatGPT significantly accelerated model development through automated code generation and optimization suggestions. CONCLUSIONS Deep learning models, particularly TIDE, show promise for ILI forecasting in China, with performance varying by region. Large language models like ChatGPT can substantially enhance research efficiency in epidemic prediction modeling, offering a scalable approach for public health preparedness.