Accepted for/Published in: Journal of Medical Internet Research
Date Submitted: Mar 24, 2025
Open Peer Review Period: Mar 25, 2025 - May 20, 2025
Date Accepted: May 8, 2025
(closed for review but you can still tweet)
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
ChatGPT-Assisted Deep Learning Models for Influenza-Like Illness Prediction in Mainland China
ABSTRACT
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.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.