Harnessing the power of AI: Advanced deep learning models optimization for accurate SARS-CoV-2 forecasting.

Area of Science:

• Epidemiology
• Computational Biology
• Public Health

Background:

• The COVID-19 pandemic has impacted global health, necessitating accurate forecasting tools for Malaysia.
• Developing precise prediction models is crucial for effective public health policy and intervention strategies.

Purpose of the Study:

• To evaluate and identify the most reliable deep learning model for forecasting SARS-CoV-2 cases in Malaysia.
• To compare the performance of various advanced deep learning architectures for infectious disease prediction.

Main Methods:

• Utilized advanced deep learning models including LSTM, Bi-LSTM, CNN, CNN-LSTM, MLP, GRU, and RNN.
• Trained and assessed models using a comprehensive dataset of confirmed cases, demographic, and socio-economic factors specific to Malaysia.

Main Results:

• Each deep learning model demonstrated varying levels of accuracy and precision in predicting SARS-CoV-2 cases.
• A comprehensive performance evaluation identified the most suitable deep learning architecture for Malaysia's unique context.

Conclusions:

• The study provides valuable insights into applying sophisticated deep learning for timely and accurate SARS-CoV-2 case predictions in Malaysia.
• Findings support public health decision-making, enabling data-driven interventions to mitigate the pandemic's impact.