Enhancing Predictive Modeling for Infectious Diseases with GPU and ML

EasyChair Preprint 14117

Abstract

The proliferation of infectious diseases presents a significant global health challenge, necessitating the advancement of predictive modeling techniques to anticipate and mitigate outbreaks. This study explores the integration of Graphics Processing Units (GPUs) with machine learning (ML) to enhance the accuracy and efficiency of predictive models for infectious diseases. Leveraging the parallel processing capabilities of GPUs, we aim to accelerate complex computations inherent in large-scale epidemiological data analysis. Machine learning algorithms, particularly deep learning models, are employed to identify patterns and predict disease spread with higher precision. This research demonstrates that GPU-accelerated ML models can process vast datasets more rapidly, enabling real-time predictions and timely interventions. By comparing traditional CPU-based models with GPU-enhanced models, we highlight the significant improvements in computational speed and predictive performance. The findings underscore the potential of GPU and ML integration in transforming infectious disease modeling, offering a robust framework for public health authorities to proactively address emerging health threats and implement targeted prevention strategies.

Keyphrases: Centers for Disease Control and Prevention (CDC), Graphics Processing Units (GPUs), Machine Learning (ML)

@booklet{EasyChair:14117,
  author    = {Abi Litty},
  title     = {Enhancing Predictive Modeling for Infectious Diseases with GPU and ML},
  howpublished = {EasyChair Preprint 14117},
  year      = {EasyChair, 2024}}