Optimization and Application of Cloud-based Deep Learning Architecture for Multi-Source Data Prediction

TL;DR

This paper presents a cloud-based deep learning system on AWS for early diabetes prediction, achieving high accuracy, fast training, and effective large-scale public health interventions.

Contribution

It introduces a scalable cloud architecture with automated pipelines for efficient diabetes risk prediction, improving training speed and clinical accuracy.

Findings

Reduced training time by 93.2% using GPU instances

Achieved 94.2% overall prediction accuracy

Led to a 37.5% reduction in diabetes incidence

Abstract

This study develops a cloud-based deep learning system for early prediction of diabetes, leveraging the distributed computing capabilities of the AWS cloud platform and deep learning technologies to achieve efficient and accurate risk assessment. The system utilizes EC2 p3.8xlarge GPU instances to accelerate model training, reducing training time by 93.2% while maintaining a prediction accuracy of 94.2%. With an automated data processing and model training pipeline built using Apache Airflow, the system can complete end-to-end updates within 18.7 hours. In clinical applications, the system demonstrates a prediction accuracy of 89.8%, sensitivity of 92.3%, and specificity of 95.1%. Early interventions based on predictions lead to a 37.5% reduction in diabetes incidence among the target population. The system's high performance and scalability provide strong support for large-scale diabetes prevention and management, showcasing significant public health value.