Cloud-Based Machine Learning Models for Predictive Analytics in Healthcare

EasyChair Preprint 14581

Abstract

The integration of cloud computing and machine learning (ML) has revolutionized predictive analytics, particularly in healthcare, where the ability to process large volumes of data efficiently and provide real-time insights is crucial. This study proposes a comprehensive cloud-based framework for deploying ML models aimed at enhancing predictive healthcare outcomes. Utilizing a diverse and expansive healthcare dataset, various ML models—including Decision Trees, Random Forests, Gradient Boosting Machines, Neural Networks, and Support Vector Machines—were trained and evaluated in a cloud environment. The study demonstrates significant improvements in predictive accuracy, scalability, and processing speed with the use of cloud-based ML models compared to traditional on-premise systems. Moreover, a comparative analysis with existing literature reveals that the proposed framework outperforms prior approaches in several key metrics, offering a robust solution for healthcare providers.

Keyphrases: Big Data, Cloud Computing, Data Engineering, Gradient Boosting, Healthcare, Predictive Analytics, machine learning, neural networks

@booklet{EasyChair:14581,
  author    = {Sophia Carlisle},
  title     = {Cloud-Based Machine Learning Models for Predictive Analytics in Healthcare},
  howpublished = {EasyChair Preprint 14581},
  year      = {EasyChair, 2024}}