Optimizing Healthcare Framework using Cognitive Computing Techniques in Cloud: A Study on Enhancing Diagnostic Accuracy and Decision-Making

Jagadeeswaran, Rajaram (2024) Optimizing Healthcare Framework using Cognitive Computing Techniques in Cloud: A Study on Enhancing Diagnostic Accuracy and Decision-Making. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (755kB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

The utilization of cloud platforms with cognitive technologies in healthcare delivers significant enhancements in decision-making and diseases diagnostics. The objective of this research project aims to address present difficulties in the using cognitive technologies in healthcare by utilizing cloud platforms features such as scalability, processing capability, and productive storage. The primary objective of this research is to investigate the possible breakthrough potential of cognitive computing in healthcare while simultaneously being aware of its limitations. Through a comparative evaluation, this study will examine the efficiency of various cognitive platforms such as generative AI's foundation models from AWS Bedrock and AWS SageMaker in disease prediction tasks. We proposed utilizing real-world datasets associated with specific diseases, with a focus on Text Generation to evaluate the diagnostic decision-making efficiency and accuracy of these platforms. The procedure incorporates collecting data, training the model, fine-tuning, deployment, and extensively evaluating its accuracy. Using AWS SageMaker for custom model deployment and AWS Bedrock for leveraging pre-trained models, we will fine-tune and deploy these models, followed by a comprehensive benchmarking process. Measures of performance including accuracy, precision, and inference times will be examined by the comparison framework. The evaluations from the investigations and implementations are intended to advance the development of cognitive computing technologies with the benefits and drawbacks in healthcare and provide insightful information for further study and the development of prototype in this domain.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Kumar Sharma, Jitendra UNSPECIFIED
Uncontrolled Keywords:	Healthcare; Cognitive Computing; Cloud Computing; Diagnostic Accuracy; Decision-Making; Comparison Framework; AWS Bedrock; AWS SageMaker; Streamlit
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence T Technology > T Technology (General) > Information Technology > Cloud computing R Medicine > Healthcare Industry Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Cloud Computing
Depositing User:	Ciara O'Brien
Date Deposited:	03 Jul 2025 10:56
Last Modified:	03 Jul 2025 10:56
URI:	https://norma.ncirl.ie/id/eprint/8021

Actions (login required)

View Item