AI and Big Data Convergence on the Cloud for Intelligent Decision-Making

Abstract

Recent years have seen a record-breaking pace of data production, which has resulted in a massive quantity of data. Current computational platforms also produce data in a variety of types, including semi-organized, organized, and unorganized. In the age of technological advancement, the incorporation of Big Data and Deep learning (DL) technology into healthcare decision-making procedures has grown more and more important. These cutting-edge methods present previously rare possibilities to improve decision-making procedures given the complication of medical issues and the quick expansion of data production. By offering adaptable, safe, and reasonably priced systems for data analyzing, evaluation, and preservation, cloud-based settings further improve these features. This study examines the use of AI and Big Data convergence, in cloud-based settings, to improve healthcare decision-making procedures. The study suggests a unified architecture for creating generated medical data and delivering it to cloud systems by utilizing Long Short-Term Memory (LSTM) systems in comparison with other AI methods to improve decision-making process and clinical diagnosis. Preprocessing, average attribution, and standardization all help to improve the uniformity and reliability of data, and visualizing helps decisionsupport platform by offering functional information. When estimating clinical results, the statistical LSTM-based system produced a precision score of 97.2% and an accuracy value of 98.1%. Major issues including data confidentiality, accessibility, and technical constraints will be resolved by safe cloud storing combined with adaptable analytical systems. These issues are important for changing the medical supply paradigm.

Ähnliche Arbeiten