Healthcare Databases Analysing Using Predictive Data Analysis Approach

EasyChair Preprint 15184

Abstract

The healthcare databases are coagulating at a poriferous rate, making it difficult to evaluate the many parameters and find hidden patterns for further knowledge development. Over the past ten years, data analytics has demonstrated a wide range of success in collecting or extracting information from central databases. It has raised awareness among scientists and researchers all around the world to develop technologies for knowledge discovery in massive datasets. In fact, with the advent of cutting-edge IT-based technologies for medical diagnostics, healthcare databases have experienced exponential growth in volume and dimensionality. According to medical databases, congenital heart disease ranks among the leading causes of new born fatalities in both industrialised and developing nations. Patients with genetic abnormalities are living longer thanks to potential cures for congenital disabilities that have surfaced as a result of recent advancements in the healthcare industry. As a result, the affected individuals can now live longer. The current study used a clustering technique to locate hidden ways to find hidden patterns from congenital cardiac databases for future medical diagnosis. The designs were examined between 2006 and 2016 in India based on the death rate from congenital cardiac abnormalities in different age groups.

Keyphrases: Data Mining, Healthcare Analytics, Healthcare Databases, machine learning, predictive data analysis

@booklet{EasyChair:15184,
  author    = {Lucky Adhikari and Sudipta Hazra and Senjuti Banerjee and Siddhartha Chatterjee and Aaliya Nashat},
  title     = {Healthcare Databases Analysing Using Predictive Data Analysis Approach},
  howpublished = {EasyChair Preprint 15184},
  year      = {EasyChair, 2024}}