Exploratory Data Analysis for Malaysian Cases of Covid-19
Sahnius Usman, Norulhusna Binti Ahmad, Muhd Faiq Nurhakim Nor Iskandar, Siti Zura A. Jalil · 2024
Risk factor analysis is essential in medical research and patient care, offering insights into the determinants of mortality and severe outcomes. It aids healthcare providers in improving patient management, tailoring interventions, and optimizing resource allocation. The COVID-19 pandemic underscored the importance of rapid and collaborative risk factor analysis. Machine learning (ML) algorithms have emerged as powerful tools for predicting risk factors, but they require thorough data cleaning and preparation. This paper focuses on the exploratory data analysis (EDA) of Malaysian COVID-19 cases to identify feasible variables for subsequent risk factor analysis, enhancing the precision and effectiveness of ML models in healthcare. In this study, data from 128 records from Hospital Sg Buloh were analyzed, focusing on 34 variables. The process involved data cleaning and various analytical techniques, including univariate, bivariate, and multivariate analyses. This exploratory data analysis (EDA) is crucial as it facilitates the identification and extraction of significant features for machine learning algorithms. EDA helps in understanding data patterns, relationships, and structures, ensuring that the resulting ML models are precise and effective. By thoroughly analyzing the data, EDA lays the foundation for robust risk factor analysis, ultimately enhancing decision-making and patient care in healthcare settings.