Big Data Analytics: Utilizing Machine Learning to Enhance Predictions

This is the authors' abstract. We don't add key points for this paper.

The healthcare sector generates enormous amounts of big data, which uses patterns or hidden information to influence decisions. Based on the abundance of data, decisions are made more accurately than intuition. EDA, or investigative data analysis, is used to find pertinent information, confirm hypotheses, find mistakes, and establish the relationship between the explanatory elements. The main objective of this study is to develop predictive algorithms that can precisely detect and forecast the occurrence of diseases. Methodical approach to disease prediction, beginning with the loading and investigation of data. The dataset is then examined using sophisticated data visualization tools. Machine learning algorithms (Decision Tree Classifer, Random Forest Classifer and Logistic Regression Classifer) are used to train and assess models, and the top-performing model is chosen. The selected model is applied to new data to predict the presence of disease, and the outcomes are analyzed to determine the elements that influenced the predictions. Also, An Anticipation Predictions were produced using the stored Logistic Regression model with a sample input. At the highest level of confidence, “fungal infection” was the predicted class (0.8956).