Analysis of covid 19 clinical data through machine learning techniques
Loading...
Date
2022
Journal Title
Journal ISSN
Volume Title
Publisher
UMT Lahore
Abstract
Analysis of COVID-19 related data has been a hot topic of research. Many researchers have been working hard to play their part to take the research forward. In this research we have used different machine learning techniques to perform analysis on the Covid clinical data repository taken from carbon health team. The objective of this research was to train a model which can diagnose and predict result with best accuracy. This research
helps to study what Covid is at early stage. The dataset used in this study corresponds to front lines ground realities. This Research helps in-patients and out-patients to know their vitals through symptoms along with Covid Test results. The data we used here required pre-processing. In the first phase we pre-processed the data and brought it in such a shape which could be used to perform different analytical operations. We selected the most
important features by evaluating their scores. In the second phase we used multiple classification methods including decision tree classifier, random forest classifier, SVM, etc. for data classification. We experimented with different validation techniques like train test split, K fold cross validation, etc. Performance of the classifiers have been reported using confusion matrices. We also report other evaluation measures including accuracy, precision, and recall, etc. Finally, we are able to successfully train a classification model that has high accuracy, ROC AUC curve and Matthew correlation coefficient values. Hence the proposed method can find its application in the real-world scenarios of COVID-19 to diagnose the disease with better accuracy.