Machine Learning Approaches to Predict Post Covid-19 Severity: A Detail Case Study

The entire world has witnessed a horrific pandemic in last three years, whose long term and short-term impact to human body has been observed in large scale in these post covid-19 years. Machine learning (ML) techniques have been successfully implemented in medical field since last one decade. The emergence of post covid-19 pandemic symptoms are compelling researchers to re-search for minute detection and predict patient's probable infection rate. Long lasting chest pain, breathing issues, liver and kidney dialysis issues have been apparently visible as post covid-19 symptoms. In this paper, the journals regarding the prediction of covid-19 severity based on symptoms have been discussed. Several researchers have established deep learning-based models for the prediction. They have used the test data from the hospitals for their research process. The KNN models, ANN models, and SVM models have been discussed. The limitations of the past research process have been evaluated to be the biased test data set and missing values. The methodology that was used for the research process has been described. Mixed method of data collection was used for the research processes. The secondary data was collected from reliable sources for this research process. Considerable amount of test data has been retrieved from Kaggle database regarding post covid-19 patient's symptoms. The data analysis is performed on the Weka tool using various machine learning models.