Predictive Modeling and Analysis of COVID-19 with Machine Learning Techniques

• Published in: 2024 5th International Conference on Image Processing and Capsule Networks (ICIPCN) pp. 243 - 247
• Main Authors: Pant, Garima, Pant, Janmejay, Kotlia, Priyanshi, Singh, Devendra, Khulbe, Sumit, Bhatt, Jaishankar
• Format: Conference Proceeding
• Language: English
• Published: IEEE 03.07.2024
• Subjects: Accuracy; Analytical models; classification and prediction; Computational modeling; COVID-19; logistic regression (LR); MachineLearning (ML); Radio frequency; random forest (RF); Supervised learning; Training
• DOI: 10.1109/ICIPCN63822.2024.00047

For successful management of COVID-19 pandemic outbreak, case detection has to be done through Machine Learning (ML). The Machine Learning (ML) techniques can be used to process the patient's data, such as imaging and results of various tests, to detect Covid19 cases. This study aims to present a computer learning model for COVID-19 severity and course prediction using initial manifestations. As a result of training and classification, supervised learning methods are included in the proposed approach in order to detect the presence of the corona virus COVID-19 and classify it. Estimation and predication of COVID-19 infection can be accomplished by machine learning principle and statistical and computational models on how to assess negative and positive impacts of the virus. The data was analyzed using two machine learning models: Random forest (RF) and Logistic regression (LR) have been chosen as classification algorithms to build models based on the obtained data. The results found out that both LR and RF were equally accurate knowing that the overall accuracy recorded was good. The following model provides a wayof accurately categorizing patients, making it easier for health care professionals and policymakers to track the risky individuals.