Prediction and Diagnosis of COVID-19 using Machine Learning Algorithms

The world is reworking in a digital era. However, the field of medicine was quite repulsive to technology. Recently, the advent of newer technologies like machine learning has catalyzed its adoption into healthcare. The blending of technology and medicine is facilitating a wealth of innovation that continues to improve lives. With the realm of possibility, machine learning is discovering various trends in a dataset and it is globally practiced in various medical conditions to predict the results, diagnose, analyze, treat, and recover. Machine Learning is aiding a lot to fight the battle against Covid-19. For instance, a face scanner that uses ML is used to detect whether a person has a fever or not. Similarly, the data from wearable technology like Apple Watch and Fitbit can be used to detect the changes in resting heart rate patterns which help in detecting coronavirus. According to a study by the Hindustan Times, the number of cases is rapidly increasing. Careful risk assessments should identify hotspots and clusters, and continued efforts should be made to further strengthen capacities to respond, especially at sub-national levels. The core public health measures for the Covid-19 response remain, rapidly detect, test, isolate, treat, and trace all contacts. The work presented in this paper represents the system that predicts the number of coronavirus cases in the upcoming days as well as the possibility of the infection in a particular person based on the symptoms. The work focuses on Linear Regression and SVM models for predicting the curve of active cases. SVM is least affected by noisy data, and it is not prone to overfitting. To diagnose a person our application has a certain question that needs to be answered. Based on this, the KNN model provides the maximum likelihood result of a person being infected or not. Tracking and monitoring in the course of such pandemic help us to be prepared