Data-driven prognosis of long COVID in patients using machine learning

Long-COVID is a health condition in which individuals experience persisting, returning or new symptoms longer than 4 weeks after they have recovered from COVID-19 and this condition can even last for months. It can cause multi-organ failure and in some cases, it can even lead to death. The effects and symptoms of Long COVID can vary from person to person. Even though it’s rising globally, there is a limited understanding about its prediction, risk factors and whether its prognosis can be predicted in the initial first week of acute COVID-19. Artificial Intelligence (AI) and Machine Learning (ML) have aided the medical industry in a variety of ways including the diagnosis, prediction, and prognosis of many diseases. This paper introduces a novel method to determine Long COVID in the early or first week of acute COVID-19 by considering the basic demographics, and symptoms during COVID-19, along with the clinical lab results of the patients hospitalized. In comparison with different ML models such as Logistic Regression, Support Vector Machine (SVM), XGBoost and Artificial Neural Network (ANN) to predict and classify the patients as Long COVID or Short COVID during the first week of COVID-19, ANN has outperformed the other models with an accuracy of 81% when considering the symptoms of COVID-19 and a 79% for the clinical test data. The predictive factors and the significant clinical tests for the Long COVID are also determined by using different methods like Chi-square Test and Pearson Correlation.