Building Prognostic Model for Covid-19 Outcome Using Machine Learning Techniques

Abstract

The global covid-19 pandemic puts great pressure on medical resources worldwide and leads healthcare professionals to question which individuals are in imminent need of care. With appropriate data of each patient, hospitals can heuristically predict whether or not a patient requires death or survive from the pandemic. We adopted a machine learning model to prognostic of individuals who tested positive given the patient’s underlying health conditions, age, sex, and other factors. As the allocation of resources toward a vulnerable patient could mean the difference between life and death, a prediction model serves as a valuable tool to healthcare workers in prioritizing resources and hospital space. In this work, we use the patient demographics, laboratory data and clinical reports as the predictors. The used models are the random forest, sector vector machine, K- Nearest Neighbor, logistic regression and multiline perceptron. In our experiment, we use Confusion matrix, precision, accuracy, and f1-score for performance metrics. RF score better accuracy from the selected machine learning models, the result of RF shows (accuracy =97.87, precision = 0.8, F1-score = 0.44, Recall = 0.51). Results indicate that the RF model outperforms form other machine learning models