The rapid advancement of electric vehicles (EVs) has highlighted the critical importance of reliable and durable energy storage systems. Accurate prediction of battery health, specifically in terms of state of health monitoring and remaining useful life (RUL), is essential for optimizing battery usage, ensuring safe operation, and minimizing maintenance costs. This work attempts to estimate the state of health of lithium-ion batteries and predict RUL by employing data-driven models based on machine learning and artificial intelligence techniques. Two different models namely ensemble machine learning model and artificial neural network based models are tested using publicly available data sets from NASA and CALCE and the results are compared. The ensemble machine learning model built using the combination of Random Forest Regressors, Gradient Boosting Regressors, and Support Vector Machines (SVMs) classified by using the Voting Regressor is found to give the best result as evidenced by values of metrics such as the coefficient of determination (R2), Root Mean Square Error (RMSE), and Mean Absolute Error (MAE).