The main idea of this work is generated from studying the main challenges in the healthcare field. The goal is to identify patients who will be admitted to the hospital within the next year by using historical claims data including Information about patient and analysis it to solve the problem. But this work is dealing with very huge databases. Therefore, the new challenge is occurred the time required for executing the prediction methods and analysis, it bases on five error predicate measures, it including (Maximum error, RMSE, MSE, MAE and MAPE). As a result, cloud is suggested as a tool to solve the problem of analysing the predictions of a huge health care database. A new predictor is proposed to determine how many days in the next year a patient will spend in the hospital. In this work, we attempt to satisfy the idea that explains in Fig. 1. The main challenge here, how we can build the predictor that satisfies the gold triangle. The traversal of the T-Graph) cloud computing “i.e., Speed execution”, data mining algorithm “i.e., Abilities to deal with very huge databases” and Predication techniques” i.e., Ability to plan of the next years. Fig. 1. Fig. 2.