Blood disorders represent a broad spectrum of problems that affect various components and functions of blood, including red blood cells, white blood cells, platelets, and plasma. Common blood disorders, such as anemia, leukemia, thrombocytopenia, and hemophilia, each exhibit distinct pathophysiological characteristics. Symptoms can vary significantly but often include fatigue, weakness, shortness of breath, excessive bruising, prolonged bleeding, and frequent infections. The prediction of these disorders is complicated due to the involvement of a large number of predictor variables. This study presents a machine learning approach that utilizes ensemble models, specifically bagged trees, random forest, RUSBoosted trees, and Support Vector Machines (SVM), developed to classify and predict various types of blood disorders. The models were trained on a comprehensive dataset of over 1,000 patient cases, representing a wide array of blood disorders. By leveraging advanced classification algorithms such as decision trees, boosting techniques, and support vector machines, the models analyze key hematological parameters and clinical features to accurately differentiate between conditions. Among the models tested, the ensemble method utilizing bagged trees outperformed others, achieving an accuracy of 99.4%.