University of Toronto

Mechanical & Industrial Engineering Department

Sharif University of Technology

Industrial Engineering Department

Iran University of Science & Engineering

Industrial Engineering Department

Diseases requiring bone marrow transplants (BMTs), also called stem cell transplants, include leukemia, lymphoma, sickle cell disease and aplastic anemia, as well as some immunodeficiencies. The success of a bone marrow transplant is uncertain, and depends on many factors, including underlying diagnosis, health status, donor relation, etc. Other important factors may exist that are not yet known or well-understood by clinicians. By examining historical records of BMTs, we develop machine learning tools to predict the success of a BMT with a particular patient and donor, using only data regularly collected during the course of treatment. We transform these predictions into conventional Kaplan-Meier survival functions to help clinicians and patients understand individualized survival probabilities and select the best course of treatment.

Short-term survival after liver transplantation has improved dramatically over time, however long-term survival has not increased due to significant compromise particularly by metabolic and malignant complications. In this project our goal is to first, accurately predict the long-term survival of patients undergone liver transplant. Then, we will identify the important features in long-term graft survival. Second, We will develop a dynamic tool for physicians to predict the future survival of any patient at any time after transplant.

In this project, we investigated the inventory review policy for a healthcare facility to minimize the impact of inevitable drug shortages. Usually, healthcare providers do not rely on a single source, and alternative supply mechanisms are present. Our aim in this paroject was to determine the inventory management policy of a healthcare facility, that is how optimal inventory parameters are adjusted depending on the availability of the primary supplier. We modeled the system as a Markov chain, proposed solution approaches, and evaluated the results by simulation study.

The main objective of this study was to predict the level of serum Ferritin in men suffering Anemia and to specify the basic predictive factors of iron deficiency anemia using machine learning. An improved method of clustering, based on Random Forests and k-medoids algorithms has been developed which overcomes the drawbacks of the current k-medoid algorithm in healthcare data. The method has been applied on a data set that contains 306 records of male Anemia patients with 22 laboratory and clinical features. The impact of new factors such as gastrointestinal hemorrhoids, gastrointestinal surgeries, different gastrointestinal diseases and gastrointestinal ulcers are considered in this project. Three clusters of patients attained: iron deficiency anemia, severe iron deficiency anemia and other causes of anemia. The resulting rules of the clusters designed to improve the process of diagnosing and treatment of the patients with iron deficiency Anemia and reduce costs of treatment.