AN INFLUENCE DIAGRAM FOR ASSESSING GVHD PROPHYLAXIS AFTER BONE-MARROWTRANSPLANTATION IN CHILDREN

Graft-versus-host disease (GVHD) represents one of the major complicat ions of allogeneic bone marrow transplantation (BMT). Nevertheless, th e occurrence of mild GVHD could be desirable in high-risk leukemic pat ients, due to a relapse-preventing effect known as the graft-versus-le ukemia (GVL) effect. Given that different prophylactic interventions a re available to prevent GVHD development, the decision problem consist s in assessing both type and dosage of the drugs in order to avoid or induce GVHD, according to the specific patient's condition. The decisi on problem can be represented and solved by using an influence diagram . The choice of this formalism allows using new available methods for building and updating the model of the decision problem. The qualitati ve structure of the model and the conditional probabilities were first derived by combining literature results with a medical expert's judge ment. More specifically, probabilities were initially assigned as rang es rather than as point values. Then, conditional probabilities were u pdated, by using a learning algorithm, as new cases became available. The authors analyzed 50 cases of pediatric patients affected by either malignant or nonmalignant diseases, undergoing BMT and receiving GVHD prophylaxis. They used the first 25 cases to adjust the initially ass igned conditional probabilities, then checked the model obtained on th e remaining patients. The overall performance for GVHD prediction was about 80%.