Search

Bone-marrow transplantation is considered the treatment of choice for pediatric patients with recurring acute lymphoblastic leukemia, provided that a suitable donor is available. Many prognostic factors are known that help to predict the likely outcome of transplantation. We have implemented a system that applies probabilistic reasoning to the available data about individual patients to help determine the risk of recurrence and morbidity after transplantation, and to predict life expectancy. The resulting predictions can be used to decide whether marrow transplantation is the most desirable treatment modality for the patient.

ALARM (A Logical Alarm Reduction Mechanism) is a diagnostic application used to explore probabilistic reasoning techniques in belief networks. ALARM implements an alarm message system for patient monitoring; it calculates probabilities for a differential diagnosis based on available evidence [1]. The medical knowledge is encoded in a graphical structure connecting 8 diagnoses, 16 findings and 13 intermediate variables.