Medical Diagnosis Using Temporal Probabilistic Networks

DIAGNOSIS AND PREDICTION IN SOME DOMAINS, LIKE MEDICINE, REQUIRE AN ADEQUATE REPRESENTATION THAT COMBINES UNCERTAINTY MANAGEMENT AND TEMPORAL REASONING. THIS PAPER PRESENTS A NOVEL REPRESENTATION CALLED TEMPORAL NODES BAYSIN NETWORK (TNBN). A TNBN IS A BAYESIAN NETWORK IN WHICH EACH NODE REPRESENTS AN EVENT OR STATE CHANGES OF A VARIABLE, AND AN ARE CORRESPONDS TO A CAUSAL-TEMPORAL RELATIONSHIP. A TEMPORAL NODE REPRESENTS THE TIME THAT A VARIABLE CHANGES STATE. INCLUDING AN OPTION OF NO-CHANGE. THE TEMPORAL INTERVALS CAN DIFFER IN NUMBER AND SIZE FOR CACH TEMPORAL NODE, SO THIS ALOWS MULTIPLE GRANULARY, THE PROPOSED APPROACH IS APPLIED TO MEDICAL DIAGNOSIS THROUGH A CASE STUDY WHE A CAR ACCIDENT OCCURS. THE RESULTS OF THIS STUDY FOR DIFFERENT