Unification of Heterogeneous Data Towards the Prediction of Oral Cancer Reoccurrence

Oral cancer is the predominant neoplasm of the head and neck. Annually, more than 500.000 new cases of oral cancer are reported, worldwide. After the initial treatment of cancer and its complete disappearance, a state called remission, reoccurrence rates still remain quite high and the early identification of such relapses is a matter of great importance. Up to now, several approaches have been proposed for this purpose yielding however, unsatisfactory results. This is mainly attributed to the fragmented nature of these studies which took into account only a limited subset of the factors involved in the development and reoccurrence of oral cancer. In this work we propose a unified and orchestrated approach based on Dynamic Bayesian Networks (DBNs) for the prediction of oral cancer reoccurrence after the disease has reached remission. Several heterogeneous data sources featuring clinical, imaging and genomic information are assembled and analyzed over time, in order to procure new and informative biomarkers which correlate with the progression of the disease and identify early potential relapses (local or metastatic) of the disease.