In this paper, a new hybrid adaptation model for cancer diagnosis has been developed. It combines transformational and hierarchical adaptation techniques with artificial neural networks (ANN’s) and certainty factors (CF’s). The model consists of a hierarchy of three phases, which simulates the expert doctor phases of cancer diagnosis. Each phase uses a single ANN to learn the adaptation knowledge to perform the main adaptation task. The model has been tested with 820 thyroid cancered patient cases. Cross-validation test has shown a very high diagnosis performance rate that reaches 99.47%. The model is described in a context of a prototype expert system namely Cancer-C.