Artificial intelligence (AI) techniques such as machine learning (ML) have wide application in medical informatics systems. In this chapter we employ AI techniques to assist in deriving software specifications of e-Health and m-Health systems from informal requirements statements. We use natural language processing (NLP), optical character recognition (OCR) and machine learning to identify required data and behaviour elements of systems from textual and graphical requirements documents. Heuristic rules are used to extract formal specification models of the systems from these documents. The extracted specifications can then be used as the starting point for automated software production using model-driven engineering (MDE). We illustrate the process using an example of a stroke recovery assistant app, and evaluate the techniques on several representative systems.