The main branch of Dr Keravnou-Papailiou’s research falls in the area of Artificial Intelligence in Medicine. She has been a member of the Editorial Board and subsequently Associate Editor of the scientific journal Artificial Intelligence in Medicine (Elsevier) that represents the premier forum for the publication of research results in this area, since its establishment in 1989. Currently her research work focuses on Temporal Information Systems in Medicine and she collaborates with scientists from Beer Sheva University in Israel and the University of Verona in Italy. The particular problems she investigates deal with:

(a) The development of a theoretical model for clinical temporal diagnosis that integrates causal, temporal and action knowledge (C-T-A model).

(b) The formulation of an abstract data structure, the Abstract Temporal Graph (ATG) for modelling general temporal constraints encountered in medical reasoning and developing algorithms for the classical problems of checking the consistency of a set of constraints and deciding the satisfiability of some constraint (the ATG is instantiated for different types of constraints of relevance to clinical diagnosis ranging from simple homogeneous structures to complex hybrid structures involving mixed constraints).

(c) The investigation of intelligent knowledge-based methods for temporal data abstraction, in particular the derivation of complex periodic abstractions and the encapsulation of these methods in task independent engines for pre-processing medical data.

(d) The development of a generic time ontology and associated temporal reasoning for medical tasks, based on two primitives, the time-axis and the time-object (the notion of a time-axis enables the representation of multiple conceptual temporal contexts and multiple time granularities, while the notion of a time-object enables the modelling of time as an integral aspect of occurrences, both abstractly and concretely).

(e) Finally, the investigation of temporal abductive diagnosis (not only for clinical domains) and in particular the formulation of criteria for the evaluation of plausible (complex) solutions and for selecting the best solutions under uncertainty and incompleteness.

Dr Keravnou-Papailiou, together with scientists from the J. Stefan Institute in Ljubljana, Slovenia, founded in 1996 the successful Workshop Series “Intelligent Data Analysis in Medicine and Pharmacology (IDAMAP)”. Another area in which she has carried out research is that of hybrid decision support systems, where she has successfully supervised two PhD theses (E. Christodoulou (1999) with application results in the histological classification of breast carcinomas, and H. Kazeli (2006) with application results in water management). More recently, and as a result of her involvement in coordinating the application of the Bologna reforms at the University of Cyprus in her capacity as Vice-Rector for Academic Affairs (2002-2006), she became interested in research matters concerned with quality in higher education.