Temporal representation and reasoning in medicine: Research directions and challenges

Objective. The main aim of this paper is to propose and discuss some promising research directions in the area of temporal representation and reasoning for medicine, taking into consideration both the recent scientific literature and the current challenging issues, according to the different research erspectives of the authors of the paper. Background. Temporal representation and reasoning in medicine is a well-known research area in both the medical and computer science communities: it ranges over several topics, such as reasoning on temporal clinical data for therapeutic assessments, ummarizing data from temporal clinical databases, modelling incertainty in clinical knowledge and data, and is related to several medical tasks, as monitoring intensive care patient, providing therapies for long term patient, supporting the planning and scheduling of clinical routine activities within complex healthcare organizations. Methodology. First, the authors jointly identified a few main research areas that are both important because of their temporal representation and reasoning issues and promising for future research efforts according to the different expertise and feeling of the authors. Then, each area has been deeply considered by one or two authors and then discussed with all the other authors, to reach a shared agreement on all the promising research directions. Results. We identified and focused on four research areas, namely (i) fuzzy logic, time, and medicine, (ii) temporal reasoning and data mining, (iii) health information systems, business processes, and time, and (iv) temporal clinical databases. For every area, which is not to be considered exhaustively with respect to the possible research topics regarding temporal representation and reasoning in medicine, we first highlighted some basic notions allowing the reader, even if not familiar with these topics, to understand the main goals of each area; then, we discuss some interesting and promising research directions, both considering some recent literature and underlining the still open medical/clinical issues which deserve further scientific investigation. As a matter of fact, it is quite obvious that the considered research areas are not disjoint ones, as they could share some common theoretical and methodological bases. Moreover, some urgent needs from the medical field can be considered and studied within more than one of the considered areas. Conclusions. Through this work, we tried to propose and discuss some promising research directions, to be considered for developing software systems that properly manage the multifaceted temporal aspects of information and knowledge physicians could encounter during their clinical activities. As the considered research directions are the result of merging different perspectives from the different authors working and discussing together, we hope that this paper will succeed in stimulating discussion and multidisciplinary efforts in the considered research issues.