Representing and querying now-relative relational medical data

• Published in: Artificial intelligence in medicine 2018-03, Vol.86, p.33-52
• Main Authors: Anselma, Luca, Piovesan, Luca, Stantic, Bela, Terenziani, Paolo
• Format: Article
• Language: English
• Subjects: Artificial Intelligence; Data Mining - methods; Databases, Factual; Decision Support Systems, Clinical; Decision Support Techniques; Electronic Health Records; Humans; Medical Informatics - methods; Now-relative data; Practice Guidelines as Topic; Reaction Time; Relational model and algebra; Temporal relational data; Time Factors
• ISSN: 0933-3657; 1873-2860
• DOI: 10.1016/j.artmed.2018.01.004

•Temporal information plays a crucial role in medicine.•Current relational approaches have notable limitations in treating “now-relative” data (i.e., holding at the current time).•We propose an approach to treat now-relative relational data which can be paired with different decision support systems.•We define a new data model and temporal algebra supporting possible and necessary time, and Allen’s temporal relations.•We exemplify the impact of our approach, and study its theoretical and computational properties. Temporal information plays a crucial role in medicine. Patients’ clinical records are intrinsically temporal. Thus, in Medical Informatics there is an increasing need to store, support and query temporal data (particularly in relational databases), in order, for instance, to supplement decision-support systems. In this paper, we show that current approaches to relational data have remarkable limitations in the treatment of “now-relative” data (i.e., data holding true at the current time). This can severely compromise their applicability in general, and specifically in the medical context, where “now-relative” data are essential to assess the current status of the patients. We propose a theoretically grounded and application-independent relational approach to cope with now-relative data (which can be paired, e.g., with different decision support systems) overcoming such limitations. We propose a new temporal relational representation, which is the first relational model coping with the temporal indeterminacy intrinsic in now-relative data. We also propose new temporal algebraic operators to query them, supporting the distinction between possible and necessary time, and Allen’s temporal relations between data. We exemplify the impact of our approach, and study the theoretical and computational properties of the new representation and algebra.