Mining approximate temporal functional dependencies with pure temporal grouping in clinical databases. (1st July 2015)

• Record Type: Journal Article
• Authors: Combi, Carlo; Mantovani, Matteo; Sabaini, Alberto; Sala, Pietro; Amaddeo, Francesco; Moretti, Ugo; Pozzi, Giuseppe
• Is Part Of: Computers in biology and medicine. Volume 62(2015)
• Page Start: 306
• Page End: 324
• Publication Date: 2015-07-01
• Subjects: Approximate temporal functional dependency -- Temporal granule -- Sliding window -- Grouping -- Psychiatric patients -- Pharmacovigilance; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2014.08.004
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Functional dependencies (FD s) typically represent associations over facts stored by a database, such as " patients with the same symptom get the same therapy ." In more recent years, some extensions have been introduced to represent both temporal constraints (temporal functional dependencies – TFD s), as " for any given month, patients with the same symptom must have the same therapy, but their therapy may change from one month to the next one, " and approximate properties (approximate functional dependencies – AFD s), as " patients with the same symptom generally have the same therapy ." An AFD holds most of the facts stored by the database, enabling some data to deviate from the defined property: the percentage of data which violate the given property is user-defined. According to this scenario, in this paper we introduce approximate temporal functional dependencies (ATFD s) and use them to mine clinical data. Specifically, we considered the need for deriving new knowledge from psychiatric and pharmacovigilance data. ATFD s may be defined and measured either on temporal granules (e.g. grouping data by day, week, month, year) or on sliding windows (e.g. a fixed-length time interval which moves over the time axis): in this regard, we propose and discuss some specific and efficient data mining techniques for ATFD s. We also developed two running prototypes and showed the feasibility of our proposal by mining two real-world clinical data sets. The clinical interest of the dependencies derived considering the psychiatry and pharmacovigilance domains confirms the soundness and the usefulness of the proposed techniques. Abstract : Graphical abstract: Abstract : Highlights: We focus on dependencies over facts (e.g. diagnosis vs therapy) stored in a database. Dependencies may generally hold: deviating facts set up an approximate dependency. We group data in sets, either by temporal granules or by fixed-length sliding windows Within every set, we look for temporal approximate dependencies. We mine psychiatry and pharmacovigilance data sets and derive new knowledge.