Applying Temporal Abstraction in Medical Information Systems

Department of Information Systems EngineeringBen Gurion University, Beer Sheva 84105, Israelmira@cs.bgu.ac.il{dboaz,yshahar}@bgumail.bgu.ac.ilAbstract—Physicians and medical decision-support ap-plications, such as for diagnosis, therapy, monitoring,quality assessment, and clinical research, reason aboutpatients in terms of abstract, clinically meaningful con-cepts, typically over significant time periods. Clinicaldatabases, however, store only raw, time-stamped data.Thus, there is a need to bridge this gap. We introducethe Temporal Abstraction Language (TAR) which enablesspecification of abstract relations involving raw data andabstract concepts, and use it for defining typical medicalabstraction patterns. For each pattern we further analyzefiniteness properties of the answer set. The TAR languageis implemented as the reasoning module in a practicaldiagnosis system.Index Terms—temporal reasoning, temporal databases,temporal query languages, knowledge-based systems andknowledge representation, medical informatics and tem-poral abstraction.

[1]  Yuval Shahar,et al.  Knowledge-based temporal abstraction in clinical domains , 1996, Artif. Intell. Medicine.

[2]  Elpida T. Keravnou Temporal Abstraction of Medical Data: Deriving Periodicity , 1997 .

[3]  Anthony J. Bonner,et al.  Query Languages for Sequence Databases: Termination and Complexity , 2001, IEEE Trans. Knowl. Data Eng..

[4]  Yuval Shahar,et al.  Dynamic temporal interpretation contexts for temporal abstraction , 1998, Annals of Mathematics and Artificial Intelligence.

[5]  Yuval Shahar,et al.  CAPSUL: A constraint-based specification of repeating patterns in time-oriented data , 2001, Annals of Mathematics and Artificial Intelligence.

[6]  Jeffrey D. Uuman Principles of database and knowledge- base systems , 1989 .

[7]  Yuval Shahar,et al.  Analysis of Temporal Abstraction in Medical Databases , 2003, KRDB.

[8]  Yuval Shahar,et al.  KNAVE-II : A Distributed Architecture for Interactive Visualization and Intelligent Exploration of Time-Oriented Clinical Data , 2003 .

[9]  Jan Chomicki,et al.  Temporal Query Languages: A Survey , 1994, ICTL.

[10]  Silvia Miksch,et al.  Utilizing temporal data abstraction for data validation and therapy planning for artificially ventilated newborn infants , 1996, Artif. Intell. Medicine.

[11]  Ira J. Haimowitz,et al.  Managing temporal worlds for medical trend diagnosis , 1996, Artif. Intell. Medicine.

[12]  Yuval Shahar,et al.  A Temporal-Abstraction Rule Language for Medical Databases , 2003 .

[13]  James F. Allen Maintaining knowledge about temporal intervals , 1983, CACM.

[14]  Cristiana Larizza,et al.  M-HTP: A system for monitoring heart transplant patients , 1992, Artif. Intell. Medicine.

[15]  Michael Kifer,et al.  On the decidability and axiomatization of query finiteness in deductive databases , 1998, JACM.

[16]  Jan Chomicki,et al.  Temporal deductive databases and infinite objects , 1988, PODS.

[17]  Peter Z. Revesz,et al.  Constraint Databases: A Survey , 1995, Semantics in Databases.

[18]  MeccaGiansalvatore,et al.  Query Languages for Sequence Databases , 2001 .

[19]  Marianne Baudinet,et al.  Temporal Deductive Databases , 1993, Temporal Databases.

[20]  Yuval Shahar,et al.  Idan: A Distributed Temporal-Abstraction Mediator for Medical Databases , 2003, AIME.

[21]  R. Ramakrishnan,et al.  A framework for testing safety and effective computability of extended datalog , 1988, SIGMOD '88.

[22]  Anthony J. Bonner,et al.  Sequences, Datalog, and Transducers , 1998, J. Comput. Syst. Sci..