Multi‐level temporal abstraction for medical scenario construction

SUMMARY The automatic recognition of typical pattern sequences (scenarios), as they are developing, is of crucial importance for computer-aided patient supervision. However, the construction of such scenarios directly from medical expertise is unrealistic in practice. In this paper, we present a methodology for data abstraction and for the extraction of specific events (data mining) to eventually construct such scenarios. Data abstraction and data mining are based on the management of three key concepts, data, information and knowledge, which are instantiated via an ontology specific of our medical domain application. After a detailed description of the proposed methodology, we apply it to the supervision of patients hospitalized in intensive care units. We report the results obtained for the extraction of typical abstracted pattern sequences during the process of weaning from mechanical ventilation. Copyright # 2005 John Wiley & Sons, Ltd.

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

[2]  Denis Pomorski,et al.  Towards symbolization using data-driven extraction of local trends for ICU monitoring , 2000, Artif. Intell. Medicine.

[3]  Frank Klawonn,et al.  Finding informative rules in interval sequences , 2001, Intell. Data Anal..

[4]  Cristiana Larizza,et al.  A General Framework for Building Patient Monitoring Systems , 1995, AIME.

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

[6]  S. Keenan,et al.  Weaning protocols: here to stay , 2002, The Lancet.

[7]  Michel Dojat,et al.  Scenario recognition for temporal reasoning in medical domains , 1998, Artif. Intell. Medicine.

[8]  Sylvie Charbonnier,et al.  On-Line Extraction of Successive Temporal Sequences from ICU High-Frequency Data for Decision Support Information , 2003, AIME.

[9]  Yuval Shahar,et al.  A Framework for Knowledge-Based Temporal Abstraction , 1997, Artif. Intell..

[10]  Heikki Mannila,et al.  Discovering Frequent Episodes in Sequences , 1995, KDD.

[11]  Eamonn J. Keogh,et al.  Probabilistic discovery of time series motifs , 2003, KDD '03.

[12]  Howard J. Hamilton,et al.  Principles for mining summaries using objective measures of interestingness , 2000, Proceedings 12th IEEE Internationals Conference on Tools with Artificial Intelligence. ICTAI 2000.

[13]  William J. Clancey,et al.  Heuristic Classification , 1986, Artif. Intell..

[14]  Michel Dojat,et al.  Realistic Model for Temporal Reasoning in Real-Time Patient Monitoring , 1996, Appl. Artif. Intell..

[15]  M Dojat,et al.  Knowledge-based systems for automatic ventilatory management. , 2001, Respiratory care clinics of North America.

[16]  A. Morris.  Computerized protocols and bedside decision support. , 1999, Critical care clinics.

[17]  Yves Kodratoff,et al.  Comparing Machine Learning and Knowledge Discovery in DataBases: An Application to Knowledge Discovery in Texts , 2001, Machine Learning and Its Applications.

[18]  Eamonn J. Keogh,et al.  A symbolic representation of time series, with implications for streaming algorithms , 2003, DMKD '03.

[19]  Padhraic Smyth,et al.  From Data Mining to Knowledge Discovery in Databases , 1996, AI Mag..