Abstract
Data driven interpretation of multiple physiological measurements in the domain of intensive care is a key point to provide decision support. The abstraction method presented in this paper provides two levels of symbolic interpretation. The first, at mono parametric level, provides 4 classes (increasing, decreasing, constant and transient) by combination of trends computed at two characteristic spans. The second, at multi parametric level, gives an index of global behavior of the system, that is used to segment the observation. Each segment is therefore described as a sequence of words that combines the results of symbolization. Each step of the abstraction process leads to a visual representation that can be validated by the clinician. Construction of sequences do not need any prior introduction of medical knowledge. Sequences can be introduced in a machine learning process in order to extract temporal patterns related to specific clinical or technical events.
Keywords
- Medical Personnel
- Systolic Arterial Blood Pressure
- Provide Decision Support
- Temporal Abstraction
- Pattern Template
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Coll: Improving Control of Patient Status in Critical Care: The Improve Project. Computer Programs and Methods in Biomedicine 51, 1–130 (1996)
Larsson, J., Hayes-Roth, B., Gaba, D.: Guardian: Final Evaluation. Technical report ksl-96-25. Technical report, Knowledge Systems Laboratory, Stanford University (1996)
Manders, E., Davant, B.: Data Acquisition for an Intelligent Bedside Monitoring System. In: Proceedings of the 18th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 957–958 (1996)
Miksch, S., Horn, W., Popow, C., Paky, F.: Utilizing Temporal Data Abstraction for Data Validation and Therapy Planning for Artificially Ventilated Newborn Infants. Artificial Intell. Med. 8, 543–576 (1996)
Shahar, Y., Musen, M.: Knowledge-based Temporal Abstraction in Clinical Domains. Artificial Intell. Med. 8, 267–298 (1996)
Dojat, M., Pachet, F., Guessoum, Z., Touchard, D., Harf, A., Brochard, L.: Neoganesh: a Working System for the Automated Control of Assisted Ventilation in Icus. Artificial Intell. Med. 11, 97–117 (1997)
Haimovitz, I., Kohane, I.: Managing Temporal Worlds for Medical Trend Diagnosis. Artificial Intell. Med. 8, 299–321 (1996)
Coiera, E.: Automated Signal Interpretation. In: Monitoring in Anaesthesia and Intensive Care, pp. 32–42. W.B. Saunders Co Ltd, Philadelphia (1994)
Calvelo, D.: Apprentissage de Modeles de la Dynamique pour l’Aide a la Decision en Monitorage Clinique. PhD thesis, Lille 1 (1999)
Mora, F., Passariello, G., Carrault, G., Pichon, J.P.L.: Intelligent Patient Monitoring and Management Systems: a Review. IEEE Eng. Med. Bio. 12, 23–33 (1993)
Avent, R., Charlton, J.: A Critical Review of Trend-detection Methodologies for Biomedical Systems. Critical Reviews in Biomedical Engineering 17, 621–659 (1990)
Imhoff, M., Bauer, M., Gather, U., Lohlein, D.: Statistical Pattern Detection in Univariate Time Series of Intensive Care Online Monitoring Data. Intensive Care Medicine 24, 1305–1314 (1998)
Makivirta, A., Koski, E., Kari, A., Sukuwara, T.: The Median Filter as a Preprocessor for a Patient Monitor Limit Alarm System in Intensive Care. Computer Methods and Programs in Biomedicine 34, 139–144 (1991)
Calvelo, D., Chambrin, M.C., Pomorski, D., Ravaux, P.: Towards Symbolization Using Data-driven Extraction of Local Trends for ICU Monitoring. Artificial Intell. Med. 1-2, 203–223 (2000)
Hau, D., Coiera, E.: Learning Qualitative Models of Dynamics Systems. Machine Learning 26, 177–211 (1997)
Charbonnier, S., Becq, G., Biot, L.: On Line Segmentation Algorithm for Continuously Monitored Data in Intensive Care units. IEEE Transactions on Biomedical Engineering 51, 484–492 (2004)
Salatian, A., Hunter, J.: Deriving Trends in Historical and Real-time Continuously Sampled Medical Data. Journal of Intelligence Information Systems 13, 47–71 (1999)
Lowe, A., Jones, R., Harrison, M.: The graphical presentation of decision support information in an intelligent anaesthesia monitor. Artificial Intell. Med. 22, 173–191 (2001)
Saporta, G.: Analyse en Composantes Principales. In: Probabilités, Analyse des Données et Statistiques. Technip, pp. 159–186 (1990)
Vilhelm, C., Ravaux, P., Calvelo, D., Jaborska, A., Chambrin, M., Boniface, M.: Think!: a Unified Numerical - symbolic Knowledge Representation Scheme and Reasoning System. Artificial Intelligence 116, 67–85 (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sharshar, S., Allart, L., Chambrin, M.C. (2005). A New Approach to the Abstraction of Monitoring Data in Intensive Care. In: Miksch, S., Hunter, J., Keravnou, E.T. (eds) Artificial Intelligence in Medicine. AIME 2005. Lecture Notes in Computer Science(), vol 3581. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11527770_3
Download citation
DOI: https://doi.org/10.1007/11527770_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-27831-3
Online ISBN: 978-3-540-31884-2
eBook Packages: Computer ScienceComputer Science (R0)