Abstract
In this paper, the authors present a work-in-process neural model trained to symbolically characterize the numeric parameters of critical patients in Intensive Care Units (ICUs). The nets were designed to assign the state {very high, high, normal, low, very low} of the main haemodinamic and respiratory parameters based on the particular context of the patient. This symbolic processing allows the use of an heuristic, general module, which prescribes ventilation and oxygenation therapies and shows the diagnoses corresponding to the symbolic labels of those variables.
The problems derived from the neural features of the proposed model are commented, holding the collection of a large patient database by using a Clinical Information System (Carevue 9000), the definition of the persistence/validity of asynchronous values — half life of drugs, lab results — and temporal evolution of trends.
Preview
Unable to display preview. Download preview PDF.
Bibliography
Elena Hernandez Pereira, Vicente Moret Bonillo: “Adquisición de Datos e Infonnación e interconexión de módulos en el sistema experto PATRICIA”. End of Career Thesis. Science Computer Faculty. University of La Coruña. Spain. 1996.
V. Moret Bonillo, J. Díaz Fernández, A. Díaz Lamas: “A neural network model for Diagnosis of Critical patients receiving mechanical ventilation”, IEEE EMBS Congress, Nov 96.
C. Hernández-Sande, V. Moret-Bonillo, A. Alonso-Betanzos; “ESTER: AN expert system for management of respiratory weaning therapy”, IEEE Transactions Biomedical Engineering, Vol. 35, n∘ 5, pp 559–564, 1989
D.F. Sittig, RM. Gardner, N.L. Pace, A.H. Morris, E. Beck: “Computerized management of patient care in complex, controlled clinical trial in the intensive care unit”. Computer Methods and Programs in Biomedicine, n 30, pp 77–84, 1989.
R. Rudowski, C. Frostell, H. Hill, “A knowledge-based support system for mechanical ventilation of the lungs. The KUSIVAR concep and prototype”. Computer Methods and Programs in Biomedicine, n 30, pp 59–70, 1989.
D.A. Tong, “Weaning patients from mechanical ventilation. A knowledge-based system approach”, Computer Methods and Programs in Biomedicine, vol 35, pp 267–278, 1991.
B. Hayes-Roth, D. Washington, D. Ash, R. Hewett, A. Collinot, et col. “GUARDIAN: A Prototype Intelligent Agent for Intensive Care Monitoring”, Artificial Intelligence in Medicine, Vol. 4, n2, pp 165–185, 1992.
B.M. Dawan, S. Uckun, E.J. Manders, D.P. Lindstrom, “The SIMON project: Model-Based signals acquisition analysis, and interpretation in Intelligent Patient Monitoring”, IEEE Engineering in Medicine and Biology, vol 12, n 4, 1993.
V. Moret-Bonillo, A. Alonso-Betanzos, E. García-Martín, M.Cabrero-Canosa, B. Guijarro-berdiñas, “The PATRICIA project: A Semantic-Based Methodology for Intelligent Monitoring in the ICU”, IEEE Engineering in Medicine and Biology, vol 12, n 4, 1993.
V. Moret-Bonillo, A. Alonso-Betanzos, E.J. Truemper, E. García-Martín, A. Pazos-Sierra, “PATRICIA: An Expert System that incorporates a patient approach for the management of ICU patients”, Proc. 14th Annual Conference IEEE-EMBS, Vol 14, pp 876–877, 1992.
J.C. Principe, S.K. Gala and T.G. Chang, “Sleep Staging Automaton Based on the theory of evidence”, IEEE Transactions on Biomedical Engineering, pp 503–509, May 1989.
B.H.Jansen and B.M. Dawant, “Knowledge-Based Approach to sleep EEG Analysis: A feasibility study”, IEEE Transactions on Biomedical Engineering, pp 510–518 May 1989.
J.C Principe and C.Lefevbre. “Neurosolutions. User's Guide and Manual”. Neurodimension Inc; Gainesville.Vol 1 and 2. 1995.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Moret-Bonillo, V., Fernández, J.D., Pereira, E.H. (1997). A neural network approach for symbolic interpretation in critical care. In: Mira, J., Moreno-Díaz, R., Cabestany, J. (eds) Biological and Artificial Computation: From Neuroscience to Technology. IWANN 1997. Lecture Notes in Computer Science, vol 1240. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0032555
Download citation
DOI: https://doi.org/10.1007/BFb0032555
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63047-0
Online ISBN: 978-3-540-69074-0
eBook Packages: Springer Book Archive