Temporal abstraction for feature extraction: A comparative case study in prediction from intensive care monitoring data

Verduijn, Marion; Sacchi, Lucia; Peek, Niels; Bellazzi, Riccardo; de Jonge, Evert; de Mol, Bas A.J.M.

doi:10.1016/j.artmed.2007.06.003

« Previous Next »Artificial Intelligence in Medicine
Volume 41, Issue 1 , Pages 1-12, September 2007

Temporal abstraction for feature extraction: A comparative case study in prediction from intensive care monitoring data

Marion Verduijn
- Department of Medical Informatics, Academic Medical Center, P.O. Box 22700, 1100 DE Amsterdam, The Netherlands
- Department of Biomedical Engineering, University of Technology, P.O. Box 513, 5600 MB Eindhoven, The Netherlands
- Corresponding author at: Department of Medical Informatics, Academic Medical Center, P.O. Box 22700, 1100 DE Amsterdam, The Netherlands. Tel.: +31 20 5664543; fax: +31 20 6919840.
Lucia Sacchi
- Laboratory for Medical Informatics, University of Pavia, Via Ferrata 1, 27100 Pavia, Italy
Niels Peek
- Department of Medical Informatics, Academic Medical Center, P.O. Box 22700, 1100 DE Amsterdam, The Netherlands
Riccardo Bellazzi
- Laboratory for Medical Informatics, University of Pavia, Via Ferrata 1, 27100 Pavia, Italy
Evert de Jonge
- Department of Intensive Care Medicine, Academic Medical Center, P.O. Box 22700, 1100 DE Amsterdam, The Netherlands
Bas A.J.M. de Mol
- Department of Biomedical Engineering, University of Technology, P.O. Box 513, 5600 MB Eindhoven, The Netherlands

Received 30 June 2006; received in revised form 2 June 2007; accepted 6 June 2007.

Summary

Objectives

To compare two temporal abstraction procedures for the extraction of meta features from monitoring data. Feature extraction prior to predictive modeling is a common strategy in prediction from temporal data. A fundamental dilemma in this strategy, however, is the extent to which the extraction should be guided by domain knowledge, and to which extent it should be guided by the available data. The two temporal abstraction procedures compared in this case study differ in this respect.

Methods and material

The first temporal abstraction procedure derives symbolic descriptions from the data that are predefined using existing concepts from the medical language. In the second procedure, a large space of numerical meta features is searched through to discover relevant features from the data. These procedures were applied to a prediction problem from intensive care monitoring data. The predictive value of the resulting meta features were compared, and based on each type of features, a class probability tree model was developed.

Results

The numerical meta features extracted by the second procedure were found to be more informative than the symbolic meta features of the first procedure in the case study, and a superior predictive performance was observed for the associated tree model.

Conclusion

The findings indicate that for prediction from monitoring data, induction of numerical meta features from data is preferable to extraction of symbolic meta features using existing clinical concepts.

Keywords: Temporal classification, Feature extraction, Temporal abstraction, Monitoring data, Prognosis, Cardiac surgery, Intensive care