Discussing anomalous situations using decision trees: a head injury case study.
OBJECTIVES: Predicting the outcome of seriously ill patients is a challenging problem for clinicians. METHODS: One alternative to clinical trials is to analyse existing patient data in an attempt to predict the several outcomes, and to suggest therapies. In this paper we use decision tree techniques to predict the outcome of head injury patients. The work is based on patient data from the Edinburgh Royal Infirmary which contains both background (demographic) data and temporal (physiological) data. RESULTS: The focus of this paper is the discussion of the anomalous cases in the decision trees with the domain experts (the clinicians). CONCLUSIONS: These analyses led to the detection of several situations where both the data analysis and patient data collection should be enhanced, which in turn should lead to improved patient care.