This document gives brief descriptions for a number of Machine Discovery and Knowledge Based Refinement Systems which have recently been developed. Further, it gives an indication of their application domains. The systems described are: DaViCAND, MedMine, REFINER+, RETAX, STALKER and TIGON. Principal Contact: Professor Derek Sleeman Phone: +44(0)1224 272288 Fax: +44(0)1224 273422 email: dsleeman@csd.abdn.ac.uk www: http://www.csd.abdn.ac.uk/~sleeman /sleeman.html

OBJECT:Decision tree analysis highlights patient subgroups and critical values in variables assessed. Importantly, the results are visually informative and often present clear clinical interpretation about risk factors faced by patients in these subgroups. The aim of this prospective study was to compare results of logistic regression with those of decision tree analysis of an observational, head-injury data set, including a wide range of secondary insults and 12-month outcomes.METHODS:One hundred twenty-four adult head-injured patients were studied during their stay in an intensive care unit by using a computerized data collection system. Verified values falling outside threshold limits were analyzed according to insult grade and duration with the aid of logistic regression. A decision tree was automatically produced from root node to target classes (Glasgow Outcome Scale [GOS] score). Among 69 patients, in whom eight insult categories could be assessed, outcome at 12 months was analyzed using logistic regression to determine the relative influence of patient age, admission Glasgow Coma Scale score, Injury Severity Score (ISS), pupillary response on admission, and insult duration. The most significant predictors of mortality in this patient set were duration of hypotensive, pyrexic, and hypoxemic insults. When good and poor outcomes were compared, hypotensive insults and pupillary response on admission were significant. Using decision tree analysis, the authors found that hypotension and low cerebral perfusion pressure (CPP) are the best predictors of death, with a 9.2% improvement in predictive accuracy (PA) over that obtained by simply predicting the largest outcome category as the outcome for each patient. Hypotension was a significant predictor of poor outcome (GOS Score 1-3). Low CPP, patient age, hypocarbia, and pupillary response were also good predictors of outcome (good/poor), with a 5.1% improvement in PA. In certain subgroups of patients pyrexia was a predictor of good outcome.CONCLUSIONS:Decision tree analysis confirmed some of the results of logistic regression and challenged others. This investigation shows that there is knowledge to be gained from analyzing observational data with the aid of decision tree analysis.

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.

Predicting the outcome of seriously ill patients is a challenging problem for clinicians. 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.