- Full text PDF available (3)
In this work we present the application of inductive machine learning techniques in medical diagnosis of stroke. Our approach uses See5 algorithm-an updated version of the well known C4.5 (Quinlan J.R., 1993)-which is capable of ''learning from examples'' by constructing a decision tree which can be transformed to IF/THEN rules.
Knowledge acquisition techniques investigate ways to pick up information about the way that medical experts work and decide in order to resemble their behaviour and assist them in analysing a patient's condition. Available data can sometimes be complicated and by representing them in crisp or nominal values the diagnosis scheme loses in terms of… (More)
The purpose of this work is to test the efficiency of specific intelligent classification algorithms when dealing with the domain of stroke medical diagnosis. The dataset consists of patient records of the " Acute Stroke Unit " , Alexandra Hospital, Athens, Greece, describing patients suffering one of 5 different stroke types diagnosed by 127 diagnostic… (More)
BACKGROUND Secondary prevention studies for cardioembolic strokes show a remarkable variability in stroke recurrence rates. Various reports have raised questions regarding differences in baseline clinical characteristics and in methodology to explain this wide variability. HYPOTHESIS The purpose of the present study is to examine the 2-year outcome after… (More)