Somaraki, Vassiliki, Vallati, Mauro and McCluskey, Lee (2015) Discovering Interesting Trends in Real Medical Data: A study in Diabetic Retinopathy. In: Progress in Artificial Intelligence : 17th Portuguese Conference on Artificial Intelligence, EPIA 2015 Proceedings. Lecture Notes in Computer Science, 9273 . Springer, pp. 134-140. ISBN 978-3-319-23484-7
Abstract

In this work we present SOMA: a Trend Mining framework, based on longitudinal data analysis, that is able to measure the interestingness of the produced trends in large noisy medical databases. Medical longitudinal data typically plots the progress of some medical condition, thus implicitly contains a large number of trends. The approach has been evaluated on a large collection of medical records, forming part of the diabetic retinopathy screening programme at the Royal Liverpool University Hospital, UK.

Information
Library
Documents
[img]
SOMA_EPIA.pdf - Accepted Version
Restricted to Repository staff only

Download (114kB)
Statistics