Predicting stroke risk with an interpretable classifier
Author
dc.contributor.author
Peñafiel, Sergio
Author
dc.contributor.author
Baloian Tataryan, Nelson
Author
dc.contributor.author
Sanson, Horacio
Author
dc.contributor.author
Pino Urtubia, José
Admission date
dc.date.accessioned
2021-09-22T16:34:04Z
Available date
dc.date.available
2021-09-22T16:34:04Z
Publication date
dc.date.issued
2021
Cita de ítem
dc.identifier.citation
IEEE Access (2021) Volumen9 Página1154-1166
es_ES
Identifier
dc.identifier.other
10.1109/ACCESS.2020.3047195
Identifier
dc.identifier.uri
https://repositorio.uchile.cl/handle/2250/182063
Abstract
dc.description.abstract
Predicting an individual's risk of getting a stroke has been a research subject for many authors
worldwide since it is a frequent illness and there is strong evidence that early awareness of having that risk can
be bene cial for prevention and treatment. Many Governments have been collecting medical data about their
own population with the purpose of using arti cial intelligence methods for making those predictions. The
most accurate ones are based on so called black-box methods which give little or no information about why
they make a certain prediction. However, in the medical eld the explanations are sometimes more important
than the accuracy since they allow specialists to gain insight about the factors that in uence the risk level.
It is also frequent to nd medical information records with some missing data. In this work, we present the
development of a prediction method which not only outperforms some other existing ones but it also gives
information about the most probable causes of a high stroke risk and can deal with incomplete data records.
It is based on the Dempster-Shafer theory of plausibility. For the testing we used data provided by the regional
hospital in Okayama, Japan, a country in which people are compelled to undergo annual health checkups
by law. This article presents experiments comparing the results of the Dempster-Shafer method with the
ones obtained using other well-known machine learning methods like Multilayer perceptron, Support Vector
Machines and Naive Bayes. Our approach performed the best in these experiments with some missing data.
It also presents an analysis of the interpretation of rules produced by the method for doing the classi cation.
The rules were validated by both medical literature and human specialists.