Within medical research there is an increasing trend toward deriving multiple types of data from the same individual. The most effective prognostic prediction methods should use all available data, since this maximizes the amount of information used. In this paper we consider a variety of learning strategies to boost prediction performance based on
the use of all available data.
In this paper we consider data integration via the use of
multiple kernel learning (MKL) supervised learning methods.
We consider a scheme in which feature selection by statistical score is performed separately per data type and by pathway membership. We further consider the introduction of a confidence measure for the class assignment, both to remove some ambiguously labelled datapoints from the training data and to implement a cautious classifier which only makes predictions when the associated confidence is high.
We use the METABRIC dataset for breast cancer, with prediction of survival at 2000 days from diagnosis. Predictive accuracy is improved by using kernels which exclusively use those genes, as features, which are known members of particular pathways. We show that yet further improvements can be made by using a range of additional kernels based on clinical covariates such as ER-status.
Using this range of measures to improve prediction performance we show that the test accuracy on new instances is nearly 80%,though predictions are only made on 69.2% of the patient cohort.