A pattern mining approach for classifying multivariate temporal data
We study the problem of learning classiﬁcation models from complex multivariate temporal data encountered in electronic health record systems. The challenge is to deﬁne a good set of features that are able to represent well the temporal aspect of the data. Our method relies on temporal abstractions and temporal pattern mining to extract the classiﬁcation features. Temporal pattern mining usually returns a large number of temporal patterns, most of which may be irrelevant to the classiﬁcation task. To address this problem, we present the minimal predictive temporal patterns framework to generate a small set of predictive and non-spurious patterns. We apply our approach to the real-world clinical task of predicting patients who are at risk of developing heparin induced thrombocytopenia. The results demonstrate the beneﬁt of our approach in learning accurate classiﬁers, which is a key step for developing intelligent clinical monitoring systems.