Our main objective is to propose multi-label classiﬁcation of multivariate time series contained in medical records of chronically ill patients, by means of quantization methods, such as bag of words (BoW), and multi-label classiﬁcation algorithms. Our second objective is to compare supervised dimensionality reduction techniques to state-of-the-art multi-label classiﬁcation algorithms. The hypothesis is that kernel methods and locality preserving projections make such algorithms good candidates to study multi-label medical time series. Methods: We combine BoW and supervised dimensionality reduction algorithms to perform multi-label classiﬁcation on health records of chronically ill patients. The considered algorithms are compared with state-of-the-art multi-label classiﬁers in two real world datasets. Portavita dataset contains 525 diabetes type 2 (DT2) patients, with co-morbidities of DT2 such as hypertension, dyslipidemia, andmicrovascularormacrovascularissues. MIMIC II dataset contains 2635 patients aﬀected by thyroid disease, diabetes mellitus, lipoidmetabolism disease, ﬂuid electrolyte disease, hypertensive disease, thrombosis, hypotension, chronic obstructive pulmonary disease (COPD), liver disease and kidney disease. The algorithms are evaluated using multilabel evaluation metrics such as hamming loss, one error, coverage, ranking loss, and average precision.
Keywords: Multi-Label Classiﬁcation, Complex Patient, Diabetes Type 2, Clinical Data, Dimensionality Reduction, Kernel Methods