000000730 001__ 730
000000730 005__ 20190404105825.0
000000730 022__ $$a1532-0464
000000730 0247_ $$2DOI$$a10.1016/j.jbi.2014.05.010
000000730 037__ $$aARTICLE
000000730 041__ $$aeng
000000730 245__ $$aMulti-label classification of chronically ill patients with bag of words and supervised dimensionality reduction algorithms
000000730 260__ $$c2014
000000730 269__ $$a2014-10
000000730 300__ $$a10 p.
000000730 506__ $$avisible
000000730 520__ $$aObjective This research is motivated by the issue of classifying illnesses of chronically ill patients for decision support in clinical settings. 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, and microvascular or macrovascular issues. MIMIC II dataset contains 2635 patients affected by thyroid disease, diabetes mellitus, lipoid metabolism disease, fluid electrolyte disease, hypertensive disease, thrombosis, hypotension, chronic obstructive pulmonary disease (COPD), liver disease and kidney disease. The algorithms are evaluated using multi-label evaluation metrics such as hamming loss, one error, coverage, ranking loss, and average precision. Results Non-linear dimensionality reduction approaches behave well on medical time series quantized using the BoW algorithm, with results comparable to state-of-the-art multi-label classification algorithms. Chaining the projected features has a positive impact on the performance of the algorithm with respect to pure binary relevance approaches. Conclusions The evaluation highlights the feasibility of representing medical health records using the BoW for multi-label classification tasks. The study also highlights that dimensionality reduction algorithms based on kernel methods, locality preserving projections or both are good candidates to deal with multi-label classification tasks in medical time series with many missing values and high label density.$$9eng
000000730 592__ $$aHEG-VS
000000730 592__ $$bInstitut Informatique de gestion
000000730 592__ $$cEconomie et Services
000000730 65017 $$aInformatique
000000730 655__ $$ascientifique
000000730 6531_ $$aClinical data$$9eng
000000730 6531_ $$aComplex patient$$9eng
000000730 6531_ $$aDiabetes type 2$$9eng
000000730 6531_ $$aDimensionality reduction$$9eng
000000730 6531_ $$aKernel methods$$9eng
000000730 6531_ $$aMulti-label classification$$9eng
000000730 700__ $$uUniversity of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis)$$aSchumacher, Michael
000000730 700__ $$uUniversity of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis)$$aBromuri, Stefano
000000730 700__ $$uUniversity of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis)$$aZufferey, Damien
000000730 700__ $$aHennebert, Jean$$uUniversity of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis)
000000730 773__ $$goctobre 2014, vol. 51, pp. 165-175$$tJournal of biomedical informatics
000000730 8564_ $$uhttps://hesso.tind.io/record/730/files/bromuri_multilabelclassification_2014.pdf$$s1145409
000000730 909CO $$pGLOBAL_SET$$ooai:hesso.tind.io:730
000000730 906__ $$aNONE
000000730 950__ $$aI2
000000730 980__ $$ascientifique