Not Logged In

Interdisciplinary-driven hypotheses on spatial associations of mixtures of industrial air pollutants with adverse birth outcomes

Previous work has shown that machine learning algorithms lend themselves to clinical decision-making and are a valuable tool for physicians. For clinical data, it is often necessary to assign multiple labels to a patient record by choosing from a large number of potential labels. A key problem in learning from multi-labelled data is how to exploit the information contained in the correlations between labels. The hypergraph-based multi-label learning method learns from data by exploiting the spectral property of the hypergraph that encodes the correlation structure of labels. However, the problem with this method is the difficulty with which interpretations can be made. This is mainly due to its inability to recognize the importance of key features in the original feature space. Moreover, it is hard to comprehensively capture the complex structure of the correlations between labels. To overcome these difficulties and improve interpretability, we propose an l21-norm regularized Graph Laplacian multi-label learning to perform feature selection and label embedding simultaneously. In-depth experimental studies, using the publicly available Medical Information Mart for Intensive Care (MIMIC-III) database, validate the effectiveness of our approach.

Citation

J. Serrano-Lomelin, C. Nielsen, M. Jabbar, O. Wine, C. Bellinger, P. Villeneuve, D. Stieb, N. Aelicks, K. Aziz, I. Buka, S. Chandra, S. Crawford, P. Demers, A. Erickson, P. Hystad, M. Kumar, E. Phipps, P. Shah, Y. Yuan, O. Zaiane, A. Osornio-Vargas. " Interdisciplinary-driven hypotheses on spatial associations of mixtures of industrial air pollutants with adverse birth outcomes". Environment International Journal, 131(13), pp 1-7, October 2019.

Keywords: Multi-label learning, High dimensionality, Feature selection, Ensemble classification, MIMIC-III
Category: In Journal
Web Links: ScienceDirect
  doi

BibTeX

@article{Serrano-Lomelin+al:19,
  author = {Jesus Serrano-Lomelin and Charlene C. Nielsen and Mohomed Shazan
    Mohomed Jabbar and Osnat Wine and Colin Bellinger and Paul J. Villeneuve
    and David M. Stieb and Nancy Aelicks and Khalid Aziz and Irena Buka and Sue
    Chandra and Susan Crawford and Paul Demers and Anders C. Erickson and Perry
    Hystad and Manoj Kumar and Erica Phipps and Prakesh S. Shah and Yan Yuan
    and Osmar R. Zaiane and Alvaro R. Osornio-Vargas},
  title = { Interdisciplinary-driven hypotheses on spatial associations of
    mixtures of industrial air pollutants with adverse birth outcomes},
  Volume = "131",
  Number = "13",
  Pages = {1-7},
  journal = {Environment International Journal},
  year = 2019,
}

Last Updated: September 10, 2020
Submitted by Sabina P

University of Alberta Logo AICML Logo