Studying the Potential of Multi-target Classification to Characterize Combinations of Classes with Skewed Distribution

The identification of subpopulations with particular characteristics with respect to a disease is important for personalized diagnostics and therapy design. For some diseases, the outcome is described by more than one target variable. An example is tinnitus: the perceived loudness of the phantom signal and the level of distress caused by it are both relevant targets for diagnosis and therapy. In this work, we study the potential of multi-target classification for the identification of those screening variables, which separate best among the different subpopulations of patients, paying particular attention to subpopulations with discordant value combinations of loudness and distress. We analyse the screening data of 1344 tinnitus patients from the University Hospital Regensburg, including questions from 7 questionnaires, and report on the performance of our workflow in target separation and in ranking the questionnaires variables on their discriminative power.

[1]  J B Spitzer,et al.  Development of the Tinnitus Handicap Inventory. , 1996, Archives of otolaryngology--head & neck surgery.

[2]  M Leibetseder,et al.  [Can tinnitus be measured? Methods for assessment of tinnitus-specific disability and presentation of the Tinnitus Disability Questionnaire]. , 1999, HNO.

[3]  Sana Amanat,et al.  TINNITUS , 1979, The Lancet.

[4]  S. Skevington,et al.  The World Health Organization's WHOQOL-BREF quality of life assessment: Psychometric properties and results of the international field trial. A Report from the WHOQOL Group , 2004, Quality of Life Research.

[5]  Grigorios Tsoumakas,et al.  Multi-Label Classification: An Overview , 2007, Int. J. Data Warehous. Min..

[6]  Liujuan Cao,et al.  A novel features ranking metric with application to scalable visual and bioinformatics data classification , 2016, Neurocomputing.

[7]  W. Hiller,et al.  When Tinnitus Loudness and Annoyance Are Discrepant: Audiological Characteristics and Psychological Profile , 2007, Audiology and Neurotology.

[8]  Gilles Louppe,et al.  Understanding Random Forests: From Theory to Practice , 2014, 1407.7502.

[9]  P Bech,et al.  The sensitivity and specificity of the Major Depression Inventory, using the Present State Examination as the index of diagnostic validity. , 2001, Journal of affective disorders.

[10]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[11]  S. Džeroski,et al.  Using multi-objective classification to model communities of soil microarthropods , 2006 .

[12]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[13]  Saso Dzeroski,et al.  Constraint Based Induction of Multi-objective Regression Trees , 2005, KDID.

[14]  Gilles Louppe,et al.  Understanding variable importances in forests of randomized trees , 2013, NIPS.

[15]  D. Ridder,et al.  Tinnitus: perspectives from human neuroimaging , 2015, Nature Reviews Neuroscience.

[16]  Saso Dzeroski,et al.  Ensembles of Multi-Objective Decision Trees , 2007, ECML.

[17]  J P Rauschecker,et al.  Consensus for tinnitus patient assessment and treatment outcome measurement: Tinnitus Research Initiative meeting, Regensburg, July 2006. , 2007, Progress in Brain Research.