Advertisement

Multi-label Transduction for Identifying Disease Comorbidity Patterns

  • Ehsan AdeliEmail author
  • Dongjin Kwon
  • Kilian M. Pohl
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11072)

Abstract

Study of the untoward effects associated with the comorbidity of multiple diseases on brain morphology requires identifying differences across multiple diagnostic groupings. To identify such effects and differentiate between groups of patients and normal subjects, conventional methods often compare each patient group with healthy subjects using binary or multi-class classifiers. However, testing inferences across multiple diagnostic groupings of complex disorders commonly yield inconclusive or conflicting findings when the classifier is confined to modeling two cohorts at a time or considers class labels mutually-exclusive (as in multi-class classifiers). These shortcomings are potentially caused by the difficulties associated with modeling compounding factors of diseases with these approaches. Multi-label classifiers, on the other hand, can appropriately model disease comorbidity, as each subject can be assigned to two or more labels. In this paper, we propose a multi-label transductive (MLT) method based on low-rank matrix completion that is able not only to classify the data into multiple labels but also to identify patterns from MRI data unique to each cohort. To evaluate the method, we use a dataset containing individuals with Alcohol Use Disorder (AUD) and human immunodeficiency virus (HIV) infection (specifically 244 healthy controls, 227 AUD, 70 HIV, and 61 AUD+HIV). On this dataset, our proposed method is more accurate in correctly labeling subjects than common approaches. Furthermore, our method identifies patterns specific to each disease and AUD+HIV comorbidity that shows that the comorbidity is characterized by a compounding effect of AUD and HIV infection.

References

  1. 1.
    Adeli, E., Fathy, M.: Non-negative matrix completion for action detection. Image Vis. Comput. 39, 38–51 (2015)CrossRefGoogle Scholar
  2. 2.
    Cabral, R., Torre, F., Costeira, J., Bernardino, A.: Matrix completion for weakly-supervised multi-label image classification. IEEE TPAMI 37(1), 121–135 (2015)CrossRefGoogle Scholar
  3. 3.
    Candès, E.J., Recht, B.: Exact matrix completion via convex optimization. Found. Comput. Math. 9(6), 717–772 (2009)MathSciNetCrossRefGoogle Scholar
  4. 4.
    Chang, C.C., Lin, C.J.: LIBSVM: a library for support vector machines. ACM Trans. IST 2(27), 1–27 (2011)Google Scholar
  5. 5.
    Fama, R.: Impairments in component processes of executive function and episodic memory in alcoholism, HIV infection, and HIV infection with alcoholism comorbidity. Alcohol.: Clin. Exp. Res. 40(12), 2656–2666 (2016)CrossRefGoogle Scholar
  6. 6.
    Fisher, R.A.: The logic of inductive inference. J. R. Stat. Soc. 98(1), 39–82 (1935)CrossRefGoogle Scholar
  7. 7.
    Goldberg, A., Recht, B., Xu, J., Nowak, R., Zhu, X.: Transduction with matrix completion: three birds with one stone. In: NIPS, pp. 757–765 (2010)Google Scholar
  8. 8.
    Gongvatana, A.: A history of alcohol dependence augments HIV-associated neurocognitive deficits in persons aged 60 and older. Neurovirology 20(5), 505–513 (2014)CrossRefGoogle Scholar
  9. 9.
    Justice, A., Sullivan, L., Fiellin, D.: HIV/AIDS, comorbidity, and alcohol: can we make a difference? Alcohol Res. Health 33(3), 258 (2010)Google Scholar
  10. 10.
    Li, X., Guo, Y.: Active learning with multi-label SVM classification. In: IJCAI (2013)Google Scholar
  11. 11.
    Madsen, H., Thyregod, P.: Introduction to General and Generalized Linear Models. CRC Press, Boca Raton (2010)CrossRefGoogle Scholar
  12. 12.
    Parekh, A.K., Barton, M.B.: The challenge of multiple comorbidity for the us health care system. JAMA 303(13), 1303–1304 (2010)CrossRefGoogle Scholar
  13. 13.
    Pfefferbaum, A.: Accelerated aging of selective brain structures in human immunodeficiency virus infection. Neurobiol. Aging 35(7), 1755–1768 (2014)CrossRefGoogle Scholar
  14. 14.
    Tsoumakas, G., Katakis, I.: Multi-label classification: an overview. Int. J. Data Warehous. Min. 3(3), 1–13 (2006)CrossRefGoogle Scholar
  15. 15.
    Wang, X., Wang, F., Hu, J.: A multi-task learning framework for joint disease risk prediction and comorbidity discovery. In: ICPR, pp. 220–225. IEEE (2014)Google Scholar
  16. 16.
    Wosiak, A., Glinka, K., Zakrzewska, D.: Multi-label classification methods for improving comorbidities identification. Comput. Biol. Med. 100, 279–288 (2017)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Stanford UniversityStanfordUSA
  2. 2.SRI InternationalMenlo ParkUSA

Personalised recommendations