Abstract
Heart failure with preserved ejection fraction (HFpEF) is a heterogeneous clinical syndrome that may benefit from improved subtyping in order to better characterize its pathophysiology and to develop novel targeted therapies. The United States Precision Medicine Initiative comes amid the rapid growth in quantity and modality of clinical data for HFpEF patients ranging from deep phenotypic to trans-omic data. Tensor factorization, a form of machine learning, allows for the integration of multiple data modalities to derive clinically relevant HFpEF subtypes that may have significant differences in underlying pathophysiology and differential response to therapies. Tensor factorization also allows for better interpretability by supporting dimensionality reduction and identifying latent groups of data for meaningful summarization of both features and disease outcomes. In this narrative review, we analyze the modest literature on the application of tensor factorization to related biomedical fields including genotyping and phenotyping. Based on the cited work including work of our own, we suggest multiple tensor factorization formulations capable of integrating the deep phenotypic and trans-omic modalities of data for HFpEF, or accounting for interactions between genetic variants at different omic hierarchies. We encourage extensive experimental studies to tackle challenges in applying tensor factorization for precision medicine in HFpEF, including effectively incorporating existing medical knowledge, properly accounting for uncertainty, and efficiently enforcing sparsity for better interpretability.
Similar content being viewed by others
References
Mozaffarian, D., Benjamin, E.J., Go, A.S., et al. (2015).Heart disease and stroke statistics—2016 update. A Report From the American Heart Association.
Yancy, C. W., Jessup, M., Bozkurt, B., et al. (2013). 2013 ACCF/AHA guideline for the management of heart failure: a report of the American College of Cardiology Foundation/American Heart Association Task Force on Practice Guidelines. Journal of the American College of Cardiology, 62(16), e147–e239.
Samson, R., Jaiswal, A., Ennezat, P. V., Cassidy, M., & Le Jemtel, T. H. (2016). Clinical phenotypes in heart failure with preserved ejection fraction. Journal of the American Heart Association., 5(1), e002477.
Shah, S. J., Kitzman, D. W., Borlaug, B. A., et al. (2016). Phenotype-specific treatment of heart failure with preserved ejection fraction. A Multiorgan Roadmap., 134(1), 73–90.
Paulus, W. J., & Tschöpe, C. (2013). A novel paradigm for heart failure with preserved ejection fraction: comorbidities drive myocardial dysfunction and remodeling through coronary microvascular endothelial inflammation. Journal of the American College of Cardiology, 62(4), 263–271.
Vaduganathan, M., Michel, A., Hall, K., et al. (2016). Spectrum of epidemiological and clinical findings in patients with heart failure with preserved ejection fraction stratified by study design: a systematic review. European Journal of Heart Failure, 18(1), 54–65.
Shah, S.J., Katz, D.H., Selvaraj, S., et al. (2014). Phenomapping for novel classification of heart failure with preserved ejection fraction. Circulation :CIRCULATIONAHA. 114.010637.
Kapuku, G. K., Ge, D., Vemulapalli, S., Harshfield, G. A., Treiber, F. A., & Snieder, H. (2008). Change of genetic determinants of left ventricular structure in adolescence: longitudinal evidence from the Georgia cardiovascular twin study. American Journal of Hypertension, 21(7), 799–805.
Tang, W., Devereux, R. B., Li, N., et al. (2009). Identification of a pleiotropic locus on chromosome 7q for a composite left ventricular wall thickness factor and body mass index: the HyperGEN Study. BMC Medical Genetics, 10(1), 1.
Vasan, R. S., Glazer, N. L., Felix, J. F., et al. (2009). Genetic variants associated with cardiac structure and function: a meta-analysis and replication of genome-wide association data. Journal of the American Medical Association, 302(2), 168–178.
Smith, N. L., Felix, J. F., Morrison, A. C., et al. (2010). Association of genome-wide variation with the risk of incident heart failure in adults of European and African ancestry a prospective meta-analysis from the cohorts for heart and aging research in genomic epidemiology (CHARGE) consortium. Circulation. Cardiovascular Genetics, 3(3), 256–266.
Larson, M. G., Atwood, L. D., Benjamin, E. J., et al. (2007). Framingham Heart Study 100 K project: genome-wide associations for cardiovascular disease outcomes. BMC Medical Genetics, 8(1), 1.
Morrison, A. C., Felix, J. F., Cupples, L. A., et al. (2010). Genomic variation associated with mortality among adults of European and African ancestry with heart failure the cohorts for heart and aging research in genomic epidemiology consortium. Circulation. Cardiovascular Genetics, 3(3), 248–255.
Berezin, A. (2016). Epigenetics in heart failure phenotypes. BBA Clinical., 6, 31–37.
Kohane, I. S. (2015). Ten things we have to do to achieve precision medicine. Science, 349(6243), 37–38.
Bild, D. E., Bluemke, D. A., Burke, G. L., et al. (2002). Multi-ethnic study of atherosclerosis: objectives and design. American Journal of Epidemiology, 156(9), 871–881.
Winslow, R. L., Trayanova, N., Geman, D., & Miller, M. I. (2012). Computational medicine: translating models to clinical care. Science Translational Medicine, 4(158), 158rv111–158rv111.
Luo, Y., Uzuner, Ö., Szolovits, P. (2016). Bridging semantics and syntax with graph algorithms—state-of-the-art of extracting biomedical relations. Briefings in Bioinformatics.
Moskovitch, R., & Shahar, Y. (2015). Classification of multivariate time series via temporal abstraction and time intervals mining. Knowledge and Information Systems., 45(1), 35–74.
Lee, D. D., & Seung, H. S. (1999). Learning the parts of objects by non-negative matrix factorization. Nature, 401(6755), 788–791.
Steyvers, M., & Griffiths, T. (2007). Probabilistic topic models. Handbook of latent semantic analysis., 427(7), 424–440.
Luo, Y., Sohani, A. R., Hochberg, E. P., & Szolovits, P. (2014). Automatic lymphoma classification with sentence subgraph mining from pathology reports. Journal of the American Medical Informatics Association, 21(5), 824–832.
Luo, Y., Xin, Y., Hochberg, E., Joshi, R., Uzuner, O., Szolovits, P. (2015). Subgraph augmented non-negative tensor factorization (SANTF) for modeling clinical narrative text. Journal of the American Medical Informatics Association :ocv016.
Luo, Y., Xin, Y., Joshi, R., Celi, L., Szolovits, P. (2016). Predicting ICU mortality risk by grouping temporal trends from a multivariate panel of physiologic measurements.
Kolda, T. G., & Bader, B. W. (2009). Tensor decompositions and applications. SIAM review., 51(3), 455–500.
Cichocki, A. (2014). Tensor networks for big data analytics and large-scale optimization problems. arXiv preprint arXiv :14073124.
Han, D., Wang, S., Jiang, C., et al. (2015). Trends in biomedical informatics: automated topic analysis of <em>JAMIA</em> articles. Journal of the American Medical Informatics Association, 22(6), 1153–1163.
Wang, Y., Chen, R., Ghosh, J., et al. (2015). Rubik: knowledge guided tensor factorization and completion for health data analytics. Paper presented at: Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.
Tucker, L. R. (1966). Some mathematical notes on three-mode factor analysis. Psychometrika, 31(3), 279–311.
Carroll, J. D., & Chang, J.-J. (1970). Analysis of individual differences in multidimensional scaling via an N-way generalization of “Eckart-Young” decomposition. Psychometrika, 35(3), 283–319.
Mørup, M. (2011). Applications of tensor (multiway array) factorizations and decompositions in data mining. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery., 1(1), 24–40.
Vogelstein, B., Papadopoulos, N., Velculescu, V. E., Zhou, S., Diaz, L. A., & Kinzler, K. W. (2013). Cancer genome landscapes. Science, 339(6127), 1546–1558.
Nik-Zainal, S., Alexandrov, L. B., Wedge, D. C., et al. (2012). Mutational processes molding the genomes of 21 breast cancers. Cell, 149(5), 979–993.
Franceschini, A., Szklarczyk, D., Frankild, S., et al. (2013). STRING v9. 1: protein-protein interaction networks, with increased coverage and integration. Nucleic Acids Research, 41(D1), D808–D815.
Kanehisa, M., Goto, S., Sato, Y., Furumichi, M., Tanabe, M. (2011). KEGG for integration and interpretation of large-scale molecular data sets. Nucleic Acids Research :gkr988.
Hunter, S., Jones, P., Mitchell, A., et al. (2011). InterPro in 2011: new developments in the family and domain prediction database. Nucleic Acids Research :gkr948.
Thierry-Mieg, D., & Thierry-Mieg, J. (2006). AceView: a comprehensive cDNA-supported gene and transcripts annotation. Genome Biology, 7(1), 1.
Finn, R.D., Bateman, A., Clements, J., et al. (2013). Pfam: the protein families database. Nucleic Acids Research :gkt1223.
Luo, Y., & Szolovits, P. (2016). Efficient queries of stand-off annotations for natural language processing on electronic medical records. Biomedical Informatics Insights., 8, 29–38.
Luo, Y., Wang, F., Szolovits, P. (2016). Tensor factorization toward precision medicine. Briefings in Bioinformatics.
Cong, F., Lin, Q.-H., Kuang, L.-D., Gong, X.-F., Astikainen, P., & Ristaniemi, T. (2015). Tensor decomposition of EEG signals: a brief review. Journal of Neuroscience Methods, 248, 59–69.
Ho, J. C., Ghosh, J., Steinhubl, S. R., et al. (2014). Limestone: high-throughput candidate phenotype generation via tensor factorization. Journal of biomedical informatics., 52, 199–211.
Ho, J.C., Ghosh, J., Sun, J. (2014). Marble: high-throughput phenotyping from electronic health records via sparse nonnegative tensor factorization. Paper presented at: Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining.
Wang, F., Zhang, P., Qian, B., Wang, X., Davidson, I. (2014). Clinical risk prediction with multilinear sparse logistic regression. Paper presented at: Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining.
Kessler, D.C., Taylor, J., Dunson, D.B. (2014). Learning phenotype densities conditional on many interacting predictors. Bioinformatics :btu040.
Yang, Y., Dunson, D.B. (2015). Bayesian conditional tensor factorizations for high-dimensional classification. Journal of the American Statistical Association. (just-accepted).
Zhou, J., Bhattacharya, A., Herring, A. H., & Dunson, D. B. (2015). Bayesian factorizations of big sparse tensors. Journal of the American Statistical Association., 110(512), 1562–1576.
Rai P, Wang Y, Guo S, Chen G, Dunson DB, Carin L. (2014). Scalable Bayesian low-rank decomposition of incomplete multiway tensors. Paper presented at: ICML.
Mørup, M., Hansen, L. K., & Arnfred, S. M. (2008). Algorithms for sparse nonnegative Tucker decompositions. Neural Computation, 20(8), 2112–2131.
Sun, W., Lu, J., Liu, H., Cheng, G. (2015). Provable sparse tensor decomposition. arXiv preprint arXiv :150201425.
Acknowledgements
Dr. Ahmad is supported by the National Heart, Lung, and Blood Institute of the National Institutes of Health (NIH) under Award number T32HL069771. Dr. Shah is supported by the NIH R01 HL107577 and R01 HL127028 and American Heart Association grants #15CVGPSD27260148 and #16SFRN28780016.
Author information
Authors and Affiliations
Corresponding author
Additional information
Associate Editor Daniel P. Judge oversaw the review of this article
Rights and permissions
About this article
Cite this article
Luo, Y., Ahmad, F.S. & Shah, S.J. Tensor Factorization for Precision Medicine in Heart Failure with Preserved Ejection Fraction. J. of Cardiovasc. Trans. Res. 10, 305–312 (2017). https://doi.org/10.1007/s12265-016-9727-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12265-016-9727-8