Multi-task regression learning for survival analysis via prior information guided transductive matrix completion

Abstract

Survival analysis aims to predict the occurrence time of a particular event of interest, which is crucial for the prognosis analysis of diseases. Currently, due to the limited study period and potential losing tracks, the observed data inevitably involve some censored instances, and thus brings a unique challenge that distinguishes from the general regression problems. In addition, survival analysis also suffers from other inherent challenges such as the high-dimension and small-sample-size problems. To address these challenges, we propose a novel multi-task regression learning model, i.e., prior information guided transductive matrix completion (PigTMC) model, to predict the survival status of the new instances. Specifically, we use the multi-label transductive matrix completion framework to leverage the censored instances together with the uncensored instances as the training samples, and simultaneously employ the multi-task transductive feature selection scheme to alleviate the overfitting issue caused by high-dimension and small-sample-size data. In addition, we employ the prior temporal stability of the survival statuses at adjacent time intervals to guide survival analysis. Furthermore, we design an optimization algorithm with guaranteed convergence to solve the proposed PigTMC model. Finally, the extensive experiments performed on the real microarray gene expression datasets demonstrate that our proposed model outperforms the previously widely used competing methods.

Keywords

survival analysis / matrix completion / multi-task regression / transductive learning / multi-task feature selection

References

[1] Fernández T, Rivera N, Teh Y W. Gaussian processes for survival analysis. In: Proceedings of the 30th International Conference on Neural Information Processing Systems. 2016, 5021–5029

[2] Efron B. The efficiency of Cox’s likelihood function for censored data. Journal of the American Statistical Association, 1977, 72(359): 557–565

[3] Therneau T M, Lumley T. Package ‘survival’. R Top Doc, 2015, 128

[4] Li Y, Rakesh V, Reddy C K. Project success prediction in crowdfunding environments. In: Proceedings of ACM International Conference on Web Search and Data Mining. 2016, 247–256

[5] Crowther M J, Lambert P C. A general framework for parametric survival analysis. Statistics in Medicine, 2014, 33(30): 5280–5297

[6] Lee E T, Wang J. Statistical Methods for Survival Data Analysis. New Jersey: John Wiley & Sons, 2003

[7] Tibshirani R. The lasso method for variable selection in the Cox model. Statistics in Medicine, 1997, 16(4): 385–395

[8] Simon N, Friedman J, Hastie T, Tibshirani R. Regularization paths for Cox’s proportional hazards model via coordinate descent. Journal of Statistical Software, 2011, 39(5): 1

[9] Li Y, Wang L,Wang J, Wang J, Ye J, Reddy C K. Transfer learning for survival analysis via efficient L2, 1-norm regularized Cox regression. In: Proceedings of IEEE International Conference on Data Mining. 2016, 231–240

[10] Li Y, Wang J, Ye J, Reddy C K. A multi-task learning formulation for survival analysis. In: Proceedings of ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2016, 1715–1724

[11] Li Y, Yang T, Zhou J, Ye J. Multi-task learning based survival analysis for predicting Alzheimer’s disease progression with multi-source block-wise missing data. In: Proceedings of SIAM International Conference on Data Mining. 2018, 288–296

[12] Chen L, Zhang H, Lu J, Thung K, Aibaidula A, Liu L, Chen S, Jin L, Wu J, Wang Q, Zhou L, Shen D G. Multi-label nonlinear matrix completion with transductive multi-task feature selection for joint MGMT and IDH1 status prediction of patient with high-grade gliomas. IEEE Transactions on Medical Imaging, 2018, 37(8): 1775–1787

[13] Goldberg A, Recht B, Xu J, Nowak R, Zhu J. Transduction with matrix completion: three birds with one stone. In: Proceedings of the 23rd International Conference on Neural Information Processing Systems. 2010, 757–765

[14] Cabral R, De la Torre F, Costeira J P, Bernardino A. Matrix completion for weakly-supervised multi-label image classification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(1), 121–135

[15] Tulyakov S, Alameda-Pineda X, Ricci E, Yiu L, Cohn J F, Sebe N. Self-adaptive matrix completion for heart rate estimation from face videos under realistic conditions. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2016, 2396–2404

[16] Cox D R. Regression models and life-tables. Journal of the Royal Statistical Society: Series B (Methodological), 1972, 34(2): 187–202

[17] Indrayan A, Bansal A K. The methods of survival analysis for clinicians. Indian Pediatrics, 2010, 47(9): 743–748

[18] Wang P, Li Y, Reddy C K. Machine learning for survival analysis: a survey. ACM Computing Surveys (CSUR), 2019, 51(6): 110

[19] Aitkin M, Clayton D. The fitting of exponential, Weibull and extreme value distributions to complex censored survival data using GLIM. Journal of the Royal Statistical Society: Series C (Applied Statistics), 1980, 29(2): 156–163

[20] Bennett S. Log-logistic regression models for survival data. Journal of the Royal Statistical Society: Series C (Applied Statistics), 1983, 32(2): 165–171

[21] Li Y, Xu K S, Reddy C K. Regularized parametric regression for highdimensional survival analysis. In: Proceedings of SIAM International Conference on Data Mining. 2016, 765–773

[22] Miller R, Halpern J. Regression with censored data. Biometrika, 1982, 69(3): 521–531

[23] Koul H, Susarla V, Van Ryzin J. Regression analysis with randomly right-censored data. The Annals of Statistics, 1981, 9(6): 1276–1288

[24] Tobin J. Estimation of relationships for limited dependent variables. Econometrica, 1958, 26(1): 24–36

[25] Buckley J, James I. Linear regression with censored data. Biometrika, 1979, 66(3): 429–436

[26] Wang S, Nan B, Zhu J, Beer D G. Doubly penalized Buckley–James method for survival data with high-dimensional covariates. Biometrics, 2008, 64(1): 132–140

[27] Li Y, Vinzamuri B, Reddy C K. Regularized weighted linear regression for high-dimensional censored data. In: Proceedings of SIAM International Conference on Data Mining. 2016, 45–53

[28] Ye W, Chen L, Yang G, Dai H, Xiao F. Anomaly-tolerant traffic matrix estimation via prior information guided matrix completion. IEEE Access, 2017, 5: 3172–3182

[29] Xu Y, Yin W. A globally convergent algorithm for nonconvex optimization based on block coordinate update. Journal of Scientific Computing, 2017, 72(2): 700–734

[30] Liu J, Ji S, Ye J. Multi-task feature learning via efficient l 2, 1-norm minimization. In: Proceedings of AUAI Conference on Uncertainty in Artificial Intelligence. 2009, 339–348

[31] Sørlie T, Tibshirani R, Parker J, Hastie T, Maron J S, Nobel A, Deng S, Johnsen H, Pesich R, Geisler S, Demeter J, Perou C M, Lønning P E, Brown P O, Børresen-Dale A L, Botstein D. Repeated observation of breast tumor subtypes in independent gene expression data sets. Proceedings of the National Academy of Sciences, 2003, 100(14): 8418–8423

[32] Van’t Veer L J, Dai H, Van De Vijver M J, He Y D, Hart A A M, Mao M, Peterse H L, Wan Der Kooy K, Marton M J, Witteveen A T, Schreiber G J, Kerkhoven R M, Roberts C, Linsley P S, Bernards R, Friend S H. Gene expression profiling predicts clinical outcome of breast cancer. Nature, 2002, 415(6871): 530

[33] Beer D G, Kardia S L R, Huang C C, Giordano T J, Levin A M, Misek D E, Lin L, Chen G, Tarek G, Thomas D G, Lizyness M L, Kuick R, Hayasaka S, Taylor J, Lannettoni M D, Orringer M B, Hanash S. Gene-expression profiles predict survival of patients with lung adenocarcinoma. Nature Medicine, 2002, 8(8): 816

[34] van Houwelingen H C, Bruinsma T, Hart A A M, Van’t Veer L J, Wessels L F. Cross-validated Cox regression on microarray gene expression data. Statistics in Medicine, 2006, 25(18): 3201–3216

[35] Rosenwald A,Wright G, Wiestner A, Chan W C, Connors J M, Campo E, Gascoyne R D, Grogan T M, Muller-Hermelink H K, Smeland E B, Chiorazzi M, Giltnane J M, Hurt E M, Zhao H, Averett L, Henrickson S, Yang L, Poweel J, Wilson W, Jaffe E S, Simon R, Kiausner R D, Montserrat E, Bosch F, Greiner T, Weisenburger D D, Sanger W G, Dave B J, Lynch J C, Vose J, Armitage J O, Fisher R I, Miller T P, LeBlanc M, Ott G, Kvalo y S, Holte H, Delabie J, Staudt L M. The proliferation gene expression signature is a quantitative integrator of oncogenic events that predicts survival in mantle cell lymphoma. Cancer Cell, 2003, 3(2): 185–197

[36] Harrell Jr F E, Califf R M, Pryor D B, Lee K L, Rosati R A. Evaluating the yield of medical tests. Jama, 1982, 247(18): 2543–2546

[37] Therneau T. A package for survival analysis in S. R Package Version 2.37-4. 2013

[38] Yang Y, Zou H. A cocktail algorithm for solving the elastic net penalized Cox’s regression in high dimensions. Statistics and its Interface, 2013, 6(2): 167–173

[39] Wang L, Li Y, Zhou J, Zhu D, Ye J. Multi-task survival analysis. In: Proceedings of IEEE International Conference on Data Mining. 2017, 485–494

[40] Faraway J J. Practical Regression and ANOVA Using R. 2002

[41] Wang Z, Wang C Y. Buckley-James boosting for survival analysis with high-dimensional biomarker data. Statistical Applications in Genetics and Molecular Biology, 2010, 9(1): 1–31

[42] Zhou J, Chen J, Ye J. Malsar: multi-task learning via structural regularization. Arizona State University, 2011, 21

[43] Alameda-Pineda X, Ricci E, Yan Y, Sebe N. Recognizing emotions from abstract paintings using non-linear matrix completion. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2016, 5240–5248

[44] Boyd S, Vandenberghe L. Convex Optimization. Cambridge: Cambridge University Press, 2004

RIGHTS & PERMISSIONS

Higher Education Press and Springer-Verlag GmbH Germany, part of Springer Nature