面向癌症个体生存分析的多任务带状回归模型

doi:10.3778/j.issn.1002-8331.2201-0431

摘要/Abstract

摘要： 个体癌症生存分析对于探索个人在罹患癌病后生存状态具有重要意义。针对目前多任务线性回归方法依赖于线性转换而不能体现个人癌症病程风险累积的问题，提出了一种多任务带状回归模型，用于拟合以癌症为代表的病性慢、病程长的生存分析。引入带状校验方式建立了回归器和带状转换结合的多任务回归模型，数学推导并验证了带状检验转换矩阵的有效性和良态性。给出了多任务带状矩阵的两个特殊矩阵。在真实的癌症急病和生存分析数据集上验证了提出的模型对个人生存分析风险预测的有效性。在95%置信区间中，所提模型相比于现行主流通用神经网络生存分析模型，在METABRIC数据集中获取的一致性系数提升约0.05。

关键词: 癌症, 个体生存分析, 多任务回归, 带状校验

Abstract: Individual cancer survival analysis is important to explore the survival status of a cancer patient. Most of previous multi-task linear regression methods based on linear transformation cannot reveal the cumulative risk of individual cancer course. A multi-task banded regression model（MTBR） is proposed for the survival analysis of the chronic and long-duration diseases such as cancer. Firstly, banded verification is introduced to design a multi-task regression model combining the regression and the banded transform. The transformation matrix for banded verification is mathematically deduced and verified in terms of validity and well-condition. Then, two specific matrices are presented as the examples of the multi-task banded matrix. Finally, the proposed model is validated by predicting the risk of individual survival analysis on the real-world cancer emergency and survival analysis datasets. The proposed model performs better survival analysis on the METABRIC dataset than the mainstream survival analysis models based on neural network, by the improvement of 0.05 C-index in 95% confidence intervals.

Key words: cancer, individual survival analysis, multi-task regression, banded verification

王慧恒, 蔡念, 陈睿, 刘璇, 黎剑. 面向癌症个体生存分析的多任务带状回归模型[J]. 计算机工程与应用, 2023, 59(10): 299-305.

WANG Huiheng, CAI Nian, CHEN Rui, LIU Xuan, LI Jian. Multi-Task Banded Regression Model for Individual Cancer Survival Analysis[J]. Computer Engineering and Applications, 2023, 59(10): 299-305.

参考文献

[1] 徐勇勇，孙振球，颜虹.医学统计学[M].3版.北京：高等教育出版社，2014.
XU Y Y，SUN Z Q，YAN H.Medical statistics[M].3rd ed.Beijing：Higher Education Press，2014.
[2] LIU P，FU B，YANG S X.HitBoost：survival analysis via a multi-output gradient boosting decision tree method[J].IEEE Access，2019，7：56785-56795.
[3] KATZMAN J L，SHAHAM U，CLONINGER A，et al.DeepSurv：personalized treatment recommender system using a Cox proportional hazards deep neural network[J].BMC Medical Research Methodology，2018，18：24.
[4] LEE C，ZAME W，YOON J，et al.DeepHit：a deep learning approach to survival analysis with competing risks[C]//Proceedings of the 32nd AAAI Conference on Artificial Intelligence，2018：2314-2321.
[5] LEE C，YOON J，SCHAAR M.Dynamic-DeepHit：a deep learning approach for dynamic survival analysis with competing risks based on longitudinal data[J].IEEE Transactions on Biomedical Engineering，2020，67（1）：122-123.
[6] NAGPAL C，LI X，DUBRAWSKI A.Deep survival machines：fully parametric survival regression and representation learning for censored data with competing risks[J].IEEE Journal of Biomedical and Health Informatics，2021，25（8）：3163-3175.
[7] TANG W，MA J，MEI Q，et al.SODEN：a scalable continuous-time survival model through ordinary differential equation networks[J].Journal of Machine Learning Research，2022，23（34）：1-29.
[8] YU C N，GREINER R，LIN H C，et al.Learning patient-specific cancer survival distributions as a sequence of dependent regressors[C]//Advances in Neural Information Processing Systems 24，2011.
[9] FOTSO S.Deep neural networks for survival analysis based on a multi-task framework[J].arXiv：1801.05512，2018.
[10] HU S，FRIDGEIRSSON E，VAN WINGEN G，et al.Transformer-based deep survival analysis[C]//AAAI Symposium on Survival Prediction-Algorithms，Challenges and Applications，2021：132-148.
[11] GIUNCHIGLIA E，NEMCHENKO A，SCHAAR M.RNN-SURV：a deep recurrent model for survival analysis[C]//International Conference on Artificial Neural Networks.Cham：Springer，2018：23-32.
[12] KAPLAN E L，MEIER P.Nonparametric estimation from incomplete observations[J].Journal of the American Statistical Association，1958，53：457-481.
[13] LAWRIE J，CARLIN J B，FORBES A B.Optimal stepped wedge designs[J].Statistics & Probability Letters，2015，99：210-214.
[14] KAVCIC A，MOURA J M F.Matrices with banded inverses：inversion algorithms and factorization of Gauss-Markov processes[J].IEEE Transactions on Information Theory，2000，46（4）：1495-1509.
[15] 彭非，王伟.生存分析[M].北京：中国人民大学出版社，2004.
PENG F，WANG W.Survival analysis[M].Beijing：Renmin University of China Press，2004.
[16] RANGANATH R，PEROTTE A，ELHADAD N，et al.Deep survival analysis[C]//Proceedings of the 1st Machine Learning in Health Care Conference，2016：101-114.
[17] TUTZ G，SCHMID M.Modeling discrete time-to-event data[M].New York：Springer，2016.
[18] KVAMME H，BORGAN ?，SCHEEL I.Time-to-event prediction with neural networks and Cox regression[J].arXiv：1907.00825，2019.
[19] BERMAN A，PLEMMONS R J.Nonnegative matrices in the mathematical sciences[M]//Classics in applied mathematics 9.Philadelphia：SIAM，1994.
[20] HSIEN-TSAI，WU，JAR-FERR，et al.Source number estimators using transformed Gerschgorin radii[J].IEEE Transactions on Signal Processing，1995，43（6）：1325-1333.
[21] EBERLY W.Fast parallel band matrix arithmetic[J].Information and Computation，1995，116（1）：117-127.
[22] EL-MIKKAWY M E.A fast algorithm for evaluating nth order tri-diagonal determinants[J].Journal of Computational and Applied Mathematics，2004，166（2）：581-584.
[23] CURTIS C，SHAH S P，CHIN S F，et al.The genomic and transcriptomic architecture of 2?000 breast tumours reveals novel subgroups[J].Nature，2012，486（7403）：346-352.
[24] SCHUMACHER M，BASTERT G，BOJAR H，et al.Randomized 2x2 trial evaluating hormonal treatment and the duration of chemotherapy in node-positive breast cancer patients.German Breast Cancer Study Group[J].Journal of Clinical Oncology，1994，12（10）：2086-2093.
[25] KNAUS W A，HARRELL F E，LYNN J，et al.The SUPPORT prognostic model：objective estimates of survival for seriously ill hospitalized adults[J].Annals of Internal Medicine，1995，122（3）：191-203.
[26] ANTOLINI L，BORACCHI P，BIGANZOLI E.A time-dependent discrimination index for survival data[J].Statistics in Medicine，2005，24（24）：3927-3944
[27] BOTTOU L.Stochastic gradient descent tricks[M]//Neural networks：tricks of the trade.Berlin，Heidelberg：Springer，2012：421-436.
[28] LOSHCHILOV I，HUTTER F.Decoupled weight decay regularization[J].arXiv：1711.05101，2017.
[29] KINGMA D P，BA J.Adam：a method for stochastic optimization[J].arXiv：1412.6980，2014.
[30] ISHWARAN H，KOGALUR U B，BLACKSTONE E H，et al.Random survival forests[J].The Annals of Applied Statistics，2008，2（3）：841-860.