|Table of Contents|

DeephitTM:a Time-dependent Deep Learning Model for Medical Survival Analysis(PDF)

《南京师大学报（自然科学版）》[ISSN:1001-4616/CN:32-1239/N]

Issue:
2024年03期
Page:
138-148
Research Field:
计算机科学与技术
Publishing date:

Info

Title:
DeephitTM:a Time-dependent Deep Learning Model for Medical Survival Analysis
Author(s):
Zhang Dapeng1; 2; Cheng Xueliang2; Sun Mingxia1
(1.School of IoT Engineering,Jiangsu Vocational College of Information Technology,Wuxi 214153,China)
(2.College of information Science and Engineering,Yanshan University,Qinhuangdao 066004,China)
Keywords:
survival analysis; deep learning; temporal correlation; neural network; Deephit mode
PACS:
TP391
DOI:
10.3969/j.issn.1001-4616.2024.03.017
Abstract:
Survival analysis is a health prediction method often used in medicine. More and more scholars start to use deep learning method to model survival analysis problems to get better prediction results. Currently,existing methods assume that the joint probability of risk and time is uncorrelated,but the actual results of survival analysis data contain time factors,which cannot guarantee that the risk probability obtained at different times is uncorrelated. This paper proposes a time-dependent deep learning model,DeephitTM,to improve the existing deep learning model Deephit. Experimental results show that the performance of our model can be improved by 1 to 3 percentage points compared with the original model on different data sets.

References:

[1]COX D. Regression models and life tables[J]. Journal of the Royal Statistical Society series b:statistical methodology,1972,34(2):187-220.
[2]KAPLAN E L,MEIER P. Nonparametric estimation from in-complete observations[J]. Journal of the American Statal Association,1957,53(282):457-481.
[3]AARON S D,STEPHENSON A L,CAMERON D W,et al. A statistical model to predict one-year risk of death in patients with cystic fibrosis[J]. Journal of clinical epidemiology,2015,68(11):1336-1345.
[4]FARAGGI D,SIMON R. A neural network model for survival data[J]. Statistics in Medicine,2010,14(1):73-82.
[5]ISHWARAN H,KOGALUR U B,BLACKSTONE EUGENE H,et al. Random survival forests[J]. Journal of Thoracic Oncology Official Publication of the International Association for the Study of Lung Cancer,2008,2(12):841-860.
[6]ISHWARAN H,KOGALUR U B,BLACKSTONE EUGENE H,et al. Random survival forests for R[J]. Annals of applied statistics,2007,2(3):25-31.
[7]LUCK M,SYLVAIN T,CARDINAL H,et al. Deep learning for patient-specific kidney graft survival analysis[J/OL]. arXiv Preprint arXiv:1705.10245,2017.
[8]ALAA A M,van der SCHAAR M. Deep multi-task Gaussian processes for survival analysis with competing risks[C]//31st Annual Conference on Newral Information Processing System. Long Beach,CA:NIPS,2017,30:2326-2334.
[9]CHANG LEE,WILLIAM R ZAME,JINSUNG YOON,et al. DeepHit:a deep learning approach to survival analysis with competing risks[C]//The Thirty-Second AAAI Conference on Artificial Intelligence. New Orleans,LA:AAAI,2018:2314-2321.
[10]PLSTERL S,NAVAB N,KATOUZIAN A. Fast training of support vector machines for survival analysis[C]//Machine Learning and Knowledge Discovery in Databases:European Conference,ECML PKDD. Switzerland:Springer,2015:243-259.
[11]PLSTERL S,NAVAB N,KATOUZIAN A. An efficient training algorithm for kernel survival support vector machines[J/OL]. arXiv Preprint arXiv:1611.07054,2016.
[12]PLSTERL S,GUPTA P,WANG L,et al. Heterogeneous ensembles for predicting survival of metastatic,castrate-resistant prostate cancer patients[J]. F1000research,2016,5(2676):1-29.
[13]KATZMAN J,SHAHAM U,BATES J,et al. Deep Survival:a deep cox proportional hazards network[J/OL]. arXiv Preprint arXiv:1606.00931,2016.
[14]LIU P,FU B,YANG S X,et al. Optimizing survival analysis of XGBoost for ties to predict disease progression of breast cancer[J]. IEEE transactions on biomedical engineering,2020,68(1):148-160.
[15]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(1):24.
[16]LIM H J,ZHANG X,DYCK R,et al. Methods of competing risks analysis of end-stage renal disease and mortality among people with diabetes[J]. BMC medical research methodology,2010,10(97):1-9.
[17]LAMBERT P C,DICKMAN P W,NELSON C P,et al. Estimating the crude probability of death due to cancer and other causes using relative survival models[J]. Statistics in medicine,2010,29(7/8):885-895.
[18]BELLOT A,SCHAAR M. Tree-based bayesian mixture model for competing risks[C]//21st International Conference on Arttfical Intelligence and Statistics Lanzarote,Spain:Microcome Publishing,2018:910-918.
[19]REN K,QIN J,ZHENG L,et al. Deep recurrent survival analysis[J]. Proceedings of the AAAI conference on artificial intelligence,2019,33:4798-4805.
[20]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.
[21]RIETSCHEL C,YOON J,MIHAELA V. Feature selection for survival analysis with competing risks using deep learning[J/OL]. arXiv Preprint arXiv:1811.09317,2018.
[22]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):122-133.
[23]COLLOBERT R,WESTON J. A unified architecture for natural language processing:deep neural networks with multitask learning[C]//Machine Learning,Proceedings of the Twenty-Fifth International Conference(ICML 2008),Helsinki,Finland:ACM,2008:160-167.
[24]HE K,ZHANG X,REN S,et al. Deep residual learning for image recognition[C]//IEEE Conference on Computer Vision & Pattern Recognition. IEEE Computer Society,Piscataway,NJ:IEEE,2016:770-778.
[25]HARRELL,FRANK E. Evaluating the yield of medical tests[J]. The journal of the American Medical Association,1982,247(18):2543-2546.
[26]ANTOLINI L,BORACCHI P,BIGANZOLI E. A time-dependent dis-crimination index for survival data[J]. Statistics in medicine,2005,24(24):3927-3944.
[27]KVAMME H,BORGAN R,SCHEEL I. Time-to-event prediction with neural networks and cox regression[J]. Journal of machine learning research,2019,20(129):1-30.
[28]KVAMME H,BORGAN R. Continuous and discrete-time survival prediction with neural networks[J/OL]. arXiv Preprint arXiv:1910.06724,2019.

Memo

Memo:
-
Last Update: 2024-09-15