Deep Learning for Patient-Specific Kidney Graft Survival Analysis

Luck, Margaux; Sylvain, Tristan; Cardinal, Héloïse; Lodi, Andrea; Bengio, Yoshua

doi:10.48550/arxiv.1705.10245

Cited by 36 publications

(58 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our results also compare favorably to prior studies [1,11,15,22] using the same SRTR data we use in this study. Each study differs in inclusion criteria, time duration, and several other factors that prevent a direct comparison; however, we include their reported results here for reference.…”

Section: Related Worksupporting

confidence: 85%

“…Prior work includes multivariate analysis using Cox proportional hazards (Cox PH) models with a small number of covariates [1,15,22]. There has been more recent work on machine learning-based survival analysis applied to kidney transplantation, including an ensemble model that combines Cox PH models with random survival forests [12] and a deep learning-based approach [11].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Predicting Kidney Transplant Survival using Multiple Feature Representations for HLAs

Nemati¹,

Zhang²,

Sloma³

et al. 2021

Preprint

View full text Add to dashboard Cite

Kidney transplantation can significantly enhance living standards for people suffering from end-stage renal disease. A significant factor that affects graft survival time (the time until the transplant fails and the patient requires another transplant) for kidney transplantation is the compatibility of the Human Leukocyte Antigens (HLAs) between the donor and recipient. In this paper, we propose new biologically-relevant feature representations for incorporating HLA information into machine learning-based survival analysis algorithms. We evaluate our proposed HLA feature representations on a database of over 100,000 transplants and find that they improve prediction accuracy by about 1%, modest at the patient level but potentially significant at a societal level. Accurate prediction of survival times can improve transplant survival outcomes, enabling better allocation of donors to recipients and reducing the number of re-transplants due to graft failure with poorly matched donors.

show abstract

Section: Related Worksupporting

confidence: 85%

Section: Related Workmentioning

confidence: 99%

Predicting Kidney Transplant Survival using Multiple Feature Representations for HLAs

Nemati¹,

Zhang²,

Sloma³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…On the other hand, new models advanced by machine learning (ML), e.g., survival support vector machine (Van Belle et al 2007;Pölsterl, Navab, and Katouzian 2015), random survival forests (RSF) (Ishwaran et al 2008), gradient boosting (Wang et al 2020a), were proposed. There were also attempts using neural networks for learning representations of covariates (Luck et al 2017;Katzman et al 2018;Lee et al 2018;Ren et al 2019;Nagpal, Li, and Dubrawski 2021). However, these NN-based methods do not fully exploit the power of NNs as they only use simple multi-layer perceptron, which is inherently limited in its learning capacity.…”

Section: Related Workmentioning

confidence: 99%

“…On the other hand, deep learning (DL) was proved useful in enhancing survival analysis recently (Luck et al 2017;Lee et al 2018;Nagpal, Li, and Dubrawski 2021). However, they still suffer from insufficient training over rare events (Castañeda and Gerritse 2010).…”

Section: Introductionmentioning

confidence: 99%

SurvTRACE: Transformers for Survival Analysis with Competing Events

Wang,

Sun

2021

Preprint

View full text Add to dashboard Cite

In medicine, survival analysis studies the time duration to events of interest such as mortality. One major challenge is how to deal with multiple competing events (e.g., multiple disease diagnoses). In this work, we propose a transformerbased model that does not make the assumption for the underlying survival distribution and is capable of handling competing events, namely SurvTRACE. We account for the implicit confounders in the observational setting in multi-events scenarios, which causes selection bias as the predicted survival probability is influenced by irrelevant factors. To sufficiently utilize the survival data to train transformers from scratch, multiple auxiliary tasks are designed for multi-task learning. The model hence learns a strong shared representation from all these tasks and in turn serves for better survival analysis. We further demonstrate how to inspect the covariate relevance and importance through interpretable attention mechanisms of SurvTRACE, which suffices to great potential in enhancing clinical trial design and new treatment development. Experiments on METABRIC, SUPPORT, and SEER data with 470k patients validate the all-around superiority of our method.

show abstract

“…ML methods for survival prediction continue to multiply; here we focus on the most related class of methods -namely on those nonparametrically modeling conditional hazard or survival functions -and not on those relying on flexible implementations of the Cox proportional hazards model (e.g. [41,42,43]) or modeling (log-)time as a regression problem (e.g. [44,45,46,47,48,49]).…”

Section: Related Workmentioning

confidence: 99%

SurvITE: Learning Heterogeneous Treatment Effects from Time-to-Event Data

Curth¹,

Lee²,

Schaar³

2021

Preprint

View full text Add to dashboard Cite

We study the problem of inferring heterogeneous treatment effects from time-toevent data. While both the related problems of (i) estimating treatment effects for binary or continuous outcomes and (ii) predicting survival outcomes have been well studied in the recent machine learning literature, their combination -albeit of high practical relevance -has received considerably less attention. With the ultimate goal of reliably estimating the effects of treatments on instantaneous risk and survival probabilities, we focus on the problem of learning (discrete-time) treatment-specific conditional hazard functions. We find that unique challenges arise in this context due to a variety of covariate shift issues that go beyond a mere combination of wellstudied confounding and censoring biases. We theoretically analyse their effects by adapting recent generalization bounds from domain adaptation and treatment effect estimation to our setting and discuss implications for model design. We use the resulting insights to propose a novel deep learning method for treatment-specific hazard estimation based on balancing representations. We investigate performance across a range of experimental settings and empirically confirm that our method outperforms baselines by addressing covariate shifts from various sources.

show abstract

Deep Learning for Patient-Specific Kidney Graft Survival Analysis

Cited by 36 publications

References 8 publications

Predicting Kidney Transplant Survival using Multiple Feature Representations for HLAs

Predicting Kidney Transplant Survival using Multiple Feature Representations for HLAs

SurvTRACE: Transformers for Survival Analysis with Competing Events

SurvITE: Learning Heterogeneous Treatment Effects from Time-to-Event Data

Contact Info

Product

Resources

About