• Corpus ID: 4734635

Adversarial Time-to-Event Modeling

@article{Chapfuwa2018AdversarialTM,
  title={Adversarial Time-to-Event Modeling},
  author={Paidamoyo Chapfuwa and Chenyang Tao and Chunyuan Li and Courtney Page and Benjamin Goldstein and Lawrence Carin and Ricardo Henao},
  journal={Proceedings of machine learning research},
  year={2018},
  volume={80},
  pages={
          735-744
        }
}
Modern health data science applications leverage abundant molecular and electronic health data, providing opportunities for machine learning to build statistical models to support clinical practice. [...] Key Method We also introduce a principled cost function to exploit information from censored events (events that occur subsequent to the observation window). Unlike most time-to-event models, we focus on the estimation of time-to-event distributions, rather than time ordering. We validate our model on both…Expand
Survival Function Matching for Calibrated Time-to-Event Predictions
TLDR
A survival function estimator for probabilistic predictions in time-to-event models, based on a neural network model for draws from the distribution of event times, without explicit assumptions on the form of the distribution is presented.
SurvITE: Learning Heterogeneous Treatment Effects from Time-to-Event Data
TLDR
This work proposes a novel deep learning method for treatment-specific hazard estimation based on balancing representations and investigates performance across a range of experimental settings and empirically confirms that the method outperforms baselines by addressing covariate shifts from various sources.
Deep State-Space Generative Model For Correlated Time-to-Event Predictions
TLDR
A deep latent state-space generative model is proposed to capture the interactions among different types of correlated clinical events by explicitly modeling the temporal dynamics of patients' latent states by developing a new general discrete-time formulation of the hazard rate function.
SurvTRACE: Transformers for Survival Analysis with Competing Events
TLDR
This work proposes a transformerbased model that does not make the assumption for the underlying survival distribution and is capable of handling competing events, namely SurvTRACE, which suffices to great potential in enhancing clinical trial design and new treatment development.
ENABLING COUNTERFACTUAL SURVIVAL ANALYSIS
  • 2020
Balanced representation learning methods have been applied successfully to counterfactual inference from observational data. However, approaches that account for survival outcomes are relatively
Survival Analysis meets Counterfactual Inference
TLDR
This work proposes a theoretically grounded unified framework for counterfactual inference applicable to survival outcomes and formulates a nonparametric hazard ratio metric for evaluating average and individualized treatment effects.
Metaparametric Neural Networks for Survival Analysis
TLDR
The metaparametric neural network framework is presented that encompasses the existing survival analysis methods and enables their extension to solve the aforementioned issues and outperforms the current state-of-the-art methods in capturing nonlinearities and identifying temporal patterns, leading to more accurate overall estimations while placing no restrictions on the underlying function structure.
Deep Extended Hazard Models for Survival Analysis
Unlike standard prediction tasks, survival analysis requires modeling right censored data, which must be treated with care. While deep neural networks excel in traditional supervised learning, it
SODEN: A Scalable Continuous-Time Survival Model through Ordinary Differential Equation Networks
TLDR
A flexible model for survival analysis using neural networks along with scalable optimization algorithms is proposed to provide a broad family of continuous-time survival distributions without strong structural assumptions and allow efficient estimation of the model in large-scale applications using stochastic gradient descent.
Harmonic-Mean Cox Models: A Ruler for Equal Attention to Risk
Survival analysis models are necessary for clinical forecasting with data censorship. Implicitly, existing works focus on the individuals with higher risks while lower risk individuals are poorly
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 47 REFERENCES
Deep Survival Analysis
TLDR
Deep survival analysis is introduced, a hierarchical generative approach to survival analysis that scalably handles heterogeneous data types that occur in the EHR and is significantly superior in stratifying patients according to their risk.
Deep Multi-task Gaussian Processes for Survival Analysis with Competing Risks
TLDR
A nonparametric Bayesian model for survival analysis with competing risks, which can be used for jointly assessing a patient’s risk of multiple (competing) adverse outcomes, and which outperforms the state-of-the-art survival models.
Deep Learning for Patient-Specific Kidney Graft Survival Analysis
TLDR
A deep learning method is proposed that directly models the survival function instead of estimating the hazard function to predict survival times for graft patients based on the principle of multi-task learning, which outperforms other common methods for survival analysis.
Deep Neural Networks for Survival Analysis Based on a Multi-Task Framework
TLDR
A new method to calculate survival functions using the Multi-Task Logistic Regression model as its base and a deep learning architecture as its core, which outperforms the MTLR in all the experiments disclosed in this paper.
Gaussian Processes for Survival Analysis
TLDR
A semi-parametric Bayesian model for survival analysis that handles left, right and interval censoring mechanisms common in survival analysis, and proposes a MCMC algorithm to perform inference and an approximation scheme based on random Fourier features to make computations faster.
Learning Patient-Specific Cancer Survival Distributions as a Sequence of Dependent Regressors
TLDR
A local regression method for learning patient-specific survival time distribution based on patient attributes such as blood tests and clinical assessments is proposed and gives survival time predictions that are much more accurate than popular survival analysis models such as the Cox and Aalen regression models.
Deep convolutional neural network for survival analysis with pathological images
TLDR
From the extensive experiments on the National Lung Screening Trial (NLST) lung cancer data, it is shown that the proposed DeepConvSurv model improves significantly compared with four state-of-the-art methods.
A neural network model for survival data.
TLDR
This paper presents an approach to modelling censored survival data using the input-output relationship associated with a simple feed-forward neural network as the basis for a non-linear proportional hazards model.
Frailty models for survival data
  • P. Hougaard
  • Mathematics, Medicine
    Lifetime data analysis
  • 1995
A frailty model is a random effects model for time variables, where the random effect (the frailty) has a multiplicative effect on the hazard. It can be used for univariate (independent) failure
Development of a Prognostic Model for Breast Cancer Survival in an Open Challenge Environment
TLDR
A computational modeling approach that combined several molecular features yielded a robust breast cancer prognostic model that was independently validated in a new patient data set and was described in a Research Article that described the winning model.
...
1
2
3
4
5
...