Dynamic-DeepHit: A Deep Learning Approach for Dynamic Survival Analysis With Competing Risks Based on Longitudinal Data

Lee, ChangHee; Yoon, Jinsung; Schaar, Mihaela van der

doi:10.1109/tbme.2019.2909027

Cited by 263 publications

(340 citation statements)

References 46 publications

Supporting

Mentioning

335

Contrasting

Unclassified

Order By: Relevance

“…Continous Age 56 (48,62) 50 (43,58) 59 (52,63) 55 (48,61) 47 (35,54) 55 (49,62) 58 (50,65) HDL (mg/dL) 43 (37,53) 52 (44,63) 67 (59,85) 54 (45,66) 62 (55,70) 41 (35,48) 42 ( The inferred clusters assignment is according to the corresponding individual probability distribution q(π |ξ , {x 1 } M n=1 ), approximated according to (5).…”

Section: Covariatesmentioning

confidence: 99%

Survival cluster analysis

Chapfuwa

Mehta

et al. 2020

Proceedings of the ACM Conference on Health, Inference, and Learning

View full text Add to dashboard Cite

Conventional survival analysis approaches estimate risk scores or individualized time-to-event distributions conditioned on covariates. In practice, there is often great population-level phenotypic heterogeneity, resulting from (unknown) subpopulations with diverse risk profiles or survival distributions. As a result, there is an unmet need in survival analysis for identifying subpopulations with distinct risk profiles, while jointly accounting for accurate individualized time-to-event predictions. An approach that addresses this need is likely to improve characterization of individual outcomes by leveraging regularities in subpopulations, thus accounting for population-level heterogeneity. In this paper, we propose a Bayesian nonparametrics approach that represents observations (subjects) in a clustered latent space, and encourages accurate time-to-event predictions and clusters (subpopulations) with distinct risk profiles. Experiments on real-world datasets show consistent improvements in predictive performance and interpretability relative to existing state-of-the-art survival analysis models.

show abstract

Section: Covariatesmentioning

confidence: 99%

Survival cluster analysis

Chapfuwa

Mehta

et al. 2020

Proceedings of the ACM Conference on Health, Inference, and Learning

View full text Add to dashboard Cite

show abstract

“…Survival analysis, a.k.a. time-to-event analysis (Lee et al 2018), is a typical statistical methodology for modeling time-to-event data while handling censorship, which is a traditional research problem and has been studied over decades.…”

Section: Introductionmentioning

confidence: 99%

“…The goal of survival analysis is to estimate the time until occurrence of the particular event of interest, which can be regarded as a regression problem (Lee and Wang 2003;Wu, Yeh, and Chen 2015). It can also be viewed as to predict the probability of the event occurring over the whole timeline Lee et al 2018). Specifically, given the information of the observing object, survival analysis would predict the probability of the event occurrence at each time point.…”

Section: Introductionmentioning

confidence: 99%

“…Recently, deep learning, i.e., deep neural network, has been paid huge attention and introduced to survival analysis in many tasks (Ranganath et al 2016;Grob et al 2018;Lee et al 2018). However, in fact, many deep learning models for survival analysis (Katzman et al 2018;Ran-ganath et al 2016) actually utilize deep neural network as the enhanced feature extraction method (Lao et al 2017;Grob et al 2018) and, worse still, rely on some assumptions of the base distributions for the survival rate prediction, which also suffers from the generalization problem.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Recurrent Survival Analysis

Ren

Qin

Zheng

et al. 2019

AAAI

View full text Add to dashboard Cite

Survival analysis is a hotspot in statistical research for modeling time-to-event information with data censorship handling, which has been widely used in many applications such as clinical research, information system and other fields with survivorship bias. Many works have been proposed for survival analysis ranging from traditional statistic methods to machine learning models. However, the existing methodologies either utilize counting-based statistics on the segmented data, or have a pre-assumption on the event probability distribution w.r.t. time. Moreover, few works consider sequential patterns within the feature space. In this paper, we propose a Deep Recurrent Survival Analysis model which combines deep learning for conditional probability prediction at finegrained level of the data, and survival analysis for tackling the censorship. By capturing the time dependency through modeling the conditional probability of the event for each sample, our method predicts the likelihood of the true event occurrence and estimates the survival rate over time, i.e., the probability of the non-occurrence of the event, for the censored data. Meanwhile, without assuming any specific form of the event probability distribution, our model shows great advantages over the previous works on fitting various sophisticated data distributions. In the experiments on the three realworld tasks from different fields, our model significantly outperforms the state-of-the-art solutions under various metrics.

show abstract

“…Furthermore, it directly estimates the survival probability, which is often of direct interest to patients and physicians than the hazard function in the Cox model. However, the censored data in each interval are handled either by an oversimplified method that assumes individuals with a censoring time in the second half of an interval survived that interval [5], or by an overcomplicated method that uses a ranking loss function [7] or a combination of a ranking loss and an isotonic regression [8].…”

mentioning

confidence: 99%

Deep Neural Networks for Survival Analysis Using Pseudo Values

Zhao

Dai

2020

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

There has been increasing interest in modelling survival data using deep learning methods in medical research. Current approaches have focused on designing special cost functions to handle censored survival data. We propose a very different method with two steps. In the first step, we transform each subject's survival time into a series of jackknife pseudo conditional survival probabilities and then use these pseudo probabilities as a quantitative response variable in the deep neural network model. By using the pseudo values, we reduce a complex survival analysis to a standard regression problem, which greatly simplifies the neural network construction. Our two-step approach is simple, yet very flexible in making risk predictions for survival data, which is very appealing from the practice point of view. The source code is freely available at http://github.com/lilizhaoUM/DNNSurv.

show abstract

Dynamic-DeepHit: A Deep Learning Approach for Dynamic Survival Analysis With Competing Risks Based on Longitudinal Data

Cited by 263 publications

References 46 publications

Survival cluster analysis

Survival cluster analysis

Deep Recurrent Survival Analysis

Deep Neural Networks for Survival Analysis Using Pseudo Values

Contact Info

Product

Resources

About