SurvTRACE: Transformers for Survival Analysis with Competing Events
- URL: http://arxiv.org/abs/2110.00855v1
- Date: Sat, 2 Oct 2021 17:46:26 GMT
- Title: SurvTRACE: Transformers for Survival Analysis with Competing Events
- Authors: Zifeng Wang, Jimeng Sun
- Abstract summary: 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.
We propose a transformer-based model that does not make the assumption for the underlying survival distribution.
- Score: 37.66291997350568
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: 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
transformer-based 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 \emph{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.
Related papers
- HACSurv: A Hierarchical Copula-based Approach for Survival Analysis with Dependent Competing Risks [51.95824566163554]
HACSurv is a survival analysis method that learns structures and cause-specific survival functions from data with competing risks.
By capturing the dependencies between risks and censoring, HACSurv achieves better survival predictions.
arXiv Detail & Related papers (2024-10-19T18:52:18Z) - MENSA: A Multi-Event Network for Survival Analysis under Informative Censoring [4.0913802846346625]
We introduce MENSA, a novel, deep learning approach for multi-event survival analysis.
We consider the problem of predicting the time until a patient with amyotrophic lateral sclerosis (ALS) loses various physical functions.
Our approach achieves an L1-Margin loss of 278.8 days, compared to 355.2 days when modeling each event separately.
arXiv Detail & Related papers (2024-09-10T14:02:34Z) - Interpretable Survival Analysis for Heart Failure Risk Prediction [50.64739292687567]
We propose a novel survival analysis pipeline that is both interpretable and competitive with state-of-the-art survival models.
Our pipeline achieves state-of-the-art performance and provides interesting and novel insights about risk factors for heart failure.
arXiv Detail & Related papers (2023-10-24T02:56:05Z) - Multi-Source Survival Domain Adaptation [11.57423546614283]
We introduce a new survival metric and the corresponding discrepancy measure between survival distributions.
Our experiments on two cancer data sets reveal a superb performance on target domains, a better treatment recommendation, and a weight matrix with a plausible explanation.
arXiv Detail & Related papers (2022-12-01T10:55:22Z) - Dynamic Survival Transformers for Causal Inference with Electronic
Health Records [19.89643522713678]
We introduce the Dynamic Survival Transformer (DynST), a deep survival model that trains on electronic health records.
We derive a semi-synthetic EHR dataset from MIMIC-III to show that DynST can accurately estimate the causal effect of a treatment intervention.
arXiv Detail & Related papers (2022-10-25T18:17:46Z) - Multi-Omic Data Integration and Feature Selection for Survival-based
Patient Stratification via Supervised Concrete Autoencoders [4.846870511582627]
We develop a Supervised Autoencoder model for survival-based multi-omic integration.
We report a Concrete Supervised Autoencoder model (CSAE) which uses feature selection to jointly reconstruct the input features as well as predict survival.
Our experiments show that our models outperform or are on par with some of the most commonly used baselines.
arXiv Detail & Related papers (2022-06-21T19:44:08Z) - Practical Challenges in Differentially-Private Federated Survival
Analysis of Medical Data [57.19441629270029]
In this paper, we take advantage of the inherent properties of neural networks to federate the process of training of survival analysis models.
In the realistic setting of small medical datasets and only a few data centers, this noise makes it harder for the models to converge.
We propose DPFed-post which adds a post-processing stage to the private federated learning scheme.
arXiv Detail & Related papers (2022-02-08T10:03:24Z) - Enabling Counterfactual Survival Analysis with Balanced Representations [64.17342727357618]
Survival data are frequently encountered across diverse medical applications, i.e., drug development, risk profiling, and clinical trials.
We propose a theoretically grounded unified framework for counterfactual inference applicable to survival outcomes.
arXiv Detail & Related papers (2020-06-14T01:15:00Z) - A General Framework for Survival Analysis and Multi-State Modelling [70.31153478610229]
We use neural ordinary differential equations as a flexible and general method for estimating multi-state survival models.
We show that our model exhibits state-of-the-art performance on popular survival data sets and demonstrate its efficacy in a multi-state setting.
arXiv Detail & Related papers (2020-06-08T19:24:54Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.