Deep Survival Analysis

2016/08/06 by Rajesh Ranganath, Ranganath, Rajesh, Adler Perotte +6 · 18 citations
Computer Science · Health Professions · Mathematics · Medicine · #Artificial Intelligence (cs.AI) #Colorectal Cancer Screening and Detection #FOS: Computer and information sciences #Machine Learning (stat.ML) #Machine Learning in Healthcare #Medical Coding and Health Information #Methodology (stat.ME) #cs.AI #stat.ME #stat.ML

paper · pdf · doi:10.48550/arxiv.1608.02158

Presented at 2016 Machine Learning and Healthcare Conference (MLHC 2016), Los Angeles, CA

openalex publication_date 2016/08/06 · arxiv created 2016/09/18 · arxiv updated 2016/09/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

The electronic health record (EHR) provides an unprecedented opportunity to build actionable tools to support physicians at the point of care. In this paper, we investigate survival analysis in the context of EHR data. We introduce deep survival analysis, a hierarchical generative approach to survival analysis. It departs from previous approaches in two primary ways: (1) all observations, including covariates, are modeled jointly conditioned on a rich latent structure; and (2) the observations are aligned by their failure time, rather than by an arbitrary time zero as in traditional survival analysis. Further, it (3) scalably handles heterogeneous (continuous and discrete) data types that occur in the EHR. We validate deep survival analysis model by stratifying patients according to risk of developing coronary heart disease (CHD). Specifically, we study a dataset of 313,000 patients corresponding to 5.5 million months of observations. When compared to the clinically validated Framingham CHD risk score, deep survival analysis is significantly superior in stratifying patients according to their risk.

Citations

• Auto-Encoding Variational Bayes

Cited by

• SurvBench: A Standardised Preprocessing Pipeline for Multi-Modal Electronic Health Record Survival Analysis
• Let the Experts Speak: Improving Survival Prediction & Calibration via Mixture-of-Experts Heads
• Computational Identifiability
• C²MIL: Synchronizing Semantic and Topological Causalities in Multiple Instance Learning for Robust and Interpretable Survival Analysis
• Robust and Adaptive Spectral Method for Representation Multi-Task Learning with Contamination
• Preference Models assume Proportional Hazards of Utilities
• Inverse-Weighted Survival Games
• Dynamic Survival Prediction using Longitudinal Images based on Transformer
• A Hidden Absorbing Semi-Markov Model for Informatively Censored Temporal Data: Learning and Inference
• Enhancing Model Interpretability and Accuracy for Disease Progression Prediction via Phenotype-Based Patient Similarity Learning
• Deep Lifetime Clustering
• Deep Learning for Patient-Specific Kidney Graft Survival Analysis
• Deep Convolutional Neural Networks for Imaging Data Based Survival Analysis of Rectal Cancer
• Deep Survival Analysis in Multimodal Medical Data: A Parametric and Probabilistic Approach with Competing Risks
• FinSurvival: A Suite of Large Scale Survival Modeling Tasks from Finance
• Maximum Likelihood Estimation of Flexible Survival Densities with Importance Sampling
• SurvUnc: A Meta-Model Based Uncertainty Quantification Framework for Survival Analysis
• Patient-Specific Effects of Medication Using Latent Force Models with Gaussian Processes

Related

• Interpretable Survival Analysis for Heart Failure Risk Prediction
• DySurv: dynamic deep learning model for survival analysis with conditional variational inference
• Dynamic Survival Transformers for Causal Inference with Electronic Health Records
• SurvBench: A Standardised Preprocessing Pipeline for Multi-Modal Electronic Health Record Survival Analysis
• MixEHR-SurG: a joint proportional hazard and guided topic model for inferring mortality-associated topics from electronic health records