A Scalable Discrete-Time Survival Model for Neural Networks

Abstract

There is currently great interest in applying neural networks to prediction tasks in medicine. It is important for predictive models to be able to use survival data, where each patient has a known follow-up time and event/censoring indicator. This avoids information loss when training the model and enables generation of predicted survival curves. In this paper, we describe a discrete-time survival model that is designed to be used with neural networks, which we refer to as Nnet-survival. The model is trained with the maximum likelihood method using minibatch stochastic gradient descent (SGD). The use of SGD enables rapid convergence and application to large datasets that do not fit in memory. The model is flexible, so that the baseline hazard rate and the effect of the input data on hazard probability can vary with follow-up time. It has been implemented in the Keras deep learning framework, and source code for the model and several examples is available online. We demonstrate the performance of the model on both simulated and real data and compare it to existing models Cox-nnet and Deepsurv.

References in corpus (2)

• Scalable and accurate deep learning for electronic health records
• DeepSurv: Personalized Treatment Recommender System Using A Cox Proportional Hazards Deep Neural Network

Cited by in corpus (25)

• Deep Learning for Survival Analysis: A Review
• DeepMTS: Deep Multi-task Learning for Survival Prediction in Patients with Advanced Nasopharyngeal Carcinoma using Pretreatment PET/CT
• Predicting Time-to-conversion for Dementia of Alzheimer's Type using Multi-modal Deep Survival Analysis
• Merging-Diverging Hybrid Transformer Networks for Survival Prediction in Head and Neck Cancer
• DNNSurv: Deep Neural Networks for Survival Analysis Using Pseudo Values
• Scaling Survival Analysis in Healthcare with Federated Survival Forests: A Comparative Study on Heart Failure and Breast Cancer Genomics
• Federated Survival Forests
• AdaMSS: Adaptive Multi-Modality Segmentation-to-Survival Learning for Survival Outcome Prediction from PET/CT Images
• Predicting risk of late age-related macular degeneration using deep learning
• CNN-based Survival Model for Pancreatic Ductal Adenocarcinoma in Medical Imaging
• DeepHazard: neural network for time-varying risks
• Causal inference for observational longitudinal studies using deep survival models
• BDNNSurv: Bayesian deep neural networks for survival analysis using pseudo values
• Dynamic prediction of time to event with survival curves
• ICTSurF: Implicit Continuous-Time Survival Functions with Neural Networks
• Spectral Survival Analysis
• Case-Base Neural Networks: survival analysis with time-varying, higher-order interactions
• Survival Mixture Density Networks
• Uncovering life-course patterns with causal discovery and survival analysis
• Survival-oriented embeddings for improving accessibility to complex data structures
• WRSE -- a non-parametric weighted-resolution ensemble for predicting individual survival distributions in the ICU
• Conditional Distribution Function Estimation Using Neural Networks for Censored and Uncensored Data
• Ad Creative Discontinuation Prediction with Multi-Modal Multi-Task Neural Survival Networks
• Towards modelling hazard factors in unstructured data spaces using gradient-based latent interpolation
• Inverse-Weighted Survival Games