Uncertainty-Aware Time-to-Event Prediction using Deep Kernel Accelerated Failure Time Models (2021-07-26T00:00:00.000000Z)

TL;DR

This work proposes Deep Kernel Accelerated Failure Time models for the time-to-event prediction task, enabling uncertainty-awareness of the prediction by a pipeline of a recurrent neural network and a sparse Gaussian Process.

Abstract

Recurrent neural network based solutions are increasingly being used in the analysis of longitudinal Electronic Health Record data. However, most works focus on prediction accuracy and neglect prediction uncertainty. We propose Deep Kernel Accelerated Failure Time models for the time-to-event prediction task, enabling uncertainty-awareness of the prediction by a pipeline of a recurrent neural network and a sparse Gaussian Process. Furthermore, a deep metric learning based pre-training step is adapted to enhance the proposed model. Our model shows better point estimate performance than recurrent neural network based baselines in experiments on two real-world datasets. More importantly, the predictive variance from our model can be used to quantify the uncertainty estimates of the time-to-event prediction: Our model delivers better performance when it is more confident in its prediction. Compared to related methods, such as Monte Carlo Dropout, our model offers better uncertainty estimates by leveraging an analytical solution and is more computationally efficient.

Authors

Volker Tresp

5 papers

Zhiliang Wu

1 papers

Yinchong Yang

1 papers

TL;DR

Abstract

Authors

References65 items

Multi-output Gaussian Processes for Uncertainty-aware Recommender Systems

Quantifying Predictive Uncertainty in Medical Image Analysis with Deep Kernel Learning

Deep Kernel Survival Analysis and Subject-Specific Survival Time Prediction Intervals

Learning Individualized Treatment Rules with Estimated Translated Inverse Propensity Score

A Metric Learning Reality Check

Flexible Modelling of Longitudinal Medical Data

PyTorch: An Imperative Style, High-Performance Deep Learning Library

Parametric Gaussian Process Regressors

Time-to-Event Prediction with Neural Networks and Cox Regression

Signal-To-Noise Ratio: A Robust Distance Metric for Deep Metric Learning

Exact Gaussian Processes on a Million Data Points

The need for uncertainty quantification in machine-assisted medical decision making

GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration

When Gaussian Process Meets Big Data: A Review of Scalable GPs

Benchmarking deep learning models on large healthcare datasets

Opportunities and challenges in developing deep learning models using electronic health records data: a systematic review

Modeling Progression Free Survival in Breast Cancer with Tensorized Recurrent Neural Networks and Accelerated Failure Time Models

Predictive Modeling of Therapy Decisions in Metastatic Breast Cancer with Recurrent Neural Network Encoder and Multinomial Hierarchical Regression Decoder

Adversarial Examples, Uncertainty, and Transfer Testing Robustness in Gaussian Process Hybrid Deep Networks

On Calibration of Modern Neural Networks

In Defense of the Triplet Loss for Person Re-Identification

Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles

Gaussian process based approaches for survival analysis

Gaussian Processes for Survival Analysis

Joint modelling of time-to-event and multivariate longitudinal outcomes: recent developments and issues

Using recurrent neural network models for early detection of heart failure onset

Going Digital: A Survey on Digitalization and Large-Scale Data Analytics in Healthcare

MIMIC-III, a freely accessible critical care database

Electronic medical record phenotyping using the anchor and learn framework

Predicting Clinical Events by Combining Static and Dynamic Information Using Recurrent Neural Networks

Deep Kernel Learning

Predicting Sequences of Clinical Events by Using a Personalized Temporal Latent Embedding Model

Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning

FaceNet: A unified embedding for face recognition and clustering

Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling

Deep neural networks are easily fooled: High confidence predictions for unrecognizable images

Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation

Gaussian Processes for Big Data

Dynamic Predictions and Prospective Accuracy in Joint Models for Longitudinal and Time‐to‐Event Data

Signal from noise?

Variational Learning of Inducing Variables in Sparse Gaussian Processes

Probabilistic forecasts, calibration and sharpness

Dynamic Prediction by Landmarking in Event History Analysis

Strictly Proper Scoring Rules, Prediction, and Estimation

Pattern Recognition and Machine Learning

Dimensionality Reduction by Learning an Invariant Mapping

Distance Metric Learning for Large Margin Nearest Neighbor Classification

Sparse Gaussian Processes using Pseudo-inputs

A Unifying View of Sparse Approximate Gaussian Process Regression

Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning)

Modelling Survival Data in Medical Research

The Statistical Analysis of Failure Time Data

A Bayesian Committee Machine

Long Short-Term Memory

Evaluating the yield of medical tests.

The Statistical Analysis of Failure Time Data

Linear rank tests with right censored data

A Package for Survival Analysis in R, 2020

acquired immunodeficiency syndrome, hematologic malignancy, metastatic cancer, and admission type. The missing rates of each feature can be found in Table A.26

Deep Multi-task Gaussian Processes for Survival Analysis with Competing Risks

Modeling Survival Data Extending The Cox Model

Biomarkers in Patients with Metastatic Breast Cancer and the PRAEGNANT Study Network.

Dropout: a simple way to prevent neural networks from overfitting

Statistical Language Models Based on Neural Networks

Using the Nyström Method to Speed Up Kernel Machines

Field of Study

Venue Information

Name

Type

URL

Alternate Names