Adaptive Prediction Timing for Electronic Health Records

03/05/2020
by   Jacob Deasy, et al.
11

In realistic scenarios, multivariate timeseries evolve over case-by-case time-scales. This is particularly clear in medicine, where the rate of clinical events varies by ward, patient, and application. Increasingly complex models have been shown to effectively predict patient outcomes, but have failed to adapt granularity to these inherent temporal resolutions. As such, we introduce a novel, more realistic, approach to generating patient outcome predictions at an adaptive rate based on uncertainty accumulation in Bayesian recurrent models. We use a Recurrent Neural Network (RNN) and a Bayesian embedding layer with a new aggregation method to demonstrate adaptive prediction timing. Our model predicts more frequently when events are dense or the model is certain of event latent representations, and less frequently when readings are sparse or the model is uncertain. At 48 hours after patient admission, our model achieves equal performance compared to its static-windowed counterparts, while generating patient- and event-specific prediction timings that lead to improved predictive performance over the crucial first 12 hours of the patient stay.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/05/2021

Neural Clinical Event Sequence Prediction through Personalized Online Adaptive Learning

Clinical event sequences consist of thousands of clinical events that re...
research
08/21/2023

Personalized Event Prediction for Electronic Health Records

Clinical event sequences consist of hundreds of clinical events that rep...
research
06/10/2019

Analyzing the Role of Model Uncertainty for Electronic Health Records

In medicine, both ethical and monetary costs of incorrect predictions ca...
research
04/06/2022

Learning to Adapt Clinical Sequences with Residual Mixture of Experts

Clinical event sequences in Electronic Health Records (EHRs) record deta...
research
09/17/2019

Impact of novel aggregation methods for flexible, time-sensitive EHR prediction without variable selection or cleaning

Dynamic assessment of patient status (e.g. by an automated, continuously...
research
06/28/2021

Improving Prediction of Low-Prior Clinical Events with Simultaneous General Patient-State Representation Learning

Low-prior targets are common among many important clinical events, which...
research
06/04/2021

Latent Time-Adaptive Drift-Diffusion Model

Animals can quickly learn the timing of events with fixed intervals and ...

Please sign up or login with your details

Forgot password? Click here to reset