A
Andy Schuetz
Researcher at Sutter Health
Publications - 10
Citations - 2885
Andy Schuetz is an academic researcher from Sutter Health. The author has contributed to research in topics: Atorvastatin & Rosuvastatin. The author has an hindex of 8, co-authored 10 publications receiving 2302 citations.
Papers
More filters
Doctor AI: Predicting Clinical Events via Recurrent Neural Networks
TL;DR: Wang et al. as mentioned in this paper developed Doctor AI, a generic predictive model that covers observed medical conditions and medication uses using recurrent neural networks (RNNs) and applied it to longitudinal time stamped EHR data from 260k patients over 8 years.
Journal ArticleDOI
Using recurrent neural network models for early detection of heart failure onset.
TL;DR: Deep learning models adapted to leverage temporal relations appear to improve performance of models for detection of incident heart failure with a short observation window of 12–18 months.
Posted Content
RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism
TL;DR: The REverse Time AttentIoN model (RETAIN) is developed for application to Electronic Health Records (EHR) data and achieves high accuracy while remaining clinically interpretable and is based on a two-level neural attention model that detects influential past visits and significant clinical variables within those visits.
Proceedings Article
RETAIN: An interpretable predictive model for healthcare using reverse time attention mechanism
TL;DR: In this paper, a two-level neural attention model is proposed to detect influential past visits and significant clinical variables within those visits (e.g. key diagnoses) in reverse time order so that recent clinical visits are likely to receive higher attention.
Posted Content
Doctor AI: Predicting Clinical Events via Recurrent Neural Networks
TL;DR: Wang et al. as mentioned in this paper developed Doctor AI, a generic predictive model that covers observed medical conditions and medication uses using recurrent neural networks (RNNs) and applied it to longitudinal time stamped EHR data from 260k patients over 8 years.