ML p(r)ior | DeepCare: A Deep Dynamic Memory Model for Predictive Medicine

DeepCare: A Deep Dynamic Memory Model for Predictive Medicine

2016-02-01
Personalized predictive medicine necessitates the modeling of patient illness and care processes, which inherently have long-term temporal dependencies. Healthcare observations, recorded in electronic medical records, are episodic and irregular in time. We introduce DeepCare, an end-to-end deep dynamic neural network that reads medical records, stores previous illness history, infers current illness states and predicts future medical outcomes. At the data level, DeepCare represents care episodes as vectors in space, models patient health state trajectories through explicit memory of historical records. Built on Long Short-Term Memory (LSTM), DeepCare introduces time parameterizations to handle irregular timed events by moderating the forgetting and consolidation of memory cells. DeepCare also incorporates medical interventions that change the course of illness and shape future medical risk. Moving up to the health state level, historical and present health states are then aggregated through multiscale temporal pooling, before passing through a neural network that estimates future outcomes. We demonstrate the efficacy of DeepCare for disease progression modeling, intervention recommendation, and future risk prediction. On two important cohorts with heavy social and economic burden -- diabetes and mental health -- the results show improved modeling and risk prediction accuracy.
PDF

Highlights - Most important sentences from the article

Login to like/save this paper, take notes and configure your recommendations

Related Articles

2015-02-28

Because of their superior ability to preserve sequence information over time, Long Short-Term Memory… show more
PDF

Highlights - Most important sentences from the article

2017-04-07

The Nonlinear autoregressive exogenous (NARX) model, which predicts the current value of a time seri… show more
PDF

Highlights - Most important sentences from the article

2015-11-27

Neural network models have been demonstrated to be capable of achieving remarkable performance in se… show more
PDF

Highlights - Most important sentences from the article

2014-11-17

Models based on deep convolutional networks have dominated recent image interpretation tasks; we inv… show more
PDF

Highlights - Most important sentences from the article

2016-10-20

Until recently, research on artificial neural networks was largely restricted to systems with only t… show more
PDF

Highlights - Most important sentences from the article

2015-05-29

Countless learning tasks require dealing with sequential data. Image captioning, speech synthesis, a… show more
PDF

Highlights - Most important sentences from the article

2017-08-09

Deep learning methods employ multiple processing layers to learn hierarchical representations of dat… show more
PDF

Highlights - Most important sentences from the article

2015-02-16

We use multilayer Long Short Term Memory (LSTM) networks to learn representations of video sequences… show more
PDF

Highlights - Most important sentences from the article

2018-06-05

Memory-based neural networks model temporal data by leveraging an ability to remember information fo… show more
PDF

Highlights - Most important sentences from the article

2016-02-18
1602.05875 | stat.ML

Traditional convolutional layers extract features from patches of data by applying a non-linearity o… show more
PDF

Highlights - Most important sentences from the article

2016-10-08
1610.02583 | cs.LG

We describe recurrent neural networks (RNNs), which have attracted great attention on sequential tas… show more
PDF

Highlights - Most important sentences from the article

2016-10-29

Recurrent Neural Networks (RNNs) have become the state-of-the-art choice for extracting patterns fro… show more
PDF

Highlights - Most important sentences from the article

2018-04-21

Tackling air pollution is an imperative problem in South Korea, especially in urban areas, over the … show more
PDF

Highlights - Most important sentences from the article

2017-06-08

We present a novel recurrent neural network (RNN) based model that combines the remembering ability … show more
PDF

Highlights - Most important sentences from the article

2018-04-17

We present PredRNN++, an improved recurrent network for video predictive learning. In pursuit of a g… show more
PDF

Highlights - Most important sentences from the article

2015-03-09
1503.02510 | cs.CL

We are proposing an extension of the recursive neural network that makes use of a variant of the lon… show more