As data shift or new data become available, updating clinical machine
le...
Off-policy evaluation (OPE) aims to estimate the benefit of following a
...
Noisy training labels can hurt model performance. Most approaches that a...
Many reinforcement learning (RL) applications have combinatorial action
...
In time-series forecasting, future target values may be affected by both...
As machine learning (ML) models gain traction in clinical applications,
...
When patients develop acute respiratory failure, accurately identifying ...
Once integrated into clinical care, patient risk stratification models m...
Reinforcement learning (RL) can be used to learn treatment policies and ...
Many existing approaches for estimating feature importance are problemat...
While deep learning has shown promise in improving the automated diagnos...
People with type 1 diabetes (T1D) lack the ability to produce the insuli...
Standard reinforcement learning (RL) aims to find an optimal policy that...
In the context of stochastic gradient descent(SGD) and adaptive moment
e...
We introduce advocacy learning, a novel supervised training scheme for
a...
Compared to in-clinic balance training, in-home training is not as effec...
Recurrent neural networks (RNNs) are commonly applied to clinical time-s...
In healthcare, patient risk stratification models are often learned usin...
Recently, researchers have started applying convolutional neural network...
Given the wide success of convolutional neural networks (CNNs) applied t...
In many forecasting applications, it is valuable to predict not only the...
During the 2017 NBA playoffs, Celtics coach Brad Stevens was faced with ...
Longitudinal patient data has the potential to improve clinical risk
str...
In many settings, it is important that a model be capable of providing
r...