• Corpus ID: 13262708

Bayesian LSTMs in medicine

  title={Bayesian LSTMs in medicine},
  author={Jos van der Westhuizen and Joan Lasenby},
The medical field stands to see significant benefits from the recent advances in deep learning. Knowing the uncertainty in the decision made by any machine learning algorithm is of utmost importance for medical practitioners. This study demonstrates the utility of using Bayesian LSTMs for classification of medical time series. Four medical time series datasets are used to show the accuracy improvement Bayesian LSTMs provide over standard LSTMs. Moreover, we show cherry-picked examples of… 

Figures and Tables from this paper

Ranking Information Extracted from Uncertainty Quantification of the Prediction of a Deep Learning Model on Medical Time Series Data
A convolutional–long short-term memory network model with a Monte Carlo dropout layer for obtaining information regarding the model uncertainty for saccadic records of all patients and reaches an accuracy of 88.59% in distinguishing between the three classes of patients.
Deep Learning Methods for Heart Sounds Classification: A Systematic Review
An in-depth systematic review and an analysis of existing deep learning methods were performed, with an emphasis on the convolutional neural network (CNN) and recurrent neuralnetwork (RNN) methods developed over the last five years.
Deep CardioSound - An Ensembled Deep Learning Model for Heart Sound MultiLabelling
This work proposes a deep multilabel learning model that can automatically annotate heart sound recordings with labels from different label groups, including murmur’s timing, pitch, grading, quality, and shape.
Deep Interpretable Early Warning System for the Detection of Clinical Deterioration
The ‘Deep Early Warning System’ (DEWS) is proposed, an interpretable end-to-end deep learning model that interpolates temporal data and predicts the probability of an adverse event, defined as the composite outcome of cardiac arrest, mortality or unplanned ICU admission.
Mitigating Uncertainty in Document Classification
A novel neural-network-based model is proposed that applies a new dropout-entropy method for uncertainty measurement and a metric learning method on feature representations, which can boost the performance of drop out-based uncertainty methods with smaller prediction variance in accurate prediction trials.
High-Performance FPGA-based Accelerator for Bayesian Recurrent Neural Networks
This work proposes an FPGA-based hardware design to accelerate Bayesian LSTM-based RNNs on FPGAs and proposes a codesign framework to explore the most optimal algorithmic-hardware configurations for Bayesian Rnns.
Optimizing Bayesian Recurrent Neural Networks on an FPGA-based Accelerator
An FPGA-based hardware design to accelerate Bayesian LSTM-based RNNs on FPGAs is proposed and a co-design framework is proposed to explore the most fitting algorithmic-hardware configurations for Bayesian Rnns.
Efficient Computation Reduction in Bayesian Neural Networks Through Feature Decomposition and Memorization
Hardware simulation results on multilayer BNNs demonstrate that, when compared with the traditional BNN inference method, it provides an energy consumption reduction of 73% and a speedup at the expense of 14% area overhead.
Accelerating Bayesian Neural Networks via Algorithmic and Hardware Optimizations
This article systematically exploits the extensive structured sparsity and redundant computation in BayesNNs, and proposes a novel hardware architecture that achieves a high hardware performance using the runtime adaptable hardware engines and the intelligent skipping support.
Stein Variational Online Changepoint Detection with Applications to Hawkes Processes and Neural Networks
A Stein variational online changepoint detection (SVOCD) method is introduced to provide a computationally tractable generalization of BOCPD beyond the exponential family of probability distributions.


Learning to Diagnose with LSTM Recurrent Neural Networks
This first study to empirically evaluate the ability of LSTMs to recognize patterns in multivariate time series of clinical measurements considers multilabel classification of diagnoses, and establishes the effectiveness of a simple LSTM network for modeling clinical data.
Machine learning techniques to examine large patient databases.
Machine learning for medical diagnosis: history, state of the art and perspective
Doctor AI: Predicting Clinical Events via Recurrent Neural Networks
Great generalizability of Doctor AI is demonstrated by adapting the resulting models from one institution to another without losing substantial accuracy, significantly higher than several baselines.
Medical decision support using machine learning for early detection of late-onset neonatal sepsis
Predictive models developed from off-the-shelf and EMR data using machine learning (ML) algorithms exceeded the treatment sensitivity and treatment specificity of clinicians.
A Multivariate Timeseries Modeling Approach to Severity of Illness Assessment and Forecasting in ICU with Sparse, Heterogeneous Clinical Data
This work evaluates the use of multivariate timeseries modeling with the multi-task Gaussian process (GP) models using noisy, incomplete, sparse, heterogeneous and unevenly-sampled clinical data, including both physiological signals and clinical notes to assess and forecast patient acuity.
Uncertainty in Deep Learning
This work develops tools to obtain practical uncertainty estimates in deep learning, casting recent deep learning tools as Bayesian models without changing either the models or the optimisation, and develops the theory for such tools.
A Theoretically Grounded Application of Dropout in Recurrent Neural Networks
This work applies a new variational inference based dropout technique in LSTM and GRU models, which outperforms existing techniques, and to the best of the knowledge improves on the single model state-of-the-art in language modelling with the Penn Treebank.
Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference
This work presents an efficient Bayesian CNN, offering better robustness to over-fitting on small data than traditional approaches, and approximate the model's intractable posterior with Bernoulli variational distributions.