Ghassemi M, Wu M, Hughes MC, Szolovits P, Doshi-Velez F.
Predicting intervention onset in the ICU with switching state space models. American Medical Informatics Association (AMIA),. 2017.
Paper Glueck M, Naeini MP, Doshi-Velez F, Chevalier F, Khan A, Wigdor D, Brudno M.
PhenoLines: Phenotype Comparison Visualizations for Disease Subtyping via Topic Models. Conference on Visual Analytics Science and Technology (VAST),. 2017.
Paper Ross AS, Lage I, Doshi-Velez F.
The Neural LASSO: Local Linear Sparsity for Interpretable Explanations. Neural Information Processing Systems (NIPS) Workshop on Transparent and Interpretable Machine Learning in Safety Critical Environments. 2017.
Paper Wu M, Hughes M, Parbhoo S, Zazzi M, Roth V, Doshi-Velez F.
Beyond Sparsity: Tree Regularization of Deep Models for Interpretability. Neural Information Processing Systems (NIPS) Workshop on Transparent and Interpretable Machine Learning in Safety Critical Environments. 2017.
Paper Parbhoo S, Roth V, Doshi-Velez F.
Counterfactual Reasoning with Dynamic Switching Models for HIV Therapy Selection. Neural Information Processing Systems (NIPS) Workshop on Machine Learning for Healthcare. 2017.
Paper Hughes MC, Hope G, Weiner L, McCoy TH, Perlis RH, Sudderth EB, Doshi-Velez F.
Prediction-Constrained Topic Models for Antidepressant Recommendation. Neural Information Processing Systems (NIPS) Workshop on Machine Learning for Healthcare. 2017.
Paper Ghosh S, Doshi-Velez F.
Model Selection in Bayesian Neural Networks via Horseshoe Priors. Neural Information Processing Systems (NIPS) Workshop on Bayesian Deep Learning. 2017.
Paper Singh R, Ling J, Doshi-Velez F.
Structured Variational Autoencoders for the Beta-Bernoulli Process. Neural Information Processing Systems (NIPS) Workshop on Advances in Approximate Bayesian Inference. 2017.
Paper Tan S, Doshi-Velez F, Quiroz J, Glassman E.
Clustering LaTeX Solutions to Machine Learning Assignments for Rapid Assessment. Advancing Education with Data Knowledge Discovery and Data Mining (KDD) Workshop. 2017.
Paper Depeweg S, Hernandez-Lobato JM, Doshi-Velez F, Udluft S.
Uncertainty Decomposition in Bayesian Neural Networks with Latent Variables. International Conference on Machine Learning (ICML) Workshop. 2017.
Paper Killian T, Daulton S, Konidaris G, Doshi-Velez F.
Robust and Efficient Transfer Learning with Hidden Parameter Markov Decision Processes. Neural Information Processing Systems (NIPS). 2017.
Paper Wang T, Rudin C, Doshi-Velez F, Liu Y, Klampfl E, MacNeille P.
A Bayesian Framework for Learning Rule Sets for Interpretable Classification. Journal of Machine Learning. 2017;18 (70) :1-37.
Paper Ross AS, Hughes MC, Doshi-Velez F.
Right for the Right Reasons: Training Differentiable Models by Constraining their Explananations. International Joint Conference on Artificial Intelligence (IJCAI). 2017.
Paper Doshi-Velez F, Williamson S.
Restricted Indian Buffet Processes. Statistics and Computing. 2017;27 (5) :1205-1223.
Paper Wu M, Ghassemi M, Fend M, Celi LA, Szolovits P, Doshi-Velez F.
Understanding Vasopressor Intervention and Weaning: Risk Prediction in a Public Heterogeneous Clinical Time Series Database. Journal of the American Medical Informatics Association. 2017;24 (3) :488-495.
Abstract
Background The widespread adoption of electronic health records allows us to ask evidence-based questions about the need for and benefits of specific clinical interventions in critical-care settings across large populations.
Objective We investigated the prediction of vasopressor administration and weaning in the intensive care unit. Vasopressors are commonly used to control hypotension, and changes in timing and dosage can have a large impact on patient outcomes.
Materials and Methods We considered a cohort of 15 695 intensive care unit patients without orders for reduced care who were alive 30 days post-discharge. A switching-state autoregressive model (SSAM) was trained to predict the multidimensional physiological time series of patients before, during, and after vasopressor administration. The latent states from the SSAM were used as predictors of vasopressor administration and weaning.
Results The unsupervised SSAM features were able to predict patient vasopressor administration and successful patient weaning. Features derived from the SSAM achieved areas under the receiver operating curve of 0.92, 0.88, and 0.71 for predicting ungapped vasopressor administration, gapped vasopressor administration, and vasopressor weaning, respectively. We also demonstrated many cases where our model predicted weaning well in advance of a successful wean.
Conclusion Models that used SSAM features increased performance on both predictive tasks. These improvements may reflect an underlying, and ultimately predictive, latent state detectable from the physiological time series.
Depewag S, Hernández-Lobato JM, Doshi-Velez F, Udluft S.
Learning and Policy Search in Stochastic Dynamical Systems with Bayesian Neural Networks. ICLR. 2017.
Abstract
We present an algorithm for model-based reinforcement learning that combines Bayesian neural networks (BNNs) with random roll-outs and stochastic optimization for policy learning. The BNNs are trained by minimizing α -divergences, allowing us to capture complicated statistical patterns in the transition dynamics, e.g. multi-modality and heteroskedasticity, which are usually missed by other common modeling approaches. We illustrate the performance of our method by solving a challenging benchmark where model-based approaches usually fail and by obtaining promising results in a real-world scenario for controlling a gas turbine.
