Timezone: »
Models of disease progression are instrumental for predicting patient outcomes and understanding disease dynamics. Existing models provide the patient with pragmatic (supervised) predictions of risk, but do not provide the clinician with intelligible (unsupervised) representations of disease pathophysiology. In this paper, we develop the attentive state-space model, a deep probabilistic model that learns accurate and interpretable structured representations for disease trajectories. Unlike Markovian state-space models, in which the dynamics are memoryless, our model uses an attention mechanism to create "memoryful" dynamics, whereby attention weights determine the dependence of future disease states on past medical history. To learn the model parameters from medical records, we develop an infer ence algorithm that simultaneously learns a compiled inference network and the model parameters, leveraging the attentive state-space representation to construct a "Rao-Blackwellized" variational approximation of the posterior state distribution. Experiments on data from the UK Cystic Fibrosis registry show that our model demonstrates superior predictive accuracy and provides insights into the progression of chronic disease.
Author Information
Ahmed Alaa (UCLA)
Mihaela van der Schaar (University of Cambridge, Alan Turing Institute and UCLA)
More from the Same Authors
-
2022 : Closing Remarks »
Cheng Zhang · Mihaela van der Schaar -
2022 : Panel Discussion »
Cheng Zhang · Mihaela van der Schaar · Ilya Shpitser · Aapo Hyvarinen · Yoshua Bengio · Bernhard Schölkopf -
2022 : Opening Remarks »
Cheng Zhang · Mihaela van der Schaar -
2021 : Invited talk #5: Mihaela van der Schaar »
Mihaela van der Schaar -
2020 : Q&A for invited speaker, Mihaela van der Schaar »
Mihaela van der Schaar -
2020 : Interpretable AutoML: Powering the machine learning revolution in healthcare in the era of Covid-19 and beyond »
Mihaela van der Schaar -
2020 Poster: When and How to Lift the Lockdown? Global COVID-19 Scenario Analysis and Policy Assessment using Compartmental Gaussian Processes »
Zhaozhi Qian · Ahmed Alaa · Mihaela van der Schaar -
2020 Oral: When and How to Lift the Lockdown? Global COVID-19 Scenario Analysis and Policy Assessment using Compartmental Gaussian Processes »
Zhaozhi Qian · Ahmed Alaa · Mihaela van der Schaar -
2019 Poster: Demystifying Black-box Models with Symbolic Metamodels »
Ahmed Alaa · Mihaela van der Schaar -
2019 Poster: Differentially Private Bagging: Improved utility and cheaper privacy than subsample-and-aggregate »
James Jordon · Jinsung Yoon · Mihaela van der Schaar -
2019 Poster: Conditional Independence Testing using Generative Adversarial Networks »
Alexis Bellot · Mihaela van der Schaar -
2019 Spotlight: Conditional Independence Testing using Generative Adversarial Networks »
Alexis Bellot · Mihaela van der Schaar -
2018 Poster: Forecasting Treatment Responses Over Time Using Recurrent Marginal Structural Networks »
Bryan Lim · Ahmed Alaa · Mihaela van der Schaar -
2017 : Coffee break and Poster Session II »
Mohamed Kane · Albert Haque · Vagelis Papalexakis · John Guibas · Peter Li · Carlos Arias · Eric Nalisnick · Padhraic Smyth · Frank Rudzicz · Xia Zhu · Theodore Willke · Noemie Elhadad · Hans Raffauf · Harini Suresh · Paroma Varma · Yisong Yue · Ognjen (Oggi) Rudovic · Luca Foschini · Syed Rameel Ahmad · Hasham ul Haq · Valerio Maggio · Giuseppe Jurman · Sonali Parbhoo · Pouya Bashivan · Jyoti Islam · Mirco Musolesi · Chris Wu · Alexander Ratner · Jared Dunnmon · Cristóbal Esteban · Aram Galstyan · Greg Ver Steeg · Hrant Khachatrian · Marc Górriz · Mihaela van der Schaar · Anton Nemchenko · Manasi Patwardhan · Tanay Tandon -
2017 Poster: DPSCREEN: Dynamic Personalized Screening »
Kartik Ahuja · William Zame · Mihaela van der Schaar -
2017 Poster: Deep Multi-task Gaussian Processes for Survival Analysis with Competing Risks »
Ahmed Alaa · Mihaela van der Schaar -
2017 Spotlight: Deep Multi-task Gaussian Processes for Survival Analysis with Competing Risks »
Ahmed Alaa · Mihaela van der Schaar -
2017 Poster: Bayesian Inference of Individualized Treatment Effects using Multi-task Gaussian Processes »
Ahmed Alaa · Mihaela van der Schaar