MED-ADVANCE


Advancing Medicine through Data Science, Machine Learning and Artificial Intelligence

Prof. van der Schaar is searching for excellent PhD students on theoretical machine learning for medicine, deep learning for medicine, and natural language processing.


Research mission


Develop state-of-the-art data science, machine learning, artificial intelligence and decision theoretic methods aimed at revolutionizing the way medicine is practiced today, as well as advance the science behind understanding and practicing medicine.

Principal investigator

  • Prof. Mihaela van der Schaar (Email)

Students


Collaborators

  • Dr. Scott Hu (Emergency Care)
  • Dr. Martin Cadeiras (Transplants)
  • Dr. Mindy Ross (Asthma)
  • Dr. Raffaele Bugiardini (Cardiology)
  • Dr. Paolo Emilio Puddu (Cardiology)
  • Dr. Camelia Davtyan (Internal Medicine)
  • Dr. Douglas Bell (Internal Medicine, Renal diseases)
  • Dr. Luke Macyszyn (Neurosurgery)
  • Dr. Arash Naeim (Oncology -- Breast Cancer)

Presentations
  • Prof. van der Schaar's talk on machine learning for medicine at Alan Turing Institute. [Youtube Link]
  • Prof. van der Schaar's talk on research in her group [Youtube Link]
  • Please see the interview with Prof. van der Schaar about her vision on how machine learning can transform medical practice and discovery [Link] [pdf]
  • Preliminary report on Cystic Fibrosis [Link]

Activities
  • Mihaela and her students aim to crack the code for cystic fibrosis [Link] - see current progress here [Presentation]
  • Our research on machine learning for medicine is highlighted on EPSRC website in the article of Sir Prof. Alan Wilson, CEO of the Alan Turing Institute - Data Science: a new discipline to change the world
  • Prof. van der Schaar (together with Prof. Fei Wang and Prof. David Sontag) is organizing a pre-symposium on "Data Mining for Medical Informatics (DMMI) - Learning Health" at AMIA 2016 Annual Symposium (AMIA 2016 Annual Symposium)

Featured Projects


Publications

  • J. Yoon, W. R. Zame, M. van der Schaar, "Estimating Missing Data in Temporal Data Streams Using Multi-directional Recurrent Neural Networks," 2017. [Link]
  • B. Ricci, M. van der Schaar, J. Yoon, E. Cenko, Z. Vasiljevic, M. Dorobantu, M. Zdravkovic, S. Kedev, O. Kalpak, D. Milicic, O. Manfrini, L. Badimon, R. Bugiardini, "Machine Learning Techniques for Risk Stratification of Non-ST-Elevation Acute Coronary Syndrome: The Role of Diabetes and Age," American Heart Association Scientific Session, 2017 - Circulation, 2017; 136:A15892. [Link]
  • C. Lee, W. R. Zame, J. Yoon, M. van der Schaar, "DeepHit: A Deep Learning Approach to Survival Analysis with Competing Risks," AAAI, 2018. [Link] [Supplementary Materials]
  • O. Atan, J. Jordan, M. van der Schaar, "Deep-Treat: Learning Optimal Personalized Treatments from Observational Data using Neural Networks," AAAI, 2018. [Link]
  • M. K. Ross, J. Yoon, M. van der Schaar, "Discovering Pediatric Asthma Phenotypes Based on Response to Controller Medication Using Machine Learning," accepted and to appear in Annals of the American Thoracic Society, 2017.
  • A. M. Alaa, M. van der Schaar, "Deep Multi-task Gaussian Processes for Survival Analysis with Competing Risks," NIPS, 2017. [Link] - Selected as a spotlight paper
  • A. M. Alaa, M. van der Schaar, "Bayesian Inference of Individualized Treatment Effects using Multi-task Gaussian Processes," NIPS, 2017. [Link]
  • K. Ahuja, W. R. Zame, M. van der Schaar, "DPSCREEN: Dynamic Personalized Screening," NIPS, 2017. [Link][Poster]
  • O. Atan, W. R. Zame, Q. Feng, M. van der Schaar, "Constructing Effective Personalized Policies Using Counterfactual Inference from Biased Data Sets with Many Features," Submitted, 2017. [Link]
  • J. Yoon, M. van der Schaar, "E-RNN: Entangled Recurrent Neural Networks for Causal Prediction," ICML 2017 - Workshop on Principled Approaches to Deep Learning., 2017. [Link]
  • A. M. Alaa, M. Weisz, M. van der Schaar, "Deep Counterfactual Networks with Propensity-Dropout," ICML 2017 - Workshop on Principled Approaches to Deep Learning., 2017. [Link]
  • J. Yoon, W. R. Zame, M. van der Schaar, "Multi-directional Recurrent Neural Networks: A Novel Method for Estimating Missing Data," ICML 2017 - Time Series Workshop., 2017. [Link]
  • J. Yoon, W. R. Zame, and M. van der Schaar, "ToPs: Ensemble Learning with Trees of Predictors," Submitted, 2017. [Link]
  • A. M. Alaa, J. Yoon, S. Hu, and M. van der Schaar, "Individualized Risk Prognosis for Critical Care Patients: A Multi-task Gaussian Process Model," Big Data in Medicine: Tools, Transformation and Translation, Cambridge, 2017. [Link]
  • A. M. Alaa, S. Hu, and M. van der Schaar, "Learning from Clinical Judgments: Semi-Markov-Modulated Marked Hawkes Processes for Risk Prognosis," ICML, 2017. [Link]
  • A. Alaa, J. Yoon, S. Hu and M. van der Schaar, "Personalized Risk Scoring for Critical Care Prognosis using Mixtures of Gaussian Processes," accepted and appear to IEEE Transactions on Biomedical Engineering, 2017. [Link]
  • A. Banerjee, J. Yoon, W. R. Zame, M. Cadeiras, A. M. Alaa, M. van der Schaar, "Personalized Risk Prediction using Predictive Pursuit Machine Learning: A Pilot Study in Cardiac Transplantation," European Society of Cardiology Congress, 2017.- Selected as Best Posters in Advanced Heart Failure.
  • J. Yoon, W. R. Zame, A. Banerjee, M. Cadeiras, A. M. Alaa, M. van der Schaar, "Personalized Risk Prediction using Predictive Pursuit Machine Learning: A Pilot Study in Cardiac Transplantation," Evidence Live Conference, 2017. [Link]
  • M. K. Ross, J. Yoon, K. Moon, M. van der Schaar, "A Personalized Approach to Asthma Control Over Time: Discovering Phenotypes Using Machine Learning," American Thoracic Society (ATS) International Conference, 2017. [Link]
  • A. M. Alaa, J. Yoon, Scott Hu, M. van der Schaar, "A Semi-Markov Switching Linear Gaussian Model for Censored Physiological Data," NIPS - Workshop on Machine Learning for Health, 2016. [Link]
  • J. Yoon, A. M. Alaa, M. Cadeiras, M. van der Schaar, "Personalized Donor-Recipient Matching for Organ Transplantation," AAAI, 2017. [Link] [Poster]
  • A. Alaa and M. van der Schaar, "A Hidden Absorbing Semi-Markov Model for Informatively Censored Temporal Data: Learning and Inference," accepted and to appear in Journal of Machine Learning Research (JMLR), 2017. [Link]
  • C. Tekin, J. Yoon, and M. van der Schaar, "Adaptive Ensemble Learning with Confidence Bounds," accepted and to appear in IEEE Trans. Signal Process., 2016. [Link]
  • A. M. Alaa and M. van der Schaar, "Balancing Suspense and Surprise: Timely Decision Making with Endogenous Information Acquisition ," NIPS, 2016. [Link] [Poster]
  • W. Hoiles and M. van der Schaar, "A Non-parametric Learning Method for Confidently Estimating Patient's Clinical State and Dynamics ," NIPS, 2016. [Link] [Poster]
  • A. Alaa, K. H. Moon, W. Hsu and M. van der Schaar, "ConfidentCare: A Clinical Decision Support System for Personalized Breast Cancer Screening," accepted and to appear in IEEE Transactions on Multimedia - Special Issue on Multimedia-based Healthcare, 2016. [Link]
  • A. M. Alaa, J. Yoon, S. Hu, M. van der Schaar, "Personalized Risk Scoring for Critical Care Patients using Mixtures of Gaussian Process Experts," ICML 2016 - Workshop on Computational Frameworks for Personalization., 2016. [Link]
  • J. Yoon, A. M. Alaa, S. Hu, M. van der Schaar, "ForecastICU: A Prognostic Decision Support System for Timely Prediction of Intensive Care Unit Admission," ICML 2016. [Link]
  • E. Soltanmohammadi, M. Naraghi-Pour, and M. van der Schaar, " Context-based Unsupervised Ensemble Learning and Feature Ranking," accepted and to appear in Machine Learning, pp. 1-27, June 2016. [Link]
  • C. Tekin, J. Yoon, M. van der Schaar, "Adaptive ensemble learning with confidence bounds for personalized diagnosis," accepted and to appear in AAAI Workshop on Expanding the Boundaries of Health Informatics using AI (HIAI'16):Making Proactive, Personalized, and Participatory Medicine A Reality, 2016. [Link]
  • J. Yoon, C. Davtyan, M. van der Schaar, "Discovery and Clinical Decision Support for Personalized Healthcare," accepted and to appear in IEEE J. Biomedical and Health Informatics, 2016. [Link]
  • L. Song, W. Hsu, J. Xu and M. van der Schaar, "Using contextual learning to improve diagnostic accuracy: application in breast cancer screening," IEEE J. Biomedical and Health Informatics, vol. PP, no. 99, 2015. [Link]
  • E. Soltanmohammadi, M. Naraghi-Pour, M. van der Schaar, "Context-based Unsupervised Data Fusion for Decision Making," ICML, 2015. [Link]
  • O. Atan, C. Tekin, J. Xu and M. van der Schaar, "Discovering Action-Dependent Relevance: Learning from Logged Data," Submitted, 2015. [Link]
  • C. Tekin, O. Atan and M. van der Schaar, "Discover the Expert: Context-Adaptive Expert Selection for Medical Diagnosis," IEEE Transactions on Emerging Topics in Computing, vol. 3, no. 2, pp. 220 - 234, 2015. [Link]
  • J. Xu, D. Sow, D. Turaga and M. van der Schaar, "Online Transfer Learning for Differential Diagnosis Determination," AAAI Workshop on the World Wide Web and Public Health Intelligence, 2015. [Link]
  • C. Tekin and M. van der Schaar, "Active Learning in Context-Driven Stream Mining with an Application to Image Mining," IEEE Trans. Image Process., vol. 24, no. 11, pp. 3666-3679, 2015. [Link]
  • O. Atan and M. van der Schaar, "Discover Relevant Sources : A Multi-Armed Bandit Approach," Submitted, 2015. [Link]
  • M. Wolf, M. van der Schaar, H. Kim and J. Xu, "Analysis and Decision-Making in Caring Environments for Adults with Special Needs Adults," IEEE Design & Test, Special Issue on Cyber-Physical systems for Medical Applications, vol. 32, no. 5, Oct. 2015. [Link]
  • J. Xu, J. Y. Xu, L. Song, G. Pottie, and M. van der Schaar, "Personalized Active Learning for Activity Classification using Wireless Wearable Sensors," IEEE Journal on Selected Topics in Signal Processing, 2016. [Link]