MIT Clinical and Applied Machine Learning Group

We develop machine learning techniques with clinical inspiration and real-world relevance. Our current research touches on computer vision, fairness, optimization and causality in networks.


Principal Investigator


PhD Students

M. Eng. Students

Advaith Anand
Courtney Guo
Emily Mu

Lab Alumni


Guha Balakrishnan (postdoc @ MIT)
Joel Brooks (Righthand Robotics)
Jen J. Gong (postdoc @ Berkeley)
Yun Liu (Google)
Anima Singh (Google)
Zeeshan Syed (University of Michigan and Google)

Gartheeban Ganeshapillai (BlackRock)
Jenna Wiens (University of Michigan)
Alaa Kharbouch (Verizon Big Data Analytics Group)
Asfandyar Qureshi (Google)
Eugene Shih (Cambridge Mobile Telematics, Inc.)
Ali Shoeb (Google)


Dina Levy-Lambert
Maryann Gong
Akhil Nistala

Visiting Students

Wayne Chien (Wistron)

Current Projects

VoxelMorph: Unsupervised Learning for Image Registration

VoxelMorph is a fast, unsupervised, learning-based framework for deformable, pairwise medical image registration. VoxelMorph combines a probabilistic model with unsupervised learning that makes use of recent developments in convolutional neural networks (CNNs). This results in state of the art accuracy and very fast runtimes, while providing diffeomorphic guarantees and uncertainty estimates.

Learn more

Anatomical Priors in Convolutional Networks for Biomedical Segmentation

In this project we specifically address the frequent scenario where we have no (or very few) paired training data that contains images and their manual segmentations. We explore generative probabilistic models that employ priors learned from external data through convolutional neural networks, enabling segmentations in unsupervised or semi-supervised settings.

Learn more

Unsupervised Data Imputation

In this project we focus on unsupervised estimation of missing image data, where no full observations are available - a common situation in practice. Unsupervised imputation methods for images often employ a simple linear subspace to capture correlations between data dimensions, ignoring more complex relationships. Instead, we work with a general probabilistic model that describes sparse high dimensional imaging data as being generated by a deep non-linear embedding.

and more!

Recent News

Model improves prediction of mortality risk in ICU patients

By training on patients grouped by health status, neural network can better estimate if patients will die in the hospital. Read on MIT News →

Faster analysis of medical images

Algorithm makes the process of comparing 3-D scans up to 1,000 times faster. Read on MIT News →

Machine learning model predicts C. difficile infection risk

Machine learning models specifically tailored to individual institutions can predict a patient’s risk of developing C. difficile much earlier than it would be diagnosed with current methods. Read on MIT News →

Recent Publications


G. Balakrishnan, A. Zhao, A.V. Dalca, F. Durand, and J. Guttag, “Synthesizing Images of Humans in Unseen Poses,” CVPR: Conference on Computer Vision and Pattern Recognition, June 2018 (to appear).

G. Balakrishnan, A. Zhao, M. R. Sabuncu, J. Guttag, and A.V. Dalca, “An Unsupervised Learning Model for Deformable Medical Image Registration,” CVPR: Conference on Computer Vision and Pattern Recognition, June 2018 (to appear).

A.V. Dalca, J. Guttag, and M. R. Sabuncu, “Anatomical Priors in Convolutional Networks for Unsupervised Biomedical Segmentation, CVPR: Conference on Computer Vision and Pattern Recognition,” June 2018 (to appear).

J.P. Cortes, V. Espinoza, M. Ghassemi, D. Mehta, J. Van Stan, R. Hillman, J. Guttag, and M. Zañartu,

“Using Aerodynamic Features and Their Uncertainty for the Ambulatory Assessment of Phonotraumatic Vocal Hyperfunction,” IEEE International Conference on Biomedical and Health Informatics, March 2018 (to appear).

J. Oh, M. Makar, C. Fusco, R. McCaffrey, K. Rao, E. Ryan, L. Washer, L. West, V. Young, J. Guttag, D. Hooper, E. Shenoy, and J. Wiens, “A generalizable, data-driven approach to predict daily risk of Clostridium difficile infection at two large academic health centers,” Infection Control & Hospital Epidemiology, 2018 (to appear).

M. Makar, J. Wiens, and J. Guttag, “Learning the Probability of Activation in the Presence of Latent Spreaders,” AAAI, February 2018.


R. Jaroensri, A. Zhao, G. Balakrishnan, D. Lo, J. Schmahmann, F. Durand, and J. Guttag, “A Video-based Method for Automatically Rating Ataxia,” Machine Learning in Healthcare, August 2017.

D. Blalock and J. Guttag, “Bolt: Accelerated Data Mining with Fast Vector Compression,” KDD 2017, August 2017.

J. Gong, T. Naumann, P. Szolovits, and J. Guttag, “Predicting Clinical Outcomes Across Changing Electronic Health Record Systems,” KDD 2017, August 2017 (to appear).


D. Blalock and J. Guttag, “EXTRACT: Strong Examples from Weakly-labeled Sensor Data,” ICDM 2016, December 2016.

J. Brooks, M. Kerr, and J. Guttag, “Developing a Data-driven Player Ranking in Soccer Using Predictive Model Weights, KDD 2016, August 2016.

J. Gong, M. Gong, D. Levy-Lambert, J. Green, T. Hogan, and J. Guttag, “Towards an Automated Screening Tool for Developmental Speech and Language Impairments,” Interspeech 2016, September 2016.

M. Ghassemi, J. Hillman, D. Mehta, J. Van Stan, Z. Syed, and J. Guttag, “Uncovering Voice Misuse Using Symbolic Mismatch,” Machine Learning in Healthcare, August 2016.

Y. Liu, C. Stultz, and J. Guttag, “Transferring Knowledge from Text to Predict Disease Onset,” Machine Learning in Healthcare, August 2016.

J. Brooks, M. Kerr, and J. Guttag, “Using Machine Learning to Draw Inferences from Pass Location Data in Soccer,” Statistical Analysis and Data Mining, August 2016.

J. Wiens, J. Guttag, and E. Horvitz, “Patient Risk Stratification with Time-varying Parameters: a Multitask Learning Approach, Journal of Machine Learning Research, 17(77), June 2016.

A. McIntyre, J. Brooks, J. Guttag, and J. Wiens, “Recognizing and Analyzing Ball-screen Defense in the NBA,” Sloan Sports Analytics Conference, March 2016.

J.P.  Cortes, V. Espinoza, M. Zanartu, M. Ghassemi, J. Guttag, D. Mehta, J. Van Stan, and R. Hillman, “Discriminating patients with vocal fold nodules from matched controls using acoustic and aerodynamic features from ambulatory voice monitoring data,” 10th International Conference on Voice Physiology and Biomechanics, March 2016.