Deep Learning Models for Health Care - Challenges and Solutions


It is widely believed that deep learning and artificial intelligence techniques will fundamentally change healthcare industries. Even though recent development in deep learning has achieved successes in many applications, such as computer vision, natural language processing, speech recognition and so on, healthcare applications pose many significantly different challenges to existing deep learning models. Examples include but not are limited to interpretations for prediction, heterogeneity in data, missing value, multi-rate multi-resolution data, big and small data, and privacy issues. In this tutorial, we will discuss a series of problems in healthcare that can benefit from deep learning models, the challenges as well as recent advances in addressing those. We will also include data sets and demos of working systems.


● Introduce diverse types of healthcare data

● Overview different ML problems for healthcare applications

● Explain the technical challenges for applying deep learning for healthcare applications

Recently, there are substantially growing interest in ML in health applications, thanks to the heterogeneous healthcare data such as electronic health records, medical images, clinical notes and continuous monitoring data. The analytic problems in healthcare pose many unique ML challenges that are worth discussing.

Target audience

The tutorial is targeted at researchers in machine learning as well as researchers working on the health-related applications. It will also attract a broader of audience who work on applying deep learning models to applications with heterogeneous data. The prerequisites include graduate-level machine learning classes and basic knowledge on deep learning.

Tutorial Resources

Slides: [PDF]

Related publications from the Speakers:

  1. Variational Adversarial Deep Domain Adaptation for Healthcare Time Series Analysis. Sanjay Purushotham, Wilka Carvalho and Yan Liu. ICLR, 2017.
  2. Deep Computational Phenotyping. Zhengping Che, David Kale, Wenzhe Li, Mohammad Taha Bahadori, and Yan Liu. Proceedings of the 21st ACM SIGKDD Conference on Knowledge Discovery and Data Mining (SIGKDD), 2015.
  3. RETAIN: Interpretable Predictive Model in Healthcare Using Reverse Time Attention Mechanism. Choi, Edward, Mohammad Taha Bahadori, Andy Schuetz, Walter F. Stewart, and Jimeng Sun, NIPS’16
  4. Multi-layer Representation Learning for Medical Concepts. Edward Choi, Mohammad Bahadori, Elizabeth Searles, Catherine Coffey, Michael Thompson, James Bost, Javier Tejedor-Sojo,and Jimeng Sun, KDD 16.
  5. Interpretable Deep Models for ICU Outcome Prediction. Zhengping Che, Sanjay Purushotham, Robinder Khemani, and Yan Liu. Proceedings of the American Medical Informatics Association Annual Symposium (AMIA), 2016.
  6. Recurrent Neural Networks for Multivariate Time Series with Missing Values. Zhengping Che, Sanjay Purushotham, Kyunghyun Cho, David Sontag, and Yan Liu. arXiv preprint arXiv:1606.01865, 2016.
  7. Real-time Detection and Exploratory Discovery of Anomalies for Pediatric Ventilator Management. Tanachat Nilanon, Yan Liu, Justin Hotz and Robinder Khemani, Proceedings of Machine Learning in Health Care (MLHC), 2016.
  8. Normal / Abnormal Heart Sound Recordings Classification Using Deep Recurrent Neural Network. Tanachat Nilanon, Sanjay Purushotham and Yan Liu. Proceedings of the Computing in Cardiology (CinC), 2016.
  9. Distilling Knowledge from Deep Networks with Applications to Computational Phenotyping. Zhengping Che, Sanjay Purushotham, and Yan Liu. Workshop on Data Science, Learning and Applications to Biomedical and Health Sciences (DSLA-BHS), 2016.
  10. Distilling Knowledge from Deep Networks with Applications to Healthcare Domain. Zhengping Che, Sanjay Purushotham, and Yan Liu. NIPS Workshop on Machine Learning for Healthcare (NIPS-MLHC), 2015.
  11. Causal Phenotype Discovery via Deep Networks. David C. Kale, Zhengping Che, Mohammad Taha Bahadori, Wenzhe Li, and Yan Liu. Proceedings of the American Medical Informatics Association Annual Symposium (AMIA), 2015.
  12. Using recurrent neural network models for early detection of heart failure onset. Choi, Edward, Andy Schuetz, Walter F Stewart, and Jimeng Sun, Journal of the American Medical Informatics Association 2016; doi: 10.1093/jamia/ocw112
  13. Doctor AI: Predicting Clinical Events via Recurrent Neural Networks. Edward Choi, Mohammad Taha Bahadori, Andy Schuetz, Walter F. Stewart, and Jimeng Sun, Machine learning for Healthcare 2016, arXiv:1511.05942 [cs.LG]
  14. Benchmark of Deep Learning Models on Large Healthcare MIMIC Datasets. Sanjay Purushotham, Chuizheng Meng, Zhengping Che, and Yan Liu. arXiv preprint arXiv:1710.08531 (2017).
  15. Generating Multi-label Discrete Patient Records using Generative Adversarial Networks, Edward Choi, Siddharth Biswal, Bradley Malin, Jon Duke, Walter F. Stewart, Jimeng Sun, 2017, Proc. of Machine Learning for Healthcare (MLHC) 2017
  16. Boosting Deep Learning Risk Prediction with Generative Adversarial Networks for Electronic Health Records, Zhengping Che*, Yu Cheng*, Shuangfei Zhai, Zhaonan Sun, and Yan Liu. (*contributed equally) , Proceedings of the IEEE 17th International Conference on Data Mining (ICDM), 2017
  17. Deep Learning Solutions for Classifying Patients on Opioid Use, Zhengping Che, Jennifer St. Sauver, Hongfang Liu, and Yan Liu. Proceedings of the American Medical Informatics Assocation Annual Symposium (AMIA), 2017.
  18. Deep Multi-Instance Learning for Concept Annotation from Medical Time Series Data, Sanjay Purushotham, Zhengping Che, Bo Jiang, and Yan Liu. NIPS Workshop on Machine Learning for Health (NIPS-ML4H), 2017

Speaker Bios

Edward Choi is a PhD student at Georgia Tech advised by Dr. Jimeng Sun. His research is focused on analyzing longitudinal electronic health records with machine learning techniques. His works include representation learning for healthcare concepts, interpretable sequence prediction, and synthetic EHR generation.

Sanjay Purushotham is a Postdoctoral researcher in the Department of Computer Science at the University of Southern California (USC). His research interests are in machine learning, data mining, and its applications to healthcare & bio-informatics. Recently, he has been developing deep learning solutions for healthcare time series analysis.

Yan Liu is an Associate Professor in Computer Science Department at the University of Southern California from 2010. Before that, she was a researcher at IBM from 2006-2010. Her research interests are developing scalable machine learning algorithms with applications to health and biology applications, social media analysis, and climate modeling.

Jimeng Sun is an Associate Professor of College of Computing at Georgia Tech. Prior to Georgia Tech, he was a researcher at IBM TJ Watson Research Center. His research focuses on health analytics and data mining, especially in designing tensor factorizations, deep learning methods, and large-scale predictive modeling systems.