EE Student Information

The Department of Electrical Engineering supports Black Lives Matter. Read more.

• • • • •

EE Student Information, Spring Quarter through Academic Year 2020-2021: FAQs and Updated EE Course List.

Updates will be posted on this page, as well as emailed to the EE student mail list.

Please see Stanford University Health Alerts for course and travel updates.

As always, use your best judgement and consider your own and others' well-being at all times.

Workshop in Biostatistics presents "Machine Learning in Real-world Healthcare Settings: How Far We've Come and Where We Are Going"

Topic: 
Machine Learning in Real-world Healthcare Settings: How Far We've Come and Where We Are Going
Thursday, November 5, 2020 - 2:30pm
Venue: 
Zoom ID 926 9609 8893 (+password)
Speaker: 
Prof. Katherine Heller (AI Researcher at Google Medical Brain; Duke University)
Abstract / Description: 

In this talk, I will discuss three real-world Health applications of Machine Learning research, the progress that we have made in deployment to hospitals or directly to individuals, and where we hope to be heading next. In the first part, I will discuss Sepsis Watch, our Sepsis prediction system that has been deployed to the emergency departments of Duke University hospitals. This system performs prediction for incoming patients through a combination of Gaussian Processes, which estimate patient features in continuous time from uneven measurements, and Recurrent Neural Networks. Next I discuss Graph-coupled HMMs, work that we have done making individual-level predictions of disease spread in a social network in influenza, and how this might affect prediction abilities in other diseases, such as Coronavirus. Lastly, I will discuss the iOS app developed to record data on people with Multiple Sclerosis outside of a clinic environment, what collected data and basic analyses imply for our ability to do symptom and subpopulation prediction in this setting, and where we are headed in the future.

Suggested Readings:

  • Learning to Detect Sepsis with a Multitask Gaussian Process RNN Classifier
  • Real-World Integration of a Sepsis Deep Learning Technology Into Routine Clinical Care: Implementation Study
  • Graph-Coupled HMMs for Modeling the Spread of Infection
  • Hierarchical Graph-Coupled HMMs for Heterogeneous Personalized Health Data
  • Understanding MS Fatigue: Initial Subtype Discovery from the MS Mosaic Project