Machine Learning for Healthcare

With massive amounts of data flowing from EMRs, wearables, and countless other new sources, the potential for machine learning and AI to transform healthcare is perhaps more drastic and profound than any other industry.

But there are unique challenges that exist in healthcare that make it difficult to apply new technologies in the industry, including patient privacy issues, the lack of interoperability, and the diversity of digital health data. In this course, you'll gain practical knowledge that will enable you to overcome these hurdles and apply the latest advances in healthcare AI tools and techniques to:

  • Automate medical discoveries
  • Predict patient outcomes
  • Model disease progression
  • Identify & manage high-risk patients
  • Implement patient health initiatives
  • Prevent high-cost care

You'll also come away with a strong understanding of the impact of healthcare.

Lead Instructor(s): 

David Sontag


Jul 16, 2018 - Jul 17, 2018

Course Length: 

2 Days

Course Fee: 



  • Registration opening soon
This course has limited enrollment. Apply early to guarantee your spot.

Participant Takeaways: 

  • Understand current ML trends and opportunities that they bring in healthcare
  • Outline practical problems that impact the application
  • See how to break down data silos between patients, providers and payers
  • Discover how to deploy ML to improve patient outcomes and/or impact the financial performance of your organization
  • Grasp what predictive analytics often does not provide

Who Should Attend: 

This course will be applicable to data scientists, software engineers, software engineering managers, and those working on health outcomes data from a range of industries including insurance, pharmaceuticals, electronic health records, health-related start-ups, Example companies include Philips Research, Kaiser, Blue Cross Blue Shield, Athena Health, Atrius Health, IBM Watson Health, Shire, Johnson & Johnson, Novartis, PatientsLikeMe.

Participants should be familiar with machine learning and comfortable programming in Python, performing basic data analysis, and using the machine learning toolkit Scikit-learn. Additionally participants should be familiar with machine learning (we recommend the MIT Professional Education course Machine Learning for Big Data and Text Processing: Foundations for participants who feel they need preparation in this area).

Computer requirements:

Laptops with Python and Scikit-learn installed are required. 

Program Outline: 

Day 1

  • What makes Healthcare unique? (9:00 am - 9:30 am)
  • Supervised Learning For Risk Stratification (9:30 am -10:30 am)
  • Break (10:30 am -10:45 am)
  • Case Study for Risk Stratification (10:45 am -Noon)
  • Lunch (Noon-1:00 pm)
  • Lab Work (1:00 pm -3:00 pm)
  • Break (3:00 pm -3:15 pm)
  • Time-Series Modeling (3:15 pm -5 pm)

Day 2:

  • Predicting the Outcome of Interventions: Causal Interference from Observational Data (9:00 am -10:00 am)
  • Break (10:00 am -10:15 am)
  • Lab Work (10:15 am -12:30 pm)
  • Lunch (12:30 pm -1:30 pm)
  • Interpretability of Machine Learning Models (1:30 pm -3:00 pm)
  • Break (3:00 pm -3:15 pm)
  • Deploying Machine Learning in Healthcare Settings (3:15 pm -4:30 pm)
  • Conclusion (4:30 pm -5:00 pm)

Course Schedule: 

This course runs 9:00 am - 5:00 pm each day.



This course takes place on the MIT campus in Cambridge, Massachusetts. We can also offer this course for groups of employees at your location. Please complete the Custom Programs request form for further details.