Health Catalyst Upcoming Webinar
register arrow

Register Now

Machine Learning Misconceptions

With all the buzz around machine learning, predictive analytics, and artificial intelligence (AI) there are a lot of misconceptions and misunderstandings surrounding the optimal use of modern machine learning tools., a free software package developed by the Health Catalyst data science team, was recently released to help hospitals gain valuable insights and advance outcomes improvements from their immense data sets. The software automates machine learning tasks and democratizes machine learning by making it accessible to ‘citizen data scientists’. We have received several questions about machine learning in healthcare, such as how do you define machine learning, how is it different than AI, what are some common uses cases for machine learning in healthcare, and what are the pitfalls. This webinar will develop a common vocabulary around these ideas. We’ll cover the differences between the most cutting-edge predictive techniques, how a model can be improved over time, and use case vignettes to understand and avoid typical machine learning pitfalls. In today’s healthcare industry, the fastest path to healthcare outcomes is often achieved using the simplest predictive tools.

Wednesday, May 3
1:00-2:00 PM EST

Mike Mastanduno, PhD, data scientist, and Levi Thatcher, PhD, director of data science, will discuss the landscape of healthcare-specific machine learning. Mike and Levi have extensive experience building and deploying impactful machine learning models using and have worked at the cutting edge of medical research. During and after the discussion, they will answer viewer-submitted questions. This webinar will:

  1. Compare and contrast machine learning and AI.
  2. Discuss techniques that offer feedback into the system and when it’s necessary to retrain a model.
  3. Give advice on how to avoid common pitfalls in machine learning implementation.
  4. Provide use case example and vignette examples on how to apply the different classes of machine learning techniques.

We look forward to you joining us!

Dr. John Haughom, MD
Michael Mastanduno, PhDData Scientist, Health Catalyst

Mike Mastanduno joined Health Catalyst in November of 2016 as a Data Scientist. He received his PhD from Dartmouth College in Biomedical Engineering, where he designed hardware and software tools to aid in the early diagnosis of breast cancer. Mike’s dissertation culminated in a 60-patient clinical trial to evaluate the technology he had developed. Mike then went on to a postdoctoral fellowship at the Stanford School of Medicine where he won a National Institute of Health award to study medical imaging of ovarian cancers. During his academic career, Mike was able to publish over 10 journal papers, 25 conference papers, and won numerous awards for speaking and research. Since leaving Stanford, Mike studied with Insight Data Science and then joined Health Catalyst to continue improving healthcare through developing software tools. He is excited by the opportunity to impact patients nationwide by building machine learning and artificial intelligence models with Health Catalyst. You can see his contributions on, find him teaching others how to think about machine learning problems, and implementing predictive analytics in clinical environments.

Dr. John Haughom, MD
Levi Thatcher, PhDDirector of Data Science, Health Catalyst

Levi did his graduate work at the University of Utah, focusing on atmospheric predictability. There he used ensemble methods to improve numerical models, in terms of both the lead time and estimated intensity of hurricane development. At Health Catalyst, Levi started out on the platform engineering team, creating software improvements to the company’s core ETL offering. Since he moved internally to lead the data science team, Levi founded, the first open-source machine learning project focused on healthcare outcomes. He’s now working to integrate into each of Health Catalyst’s products and make the international center of collaboration for healthcare machine learning.