One of the most exciting and practical goals of combining healthcare with technology is to mine large quantities of data to discover what, if anything, has eluded researchers—either through a lack of sufficiently large datasets or a lack of human ability to notice unlikely relationships. Unsupervised learning is a promising avenue for pursuing this goal, because unsupervised machine learning techniques do not require existing human knowledge to generate new insights about structure within datasets. This video, designed for learners with a basic understanding of statistics and computer programming, provides a detailed introduction to three specific types of unsupervised learning: cluster analysis, association analysis, and principal components analysis, as applied to health data sets both at the individual and population levels. Examples will be introduced in both Python and R.

• Discover how unsupervised learning generates novel insights and metrics from healthcare data
• Learn how to appropriately process healthcare data for unsupervised learning methodologies
• Understand association analysis and how it applies to health data sets in business and research
• Explore cluster analysis and how it's used in epidemiological and clinical applications
• Learn about principal components analysis and its use in medical literature

Aileen Nielsen is a software engineer at One Drop, an AI/ML heathtech company working on diabetes-management products. A member of the New York City Bar Association’s Science and Law committee, Aileen holds degrees in anthropology, law, and physics from Princeton, Yale, and Columbia, respectively.