Examines data mining perspectives and methods in a healthcare context. Introduces the theoretical foundations for major data mining methods and studies how to select and use the appropriate data mining method and the major advantages for each. Students are exposed to contemporary data mining software applications and basic programming skills. Focuses on solving real-world problems, which require data cleaning, data transformation, and data modeling.
Class Deals by MOOC List - Click here and see Coursera's Active Discounts, Deals, and Promo Codes.
Syllabus
Demystifying Data Mining and Artificial Intelligence
Module 1
In this module, we’ll start demystifying the terminology. We’ll begin by exploring the differences between AI, machine learning and deep learning. You’ll also gain hands-on experience in planning your own AI algorithm development, and learn what goes into preparing and constructing datasets for research questions.
Exploring the AI/Machine Learning Toolbox
Module 2
In this module, we’ll take a deep dive into several sophisticated AI modeling techniques, including random forest modeling, gradient boosting, clustering and neural networks.
Practical Application of AI/Machine Learning
Module 3
In this module, you’ll dive deeper into the nitty gritty of how AI algorithms are trained and validated, and examine how they compare to clinicians in the field.
The Credibility Gap
Module 4
In this module, we’ll explore why so many potentially useful algorithms are not being implemented by healthcare providers. That critique will explore the black box dilemma, and the challenges involved in developing accurate and equitable data sets. That means examining the many ways in which algorithms can discriminate against various marginalized segments of the population.
