With the transition to electronic health records (EHR) over the last decade, the amount of EHR data has increased exponentially, providing an incredible opportunity to unlock this data with AI to benefit the healthcare system. Learn the fundamental skills of working with EHR data in order to build and evaluate compliant, interpretable machine learning models that account for bias and uncertainty using cutting-edge libraries and tools including Tensorflow Probability, Aequitas, and Shapley. Understand the implications of key data privacy and security standards in healthcare. Apply industry code sets, transform datasets at different EHR data levels, and use Tensorflow to engineer features.
Overview
Syllabus
- Applying AI to EHR Data Introduction
- This lesson will provide you with an Introduction to the EHR Data course outline, content, as well as introduce you to your instructor.
- EHR Data Security and Analysis
- In this lesson, you will learn about the importance of data security and the different standards that apply to EHR, as well as analyzing EHR data.
- EHR Code Sets
- In this lesson you will learn how to work with different EHR codes and how to map them properly to records.
- EHR Transformations & Feature Engineering
- In this lesson, you'll gain skills in feature engineering and transformation of EHR.
- Building, Evaluating and Interpreting Models
- In this final lesson, you'll be putting all of your skills together to build, evaluate and interpret ML models for Bias and Uncertainty.
- Project: Patient Selection for Diabetes Drug Testing
- In this project students will use what they learn in the classroom to apply AI in healthcare for patient data.
Taught by
Michael DAndrea
