About Information extraction from free text data in healthcare course
In this MOOC, you will learn advanced machine learning and natural language processing techniques to analyze and extract information from unstructured text documents in healthcare, such as patient records, radiology reports, and hospital discharge summaries. Whether you are a budding data scientist or a data or IT professional in healthcare, it is essential for you to continually improve your skills in information extraction and analysis.
To succeed in this course, you will build on the concepts learned in other intermediate-level MOOCs and Data Science specializations offered at the University of Michigan. This will allow you to delve deeper into the challenges of recognizing medical entities in healthcare documents, extracting clinical information, disambiguating and polysemy to assign them to the right concept types, and developing tools and techniques for analyzing new genres of healthcare information. By the end of this course, you will be able to: Identify the text mining approaches needed to identify and extract different types of information from healthcare-related text data Build an end-to-end NLP pipeline for extracting medical concepts from clinical free text using a single terminology resource Distinguish how training deep learning models differs from training traditional machine learning models Tune a deep neural network model to detect adverse events from drug reviews List the pros and cons of deep learning approaches.
