Clinical Natural Language Processing (Coursera)

Finally, you will have a chance to put your skills to the test with a real-world practical application where you develop text processing algorithms to identify diabetic complications from clinical notes. You will complete this work using a free, online computational environment for data science hosted by our Industry Partner Google Cloud.

What You Will Learn

- Recognize and distinguish the difference in complexity and sophistication of text mining, text processing, and natural language processing.

- Write basic regular expressions to identify common clinical text.

- Assess and select note sections that can be used to answer analytic questions.

- Write R code to search text windows for other keywords and phrases to answer analytic questions.

Course 4 of 6 in the Clinical Data Science Specialization

Syllabus

WEEK 1

Introduction: Clinical Natural Language Processing

This module covers the basics of text mining, text processing, and natural language processing. It also provides a information on the linguistic foundations that underly NLP tools.

WEEK 2

Tools: Regular Expressions

This module introduces regular expressions, the method of text processing, and how to work with text data in R. Mastery is demonstrated through a programming assignment with applied questions.

WEEK 3

Techniques: Note Sections

This module discusses how the section of a clinical note can affect the meaning of text in the section. A programming assignment provides hands on practice with how to apply this knowledge to process clinical text.

WEEK 4

Techniques: Keyword Windows

This module discusses how you can build windows of text around keywords of interest to understand the context and meaning of how the keyword is being used. A programming assignment provides hands on practice with how to apply this technique to process clinical text.

WEEK 5

Practical Application: Identifying Patients with Diabetic Complications

Apply the tools and techniques that you have learned in the course to a real-world example!