Course Summary
This course introduces the concept of computational phenotyping, which involves the use of computational methods to identify and analyze patterns in large datasets of medical information. Students will learn how to apply machine learning algorithms to clinical data, and how to use these tools to improve patient outcomes.Key Learning Points
- Understand the basics of computational phenotyping
- Apply machine learning algorithms to clinical data
- Improve patient outcomes through data analysis
Related Topics for further study
Learning Outcomes
- Understand the principles of computational phenotyping
- Apply machine learning algorithms to clinical data
- Develop an understanding of how data analysis can improve patient outcomes
Prerequisites or good to have knowledge before taking this course
- Basic knowledge of statistics
- Familiarity with programming languages such as R or Python
Course Difficulty Level
IntermediateCourse Format
- Online
- Self-paced
Similar Courses
- Introduction to Clinical Data Science
- Machine Learning for Healthcare
Related Education Paths
Notable People in This Field
- Director of the Scripps Research Translational Institute
- Surgeon and Public Health Researcher
Related Books
Description
This course teaches you the fundamentals of computational phenotyping, a biomedical informatics method for identifying patient populations. In this course you will learn how different clinical data types perform when trying to identify patients with a particular disease or trait. You will also learn how to program different data manipulations and combinations to increase the complexity and improve the performance of your algorithms. Finally, you will have a chance to put your skills to the test with a real-world practical application where you develop a computational phenotyping algorithm to identify patients who have hypertension. You will complete this work using a real clinical data set while using a free, online computational environment for data science hosted by our Industry Partner Google Cloud.
Knowledge
- Create a computational phenotyping algorithm
- Assess algorithm performance in the context of analytic goal.
- Create combinations of at least three data types using boolean logic
- Explain the impact of individual data type performance on computational phenotyping.
Outline
- Introduction: Identifying Patient Populations
- Welcome to Identifying Patient Populations
- Introduction to Computational Phenotyping
- Introduction to Manual Record Review
- Manual Record Review: Selecting Reviewers and Records
- Manual Record Review: Tools and Techniques
- Introduction to Specialization Instructors
- Course Policies
- Accessing Course Data and Technology Platform
- Introduction to Course Example
- Introduction to Manual Record Review
- Methods - Selecting Reviewers
- Methods - Selecting Records for Review
- Methods - Creating Review Instruments and Protocols
- Methods - Assessing Review Quality
- Week 1 Practice Quiz
- Week 1 Assessment
- Tools: Clinical Data Types
- Data Types for Computational Phenotyping
- Computational Phenotyping: Billing Data
- Computational Phenotyping: Laboratory Data
- Computational Phenotyping: Clinical Observations
- Computational Phenotyping: Medications
- Testing Individual Data Types
- Note about the Assessment
- Programming Exercises Practice Quiz
- Week 2 Assessment
- Techniques: Data Manipulations and Combinations
- Manipulating Individual Data Types
- Combining Multiple Data Types
- Data Manipulations
- Data Combinations
- Programming Exercises Practice Quiz
- Week 3 Assessment
- Techniques: Algorithm Selection and Portability
- Selecting a Final Algorithm
- Assessing Algorithmic Accuracy, Complexity, and Portability
- Week 4 Assessment
- Practical Application: Develop a Computational Phenotyping Algorithm to Identify Patients with Hypertension
- Welcome to Practical Applications!
Summary of User Reviews
Discover the fascinating world of computational phenotyping with this Coursera course. Students have lauded the course for its comprehensive content and engaging delivery.Key Aspect Users Liked About This Course
The course's comprehensive contentPros from User Reviews
- Well-structured course content
- Engaging delivery by the instructor
- Great opportunity to learn about computational phenotyping
- Helpful resources and assignments
- Accessible for beginners and experts alike
Cons from User Reviews
- Some parts of the course may be too technical for beginners
- Limited interaction with instructor and other students
- No certificate of completion without paying for a subscription
- Lacks practical application examples
- Not suitable for those looking for a quick course
Laura K. Wiley, PhD
4.5 Raiting
Identifying Patient Populations
- 4.5
-
![]()
![]()
![]()
![]()
![]()
This course teaches you the fundamentals of computational phenotyping, a biomedical informatics method for identifying patient populations. Introduction: Identifying Patient Populations...
HI-FIVE: Health Informatics For Innovation, Value & Enrichment (Clinical Perspective)
- 4.6
-
![]()
![]()
![]()
![]()
![]()
The training is role-based and uses case scenarios. Also, it has additional, optional modules on other topics of interest or relevance....
