Stanford University - Introduction to Clinical Data
- Offered byCoursera
Introduction to Clinical Data at Coursera Overview
Duration | 12 hours |
Total fee | Free |
Mode of learning | Online |
Difficulty level | Beginner |
Official Website | Explore Free Course  |
Credential | Certificate |
Introduction to Clinical Data at Coursera Highlights
- This Course Plus the Full Specialization.
- Shareable Certificates.
- Graded Programming Assignments.
Introduction to Clinical Data at Coursera Course details
- This course introduces you to a framework for successful and ethical medical data mining. We will explore the variety of clinical data collected during the delivery of healthcare. You will learn to construct analysis-ready datasets and apply computational procedures to answer clinical questions. We will also explore issues of fairness and bias that may arise when we leverage healthcare data to make decisions about patient care.
- The Stanford University School of Medicine is accredited by the Accreditation Council for Continuing Medical Education (ACCME) to provide continuing medical education for physicians. Visit the FAQs below for important information regarding 1) Date of original release and Termination or expiration date; 2) Accreditation and Credit Designation statements; 3) Disclosure of financial relationships for every person in control of activity content.
Introduction to Clinical Data at Coursera Curriculum
Asking and answering questions via clinical data mining
Welcome
Introduction to the data mining workflow
Real Life Example
Example: Finding similar patients
Example: Estimating risk
Putting patient data on timeline
Revisit the data mining workflow steps
Types of research questions
Research questions suited for clinical data
Example: making decision to treat
Properties that make answering a research question useful
Wrap Up
Study Guide Module 1
Citations and Additional Readings
Reflection Exercise
Reflection Exercise
Knowledge Check
Data available from Healthcare systems
Review of the healthcare system
Review of key entities and the data they collect
Actors with different interests
Common data types in Healthcare
Strengths and weaknesses of observational data
Bias and error from the healthcare system perspective
Bias and error of exposures and outcomes
How a patient's exposure might be misclassified
How a patient's outcome could be misclassified
Electronic medical record data
Claims data
Pharmacy
Surveillance datasets and Registries
Population health data sets
A framework to assess if a data source is useful
Wrap Up
Video Image Credit
Study Guide Module 2
Citations and Additional Readings
Reflection Exercise
Reflection Exercise
Reflection Exercise
Knowledge Check
Representing time, and timing of events, for clinical data mining
Introduction
Time, timelines, timescales and representations of time
Timescale: Choosing the relevant units of time
What affects the timescale
Representation of time
Time series and non-time series data
Order of events
Implicit representations of time
Different ways to put data in bins
Timing of exposures and outcomes
Clinical processes are non-stationary
Wrap Up
Study Guide Module 3
Citations and Additional Readings
Reflection Exercise
Reflection Exercise 2
Knowledge Check
Creating analysis ready datasets from patient timelines
Turning clinical data into something you can analyze
Defining the unit of analysis
Using features and the presence of features
How to create features from structured sources
Standardizing features
Dealing with too many features
The origins of missing values
Dealing with missing values
Summary recommendations for missing values
Constructing new features
Examples of engineered features
When to consider engineered features
Main points about creating analysis ready datasets
Structured knowledge graphs
So what exactly is in a knowledge graph
What are important knowledge graphs
How to choose which knowledge graph to use
Wrap Up
Study Guide Module 4
Citations and Additional Readings
Reflection Exercise
Reflection Exercise
Knowledge Check
Handling unstructured healthcare data: text, images, signals
Introduction to unstructured data
What is clinical text
The value of clinical text
What makes clinical text difficult to handle
Privacy and de-identification
A primer on Natural Language Processing
Practical approach to processing clinical text
Summary - Clinical text
Overview and goals of medical imaging
Why are images important?
What are images?
A typical image management process
Summary - Images
Overview of biomedical signals
Why are signals important?
What are signals?
What are the major issues with using signals?
Summary - Signals
Wrap Up
Video Image Credit
Video Image Credit
Study Guide Module 5
Citations and Additional Readings
Reflection Exercise
Reflection Exercise
Knowledge Check
Putting the pieces together: Electronic phenotyping
Introduction to electronic phenotyping
Challenges in electronic phenotyping
Specifying an electronic phenotype
Two approaches to phenotyping
Rule-based electronic phenotyping
Examples of rule based electronic phenotype definitions
Constructing a rule based phenotype definition
Probabilistic phenotyping
Approaches for creating a probabilistic phenotype definition
Software for probabilistic phenotype definitions
Wrap Up
Video Image Credit
Study Guide Module 6
Citations and Additional Readings
Reflection Exercise
Reflection Exercise
Knowledge Check
Ethics
Introduction to Research Ethics and AI
The Belmont Report: A Framework for Research Ethics
Ethical Issues in Data sources for AI
Secondary Uses of Data
Return of Results
AI and The Learning Health System
Ethics Summary
Instructor Introduction
Study Guide Module 7
Course Conclusion
Conclusion
Final Assessment Note
Claim CME Credit
Full Study Guide
Final Assessment
Other courses offered by Coursera
Student Forum
Anything you would want to ask experts?
Useful Links
Know more about Coursera
Know more about Programs
- Medical Courses
- Public Health & Management
- Hospital Management Course
- Medical Transcription
- Perfusion Technology
- Diabetology
- Forensic Medical Science
- Dialysis Technology
- Cardiovascular Technology
- Cath Lab Technology
- BSc Operation Theatre Technology
- BSc in Perfusion Technology
- Physician Assistant
- BSc Physician Assistant
- BSc in Respiratory Care Technology