Before each session, Tech Training will provide a Zoom link for live online classes, along with any required class materials.
Data science and digital image processing are becoming an increasingly integral part of health care. This course exposes you to ways data science is used to extract innovative and actionable insights from healthcare-related datasets and medical imaging.
In this course, we will examine how predictive modeling is used to assess outcomes, needs, and potential interventions. We will also explore medical image analysis which has become an inherent part of medical technology.
Prerequisites:
Basic Python programming experience
Learning Objectives:
During this course, you will have the opportunity to:
- Install Anaconda on a personal computer.
- Prepare and explore healthcare-related datasets using the primary tools for data science in Python (e.g., NumPy, Pandas, Matplotlib, Scikit-learn).
- Examine many of the unique qualities and challenges of healthcare data.
- Understand how data science is impacting medical diagnosis, prognosis, and treatment.
- Use a data-science approach to evaluate and learn from healthcare data (e.g., behavioral, genomic, pharmacological).
- Use deep learning and TensorFlow to interpret and classify medical images.
- Perform feature extraction, segmentation, and quantitative measurements of medical images.
- Understand the increasing importance of data science and image processing in healthcare.
Topic Outline:
- Course Introduction
- Overview of Data Science in Healthcare
- Milestone 1: Install Anaconda/Work with Jupyter Notebooks
- The Data Science Process
- How Data Science is transforming the healthcare sector
- Essential Python Data Science Libraries
- NumPy
- Pandas
- Matplotlib
- Scikit-learn - Data Visualization
- Line Chart
- Scatterplot
- Pairplot
- Histogram
- Density Plot
- Boxplot
- Customizing Charts - Milestone 2: Perform Exploratory Data Analysis of Healthcare Datasets
- Milestone 3: Use Scikit-learn to Apply Machine Learning to Healthcare Questions
- Introduction to Deep Learning for Medical Image Analysis
- Digital Image Processing
- Contrast and Brightness Correction
- Edge Detection
- Image Convolution
- Milestone 4: Use TensorFlow to Interpret and Classify Medical Images
- Conclusion: Next Steps
Structured Activity/Exercises/Case Studies:
- Milestone 1: Install Anaconda/Work with Jupyter Notebooks
- Milestone 2: Perform Exploratory Data Analysis of Healthcare Datasets
- Milestone 3: Use Scikit-learn to Apply Machine Learning to Healthcare Questions
- Milestone 4: Use TensorFlow to Interpret and Classify Medical Images
University IT Technology Training classes are only available to Stanford University staff, faculty, students and Stanford Hospitals & Clinics employees. A valid SUNet ID is needed in order to enroll in a class.
