AI in Medicine

This course offers a thorough introduction to core machine learning methods and techniques, with a focus on applications in the healthcare and biomedical domains. Students will explore foundational concepts in computer vision, natural language processing (NLP), and deep learning, and learn how these tools are used to analyze and interpret complex medical data. The primary objective of the course is to equip students with the theoretical background and practical skills necessary to apply machine learning techniques to real-world problems. Through guided assignments and project-based learning, students will gain hands-on experience developing models for tasks such as medical image classification and clinical text analysis. The course will also address key ethical considerations in the use of AI in medicine, including fairness, transparency, and data privacy.

Learning Outcomes

Upon completing this course, students will: 

1. Demonstrate a foundational understanding of core machine learning frameworks and methodologies, including supervised and unsupervised learning.
2. Apply practical knowledge of key machine learning techniques such as Convolutional Neural Networks (CNNs), Transformer models, and object detection algorithms.
3. Analyze real-world biomedical data using AI tools for both image-based and text-based tasks (e.g., X-rays, clinical notes, MRI).
4. Develop and evaluate machine learning models using Python libraries such as TensorFlow, PyTorch, and Scikit learn
5. Identify and address key ethical considerations in AI development, including bias, data privacy, and model transparency.
6. Work collaboratively on a team-based project that applies AI to a real-world healthcare problem.

Tangible Outcomes 

• A working CNN-powered web app for pneumonia classification from chest X-rays.
• Case study-style class projects solving real-world healthcare AI problems.
• Ethics in AI debate competition exploring controversial medical AI scenarios.
• IBM Z Certification in AI, recognized by industry employers.
• Kaggle platform experience with completed datasets and competition submissions.
• A GitHub portfolio containing code from all hands-on projects.
• Mini hackathon prototype built with a team to address a medical challenge.
• An “Ethical AI Checklist” co-created with peers, usable in real hospital settings.
• Project presentations to peers and guest speakers from academia and industry.
• Practical experience with AI tools such as Google Colab, PyTorch, TensorFlow, and 3D Slicer

Hands-on Activities

• A working CNN-powered web app for pneumonia classification from chest X-rays.
• Case study-style class projects solving real-world healthcare AI problems.
• Ethics in AI debate competition exploring controversial medical AI scenarios.
• IBM Z Certification in AI, recognized by industry employers.
• Kaggle platform experience with completed datasets and competition submissions.
• A GitHub portfolio containing code from all hands-on projects.
• Mini hackathon prototype built with a team to address a medical challenge.
• An “Ethical AI Checklist” co-created with peers, usable in real hospital settings.
• Project presentations to peers and guest speakers from academia and industry.
• Practical experience with AI tools such as Google Colab, PyTorch, TensorFlow, and 3D Slicer

Guest Speakers

• Ayon Roy, HP Z Global Data Science Ambassador and leading data scientist
• Dr. Manu Goyal, Research Scientist at CPHAI

Field Trips

• Dali Lab
• Mechanical Workshop

Information is subject to change as instructors finalize course content and syllabi.