AI Biomedical Applications Workshop

In three fascinating projects, learn how to create biomedical AI applications and deploy them. First, you’ll discover the basics of AI and machine learning using Python and Scikit-Learn, building a model to detect Parkinson’s disease from voice patterns. Next, you’ll dive into deploying a Parkinson’s detection app using Docker and Kubernetes, no prior knowledge is needed. Finally, using PyTorch and computer vision techniques, you’ll develop an algorithm that identifies metastatic cancer from digital pathology scans. By the end, you’ll have the skills to tackle real-world biomedical problems.

This course covers machine learning in the biomedical field through three projects. You will learn how to build and deploy AI models, including detecting Parkinson’s Disease and identifying metastatic cancer. By the end, you’ll be equipped with practical skills to apply machine learning to real-world problems and contribute to healthcare innovation.Part 1. parkinson detection; Part 2. deploy the docker container of the parkinson app; Part 3. cancer detection with pytorch.
Course Syllabus
Part 1: Using Machine Learning to Analyze Voice Disorders for Parkinson’s Disease Detection
Introduction to machine learning and its applications in Biomedicine
Understanding voice disorders and Parkinson’s disease
Implementing different machine learning algorithms such as decision trees and support vector machines
Conducting grid search to optimize model parameters
Visualizing the models for interpretation and feature identification
Building a machine learning model that can accurately predict Parkinson’s disease based on voice recordings
Part 2: Deploying AI Application on IBM Code Engine
Introduction to IBM Code Engine and its features
Understanding serverless platforms and their advantages
A step-by-step guide to deploying the AI application on IBM Cloud using IBM Code Engine
Using Parkinson’s detection model as an example
Creating a Docker container image with Kubernetes for app deployment
Part 3: Cancer Detection with PyTorch
Introduction to the convolutional neural network and transfer learning
Understanding pre-trained CNNs
Dataset preparation for PCAM images
Training and testing the model
Improving model performance using transfer learning
Overall, this course will provide an in-depth understanding of machine learning applications in biomedicine, from detecting Parkinson’s disease to identifying metastatic cancer. By the end of the course, students will have the skills to build and deploy AI models and contribute to healthcare innovation.