Machine Learning for Medical Data

About this course

This course builds on foundational AI concepts to teach machine learning (ML) techniques tailored for healthcare. You will apply ML and deep learning techniques to develop predictive models for patient risk assessment. You will also translate healthcare data into actionable insights by experimenting with model design, training, and evaluation, strengthening both technical and clinical reasoning skills through practical, outcome-driven projects. Case studies and real-world examples will demonstrate how ML supports disease prediction, treatment optimization, and clinical decision support. The curriculum emphasizes data preprocessing, feature engineering, model selection, and evaluation using clinical metrics and validation strategies. Through hands-on exercises, you will apply supervised and unsupervised methods, design and train neural networks, and address practical challenges such as class imbalance, privacy, and interpretability. You will use Jupyter Notebook files in a Google Colab environment to complete labs. By the end of this course, you will be prepared to implement ML workflows that are clinically relevant, statistically sound, and ethically responsible.

Course objectives

• strengthen technical and clinical reasoning skills
• demonstrate the support of ML in disease prediction and treatment optimization
• complete hands-on exercises using Jupyter Notebook in Google Colab