Introduction to Machine Learning for Clinical Data Analysis

Build a practical foundation in machine learning for clinical data analysis at this in-person workshop in North Melbourne. Designed for life scientists and clinicians new to predictive modelling, the session uses a clinical dataset of 569 breast tissue biopsies to develop and assess a classifier for malignant and benign tumours. The emphasis is on intuition rather than mathematics.

What you’ll learn

• Translate clinical research questions into machine learning concepts such as features, labels, classification and regression
• Prepare and scale clinical tabular data with pandas and scikit-learn
• Use Principal Component Analysis (PCA) to visualise 30 features in a 2D plot
• Train, evaluate and interpret a Random Forest classifier
• Use sensitivity, specificity and feature importance to interpret model results

Eligibility and preparation

This free workshop is available to staff and students at The University of Melbourne and its affiliated institutes. Register using an affiliated institutional email address, or your registration may be cancelled.

Basic Python knowledge is expected, including variables, lists, dictionaries and pandas DataFrames. No prior machine learning experience is required.

Bring your own computer and preferably a charger. You will also need a Google account for Google Colab, access to UniWireless or Eduroam, and a web browser (Firefox or Chrome recommended). No software installation is required.

Register for the workshop

Attendance policy

From 1 August 2025, participants who miss two or more workshops within 12 months without proper notice — less than 48 hours’ notice or attending under 50% — will be placed on a six-month waitlist for full workshops. Cancellations must be made at least 24 hours in advance, except in emergencies. Read the full policy.

For access requirements or further information, contact Melbourne Bioinformatics at bioinformatics-training@unimelb.edu.au.