Machine learning

Machine learning explained

The science behind the magic — what machine learning is, how models learn from data and how they become trustworthy medical tools.

12curriculum articles, from the basics to deployment12topics

Machine learning explained

The science behind the magic — what machine learning is, how models learn from data and how they become trustworthy medical tools.

Explore this section

What is machine learning?

Machine learning is how computers learn from examples instead of being programmed rule by rule — the engine of today's medical AI.

What is artificial intelligence?

Artificial intelligence gives machines the ability to learn from data, recognise patterns and make decisions — insight engines that now support medicine.

The three ways machines learn

Supervised, unsupervised and reinforcement learning — the three families of machine learning and when each is used in medicine.

How machine learning learns

Training, validation, test — the three-phase journey every model takes before it can be approved.

The classic algorithms behind medical AI

Behind modern diagnostics stand surprisingly simple algorithms — for well-organised medical data they are often the best and most transparent choice.

Ensembles: many models, one stronger decision

Combine several models and their weaknesses cancel out — random forests and boosting are among the most reliable classifiers in medicine.

Machine learning vs deep learning

Two branches of the same idea — when classic machine learning wins and when deep learning takes over.

Deep learning and neural networks

Deep neural networks, inspired by the brain, power today's imaging AI — and convolutional networks were designed for images.

Training data, the raw material

An AI is only as good as its training data — where it comes from, how it is labelled and how bias slips in.

How models are evaluated

Accuracy is only the beginning — sensitivity, specificity, robustness and calibration each tell part of the story.

From model to clinic

Bringing a trained model into a hospital is a journey of evidence, regulation, integration and trust — here is the path.

Traditional diagnosis vs AI-assisted diagnosis

Mammography, ultrasound, biopsy and MRI — how artificial intelligence builds on the classic toolbox and where it adds the most.

Explore the AI knowledge base

Six connected domains, each with its articles, evidence and practical advice — designed as a journey, not a single page.

Back to the AI hub