We keep on hearing about how machine learning is going to revolutionise Medicine 🤖
But what’s hype, and what’s realistic? How can you be at the forefront of the revolution?
As a healthcare worker, it can be difficult to understand what’s going on.
The problem? Most courses are aimed at computer scientists (nerds) and get technical very quickly.
This course is made for the rest of us. Medics who want to lead the charge and not just sit on the sidelines.
I’m Chris. I’m a Cambridge-trained medical doctor and a data scientist. Basically, I’ve got one foot in Medicine and the other in machine learning.
I’ve been running this course for 18 months in-person. Then COVID hit and I recreated it online.
It provides a less-technical and more healthcare-tailored introduction to machine learning, and the nuances of applying it to healthcare.
It will help you distinguish hype from reality, contribute to exciting research and impactful companies and, ultimately, to scale your positive health impact.
Specifically, it covers:
- What is machine learning and how do we train an algorithm?
- What have ‘neural networks’ and ‘deep learning’ got to do with medicine?
- How do we assess the performance and clinical impact of machine learning models?
- How to read a medical machine learning paper
- How can you combine machine learning with a medical career?
I’ve been making and tweaking this content for almost two years. Each video is short, snappy and gives you just enough info without overwhelming you.
I know you’re busy so I don’t want you to waste time making notes. I’ve created a PDF summary of the course, which you can download at the bottom of this page.
All the course and its contents are free. If you want to support me in making future free resources, you can buy me a coffee.
I hope this course sets you on the journey. Healthcare needs more machine learning medics.
So let’s get started. What exactly is machine learning… and what has it got to do with medicine?
1. Course Overview. Why learn about AI and Machine Learning?
In this video, I outline the course on machine learning for healthcare, and share my top two reasons why medical professionals should learn machine learning.
2. What is Machine Learning and why Healthcare?
In this video, we cover different elements of machine learning and why it's well-suited to disrupting healthcare.
3. How does a machine learning model learn?
In this video, we talk about different ways machine learning models ‘learn’, including the 'gradient descent' approach (which underlies much of the recent excitement). We also look at the difference between supervised and unsupervised learning.
4. What happens in a neural network (with medical examples)?
In this video, we go inside a neural network and understand how it works, and why it's such a powerful machine learning algorithm. We build intuition by looking at medical examples.
5. What is deep learning and how will it change healthcare?
In this video we cover the two main types of deep learning algorithm; convolutional and recurrent neural networks. We gain intuition for how they work and explore how they're being used in healthcare.
6. How to assess the performance of machine learning models
In this video, we look at how the performance of machine learning models can be measured. We cover the confusion matrix, F1 score, AUC and metrics for regression.
7. How to ensure a positive clinical impact with machine learning models
In this video, we talk about important considerations for translating a good model into a good clinical outcome. We discuss the different levels of clinical evidence required.
8. How to read a machine learning paper
In this video, I share a framework for reading machine learning for healthcare papers. We look at how reading papers is useful for building up understanding and keeping up-to-date with the field.
9. Next steps for getting started and recommended resources
In this video, I share my thoughts about how best to get started with machine learning as a healthcare professional. I answer common questions such as “should I learn to code?” and “how much maths do I need to know?” as well as sharing resources for next steps.
LINKS AND SUGGESTED RESOURCES
From this course:
Other useful resources:
- Luke Oakden-Rayner's blog - Great deep-dives into different aspects of ML being applied to healthcare
- TowardsDataScience.com (Medium publication) – limit search by ‘healthcare’ or similar terms to find relevant article
- “Deep Medicine: How AI can make healthcare human again” by Dr Eric Topol – a book taking a broad consideration of AI applications in healthcare
Learn to code:
- Course on Coding for Medicine
- Machine learning basics in Python – python codes of basic machine learning algorithms, to help provide an understanding of the algorithms and their underlying structure. For those familiar with Python.
I hope you enjoyed the course! If you want to support me in making further free content, you can buy me a coffee.