Cookies on this website

We use cookies to ensure that we give you the best experience on our website. If you click 'Accept all cookies' we'll assume that you are happy to receive all cookies and you won't see this message again. If you click 'Reject all non-essential cookies' only necessary cookies providing core functionality such as security, network management, and accessibility will be enabled. Click 'Find out more' for information on how to change your cookie settings.

In this blog, Dr Tom Fanshawe, course lead on our new accredited short course, Clinical Prediction Rules, details how clinical prediction rules can be applied to improve health care, and how the course aims to teach all aspects of studies from design and model development to interpretation and validation.

Law gavel stethoscope Health care business rules © Shutterstock

What is your risk of currently having undiagnosed cancer, or developing cardiovascular disease in the next 10 years? What about your risk of side effects when receiving a particular treatment, or experiencing serious complications after surgery?

These are just some of the many questions that can be answered with the use of clinical prediction rules. Clinical prediction rules, also known as “prediction algorithms” or “prediction models”, have become increasingly prominent over the past two years and are frequently mentioned in the media. In reality clinical prediction rules have been in use much longer than that, and have a range of applications across many different areas of medicine.

Why have clinical prediction rules become so popular?

An important factor is that we currently live in the era of “big data”, and large, routinely collected datasets that are very rich in information can provide plenty of scope for developing new prediction rules. This in combination with increased computational power has created a very good opportunity for this field to quickly develop and evolve.

But what exactly are clinical prediction rules, and how they can actually help?

In simple terms, a clinical prediction rule is a mathematical equation which combines different characteristics to assess the probability of a particular event happening – such as a patient developing a certain condition in the future. These characteristics can include a variety of information, ranging from basic demographic characteristics to previous medical conditions and treatments. A clinical prediction rule combines all these pieces of information to provide an individualised assessment, which can then inform clinical decision-making.

Generating a clinical prediction rule is however a complex process, which involves many steps and contains many hidden traps. For this reason a new course, Clinical Prediction Rules, will run as a new accredited short course in May 2022.

What does this short course cover?

This course will cover all aspects of clinical prediction rule studies, from design and model development to interpretation and validation. By the end of the course, students will have acquired knowledge of the key concepts relevant to each of these areas, and should be confident to conduct a clinical prediction rule study themselves and appraise existing clinical prediction rules in the medical literature.

This course will be led by Dr. Tom Fanshawe and Dr. Constantinos Koshiaris, supported by other teaching and research staff from the Nuffield Department of Primary Care Health Sciences.

How can I apply?

Clinical Prediction Rules will run as an accredited short course in May 2022. It will also be available for students joining the MSc in EBHC Medical Statistics in 2022/23, and so provides an ideal stepping-stone for students who are considering applying to that programme.

For more information and to apply, visit: Clinical Prediction Rules | Oxford University Department for Continuing Education

To start your application now, click here: Short Course Application Form Department for Continuing Education, University of Oxford

Pleas note: The last date for receipt of complete applications is 5pm Friday 18th March 2022. Regrettably, late applications cannot be accepted.