Skip main navigation

Learn about current uses of AI in healthcare

Choose from a selection of case studies illustrating how AI can impact healthcare, it includes paediatric cancer, osteoporosis and bipolar disorder.
ball point pen paper and stethoscope

In this step, we will explore some current uses of AI in healthcare with conditions such as paediatric cancer, osteoporosis and bipolar disorder. We will begin with two case studies on paediatric cancer.

Paediatric Brain Tumour Case Studies

Catherine Pringle is a Neurosurgery Specialist Registrar, Health Education North West and she is currently doing her PhD on Paediatric Brain Tumour patients treated at Royal Manchester Children’s Hospital and she introduces two case studies where AI is being used.

Paediatric brain tumour patients present a high dimensional data problem in that they are a relatively small clinical patient cohort but each patient is accompanied by a feature-rich and deep data set.

This means that:

  • generating accurate survival outcomes and risk stratification is difficult;
  • traditional statistical analysis methods are not often accurate when tasked with these data sets;
  • the overwhelming volume of data can be prohibitive to accurate human decision making.

Paediatric Cancer – Improving Diagnosis

A project completed by my supervisory team which includes Professor Stavros Stivaros (paediatric neuroradiology), Professor John-Paul Kilday (paediatric neuro-oncology) and Professor Ian Kamaly-Asl (paediatric neurosurgery) has successfully classified molecular sub-groups of Atypical Teratoid Rhabdoid Tumours (ATRTs) which are rare and aggressive brain tumours predominantly affecting children) through language modelling and Random Forest Techniques. It discovered three discrete ATRT biological subgroups, and their associated survival profiles, had discrete tumour location, contrast enhancement and diffusion patterns on MRI.

Paediatric Cancer – Improving Care

We are currently investigating whether artificial intelligence techniques can be harnessed to improve the following two elements of paediatric brain tumour patients’ care. Firstly, we are investigating whether non-invasive diagnosis from advanced metric MRI brain scans can be optimised at the time of presentation. Secondly, we are looking whether artificial intelligence models can be applied to the histological, biological and clinical data that accompanies advanced MRI scans in order to improve outcome prediction and risk stratification of paediatric brain tumour patients, on an individual basis.

Providing, accurate, bespoke outcome predictions at the time of presentation will provide patients and their patents with invaluable information during a very challenging period.

More Case Studies

The following case studies give an overview of each one and have links to where they will go into more depth throughout the course:

The MOBILISE Project

David Jenkins is a Research Associate at The University of Manchester and also a statistician at the NIHR Greater Manchester Patient Safety Translational Research Centre. The MOBILISE Project aims to recognise a person at risk from bipolar before they ever have a manic episode through the use of statistical algorithms on real-world health data to identify important factors that will influence whether someone goes on to get bipolar. This case study starts in Week 3 here.

STOpFrac Project

Paul Bromiley is a Lecturer in Health Data Sciences at The University of Manchester. Paul works on a project called STOpFrac, which focusses on osteoporosis, a disease that makes a patient’s bones weaker and causes them to suffer from fractures. In clinical practice, this disease is underdiagnosed. This project is using AI systems to help radiologists identify and diagnose these fractures on existing patient images to make the process of identifying and reporting osteoporosis more efficient so that patients with the disease can be diagnosed earlier to reduce the chances they will go on to suffer serious compromising fractures in the future. This case study starts in Week 3 here.

AI in Cancer Care

Rhidian Bramley works for The Christie NHS Foundation Trust in Manchester. He talks to us about how AI is being embedded into existing workflows to transform health care services and improve patient care. He also talks about the importance of getting healthcare data into the correct format to use in an AI workflow and the challenges around training the workforce in these new skills. This case study starts in Week 3 here.

Facial recognition software

Tim Cootes is a Professor of Computer Vision at The University of Manchester. His research focusses on developing techniques for extracting useful information from images, specifically face recognition. Facial recognition is a piece of computer technology for trying to identify who somebody is in an image, and it can be broken down into two different areas – face verification and face recognition. This case study starts in Week 4 here.

Citizen juries

Lamiece Hassan is a Health Services Researcher based at The University of Manchester with a background in Psychology. Her research looks at how different sources of data about health can be used and linked to improving health, and what patients and the public think about this.T his case study starts in Week 4 here.

© The University of Manchester
This article is from the free online

AI for Healthcare: Equipping the Workforce for Digital Transformation

Created by
FutureLearn - Learning For Life

Reach your personal and professional goals

Unlock access to hundreds of expert online courses and degrees from top universities and educators to gain accredited qualifications and professional CV-building certificates.

Join over 18 million learners to launch, switch or build upon your career, all at your own pace, across a wide range of topic areas.

Start Learning now