Every day, health professionals use their intelligence to solve problems. But could computers carry out some of this brain work, or even go further? Research on artificial intelligence (AI) in healthcare, taking place across Imperial College London, sets out to answer this question. It involves close collaborations between medical science, computing, and engineering in order to devise innovative approaches that satisfy the high standards required when dealing with people’s health.

" />

Researchers developing AI to solve healthcare challenges

AI_Williams

Every day, health professionals use their intelligence to solve problems. But could computers carry out some of this brain work, or even go further? Research on artificial intelligence (AI) in healthcare, taking place across Imperial College London, sets out to answer this question. It involves close collaborations between medical science, computing, and engineering in order to devise innovative approaches that satisfy the high standards required when dealing with people’s health.

Some of these research projects aim to automate or optimise what a doctor can do, for example when interpreting medical images to produce a diagnosis. But others plan to go further, creating systems that continuously monitor patients, tracking developments in their health.

Signatures in movement

One of these involves ethomics, an approach that makes deductions about a person’s health by closely watching how they behave. “Anything that affects your brain, your nervous system or your physiology will have a signature in your movement behaviour,” explains Dr Aldo Faisal, whose group straddles the Departments of Computing and Bioengineering.

He calls these signatures ‘ethomic’ biomarkers, a reference to ethology, the science of animal behaviour. They can be seen and monitored by measuring someone’s movement behaviour at a very high resolution and applying novel computer algorithms to the data produced.

“We have developed, patented and published a whole range of completely novel ethomic biomarkers that allows us to detect disease progression much faster and much more precisely than was possible before, especially in the area of degenerative diseases.”

These conditions are particularly challenging because their progress can be slow, subtle and hard to measure. This not only delays decisions about treatment, but also the development of new therapies, since it can take years for a positive effect in a clinical trial to be confirmed. Using ethomic biomarkers speeds up the process. “We have been able reduce the amount of time it takes to run a clinical trial by 50%,” Dr Faisal says.

Reading a walk

Movement is also the key to BrainWear, a system for assessing the progress of brain tumours, which is being developed and trialled by Dr Matthew Williams, a researcher within the NIHR Imperial BRC Cancer Theme. He leads the Computational Oncology Group at Imperial, which connects the Departments of Computing, and Surgery and Cancer.

“The underlying idea is that there is a close link in the brain between location and function,” he explains. “As a brain tumour gets bigger, it is likely to affect function in different ways. Some tumours might affect speech, some might affect walking, some might affect other functions.”

Movement is measured with a wrist accelerometer that gathers data in three dimensions, 100 times a second. Unlike a commercial fitness tracker, which reduces motion data to a simple measure such as the number of steps taken, the BrainWear monitor produces a huge amount of raw data for the AI to work with.

“We don’t just want to measure how much you are walking, but how you are walking,” Dr Williams says. “So we apply deep learning to that data to pick out significant features of someone’s gait, to establish what is normal and recognise changes that are down to the disease.”

Meanwhile, factoring in the patient’s treatment should make it possible to rule out changes due to ongoing therapy. “We are now at the stage of collecting data from patients and carers, and looking at what that can tell us.” Ultimately the goal is to integrate different sources of data, such as fatigue, quality of life and activity, to provide a coherent picture of the patient over time.

Learn more

For a deeper dive into Imperial’s research on the topic, view the Enterprise long-read on AI in healthcare.

This covers projects involving foetal ultrasound, heart and lung health, cancer diagnosis, intensive care, and healthcare scheduling, along with plans for the recently established UKRI Centre for Doctoral Training in Artificial Intelligence for Healthcare.

To find out more about how Imperial connects its research with industry challenges, visit the Enterprise home page.

This news story was written by Ryan O’Hare, and is © Imperial College London.

More stories from Cancer, Informatics & Biobanking, Surgery & Technology