A multi-disciplinary team of researchers has developed a strategy to monitor the progression of movement disorders using motion capture technology and AI.

In two ground-breaking studies, published in Nature Medicine, a cross-disciplinary team of AI and clinical researchers have shown that by combining human movement data gathered from wearable tech with a robust latest medical AI technology they can discover clear movement patterns, predict future disease progression and significantly increase the efficiency of clinical trials in two very different rare disorders, Duchenne muscular dystrophy (DMD) and Friedreich’s ataxia (FA).

DMD and FA are rare, degenerative, genetic diseases that affect movement and eventually result in paralysis. There are currently no cures for either disease, but researchers hope that these results will significantly speed up the search for brand new treatments.

Tracking the progression of FA and DMD is generally done through intensive testing in a clinical setting. These papers offer a significantly more precise assessment that also increases the accuracy and objectivity of the information collected.

The researchers estimate that using these disease markers mean that significantly fewer patients are required to develop a latest drug in comparison to current methods. This is especially essential for rare diseases where it could actually be hard to discover suitable patients.

Scientists hope that in addition to using the technology to watch patients in clinical trials, it could also sooner or later be used to watch or diagnose a variety of common diseases that affect movement behaviour comparable to dementia, stroke and orthopaedic conditions.

Senior and corresponding creator of each papers, Professor Aldo Faisal, from Imperial College London’s Departments of Bioengineering and Computing, who can be Director of the UKRI Centre for Doctoral Training in AI for Healthcare, and the Chair for Digital Health on the University of Bayreuth (Germany), and a UKRI Turing AI Fellowship holder, said: “Our approach gathers huge amounts of information from an individual’s full-body movement – greater than any neurologist could have the precision or time to watch in a patient. Our AI technology builds a digital twin of the patient and allows us to make unprecedented, precise predictions of how a person patient’s disease will progress. We imagine that the identical AI technology working in two very different diseases, shows how promising it’s to be applied to many diseases and help us to develop treatments for a lot of more diseases even faster, cheaper and more precisely.”

The 2 papers highlight the work of a big collaboration of researchers and expertise, across AI technology, engineering, genetics and clinical specialties. These include researchers at Imperial’s Department of Bioengineering and Department of Computing, the MRC London Institute of Medical Sciences (MRC LMS), the UKRI Centre in AI for Healthcare, UCL Great Ormond Street Institute for Child Health (UCL GOS ICH), the NIHR Great Ormond Street Hospital Biomedical Research Centre (NIHR GOSH BRC), Imperial College London, Ataxia Centre at UCL Queen Square Institute of Neurology, Great Ormond Street Hospital the National Hospital for Neurology and Neurosurgery, the National Hospital for Neurology and Neurosurgery (UCLH and UCL/UCL BRC), the University of Bayreuth in Germany and the Gemelli Hospital in Rome, Italy.

Movement fingerprints – the trials intimately

Within the DMD-focused study, researchers and clinicians at Imperial College London, Great Ormond Street Hospital and University College London trialled the body worn sensor suit in 21 children with DMD and 17 healthy age-matched controls. The kids wore the sensors while carrying out standard clinical assessments (just like the 6-minute walk test) in addition to going about their on a regular basis activities like having lunch or playing.

Within the FA study, teams at Imperial College London and the Ataxia Centre, UCL Queen Square Institute of Neurology worked with patients to discover key movement patterns and predict genetic markers of disease. FA is essentially the most common inherited ataxia and is brought on by an unusually large triplet repeat of DNA, which switches off the FA gene. Using this latest AI technology, the team were capable of use movement data to accurately predict the ‘switching off’ of the FA gene, measuring how lively it was without the necessity to take any biological samples from patients.

The team were capable of administer a rating scale to find out level of disability of ataxia SARA and functional assessments like walking, hand/arms movements (SCAFI) in 9 FA patients and matching controls. The outcomes of those validated clinical assessments were then compared with the one obtained from using the novel technology on the identical patients and controls. The latter showing more sensitivity in predicting disease progression.

In each studies, all the information from the sensors was collected and fed into the AI technology to create individual avatars and analyse movements. This vast data set and powerful computing tool allowed researchers to define key movement fingerprints seen in children with DMD in addition to adults with FA, that were different within the control group. Lots of these AI-based movement patterns had not been described clinically before in either DMD or FA.

Scientists also discovered that the brand new AI technique could also significantly improve predictions of how individual patients’ disease would progress over six months in comparison with current gold-standard assessments. Such a precise prediction allows to run clinical trials more efficiently in order that patients can access novel therapies quicker, and in addition help dose drugs more precisely.

Smaller numbers for future clinical trials

This latest way of analysing full-body movement measurements provide clinical teams with clear disease markers and progression predictions. These are invaluable tools during clinical trials to measure the advantages of recent treatments.

The brand new technology could help researchers perform clinical trials of conditions that affect movement more quickly and accurately. Within the DMD study, researchers showed that this latest technology could reduce the numbers of youngsters required to detect if a novel treatment could be working to 1 / 4 of those required with current methods.

Similarly, within the FA study, the researchers showed that they might achieve the identical precision with 10 of patients as a substitute of over 160. This AI technology is very powerful when studying rare diseases, when patient populations are smaller. As well as, the technology allows to check patients across life-changing disease events comparable to lack of ambulation whereas current clinical trials goal either ambulant or non-ambulant patient cohorts.

Writer quotes

Co-author on each studies Professor Thomas Voit, Director of the NIHR Great Ormond Street Biomedical Research Centre (NIHR GOSH BRC) and Professor of Developmental Neurosciences at UCL GOS ICH, said:”These studies show how revolutionary technology can significantly improve the best way we study diseases day-to-day. The impact of this, alongside specialised clinical knowledge, won’t only improve the efficiency of clinical trials but has the potential to translate across an enormous number of conditions that impact movement. It’s because of collaborations across research institutes, hospitals, clinical specialities and with dedicated patients and families that we are able to start solving the difficult problems facing rare disease research.”

Joint first creator on each studies, Dr Balasundaram Kadirvelu, post-doctoral researcher at Imperial College London’s Departments of Computing and Bioengineering, said “We were surprised to see how our AI algorithm was capable of spot some novel ways of analysing human movements. We call them ‘behaviour fingerprints’ because similar to your hand’s fingerprints allow us to discover an individual, these digital fingerprints characterise the disease precisely, regardless of whether the patient is in a wheelchair or walking, within the clinic doing an assessment or having lunch in a café.”

Joint first creator on the DMD study and co-author on the FA study, Dr Valeria Ricotti, honorary clinical lecturer on the UCL GOS ICH said: “Researching rare conditions will be substantially more costly and logistically difficult, which suggests that patients are missing out on potential latest treatments. Increasing the efficiency of clinical trials gives us hope that we are able to test many more treatments successfully.”

Co-author Professor Paola Giunti, Head of UCL Ataxia Centre, Queen Square Institute of Neurology, and Honorary Consultant on the National Hospital for Neurology and Neurosurgery, UCLH, said: “We’re thrilled with the outcomes of this project that showed how AI approaches are actually superior in capturing progression of the disease in a rare disease like Friedreich’s ataxia. With this novel approach we are able to revolutionise clinical trial design for brand new drugs and monitor the results of already existing drugs with an accuracy that was unknown with previous methods.”

“The big variety of FA patients who were thoroughly characterised each clinically and genetically on the Ataxia Centre UCL Queen Square Institute of Neurology along with our crucial input on the clinical protocol has made the project possible. We’re also grateful to all our patients who participated on this project.”

Co-author of each studies Professor Richard Festenstein, from the MRC London Institute of Medical Sciences and Department of Brain Sciences at Imperial College London said: “Patients and families often wish to understand how their disease is progressing, and motion capture technology combined with AI could help to offer this information. We’re hoping that this research has the potential to remodel clinical trials in rare movement disorders, in addition to improve diagnosis and monitoring for patients above human performance levels.”

The research was funded by a UKRI Turing AI Fellowship to Professor Faisal, NIHR Imperial College Biomedical Research Centre (BRC), the MRC London Institute of Medical Sciences, the Duchenne Research Fund, the NIHR Great Ormond Street Hospital (GOSH) BRC, the UCL/UCLH BRC, and the UK Medical Research Council.

Source:

Journal reference:

Kadirvelu, B., et al. (2023) A wearable motion capture suit and machine learning predict disease progression in Friedreich’s ataxia. Nature Medicine. doi.org/10.1038/s41591-022-02159-6.