Taking a cue from motion capture, researchers have developed an algorithm that can also increase the effectiveness of clinical trials
A multidisciplinary team of researchers from the UK, Germany and Italy have developed a way to monitor the progression of movement disorders using the technology of motion capture (the technology that records the movement of people or objects through wearable sensors, widely used in the film industry) and artificial intelligence (AI).
In two studies, published in nature medicinean interdisciplinary team of AI and clinical researchers (including researchers from Imperial College and University College London; Policlinico Gemelli in Rome; University of Bayreuth in Germany) demonstrated that combining data on human movement collected by wearable technology with a new powerful medical AI technology, they are able to identify clear movement patterns, predict future disease progression and significantly increase the efficiency of clinical trials in two very different rare diseases, Duchenne muscular dystrophy (DMD) and Friedreich’s ataxia (FA).
“These are two very innovative studies because the algorithm that was developed in the research allows for a more sophisticated analysis of movement and offers an advanced tool in evaluating the efficacy of the most modern gene therapies at our disposal”, he explains Eugene Mercuri, full professor at the Catholic University of Rome and director of the Child Neuropsychiatry Operations Unit at the Gemelli Polyclinic as well as scientific director of the Nemo Pediatric Center at the hospital. The research involves two other Italian experts who studied in the UK and then stayed there: Valeria Ricotti honorary clinical lecturer at UCL GOS ICH, e Paola Giunti, Head of the UCL Ataxia Centre, Queen Square Institute of Neurology and Honorary Consultant at the National Hospital for Neurology and Neurosurgery, UCLH.
DMD and AF are rare genetic diseases, degenerative, affecting movement and eventually leading to paralysis.
There is currently no cure for either disease
but especially for Duchenne dystrophy there are numerous ongoing clinical trials including those of gene therapy.
The researchers hope these findings will significantly speed up the way we evaluate the efficacy of these new treatments. Monitoring the progression of AF and DMD is usually done through intensive testing in a clinical setting.
The two new studies offer a significantly more precise assessment that also increases the accuracy and objectivity of the data collected. The researchers estimate that using these disease markers means that significantly fewer patients are required to develop a new drug than current methods. This is especially important for rare diseases where it can be difficult to identify suitable patients.
Scientists hope that in addition to using the technology to monitor patients in clinical trials, may one day also be used to monitor or diagnose a number of common diseases affecting movement behavior such as dementia, stroke and orthopedic conditions.
“Our approach collects huge amounts of data from the movement of a person’s whole body, more than any neurologist will have the precision or time to observe in a patient,” explains the Professor Aldo Faisal, lead author of both studies, Departments of Bioengineering and Computer Science at Imperial College London, who is also Director of the UKRI Center for Doctoral Training in AI for Healthcare, and Chair for Digital Health at the University of Bayreuth (Germany ), holder of the UKRI Turing AI Fellowship —. Our AI technology creates a digital twin of the patient and allows us to make unprecedented and accurate predictions about how an individual patient’s disease will progress. We believe the same AI technology works in two very different diseasesshows how promising it is to be applied to many diseases, and helps us develop treatments for many more diseases even faster, cheaper and more precisely.”
«Patients and families often want to know how their disease is progressing and motion capture technology combined with artificial intelligence could help deliver this information. We hope this research has the potential to transform clinical trials into rare movement disorders, as well as improve diagnosis and monitoring for patients above human performance levels,” Professor points out. Richard Festenstein from the MRC London Institute of Medical Sciences and Imperial’s Department of Brain Sciences, who co-authored both studies.
In the one focusing on DMD, researchers and doctors from Imperial College London, Great Ormond Street Hospital and University College London tested a sensor suit worn by 21 children with DMD and 17 other children as age-matched “healthy controls”. The children wore the sensors during standard clinical assessments (such as the 6-minute walk test) and during their daily activities such as eating lunch or playing. In the FA study, teams from Imperial College London and the Ataxia Centre, UCL Queen Square Institute of Neurology worked with patients to identify key movement patterns and predict genetic markers of disease. FA is the most common hereditary ataxia and is caused by an unusually large DNA triplet that turns off the FA gene.
Using this new AI technology, the team was able to use movement data to accurately predict FA gene ‘switch-off’, measuring its activity without the need to take biological samples from patients. The team was able to administer a rating scale to determine the level of SARA ataxia disability and functional assessments such as walking, hand/arm movements (SCAFI) in 9 AF patients and matched controls. The results of these validated clinical evaluations were then compared with those obtained using the new technology on the same patients and controls. The latter shows greater sensitivity in predicting disease progression.
«Fingerprints» of movements
In both studies, all sensor data was collected and fed into AI technology for create individual avatars and analyze movements. This vast data set and this powerful computer tool have allowed researchers to define fingerprints of key movements observed in children with DMD and adults with FA, which were different in the control group. Many of these AI-based movement patterns had not been clinically described before in either DMD or FA.
Scientists also discovered that the new artificial intelligence technique could too significantly improve predictions of how individual patients’ disease will progress over six months compared to the current ‘gold standard’ valuations. Such an accurate forecast allows you to run clinical trials more efficiently so that patients can access new therapies more quickly and also help to dose medications more precisely.
Smaller numbers for future clinical trials
This new way of analyzing whole-body motion measurements provides clinical teams clear disease markers and predictions of progression; invaluable tools during clinical trials to measure the benefits of new treatments. The new technology could help researchers conduct clinical studies of conditions that affect movement faster and more accurately.
In the DMD study, researchers demonstrated that this new technology could reduce the number of children needed to detect whether a new treatment would work to a quarter of those required with current methods. Similarly, in the FA study, the researchers showed they could achieve the same accuracy with 10 patients instead of over 160. This AI technology is especially powerful when studying rare diseases, when patient populations are smaller. Furthermore, technology makes it possible to study patients through life-changing pathological eventssuch as loss of ambulation, while current clinical trials target cohorts of ambulant or non-ambulant patients.
«Rare disease research can be substantially more expensive and logistically challenging, which means patients are missing out on potential new treatments. Increasing the efficiency of clinical trials gives us hope to successfully test many more treatments,” he says Valeria Ricotti, joint first author of the DMD study and co-author of the AF study. “We are thrilled with the results of this project which have shown that AI approaches are certainly superior in capturing disease progression in a rare disease such as Friedreich’s ataxia. With this new approach we can revolutionize clinical trial design for new drugs and monitor the effects of existing drugs with a precision unknown with the previous method», adds Paola Giunti co-author.
March 18, 2023 (change March 18, 2023 | 08:47)
© REPRODUCTION RESERVED
#Duchenne #muscular #dystrophy #ataxia #symptoms #life #expectancy #artificial #intelligence