An interdisciplinary research team has developed a method for monitoring the progression of movement disorders using motion capture technology and artificial intelligence.
In two groundbreaking studies published in the journal Nature Medicine, an interdisciplinary team of artificial intelligence and clinical researchers showed that by combining human movement data collected from wearable devices with powerful new artificial intelligence medical techniques, they were able to identify clear movement patterns, predict future disease progression and greatly improve clinical trial performance for two very different rare diseases, Duchenne muscular dystrophy (DMD) and Friedreich’s ataxia (FA).
DMD and FA are rare degenerative genetic diseases that affect mobility and eventually lead to paralysis. None of these diseases currently have a cure, but the researchers hope the findings will greatly accelerate the search for new treatments.
Tracking the progression of FA and DMD is usually done through intensive clinical testing. These documents provide a more accurate assessment, as well as improve the accuracy and objectivity of the collected data.
The researchers estimate that the use of these disease markers will mean that much fewer patients will be needed to develop new drugs than existing approaches. This is especially important for rare diseases where it is difficult to identify suitable patients.
In addition to using the technology to monitor patients in clinical trials, the scientists hope that it could one day be used to monitor or diagnose a number of common conditions that affect movement behavior, such as dementia, stroke and orthopedic disorders.
The senior author and corresponding author of both articles is Professor Aldo Faisal of the Faculty of Bioengineering and Computing at Imperial College London, who is also Director of the UKRI Center for Doctoral Studies in Medical Artificial Intelligence and the Department of Digital Health at the University of Bayreuth. (Germany) and recipient of the UKRI Turing AI Fellowship said: “Our method collects a huge amount of data on the movements of the entire human body – more than any neuroscientist has ever observed in a patient with accuracy or time.” a digital twin of the patient, which allows us to make unprecedentedly accurate predictions of the development of the disease in an individual patient. We believe that the same AI technology works for two very different diseases, demonstrating its usefulness.” How promising it is for many diseases and helping us develop treatments for many other diseases faster, cheaper and more accurately.”
The two papers highlight the extensive collaboration of researchers and experts in artificial intelligence technologies, engineering, genetics and clinical specialties. These include Imperial College London, UKRI Center for Artificial Intelligence in Healthcare, MRC Institute of Medical Sciences London (MRC LMS), UCL Great Ormond Street Institute of Child Health (UCL GOS ICH), NIHR Great Ormond Street Hospital (NIHR GOSH) Center for Biomedical Research. BRC), UCL Queen Square Neurological Institute Ataxia Center, Great Ormond Street Hospital, National Hospital for Neurology and Neurosurgery (UCLH and UCL/UCL BRC), University of Bayreuth, Rome, Italy, Gemelli Hospital and NIHR Imperial College Research Center.
Co-author of both studies, Prof Richard Festenstein of the MRC Institute of Medical Sciences London and Imperial College’s Department of Brain Sciences, said: “Patients and families often want to know how their disease is progressing, and motion capture technology combined with artificial intelligence can help.” . This information has been provided. We hope this study can change the clinical testing of rare movement disorders and improve the diagnosis and monitoring of patients with above-human performance levels.”
In a DMD study, researchers and clinicians from Imperial College London, Great Ormond Street Hospital and University College London tested the wearable device on 21 children with DMD and 17 healthy healthy adults of the same age. Children wear sensors during routine clinical examinations, such as the 6-minute walk test, and during daily activities, such as lunch or play.
In the FA study, teams from Imperial College, the Ataxia Centre, the UCL Queen Square Institute of Neurology and the MRC Institute for Medical Sciences of London worked with patients to identify key movement patterns and predict genetic markers of the disease. FA, the most common hereditary ataxia, is caused by an abnormally large DNA triple repeat that turns off the FA gene. Using this new AI technique, the team was able to use motion data to accurately predict the “turn off” of the FA gene by measuring its activity without taking any biological samples from the patient.
The team was able to introduce a rating scale for SARA ataxia disability and functional assessments such as ambulation, hand/arm movement (SCAFI) in nine FA patients and their respective controls. The results of these validated clinical assessments are then compared with those obtained using the new technique in the same patients and controls. The latter showed higher sensitivity in predicting disease progression.
In both studies, all sensor data was collected and fed into artificial intelligence technology to create personal avatars and analyze movements. This large dataset and powerful computational tools allowed the researchers to identify key motor fingerprints seen in children with DMD as well as in adults with FA that differed in the control group. Many of these AI-based motor patterns have not previously been described clinically in DMD or FA.
The scientists also found that the new AI method could also significantly improve predictions of how an individual patient’s disease will progress over a six-month period, compared to the current gold standard of assessment. Such accurate predictions enable more efficient clinical trials, giving patients faster access to new treatments, and can also help with more accurate drug delivery.
This new whole-body movement analysis method provides medical teams with clear disease markers and progression predictions. These are valuable tools for measuring the benefits of new treatments during clinical trials.
The new technique could help researchers conduct clinical trials of conditions that affect movement faster and more accurately. In the DMD study, researchers showed that the new technique could cut the number of children needed to test the effectiveness of a new treatment to just a quarter of the number required by current methods.
Similarly, in the FA study, the researchers showed that they could achieve the same accuracy with 10 patients instead of more than 160. This AI method is especially effective in studying rare diseases when the number of patients is small. In addition, the technology makes it possible to study patients during life-changing illnesses, such as the inability to walk, while current clinical trials target outpatient or non-ambulatory patient populations.
Co-author of both studies, Professor Thomas Voight, Director of the NIHR Great Ormond Street Biomedical Research Center (NIHR GOSH BRC) and UCL GOS ICH Professor of Neuroscience, said: “These studies show how innovative technologies can dramatically improve the way we work every day. diseases. Its consequences, as well as specialized clinical knowledge, will not only increase the effectiveness of clinical trials, but can also lead to various conditions that affect exercise. Through collaboration between research institutes, hospitals, clinical specialties and with dedicated patients and working together as a family, we can begin to address the complex challenges facing rare disease research.”
Dr. Balasundaram Kadirvelu, researcher at Imperial’s Department of Computing and Bioengineering and co-author of both studies, said: “We were surprised to see that our AI algorithm was able to discover some new ways to analyze human movements. “behavioral fingerprints” because, just as your fingerprints allow us to identify a person, these digital fingerprints can accurately characterize an illness, whether the patient is in a wheelchair or walking, being examined at a clinic, or having lunch at a hospital coffee shop.”
DMD study co-author and FA study co-author, Dr Valeria Ricotti, GOS ICH Honorary Clinical Lecturer at University College London, said: “The cost and logistical challenges of studying rare diseases are much higher, meaning patients are missing out on potential new treatments. Increasing the efficiency of clinical trials gives us hope that we will be able to successfully test many more treatments.”
Co-author Prof. Paola Giunti, Head of the UCL Ataxia Center, Queen Square Institute of Neurology and Honorary Consultant, National Hospital for Neurology and Neurosurgery, UCL Hospital, said: “We are delighted with the results of this project, which demonstrates how close artificial intelligence is to being confident that it better captures the progression of the disease in such a rare disease as Friedreich’s ataxia. With this new approach, we can revolutionize the design of clinical trials for new drugs and replace them with previous methods.” effects of existing drugs with unknown accuracy”.
“In addition to our significant contribution to the clinical program, the large number of FA patients at UCL’s Queen Square Neurology Institute at the Ataxia Center have an excellent clinical and genetic profile, making this project possible. We are also grateful to everyone. patients involved in the project.
The study was funded by the UKRI Turing Fellowship in Artificial Intelligence, Professor Faisal, NIHR Imperial College (BRC) Biomedical Research Centre, MRC London Institute of Medical Sciences, Duchenne Research Foundation, NIHR Great Ormond Street Hospital (GOSH) BRC, University College London. /UCLH BRC and UKRI Medical Research Council.
“Wearable whole-body tracking in daily life predicts disease trajectory in Duchenne muscular dystrophy,” Ricotti et al., January 19, 2023, Nature Medicine.
“Wearable motion capture suit and machine learning predict disease progression in Friedreich’s ataxia,” Kadirvelu et al., January 19, 2023, Nature Medicine.
Photographs and graphics copyrighted by third parties are used with permission from or © Imperial College London.
Engineering – Bioengineering, Engineering – Computing, Drug Discovery, Pharmaceuticals, Global Issues – Health & Wellness, Communications – Strategy – Real World – Benefits, Global Issues – Engineering, Engineering – Artificial Intelligence & Machine Learning, Big Data, Imaging, Children’s Health, healthcare , Artificial intelligence, Strategy – sharing miracles, Strategy – interdisciplinary – Research, Research, Strategy – Collaboration, REF
Unless you request otherwise, your comment may be published under the name you provide. Your contact details will never be made public.
Main Campus Address: Imperial College London South Kensington Campus, London SW7 2AZ Tel: +44 (0)20 7589 5111 Campus maps and information | About this site | This site uses cookies | Report Invalid Content | To come in
Post time: Apr-12-2023