A multidisciplinary team of researchers has developed a method to monitor the progression of movement disorders using motion capture technology and AI.
In two groundbreaking studies published in Nature Medicine, a multidisciplinary team of AI and clinical researchers combined human movement data gleaned from wearable technology with powerful new medical AI techniques to create clear showed that it was possible to identify distinct movement patterns. Predict future disease progression in two very different rare diseases, Duchenne muscular dystrophy (DMD) and Friedreich’s ataxia (FA), and greatly improve the efficiency of clinical trials.
“Our approach collects an enormous amount of data from a patient’s whole-body movements, which is more than the precision and time a neurologist observes a patient with.” Professor Aldo Faisal Department of Biotechnology and Computing at Imperial College London
DMD and FA are rare degenerative genetic diseases that affect locomotion and ultimately lead to paralysis. There is currently no cure for either disease, but researchers hope these results will greatly speed up the search for new treatments.
Tracking the progress of FA and DMD is typically done through intensive testing in a clinical setting. These papers provide much more accurate assessments that also improve the accuracy and objectivity of the data collected.
The researchers estimate that using these disease markers means that significantly fewer patients are needed to develop new drugs compared to current methods. This is especially important for rare diseases where it is difficult to identify suitable patients.
Scientists aren’t just using this technology to monitor patients in clinical trials, but one day a variety of common conditions that affect motor behavior, such as dementia, stroke, and orthopedic conditions. I hope it can also be used for monitoring or diagnosing
Professor Aldo Faisal, Department of Biotechnology and Computing, Imperial College London, is senior and lead author of both papers, and is also Director of the UKRI Center for PhD Training in AI for Healthcare and of the University of Bayreuth. Also Chair of Digital Health (Germany), and UKRI Turing AI Fellowship Holder said: Our AI technology builds a patient’s digital twin, enabling unprecedentedly accurate predictions of how an individual patient’s disease will progress. It shows how the same AI technology, which works for two very different diseases, has the potential to be applied to many diseases, making it faster, cheaper and easier to treat many diseases. I believe it will help you develop accurately. ”
The two papers highlight the results of a large-scale collaboration of researchers and expertise across AI technology, engineering, genetics, and clinical specialties. Imperial Bioengineering and Computing Divisions, UKRI Center for Healthcare AI, MRC London Institute of Medical Sciences (MRC LMS), UCL Great Ormond Street Institute for Children’s Health (UCL GOS ICH), NIHR Great Ormond Street Hospital Biomedical Research Center (NIHR GOSH BRC), Imperial College London, Ataxia Center at UCL Queen Square Institute of Neurology, Great Ormond Street Hospital the National Hospital for Neurology and Neurosurgery, National Hospital for Neurology and Neurosurgery (UCLH and UCL/UCL BRC), Germany University of Bayreuth, Gemelli Hospital, Rome, Italy, When NIHR Imperial College Research Facility.
Movement Fingerprint – Trial Details
In a DMD-focused study, researchers and clinicians from Imperial College London, Great Ormond Street Hospital, and University College London examined 21 children with DMD and 17 healthy-age controls to assess physical I tried the sensor suit on the . Children wore the sensors while performing standard clinical assessments (such as a 6-minute walk test) and during daily activities such as eating lunch and playing.
In the FA study, Imperial College London, Ataxia Centre, UCL Queen Square Neurological Institute, and MRC London Institute of Medical Sciences We 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 abnormally large triplet repeat of DNA that switches off the FA gene. Using this new AI technique, the team can use movement data to accurately predict the “switch-off” of her FA gene, allowing her FA gene activity to be detected without the need to take a biological sample from the patient. was able to measure
The team was able to administer rating scales to determine impairment levels in ataxia SARA and functional assessments such as gait, hand/arm movements (SCAFI) in nine FA patients and matched controls. rice field. We then compared the results of these validated clinical assessments with those obtained using the new technique on the same patients and controls. The latter has shown greater sensitivity in predicting disease progression.
In both studies, all data from sensors was collected and fed into AI technology to create individual avatars and analyze their movements. This massive data set and powerful computing tools allowed researchers to define the fingerprints of the key movements found in children with DMD and adults with FA. This was different in the control group. Many of these AI-based movement patterns, either in DMD or FA, have never been clinically described.
Scientists have also found that new AI techniques can significantly improve predictions of how an individual patient’s disease will progress in six months compared to current gold-standard assessments. Such accurate predictions allow clinical trials to be run more efficiently, enabling patients to access new treatments more quickly and drug administration more accurately.
Lower numbers for future clinical trials
This new method of analyzing whole-body kinematic measurements provides clinical teams with clear disease markers and progression prediction. These are invaluable tools for measuring the benefits of new therapies during clinical trials.
“We hope this study has the potential to transform clinical trials for rare movement disorders and improve the diagnosis and monitoring of patients beyond human capacity.” Professor Richard Festenstein MRC London Institute of Medical Sciences and Department of Neuroscience, Imperial College London
New technology will help researchers conduct clinical trials of conditions that affect movement faster and more accurately. In the DMD study, researchers found that the new technology could reduce the number of children needed to detect whether a new treatment was effective by a factor of four compared to the number needed with current methods. showed what it can do.
Similarly, in the FA study, researchers showed that the same accuracy could be achieved with 10 patients instead of over 160 patients. This AI technology is especially powerful when studying rare diseases with low patient numbers. In addition, the technology allows patients to be studied across life-changing disease events such as inability to ambulate, although current clinical trials are focused on either ambulatory or non-ambulatory patient cohorts. .
Co-author of both studies, Professor Thomas Voit, Director of the NIHR Great Ormond Street Biomedical Research Center (NIHR GOSH BRC) and Professor of Developmental Neuroscience at UCL GOS ICH, said: Learn more about illness. This influence, along with specialized clinical knowledge, may not only improve the efficiency of clinical trials, but also translate into a great variety of conditions that influence movement. It is thanks to the collaboration of research institutions, hospitals, clinical specialties, and dedicated patients and families that we can begin to solve the difficult problems facing rare disease research. ”
Co-first author of both studies, Dr Balasundaram Kadirvelu, a Postdoctoral Fellow in the Department of Computing and Bioengineering at Imperial College London, said: We call them “behavioral fingerprints”. This means that just as a person can be identified by hand fingerprints, these digital fingerprints can be used to identify patients with disease regardless of whether they are in a wheelchair or walking, undergoing an evaluation at the doctor’s office, or eating lunch. because it accurately characterizes Cafe. “
Valeria Ricotti, Ph.D., UCL GOS ICH Emeritus Clinical Lecturer, co-first author of the DMD study and co-author of the FA study, said: about potential new treatments. By increasing the efficiency of clinical trials, there is hope that more treatments can be successfully tested. ”
Co-author Professor Paola Giunti, Director of the UCL Center for Ataxia at Queen Square Neurological Institute and Emeritus Consultant at UCLH, the National Hospital of Neurology and Neurosurgery, said: It is certainly excellent for capturing disease progression in rare diseases such as Friedreich’s ataxia. This novel approach will revolutionize clinical trial design for new drugs and monitor the effects of existing drugs with a precision previously unknown. ”
“In addition to our significant input on the clinical protocol, a large number of very well-characterized clinically and genetically FA patients at the Center for Ataxia UCL Queen Square Neurology Institute made the project possible. We also thank all the patients who participated in this project.”
Co-author of both studies, Professor Richard Festenstein, Department of Neuroscience, MRC London Institute of Medical Sciences and Imperial College London, said: help provide this information. We hope that this study has the potential to transform clinical trials for rare movement disorders and improve the diagnosis and monitoring of patients beyond human competence levels. ”
This study was funded by a UKRI Turing AI Fellowship to Professor Faisal, the NIHR Imperial College Biomedical Research Center (BRC), the MRC London Institute of Medical Sciences, the Duchenne Research Fund, the NIHR Great Ormond Street Hospital (GOSH) BRC, and UCL. I was. /UCLH BRC, and the British Medical Research Council.
–
“Wearable Whole-body Motion Tracking of Activities of Daily Living Predicts Disease Trajectory in Duchenne Muscular Dystrophy,” by Ricotti et al., published January 19, 2023 in Nature Medicine.
“A Wearable Motion Capture Suit and Machine Learning Predict Disease Progression in Friedreich’s Ataxia,” Kadirvelu et al., published January 19, 2023 in Nature Medicine.
