Differentiating symptoms of Parkinson’s and PSP: Is wearable technology the answer?
Posted by
24-Jul-2020
One of the problems in trying to correctly diagnose and treat movement disorders such as Parkinson’s Disease (PD) and Progressive Supranuclear Palsy (PSP), as well as conduct clinical trials of new treatments, is that at present there is a lack of sensitive, objective and quantitative diagnostic measures of relevant functional ability.
Objective numerical measures of disease are needed for accurate diagnosis and staging of disease, monitoring of progression rate, stratification of patients for entry into clinical trials and detection of an early signal to guide critical go/no go decisions.
With the aim of addressing these challenges in 2016 UCB provided a grant to Oxford University for a highly innovative and pioneering project known as the Oxford QUantification In Parkinsonism (OxQUIP) study. The main objective of the study, led by Professor Chrystalina Antoniades, was to develop ways of accurately measuring neurological disorders such as PD and PSP, two progressive neurodegenerative brain disorders affecting movement and cognition.
This study was designed to precisely measure subtle abnormalities in the timing, speed and coordination of a range of movements in people with PD and PSP at various stages of progression over a three-year period, along with an age- and sex-matched healthy control group.
Within this study participants perform a range of tasks while wearing sensors that accurately quantify their performance. Measurements recorded included eye movements with infra-red cameras and body movements using accelerometers and cognitive function using a tablet. Participants also perform cognitive tasks on a tablet computer, testing for example their ability to deduce the rules governing the movement of shapes on the screen.
Early data from the OxQUIP study suggest wearable technology, combined with artificial intelligence and machine learning, could offer the potential to accurately distinguish symptoms of PD from PSP.
The research published in the journal Gait and Posture identified 17 features which allowed researchers to discriminate PSP with a high degree of sensitivity and specificity (86% and 90% respectively) using an array of six motion sensors.
The study also suggests that optimal separation between the two patient populations is achieved via application of motion sensors to three distinct body sites, however, a single lumbar motion sensor could deliver comparable classification, offsetting a modest loss of accuracy with increased convenience and simplicity.
“Although in the early stages the symptoms of PSP and PD can appear quite similar, from a modality perspective the two conditions have different underlying pathophysiology”, explained UCB’s Tim Buchanan, co-author of the paper and the clinical development lead on the anti-tau programme at UCB. “Being able to accurately differentiate the two diseases by harnessing wearable technology, combined with machine learning, could support movement disorder specialists in earlier diagnosis and tailored management approaches, avoiding misdiagnosis and supporting better and more targeted treatment strategies.
To maximise the benefit from any potentially disease-modifying treatment for PSP an early and accurate diagnosis will be required so that treatment may be initiated as early as possible in the course of the disease. To this end and based on the exciting initial findings from the OxQUIP study, UCB has extended its funding for an additional two years.
“We are delighted to continue our collaboration with UCB on the OxQUIP study which has the potential to be a game-changer when it comes to the early diagnosis of PSP” explained Professor Chrystalina Antoniades, lead study investigator for the programme.
The aim of the next phase of the collaboration is to increase the number of PSP patients as well as extend the acquisition of quantitative data to the real-world setting of the patient’s home. It is anticipated that this research will lead to further publications aimed to support the movement disorder community in improving the diagnosis and management of people living with this debilitating condition.
Objective numerical measures of disease are needed for accurate diagnosis and staging of disease, monitoring of progression rate, stratification of patients for entry into clinical trials and detection of an early signal to guide critical go/no go decisions.
With the aim of addressing these challenges in 2016 UCB provided a grant to Oxford University for a highly innovative and pioneering project known as the Oxford QUantification In Parkinsonism (OxQUIP) study. The main objective of the study, led by Professor Chrystalina Antoniades, was to develop ways of accurately measuring neurological disorders such as PD and PSP, two progressive neurodegenerative brain disorders affecting movement and cognition.
This study was designed to precisely measure subtle abnormalities in the timing, speed and coordination of a range of movements in people with PD and PSP at various stages of progression over a three-year period, along with an age- and sex-matched healthy control group.
Within this study participants perform a range of tasks while wearing sensors that accurately quantify their performance. Measurements recorded included eye movements with infra-red cameras and body movements using accelerometers and cognitive function using a tablet. Participants also perform cognitive tasks on a tablet computer, testing for example their ability to deduce the rules governing the movement of shapes on the screen.
Early data from the OxQUIP study suggest wearable technology, combined with artificial intelligence and machine learning, could offer the potential to accurately distinguish symptoms of PD from PSP.
The research published in the journal Gait and Posture identified 17 features which allowed researchers to discriminate PSP with a high degree of sensitivity and specificity (86% and 90% respectively) using an array of six motion sensors.
The study also suggests that optimal separation between the two patient populations is achieved via application of motion sensors to three distinct body sites, however, a single lumbar motion sensor could deliver comparable classification, offsetting a modest loss of accuracy with increased convenience and simplicity.
“Although in the early stages the symptoms of PSP and PD can appear quite similar, from a modality perspective the two conditions have different underlying pathophysiology”, explained UCB’s Tim Buchanan, co-author of the paper and the clinical development lead on the anti-tau programme at UCB. “Being able to accurately differentiate the two diseases by harnessing wearable technology, combined with machine learning, could support movement disorder specialists in earlier diagnosis and tailored management approaches, avoiding misdiagnosis and supporting better and more targeted treatment strategies.
To maximise the benefit from any potentially disease-modifying treatment for PSP an early and accurate diagnosis will be required so that treatment may be initiated as early as possible in the course of the disease. To this end and based on the exciting initial findings from the OxQUIP study, UCB has extended its funding for an additional two years.
“We are delighted to continue our collaboration with UCB on the OxQUIP study which has the potential to be a game-changer when it comes to the early diagnosis of PSP” explained Professor Chrystalina Antoniades, lead study investigator for the programme.
The aim of the next phase of the collaboration is to increase the number of PSP patients as well as extend the acquisition of quantitative data to the real-world setting of the patient’s home. It is anticipated that this research will lead to further publications aimed to support the movement disorder community in improving the diagnosis and management of people living with this debilitating condition.
Learn more about PSP here.
Leave a Comment
Wonderful developments supporting earlier diagnosis of PSP. Wishing the team continued success .