Groundbreaking RADAR-AD Study Reports the Potential of Machine Learning and Augmented Reality-based Digital Biomarkers in Alzheimer’s Detection
WASHINGTON–(BUSINESS WIRE)–#AR—Altoida announced today results from the RADAR-AD consortium study, published in Nature Digital Medicine, which evaluated its augmented reality (AR) and machine learning (ML)-based digital cognitive assessment for the early identification of individuals with Alzheimer’s Disease (AD).
The ‘Remote Assessment of Disease and Relapse – Alzheimer’s Disease’ (RADAR-AD) study was an independent validation study with 121 enrolled participants over 50 years of age, which assessed cognitive and functional decline in AD using several remote monitoring technologies (RMTs) including the Altoida AR digital cognitive and functional assessment (the “Altoida AR app”). In contrast to traditional pen-and-paper clinical assessments, RMTs are designed to detect early impairment by allowing frequent and objective monitoring of function during tasks associated with instrumental activities of daily living (IADL) without the intervention of a clinician.
The study administered the Altoida AR app in amyloid beta-negative healthy control participants (HC, N=57), amyloid beta-positive cognitively normal preclinical AD participants (preAD, N=27) and prodromal AD participants (proAD, N=37). The Altoida AR app is an investigational test that consists of both motor and AR tasks. The motor tasks involve several short exercises testing fine motor skills and reaction times to set personalized reference values against population statistics for motor skills, visual abilities, and reaction times. The AR tasks are intended to simulate a complex IADL-like activity of a “place-and-find” task in which participants have to hide-and-seek virtual objects following specific instructions. Altoida’s AR app output is generated by an ML model trained to differentiate between cognitively normal and impaired participants. Leveraging data from internal device sensors, the Altoida AR app identifies digital biomarkers that have been trained from cohort data. The Altoida AR app-based tasks were administered in the clinic alongside a standard neuropsychological assessment battery. Additionally, participants utilized the Altoida AR app independently at home on their personal devices on a weekly basis for up to 8 weeks.
The study results showed that the Altoida AR app could distinguish healthy controls from individuals with preclinical AD and prodromal AD, and preclinical AD from prodromal AD, both with in-clinic and with at-home tests. The study results highlighted a significant finding: the Altoida AR app achieved a level of performance in preclinical Alzheimer’s disease (AD) that is currently unattainable with standard cognitive tests. In addition, no learning effects were found for the Altoida AP app in this study.
“There is huge potential of digital devices and sensor technologies to enable objective and continuous monitoring of Alzheimer’s disease symptoms,” said RADAR-AD academic leader Prof. Dag Aarsland, Chair of Old Age Psychiatry, King’s College London. “Altoida’s AR cognitive assessment seems to be one of the most promising emerging technologies in this field, and the RADAR-AD study results indicate that Altoida’s test can detect subtle cognitive and functional changes in individuals with AD even before they show manifest any deficits. With the emergence of new disease-modifying Alzheimer’s drugs, early diagnosis is now more important than ever.”
“Our feature in Nature Digital Medicine is a pivotal milestone in our mission to innovate and create responsible, evidence-based digital assessments for early identification of neurological diseases, including AD,” said Marc Jones, CEO, Altoida. “The RADAR-AD data underscores Altoida’s key near-term goal: facilitating the rapid identification of suitable study participants for AD treatment developers, monitoring their cognitive and functional responses throughout the study, and collecting relevant data to support both our partner’s and Altoida’s regulatory filings. Altoida is dedicated to ongoing innovation and enhancement across all aspects of the Altoida AR app to achieve this important goal.”
AR-based assessments are designed to simulate IADL and are promising tools to measure cognition and function needed for IADL in early AD both in clinic and home settings. RMTs, such as smartphone apps and smartwatches, are changing the way functional and cognitive performance are measured in AD. Due to their sensitivity, objectivity, and the option of long-term high-frequency measurements, RMTs have the potential to detect a subtle cognitive decline that occurs in the earliest stages of AD.
RADAR-AD (Remote Assessment of Disease And Relapse – Alzheimer’s Disease) is a European project funded by the Innovative Medicines Initiative (IMI). RADAR-AD is looking at two very important areas in AD, namely functioning and technology. The term “functioning” refers to the activities a person carries out in his/her daily life. RADAR AD, looked at the impact that having AD has on a person’s functioning and how the way in which a person functions may change. RADAR-AD was also exploring how existing widely-used technology (e.g. smartphones, smart wristbands/fitness trackers, home-based sensors) could be used to measure the changes in a person’s functioning.
About Altoida Digital Neuro Signature™ (DNS) – Mild Cognitive Impairment (MCI)
Altoida’s investigational algorithm Digital Neuro Signature™ (DNS) – Mild Cognitive Impairment (MCI) combines motor and AR tasks. The digital score is an ordinal score ranging from 0 to 100, with higher scores designed to indicate better performance and lower scores designed to indicate a higher probability of having cognitive impairment. The score is based on a machine learning model trained to distinguish cognitively normal from cognitively impaired participants, using the data from the touch screen, accelerometer, and gyroscope, and based on ground truth data from clinically validated cohorts.
Altoida is a pioneer in developing digital biomarkers of neurological conditions using augmented reality and machine learning. Our technology platform is designed to enable an objective evaluation of an individual’s cognitive health, which may potentially allow for faster patient selection for clinical trials, as well as sensitive monitoring of disease progression and treatment response. Altoida’s mission is to enable a new era of precision neurology using digital biomarkers. Our proprietary evidence-based platform is founded on more than 20 years of scientific research and published in multiple peer-reviewed papers including Nature Digital Medicine. For more information, visit www.altoida.com. Follow us on Twitter @altoida.