Digital biomarker‐based individualized prognosis for people at risk of dementia

• Published in: Alzheimer's & dementia : diagnosis, assessment & disease monitoring Vol. 12; no. 1; pp. e12073 - n/a
• Main Authors: Buegler, Maximilian, Harms, Robbert L., Balasa, Mircea, Meier, Irene B., Exarchos, Themis, Rai, Laura, Boyle, Rory, Tort, Adria, Kozori, Maha, Lazarou, Eutuxia, Rampini, Michaela, Cavaliere, Carlo, Vlamos, Panagiotis, Tsolaki, Magda, Babiloni, Claudio, Soricelli, Andrea, Frisoni, Giovanni, Sanchez‐Valle, Raquel, Whelan, Robert, Merlo‐Pich, Emilio, Tarnanas, Ioannis
• Format: Journal Article
• Language: English
• Published: Hoboken John Wiley & Sons, Inc 2020; John Wiley and Sons Inc; Wiley
• Subjects: Activities of daily living; Altoida Neuro Motor Index; Alzheimer's disease; Artificial intelligence; Augmented reality; Biomarkers; Clinical medicine; Cognitive & Behavioral Assessment; Cognitive ability; cognitive aging; Dementia; digital biomarker; Machine learning; Medical prognosis; Memory; Neurodegeneration; Neuropsychology; risk prediction; Smartphones; Validation studies; Europe
• ISSN: 2352-8729; 2352-8729
• DOI: 10.1002/dad2.12073

Background Research investigating treatments and interventions for cognitive decline fail due to difficulties in accurately recognizing behavioral signatures in the presymptomatic stages of the disease. For this validation study, we took our previously constructed digital biomarker‐based prognostic models and focused on generalizability and robustness of the models. Method We validated prognostic models characterizing subjects using digital biomarkers in a longitudinal, multi‐site, 40‐month prospective study collecting data in memory clinics, general practitioner offices, and home environments. Results Our models were able to accurately discriminate between healthy subjects and individuals at risk to progress to dementia within 3 years. The model was also able to differentiate between people with or without amyloid neuropathology and classify fast and slow cognitive decliners with a very good diagnostic performance. Conclusion Digital biomarker prognostic models can be a useful tool to assist large‐scale population screening for the early detection of cognitive impairment and patient monitoring over time.