TY - JOUR
T1 - RADAR-AD
T2 - assessment of multiple remote monitoring technologies for early detection of Alzheimer's disease
AU - Lentzen, Manuel
AU - Vairavan, Srinivasan
AU - Muurling, Marijn
AU - Alepopoulos, Vasilis
AU - Atreya, Alankar
AU - Boada, Merce
AU - de Boer, Casper
AU - Conde, Pauline
AU - Curcic, Jelena
AU - Frisoni, Giovanni
AU - Galluzzi, Samantha
AU - Gjestsen, Martha Therese
AU - Gkioka, Mara
AU - Grammatikopoulou, Margarita
AU - Hausner, Lucrezia
AU - Hinds, Chris
AU - Lazarou, Ioulietta
AU - de Mendonça, Alexandre
AU - Nikolopoulos, Spiros
AU - Religa, Dorota
AU - Scebba, Gaetano
AU - Jelle Visser, Pieter
AU - Wittenberg, Gayle
AU - Narayan, Vaibhav A
AU - Coello, Neva
AU - Brem, Anna-Katharine
AU - Aarsland, Dag
AU - Fröhlich, Holger
AU - RADAR-AD
PY - 2025/1/27
Y1 - 2025/1/27
N2 - BACKGROUND: Alzheimer's disease (AD) is a progressive neurodegenerative disorder affecting millions worldwide, leading to cognitive and functional decline. Early detection and intervention are crucial for enhancing the quality of life of patients and their families. Remote Monitoring Technologies (RMTs) offer a promising solution for early detection by tracking changes in behavioral and cognitive functions, such as memory, language, and problem-solving skills. Timely detection of these symptoms can facilitate early intervention, potentially slowing disease progression and enabling appropriate treatment and care. METHODS: The RADAR-AD study was designed to evaluate the accuracy and validity of multiple RMTs in detecting functional decline across various stages of AD in a real-world setting, compared to standard clinical rating scales. Our approach involved a univariate analysis using Analysis of Covariance (ANCOVA) to analyze individual features of six RMTs while adjusting for variables such as age, sex, years of education, clinical site, BMI and season. Additionally, we employed four machine learning classifiers - Logistic Regression, Decision Tree, Random Forest, and XGBoost - using a nested cross-validation approach to assess the discriminatory capabilities of the RMTs. RESULTS: The ANCOVA results indicated significant differences between healthy and AD subjects regarding reduced physical activity, less REM sleep, altered gait patterns, and decreased cognitive functioning. The machine-learning-based analysis demonstrated that RMT-based models could identify subjects in the prodromal stage with an Area Under the ROC Curve of 73.0 %. In addition, our findings show that the Amsterdam iADL questionnaire has high discriminatory abilities. CONCLUSIONS: RMTs show promise in AD detection already in the prodromal stage. Using them could allow for earlier detection and intervention, thereby improving patients' quality of life. Furthermore, the Amsterdam iADL questionnaire holds high potential when employed remotely.
AB - BACKGROUND: Alzheimer's disease (AD) is a progressive neurodegenerative disorder affecting millions worldwide, leading to cognitive and functional decline. Early detection and intervention are crucial for enhancing the quality of life of patients and their families. Remote Monitoring Technologies (RMTs) offer a promising solution for early detection by tracking changes in behavioral and cognitive functions, such as memory, language, and problem-solving skills. Timely detection of these symptoms can facilitate early intervention, potentially slowing disease progression and enabling appropriate treatment and care. METHODS: The RADAR-AD study was designed to evaluate the accuracy and validity of multiple RMTs in detecting functional decline across various stages of AD in a real-world setting, compared to standard clinical rating scales. Our approach involved a univariate analysis using Analysis of Covariance (ANCOVA) to analyze individual features of six RMTs while adjusting for variables such as age, sex, years of education, clinical site, BMI and season. Additionally, we employed four machine learning classifiers - Logistic Regression, Decision Tree, Random Forest, and XGBoost - using a nested cross-validation approach to assess the discriminatory capabilities of the RMTs. RESULTS: The ANCOVA results indicated significant differences between healthy and AD subjects regarding reduced physical activity, less REM sleep, altered gait patterns, and decreased cognitive functioning. The machine-learning-based analysis demonstrated that RMT-based models could identify subjects in the prodromal stage with an Area Under the ROC Curve of 73.0 %. In addition, our findings show that the Amsterdam iADL questionnaire has high discriminatory abilities. CONCLUSIONS: RMTs show promise in AD detection already in the prodromal stage. Using them could allow for earlier detection and intervention, thereby improving patients' quality of life. Furthermore, the Amsterdam iADL questionnaire holds high potential when employed remotely.
KW - Alzheimer’s disease
KW - Discriminative capacity
KW - Mobile applications
KW - Remote monitoring technologies
KW - Wearables
KW - Humans
KW - Alzheimer Disease/diagnosis
KW - Female
KW - Male
KW - Aged
KW - Early Diagnosis
KW - Aged, 80 and over
KW - Remote Sensing Technology/methods instrumentation
KW - Machine Learning
KW - Neuropsychological Tests
KW - Middle Aged
U2 - 10.1186/s13195-025-01675-0
DO - 10.1186/s13195-025-01675-0
M3 - Article
SN - 1758-9193
VL - 17
JO - Alzheimer's Research & Therapy
JF - Alzheimer's Research & Therapy
IS - 1
M1 - 29
ER -