RADAR-AD: assessment of multiple remote monitoring technologies for early detection of Alzheimer’s disease

on behalf of RADAR-AD

doi:10.1186/s13195-025-01675-0

RADAR-AD: assessment of multiple remote monitoring technologies for early detection of Alzheimer’s disease

on behalf of RADAR-AD

Research output: Contribution to Journal › Article › Academic › peer-review

Abstract

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.

Original language	English
Article number	29
Pages (from-to)	1-17
Number of pages	17
Journal	Alzheimer's Research and Therapy
Volume	17
Issue number	1
Early online date	27 Jan 2025
DOIs	https://doi.org/10.1186/s13195-025-01675-0
Publication status	Published - Dec 2025

Funding

Authors AA, AKB, AM, CH, DR, GF, GW, HF, IL, LH, MGk, MGr, ML, MTG, PC, SN, VA, and VN declare no financial or non-financial competing interests. DA has received research support and/ or honoraria from Astra-Zeneca, H. Lundbeck, Novartis Pharmaceuticals, Evonik, Roche Diagnostics, and GE Health, and served as paid consultant for H. Lundbeck, Eisai, Heptares, Mentis Cura, Eli Lilly, Cognetivity, Enterin, Acadia, EIP Pharma, and Biogen. JC is an employee and a shareholder of Novartis. GS is an employee of Novartis. NC is employed by Novartis Pharma AG, Basel, Switzerland. Research of Alzheimer center Amsterdam (MM, CB) is part of the neurodegeneration research program of Amsterdam Neuroscience. Alzheimer Center Amsterdam is supported by Stichting Alzheimer Nederland and Stichting Steun Alzheimercentrum Amsterdam. MB is an employee of the Ace Alzheimer Center and an advisory board member for Grifols, Roche, Eli Lilly, Araclon Biotech, Merck, Zambon, Biogen, Novo Nordisk, Bioiberica, Eisai, Servier, and Schwabe Pharma. SG declares support for this work through the Italian Ministry of Health (Ricerca Corrente). GW and SV are employees and shareholders of Johnson & Johnson. Open Access funding enabled and organized by Projekt DEAL. The RADAR-AD project has received funding from the Innovative Medicines Initiative 2 Joint Undertaking under grant agreement No 806999. This Joint Undertaking receives support from the European Union’s Horizon 2020 research and innovation program and EFPIA and Software AG. See www.imi.europa.eu for more details. This communication reflects the views of the RADAR-AD consortium, and neither IMI nor the European Union and EFPIA are liable for any use that may be made of the information contained herein.

Funders	Funder number
Stichting Steun Alzheimercentrum Amsterdam
European Federation of Pharmaceutical Industries and Associations
Alzheimer Nederland
Horizon 2020 Framework Programme
Software AG
Innovative Medicines Initiative	806999

Access to Document

10.1186/s13195-025-01675-0Licence: CC BY

https://www.ncbi.nlm.nih.gov/pmc/articles/11771057

Persistent URL (handle)

Persistent link

Cite this

@article{1314ba8cdc4f4ddda971452ae31736fc,

title = "RADAR-AD: assessment of multiple remote monitoring technologies for early detection of Alzheimer{\textquoteright}s disease",

abstract = "Background: Alzheimer{\textquoteright}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{\textquoteright} quality of life. Furthermore, the Amsterdam iADL questionnaire holds high potential when employed remotely.",

author = "Manuel Lentzen and Srinivasan Vairavan and Marijn Muurling and Vasilis Alepopoulos and Alankar Atreya and Merce Boada and \{de Boer\}, Casper and Pauline Conde and Jelena Curcic and Giovanni Frisoni and Samantha Galluzzi and Gjestsen, \{Martha Therese\} and Mara Gkioka and Margarita Grammatikopoulou and Lucrezia Hausner and Chris Hinds and Ioulietta Lazarou and \{de Mendon{\c c}a\}, Alexandre and Spiros Nikolopoulos and Dorota Religa and Gaetano Scebba and \{Jelle Visser\}, Pieter and Gayle Wittenberg and Narayan, \{Vaibhav A.\} and Neva Coello and Anna-Katharine Brem and Dag Aarsland and Holger Fr{\"o}hlich and \{on behalf of RADAR-AD\}",

year = "2025",

month = dec,

doi = "10.1186/s13195-025-01675-0",

language = "English",

volume = "17",

pages = "1--17",

journal = "Alzheimer's Research and Therapy",

issn = "1758-9193",

publisher = "BioMed Central Ltd",

number = "1",

}

TY - JOUR

T1 - RADAR-AD: 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 - on behalf of RADAR-AD

PY - 2025/12

Y1 - 2025/12

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.

UR - https://www.scopus.com/pages/publications/85217111536

U2 - 10.1186/s13195-025-01675-0

DO - 10.1186/s13195-025-01675-0

M3 - Article

SN - 1758-9193

VL - 17

SP - 1

EP - 17

JO - Alzheimer's Research and Therapy

JF - Alzheimer's Research and Therapy

IS - 1

M1 - 29

ER -

RADAR-AD: assessment of multiple remote monitoring technologies for early detection of Alzheimer’s disease

Abstract

Funding

Access to Document

Persistent URL (handle)

Other files and links

Fingerprint

Cite this