Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Jan 27;17(1):29.
doi: 10.1186/s13195-025-01675-0.

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

Manuel Lentzen  1   2 , Srinivasan Vairavan  3 , Marijn Muurling  4   5 , Vasilis Alepopoulos  6 , Alankar Atreya  7 , Merce Boada  8   9 , Casper de Boer  4   5 , Pauline Conde  10 , Jelena Curcic  11 , Giovanni Frisoni  12 , Samantha Galluzzi  13 , Martha Therese Gjestsen  14   15 , Mara Gkioka  16 , Margarita Grammatikopoulou  6 , Lucrezia Hausner  17 , Chris Hinds  7 , Ioulietta Lazarou  6 , Alexandre de Mendonça  18 , Spiros Nikolopoulos  6 , Dorota Religa  19 , Gaetano Scebba  11 , Pieter Jelle Visser  4   20 , Gayle Wittenberg  3 , Vaibhav A Narayan  21 , Neva Coello  22 , Anna-Katharine Brem  10   23 , Dag Aarsland  10   24 , Holger Fröhlich  25   26 ; RADAR-AD
Affiliations

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

Manuel Lentzen et al. Alzheimers Res Ther. .

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.

Keywords: Alzheimer’s disease; Discriminative capacity; Mobile applications; Remote monitoring technologies; Wearables.

PubMed Disclaimer

Conflict of interest statement

Declarations. Ethics approval and consent to participate: The RADAR-AD was ethically approved in each participating country and aligns with the Helsinki Declaration of 1975, revised in 2008. All participants and their informants provided written informed consent prior to any study procedures. Competing interests: 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.

Figures

Fig. 1
Fig. 1
Overview of the study workflow to evaluate the discriminative abilities of RMTs in AD progression. The process involves 1) data acquisition and 2) feature extraction from RMTs, followed by 3) univariate analyses (ANCOVA and Tukey HSD tests) to detect significant feature differences across study groups, and 4) a machine-learning pipeline, including Logistic Regression, Decision Tree, Random Forest, and XGBoost models, to quantify how well stages of AD can be distinguished using RMT-derived data
Fig. 2
Fig. 2
Statistical Analysis of RMT Features. The figure illustrates a comprehensive univariate statistical analysis of the RMTs’ features. Each row depicts the results obtained for the six comparisons, while the label on the left indicates the corresponding RMT affiliation. Statistical outcomes of the Tukey HSD test (conducted upon significant ANCOVA) are presented in the heatmap itself. The p-values are expressed through a color-coded system, with the specific coding shown in the provided legend. The symbols “-” or “+” are used to denote the direction of the test statistic. The p-values have been adjusted for multiple testing
Fig. 3
Fig. 3
Discriminative abilities of different RMTs and their performance comparison across different disease stages. The figure depicts the Area Under the Receiver Operator Characteristic (AUROC). As we focused on optimal performance rather than specific classifiers to emphasize the highest discrimination ability, we show the AUROC only for the best-performing machine learning model in each experiment. The red and green boxes represent the base models, while the purple boxes illustrate the models trained solely on RMT data. The blue boxes depict the performance achieved for the questionnaire and test-based assessments (A-iADL and the functional domain scores derived from multiple questionnaires)
Fig. 4
Fig. 4
Distinguishing Features for HC vs. ProAD: This plot depicts the top ten features with the highest mean absolute SHAP values, offering insights into their significance in the Altoida and Fitbit-based models
Fig. 5
Fig. 5
Distinguishing Features for HC vs. MildAD: This plot depicts the top ten features with the highest mean absolute SHAP values, offering insights into their significance in the Fitbit and Mezurio-based models
See this image and copyright information in PMC

References

    1. Scheltens P, Strooper BD, Kivipelto M, Holstege H, Chételat G, Teunissen CE, et al. Alzheimer’s Disease. Lancet (London, England). 2021;397(10284):1577–90. 10.1016/S0140-6736(20)32205-4. - PMC - PubMed
    1. Jack CR Jr, Bennett DA, Blennow K, Carrillo MC, Dunn B, Haeberlein SB, et al. NIA-AA Research Framework: Toward a Biological Definition of Alzheimer’s Disease. Alzheimers Dement. 2018;14(4):535–62. 10.1016/j.jalz.2018.02.018. - PMC - PubMed
    1. Fortea J, Vilaplana E, Carmona-Iragui M, Benejam B, Videla L, Barroeta I, et al. Clinical and Biomarker Changes of Alzheimer’s Disease in Adults with Down Syndrome: A Cross-Sectional Study. Lancet. 2020;395(10242):1988–97. 10.1016/S0140-6736(20)30689-9. - PMC - PubMed
    1. Bateman RJ, Xiong C, Benzinger TLS, Fagan AM, Goate A, Fox NC, et al. Clinical and Biomarker Changes in Dominantly Inherited Alzheimer’s Disease. N Engl J Med. 2012;367(9):795–804. 10.1056/NEJMoa1202753. - PMC - PubMed
    1. Langbaum JB, Zissimopoulos J, Au R, Bose N, Edgar CJ, Ehrenberg E, et al. Recommendations to Address Key Recruitment Challenges of Alzheimer’s Disease Clinical Trials. Alzheimers Dement J Alzheimers Assoc. 2023;19(2):696–707. 10.1002/alz.12737. - PMC - PubMed