Alzheimer’s disease (AD) is a progressive neurodegenerative disease affecting cognitive and functional abilities. However, many patients presume lower cognitive or functional abilities because of aging and do not undergo clinical assessments until the symptoms become too advanced. Developing a low-cost and easy-to-use AD detection tool, which can be used in any clinical or non-clinical setting, can enable widespread AD assessments and diagnosis. This paper investigated the feasibility of developing such a tool to detect AD vs. healthy control (HC) from a simple balance and walking assessment called the Timed Up and Go (TUG) test. We collected joint position data of 47 HC and 38 AD subjects as they performed TUG in front of a Kinect V.2 camera. Our signal processing and statistical analyses provided a comprehensive analysis of balance and gait with 12 significant features for discriminating AD from HC after adjusting for age and the Geriatric Depression Scale. Using these features and a support vector machine classifier, our model classified the two groups with an average accuracy of 97.75% and an F-score of 97.67% for five-fold cross-validation and 98.68% and 98.67% for leave-one-subject out cross-validation. These results demonstrate the potential of our approach as a new quantitative complementary tool for detecting AD among older adults. Our work is novel as it presents the first application of Kinect V.2 camera and machine learning to provide a comprehensive and quantitative analysis of the TUG test to detect AD patients from HC. This study supports the feasibility of developing a low-cost and convenient AD assessment tool that can be used during routine checkups or even at home; however, future investigations could confirm its clinical diagnostic value in a larger cohort.

Accurate and scalable gait assessment is essential for clinical and research applications, including fall risk evaluation, rehabilitation monitoring, and early detection of neurodegenerative diseases. While electronic walkways remain the clinical gold standard, their high cost and limited portability restrict widespread use. Wearable inertial measurement units (IMUs) and markerless depth cameras have emerged as promising alternatives; however, prior studies have typically assessed these systems under tightly controlled conditions, with single participants in view, limited marker sets, and without direct cross-technology comparisons. This study addresses these gaps by simultaneously evaluating three sensing technologies—APDM wearable IMUs (tested in two separate configurations: foot-mounted and lumbar-mounted) and the Azure Kinect depth camera—against ProtoKinetics Zeno™ Walkway Gait Analysis System in a realistic clinical environment where multiple individuals were present in the camera’s field of view. Gait data from 20 older adults (mean age $70.06\pm 9.45$ years) performing Single-Task and Dual-Task walking trials were synchronously captured using custom hardware for precise temporal alignment. Eleven gait markers spanning macro, micro-temporal, micro-spatial, and spatiotemporal domains were compared using mean absolute error (MAE), Pearson correlation (r), and Bland–Altman analysis. Foot-mounted IMUs demonstrated the highest accuracy (MAE $=0.00$–$6.12$, $r=0.92$–$1.00$), followed closely by the Azure Kinect (MAE $=0.01$–$6.07$, $r=0.68$–0.98). Lumbar-mounted IMUs showed consistently lower agreement with the reference system. These findings provide the first comprehensive comparison of wearable and depth-sensing technologies with a clinical gold standard under real-world conditions and across an extensive set of gait markers. The results establish a foundation for deploying scalable, low-cost gait assessment systems in diverse healthcare contexts, supporting early detection, mobility monitoring, and rehabilitation outcomes across multiple patient populations.

Alzheimer’s disease and related dementias (ADRD) are growing global health challenges, projected to affect over 82 million people by 2030. Early diagnosis is essential, offering the potential to extend life expectancy by over 50% and reduce healthcare costs by up to $150,000 per patient. Dual-task (DT) testing—evaluating motor performance under cognitive load—has emerged as a promising, non-invasive method for early ADRD detection. This review provides a comprehensive synthesis of DT-based ADRD assessments from January 2010 to October 2025, integrating insights from engineering and clinical neuroscience. We explore a broad range of DT paradigms (e.g., gait, balance, upperlimb function), sensing technologies (e.g., wearable sensors, electronic walkways, infrared/depth cameras, video, tablets, and brain imaging tools like fMRI and fNIRS), and analytic approaches, from traditional statistics to deep learning. Emerging tools, including eye-tracking and AI-based video pose estimation, are also discussed. We critically examine methodological trends, highlight key findings, and identify current limitations. Emphasizing the need for equitable, scalable, and clinically viable DT systems, this review highlights the role of modern sensor and AI technologies in enhancing early ADRD detection. It serves as a key resource for engineers, data scientists, and clinicians developing technology-driven tools for early detection and monitoring of neurodegenerative diseases.

Alzheimer’s disease and related dementias (ADRD) are growing global health challenges, projected to affect over 82 million people by 2030. Early diagnosis is essential, offering the potential to extend life expectancy by over 50% and reduce healthcare costs by up to $150,000 per patient. Dual-task (DT) testing—evaluating motor performance under cognitive load—has emerged as a promising, non-invasive method for early ADRD detection. This review provides a comprehensive synthesis of DT-based ADRD assessments from 2010 to 2024, integrating insights from engineering and clinical neuroscience. We explore a broad range of DT paradigms (e.g., gait, balance, upper-limb function), sensing technologies (e.g., wearable sensors, electronic walkways, infrared/depth cameras, video, tablets, and brain imaging tools like fMRI and fNIRS), and analytic approaches, from traditional statistics to deep learning. Emerging tools, including eye-tracking and Al-based video pose estimation, are also discussed. We critically examine methodological trends, highlight key findings, and identify current limitations. Emphasizing the need for equitable, scalable, and clinically viable DT systems, this review highlights the role of modern sensor and Al technologies in enhancing early ADRD detection. It serves as a key resource for engineers, data scientists, and clinicians developing technology-driven tools for early detection and monitoring of neurodegenerative diseases.