The growth in the prevalence of dementias is associated with a phenomenon that challenges the 21st century, population aging. Dementias require physical and mental effort on the part of caregivers, making it difficult to promote controlled and active care. This review aims to explore the usability and integration of wearable devices designed to measure the daily activities of elderly people with dementia. A survey was carried out in the following databases: LILACS, Science Direct and PubMed, between 2018 and 2024 and the methodologies as well as the selection criteria are briefly described. A total of 27 articles were included in the review that met the inclusion criteria and answered the research question. As the main conclusions, the various monitoring measurements and interaction aspects are critically important, demonstrating their significant contributions to controlled, adequate and active monitoring, despite the incomplete compliance with the key aspects which could guarantee solutions economically accessible to institutions or other organizations through the application of the design requirements. Future research should not only focus on the development wearable devices that follow the essential requirements but also on further studying the needs and adversities that elderly people with dementia face as a pillar for the development of a feasible device.

INTRODUCTION: Dementia affects over 55 million people worldwide, impacting patient autonomy and increasing caregiver burden. Wearable technology offers new possibilities for monitoring and intervention. However, existing solutions often lack usability, adaptability, and caregiver integration. This study focuses on ear-based wearable devices, such as hearing aids and smart earphones, assessing their role in dementia care.OBJECTIVES: This research aims to review wearable technologies for dementia monitoring, identify key user requirements, and define guidelines for future device development.METHODS: A systematic literature review was conducted using Scopus, PubMed, IEEE Xplore, and ScienceDirect, focusing on studies from 2020-2025. Relevant articles were analysed to identify technological advancements, design considerations, and gaps in existing research.RESULTS: Findings show that ear-based wearables effectively track physiological and behavioural data. Non-invasiveness, usability, and real-time data transmission are key factors. Despite advancements, gaps remain in device adaptability, user experience, and security. A set of physical, emotional, and cognitive requirements was established to guide future development.CONCLUSION: Wearable technology can transform dementia care, but improvements in ergonomics, AI-driven analytics, and caregiver integration are needed. Future research should focus on secure data transmission and clinical validation to ensure real-world effectiveness.

INTRODUCTION: The rapidly aging global population presents significant challenges, particularly in managing neurodegenerative diseases such as dementia. Addressing these challenges requires innovative solutions that ensure continuous care and monitoring of elderly individuals. Wearable technology offers a path to more inclusive and efficient care for older adults living with cognitive decline. OBJECTIVES: This paper presents the design, development, and refinement of an integrated wrist-worn wearable system to support the monitoring and care of elderly people living with dementia, expanding a previous proof of concept into a compact and energy-efficient prototype optimized for real-world usability. METHODS: The proposed system integrates advanced sensor technologies. It includes optical (MAX30101), inertial (BMI270), and GNSS (CAM-M10Q) sensors for monitor heart rate, blood oxygen levels, motion, and location. Data are transmitted via Bluetooth Low Energy (BLE) for indoor communication and LoRa for outdoor connectivity. A custom 4×4 cm PCB was designed to consolidate all components—microcontroller, sensors, power efficiency, communication modules, and display—into a single compact and robust layout. The design process also emphasized ergonomic comfort and usability through iterative prototyping and 3D modelling. RESULTS: The refined prototype significantly reduced the physical dimensions compared with the original proof of concept, while improving power efficiency, mechanical stability, and user comfort. The device layout and button interface were optimized to ensure intuitive interaction and safe daily use by elderly individuals. CONCLUSION: The developed prototype establishes the foundation for a fully functional, energy-efficient wearable system tailored to dementia monitoring. Future work will include firmware optimization, extended functional validation, and the integration of intelligent analytics for behaviour recognition and anomaly detection, aiming to provide caregivers with timely and actionable health insights.

INTRODUCTION: Disruption of daily routines, such as irregular sleep, skipped meals or reduced mobility, is often among the earliest observable markers of functional decline in dementia, yet continuous, unobtrusive monitoring of this disruption remains difficult to build and validate at scale, mainly due to the scarcity of realistic wearable datasets and of longitudinal behavioural data. OBJECTIVES: This paper reports two complementary contributions developed within the same wearable-monitoring project: the incremental construction of a real-world multimodal wearable dataset for human activity recognition, and a routine-aware behavioural monitoring framework that uses that dataset to train and evaluate a sequential anomaly detection model. METHODS: A dual-device wearable setup, combining a wrist-worn inertial prototype with an external spot-check physiological monitor, was used to collect labelled activities of daily living from twelve adult participants under supervised conditions. The resulting activity database seeds a knowledge-informed synthetic daily-routine generator and trains a Bidirectional Gated Recurrent Unit (BiGRU) sequential model for context-dependent anomaly detection, evaluated on synthetic routines with injected behavioural deviations. RESULTS: Activity-recognition baselines trained on the dataset reach an accuracy of 0.73 (LightGBM), while the anomaly detection model attains an AUROC of 0.999 and a PR-AUC of 0.989 on synthetic routines with injected behavioural deviations. CONCLUSION: These results support the feasibility of the acquisition pipeline and of the routine-modelling approach as a foundation for future validation with longitudinal, real-world dementia cohorts.