This paper presents our experience in creating a virtual assistant tailored for use in residential care facilities, aimed at reducing the workload of facility personnel by automating the collection of patient information and addressing routine inquiries. The system integrates a wide variety of AI methods, including natural language processing (NLP), computer vision, logical inference, ontologies, and knowledge graph technology for the system to interpret user messages and generate responses, ensuring contextual and personalized interactions. The knowledge graph is populated with semantic representations of user messages and serves as a verified source of factual knowledge, enhancing the system’s ability to provide accurate and reliable answers. Challenges in NLP and the integration of diverse subsystems were addressed through a hybrid approach that utilizes a specific language for unified knowledge representation, which improves explainability and addresses limitations inherent in large language models.

Unpaid carers provide unpaid support to individuals who cannot manage independently due to disability, age, or illness. They often face significant challenges balancing their caregiving duties while managing their own well-being. With over 5.8 million unpaid carers in the UK, their role is indispensable to the healthcare system. Mobilise Care Limited, a digital care support organisation, empowers carers through AI-powered tools such as the Carer Assessment Tool and Mobilise Assistant Chat, enhancing both carer well-being and the quality of care. This research introduces an enhanced Carer digital support system, which integrates community knowledge from a growing carers network into its digital support system to improve inclusion and participation of carers in digital carer support community. Using supervised machine learning and Retrieval Augmented Generation (RAG), the tool classifies and embeds helpful peer-generated community threads into its knowledge base, providing carers with richer, and contextually relevant information. Preliminary findings suggest increased carer satisfaction, reinforcing the role of digital innovations in reducing social isolation and improving accessibility, inclusion, and digital health solutions in caregiving.

Sleep is vital for memory consolidation, emotional regulation, and overall quality of life. However, sleep disorders such as insomnia, apnea, and snoring, which affect approximately 33% of the population, can lead to symptoms like daytime sleepiness, irritability, and depression. Diagnosing these disorders typically requires all-night polysomnography (PSG) recordings, manually annotated by sleep technologists. This process is time-consuming, inconsistent, and prone to inter-rater variability. Automating sleep stage classification could address these limitations, but the heterogeneity of EEG time series data presents a significant challenge.

This study explores a hybrid approach combining machine learning techniques with interpretable linear models enriched by feature construction, benchmarking their performance against traditional methods. The integration of eXplainable Artificial Intelligence (XAI) ensures model transparency, enabling clinicians to verify automated decisions and fostering trust. The study also leverages hybrid AI to incorporate both knowledge- and data-driven approaches, further enhancing model explainability.

This article describes the development of an assistive sociotechnical system aimed at supporting active and healthy aging based on personalization and application of sensor measurements. In this work we rely on both historical and real-time data coming from environmental, behavioral and biomedical measurements. Further, this data is analyzed to highlight patterns and to identify undesirable situations based on deviations from recognized patterns. This way the user's state and lifestyle trends can be determined based on data from several sensors located in and around the home. Our results promise to increase safety of aging populations via assistive technology stack integration with daily AI-assistants that have started to fit into everyday life and modern households.