Context: Due to rapid increase in the population of elderly people, sharing healthcare information has become an essential requirement for the development of e-health system. By conducting a research in e-health and cloud computing we have explored the advantages and disadvantages of sharing healthcare information for elderly people through cloud computing. Objectives: The main purpose of this research is to investigate the suitability of cloud computing to share healthcare information. The study is conducted by exploring the advantages and disadvantages of cloud computing for e-Health systems. Investigating a suitable cloud computing platform is also one of the objectives of this research. Methods: In order to identify and get deeper understanding of these issues, we have performed literature review of E-health, EHI and Cloud Computing technologies and we have develop a prototype application as experiment. Results: Based on the finding of literature review, we came to know that E-health was huge field. It needs a huge infrastructure to establish. The healthcare information in e-health requires quick and easy sharing. In EHI research, we defined EHI and find reasons for sharing elderly healthcare information. At cloud computing research, we knew the concept of cloud computing and found out advantages and disadvantages of implementing e-health in cloud computing. From literature review, we developed sharing application which was used to share EHI in cloud computing. In experiment, we proved our supposition and discussed advantages and disadvantages of sharing EHI in cloud computing by using Google App Engine (GAE). Conclusions: We conclude that cloud computing meets the requirements of sharing EHI, but it also has some limitations due to its architecture and network condition. In this research we have identified further research area that can help in enhancing security and privacy in cloud environment.

With an increasing migrant population there is a growing need to organize interpreting practices in healthcare in order to deliver equitable high-quality care. This thesis focuses on healthcare institutions’ organization of interpreting services. The aim of the study was to explore interpreting practices in a healthcare context by comparing two different healthcare areas – elderly and emergency healthcare. The study aimed to highlight the impact of the organizational and institutional context. This study was designed as an explorative and descriptive qualitative study including 79 healthcare professionals with experience of interpreting practices recruited via purposeful sampling in elderly and emergency healthcare. Data were collected through individual and focus-group interviews and analysed with inductive qualitative content analysis. The main findings show that the processes and structures around interpreting practices were complex and mainly linked to individual and interpersonal levels and, to a limited extent, to the institutional level. On the institutional level the Public Procurement Act was the only formal policy to follow. On individual and interpersonal level interpreting practices were structured by self-established informal workplace routines developed by the professional groups. The norms and routines used was determined by access to interpreters, time aspects, characteristics of the care given, health conditions and the person’s problem, expectations and requests from the person and also from healthcare professionals. There were wishes for improvement, with better flexibility in access to professional interpreters, training for users and interpreters, and also better technical solutions and equipment. In conclusion, the use of interpreters was rooted in the organizational environment of interpreting practice, including the availability of laws, policy and guidelines, and closely related to individuals’ language skills, cultural values and social factors. The use of professional interpreters was based on the nature of care in context and access to interpreters and determined by health professionals’ estimation of the person’s current health status in order to deliver fast and individualized care based on humanistic values. Thus, it is important to consider organizational framework and cultural awareness when formulating interpreting practices adapted to the context, and formal guidelines in order to achieve the aim of personcentered and equal health care.

Le vieillissement rapide de la population implique une évolution du système de soins pour prendre en charge les personnes dépendantes dont la proportion ne cesse de croître. Une option possible est de développer et de mettre en œuvre une technologie d’assistance à domicile. Ce travail de thèse consiste à concevoir et à expérimenter des solutions de « surveillance » multicapteurs : déploiement de capteurs dans l’environnement réel du patient, fusion multisensorielle et algorithmes de diagnostics automatiques, afin d’assurer la sécurité des personnes mais également d’aider les professionnels de santé à maintenir la qualité du suivi et des soins. Ce manuscrit présente à travers une étude bibliographique, un état des connaissances et des pratiques sur les systèmes d’analyse des activités des personnes âgées. Ensuite, il détaille l’étape de conception du système de surveillance retenu et selon une approche fonctionnelle présente l’architecture matérielle et logicielle mise en œuvre pour répondre aux spécifications établies. Deux projets sont issus de ce travail : 1) Le projet Homecare qui vise à expérimenter et à qualifier, au niveau opérationnel, un système complet de Télésurveillance pour les personnes âgées atteintes de la maladie d'Alzheimer. 2) Le projet BéA qui est plutôt orienté sur la surveillance « outdoor » pour des personnes valides mais fragiles : Notre contribution a concerné la mise en place d’une architecture système qui intègre un algorithme auto-adaptatif de détection et de modélisation des déambulations par tranche horaire. Enfin, les pistes d’un modèle économique qui définit les options offertes, aujourd’hui, au déploiement de ce type de systèmes sont discutées. / The aging of the population implies an evolution of the healthcare systems, in order to take over dependent people whose proportion is growing. A possible solution is to develop and implement a home care technology. In this context, this PhD work consist to design and test a multisensory monitoring system: deployment of sensors in patient environment, sensory data fusion and automatic diagnostic algorithms, in order allowing patients to live in better safety conditions and helping health professionals to give better care quality. This manuscript presents, in the beginning, the problematic of elderly care and the state of knowledge and practices of activity analysis systems for elderly, through a literature review. Then, it describes the design step of monitoring system according to a functional approach. This approach presents the implemented hardware and software architecture in order to satisfy established specifications. We worked on two projects: 1) Homecare System aims to experiment and validate the good working of a remote monitoring system for elderly (or disabled) suffering from Alzheimer's disease. 2) BéA System (Bracelet Electronique d’Autonomie) is oriented to outdoor monitoring of able-bodied people but frail: Our contribution is to implement a system architecture which integrates a self-adaptive algorithm for detecting and modelling wandering by day-part. For these two projects, we present the results and make a first experience feedback. Finally, we propose a potential economic model that defines the available options that allow, today, the deployment these types of system.

The integration of Large Language Models (LLMs) such as GPT-4 and Gemini into healthcare, particularly for elderly care, represents a significant opportunity in the use of artificial intelligence in medical settings. This thesis investigates the capabilities of these models to understand and respond to the healthcare needs of older adults effectively. A framework was developed to evaluate their performance, consisting of specifically designed medical scenarios that simulate real-life interactions, prompting strategies to elicit responses and a comprehensive user evaluation to assess technical performance and contextual understanding.  The analysis reveals that while LLMs such as GPT-4 and Gemini exhibit high levels of technical proficiency, their contextual performance shows considerable variability, especially in personalization and handling complex, empathy-driven interactions. In simpler tasks, these models demonstrate appropriate responsiveness, but they struggle with more complex scenarios that require deep medical reasoning and personalized communication.  Despite these challenges, the research highlights the potential of LLMs to significantly enhance healthcare delivery for older adults by providing timely and relevant medical information. However, to realize a truly effective implementation, further development is necessary to improve the models’ ability to engage in meaningful dialogue and understand the nuanced needs of an aging population.  The findings underscore the necessity of actively involving older adults in the development of AI technologies, ensuring that these models are tailored to their specific needs. This includes focusing on enhancing the contextual and demographic awareness of AI systems. Future efforts should focus on enhancing these models by incorporating user feedback from the older population and applying user-centered design principles to improve accessibility and usability. Such improvements will better support the diverse needs of aging populations in healthcare settings, enhancing care delivery for both patients and doctors while maintaining the essential human touch in medical interactions. / Integrationen av stora språkmodeller (LLMs) såsom GPT-4 och Gemini inom sjukvården, särskilt inom äldrevård, representerar betydande möjligheter i användningen av artificiell intelligens i medicinska sammanhang. Denna avhandling undersöker dessa modellers förmåga att förstå och effektivt svara på äldres vårdbehov. För att utvärdera deras prestanda utvecklades ett ramverk bestående av specifikt utformade medicinska situationer som simulerar verkliga interaktioner, strategier för att framkalla relevanta svar från modellerna och en omfattande användarutvärdering för att bedöma både teknisk prestanda och kontextuell förståelse.  Analysen visar att även om LLMs såsom GPT-4 och Gemini visar på hög teknisk prestationsförmåga, är dess kontextuella förmåga mer begränsad, särskilt när det gäller personalisering och hantering av komplexa, empatidrivna interaktioner. Vid enklare uppgifter visar dessa modeller på en lämplig responsivitet, men de utmanas vid mer komplexa scenarier som kräver djup medicinsk resonemang och personlig kommunikation.  Trots dessa utmaningar belyser denna forskning potentialen hos LLMs att väsentligt förbättra vårdleveransen för äldre genom att tillhandahålla aktuell och relevant medicinsk information. Däremot krävs ytterligare utveckling för att verkligen möjliggöra en effektiv implementering, vilket inkluderar att förbättra modellernas förmåga att delta i en meningsfull dialog och förstå de nyanserade behoven hos äldre patienter.  Resultaten från denna avhandling understryker nödvändigheten av att aktivt involvera äldre individer i utvecklingen av AI-teknologier, för att säkerställa att dessa modeller är skräddarsydda för deras specifika behov. Detta inkluderar ett fokus på att förbättra den kontextuella och demografiska medvetenheten hos AI-system. Framtida insatser bör inriktas på att förbättra dessa modeller genom att integrera användarfeedback från äldre populationer och tillämpa principer för användarcentrerad design för att förbättra tillgänglighet och användbarhet. Sådana förbättringar kommer att bättre stödja de mångsidiga behoven hos äldre i vårdsammanhang, förbättra vårdleveransen för både patienter och läkare samtidigt som den väsentliga mänskliga kontakten i medicinska interaktioner bibehålls.