Background: In the treatment of diabetes mellitus, the challenge is to integrate adequate self-management into clinical care. Customization including goal setting, monitoring, and feedback could be achieved through digitization. Digital linking between different devices could simplify and promote self-management. The aim of this study is to evaluate the outcome of diabetes treatment assisted by a digital health application compared with standard diabetes therapy. - Methods: The DAVOS study is a 6-month-period prospective, multicentric, randomized controlled trial. In total, 154 diabetes patients (age ≥18; treated with insulin) will be recruited and randomized into control group or intervention group. Both groups will receive standard diabetes care. The intervention group will additionally use a diabetes app. HbA1c value will be monitored on three separate defined visits. Primary endpoint is the overall reduction of HbA1c value. Secondary endpoints (eg, usability of the app) will be determined through patient-reported outcome questionnaires. - Discussion: Through enhanced interaction of health care professionals, providers of the app, and patients, the study aims to demonstrate improvement in the self-management of diabetes. As part of the closure management, all patients will be invited to use the examined application after completion of the study. The DAVOS study will be conducted in accordance with the valid version of the present study protocol and the internationally recognized International Conference on Harmonization–Good Clinical Practice (ICH-GCP) Guidelines. Special attention will be paid to European, national, and regional requirements for the approval, provision, and use of medical devices. The study was registered in the German Register of Clinical Trials (DRKS) with number DRKS00025996.

Le phénotypage numérique mobilise les nombreux capteurs du téléphone intelligent (p. ex. : accéléromètre, GPS, Bluetooth, métadonnées d’appels) pour mesurer le comportement humain au quotidien, sans interférence, et les relier à des symptômes psychiatriques ou des indicateurs de santé mentale. L’apprentissage automatique est une composante intégrale au processus de transformation de signaux bruts en information intelligible pour un clinicien. Cette approche émerge d’une volonté de caractériser le profil de symptômes et ses variations dans le temps au niveau individuel. Ce projet consistait à prédire des variables de santé mentale (p. ex. : stress, humeur, sociabilité, hallucination) jusqu’à sept jours dans le futur à partir des données du téléphone intelligent pour des patients avec un diagnostic de schizophrénie. Le jeu de données CrossCheck, composé d’un échantillon de 62 participants, a été utilisé. Celui-ci inclut 23,551 jours de signaux du téléphone avec 29 attributs et 6364 autoévaluations de l’état mental à l’aide d’échelles ordinales à 4 ancrages. Des modèles prédictifs ordinaux ont été employés pour générer des prédictions discrètes interprétables sur l’échelle de collecte de données. Au total, 240 modèles d’apprentissage automatique ont été entrainés, soit les combinaisons de 10 variables de santé mentale, 3 horizons temporels (même jour, prochain jour, prochaine semaine), 2 algorithmes (XGBoost, LSTM) et 4 tâches d’apprentissage (classification binaire, régression continue, classification multiclasse, régression ordinale). Les modèles ordinaux et binaires ont performé significativement au-dessus du niveau de base et des deux autres tâches avec une erreur moyenne absolue macro entre 1,436 et 0,767 et une exactitude balancée de 58% à 73%. Les résultats montrent l’effet prépondérant du débalancement des données sur la performance prédictive et soulignent que les mesures n’en tenant pas compte surestiment systématiquement la performance. Cette analyse ancre une série de considérations plus générales quant à l’utilisation de l’intelligence artificielle en santé. En particulier, l’évaluation de la valeur clinique de solutions d’apprentissage automatique présente des défis distinctifs en comparaison aux traitements conventionnels. Le rôle grandissant des technologies numériques en santé mentale a des conséquences sur l’autonomie, l’interprétation et l’agentivité d’une personne sur son expérience. / Digital phenotyping leverages the numerous sensors of smartphones (e.g., accelerometer, GPS, Bluetooth, call metadata) to measure daily human behavior without interference and link it to psychiatric symptoms and mental health indicators. Machine learning is an integral component of processing raw signals into intelligible information for clinicians. This approach emerges from a will to characterize symptom profiles and their temporal variations at an individual level. This project consisted in predicting mental health variables (e.g., stress, mood, sociability, hallucination) up to seven days in the future from smartphone data for patients with a diagnosis of schizophrenia. The CrossCheck dataset, which has a sample of 62 participants, was used. It includes 23,551 days of phone sensor data with 29 features, and 6364 mental state self-reports on 4-point ordinal scales. Ordinal predictive models were used to generate discrete predictions that can be interpreted using the guidelines from the clinical data collection scale. In total, 240 machine learning models were trained, i.e., combinations of 10 mental health variables, 3 forecast horizons (same day, next day, next week), 2 algorithms (XGBoost, LSTM), and 4 learning tasks (binary classification, continuous regression, multiclass classification, ordinal regression). The ordinal and binary models performed significantly better than the baseline and the two other tasks with a macroaveraged mean absolute error between 1.436 and 0.767 and a balanced accuracy between 58% and 73%. Results showed a dominant effect of class imbalance on predictive performance and highlighted that metrics not accounting for it lead to systematic overestimation of performance. This analysis anchors a series of broader considerations about the use of artificial intelligence in healthcare. In particular, assessing the clinical value of machine learning solutions present distinctive challenges when compared to conventional treatments. The growing role of digital technologies in mental health has implication for autonomy, sense-making, and agentivity over one’s experience.

L’avènement de l’utilisation de systèmes d’intelligence artificielle (IA) en santé s’inscrit dans le cadre d’une nouvelle médecine « haute définition » qui se veut prédictive, préventive et personnalisée en tirant partie d’une quantité inédite de données aujourd’hui disponibles. Au cœur de l’innovation numérique en santé, le développement de systèmes d’IA est à la base d’un système de santé interconnecté et auto-apprenant qui permettrait, entre autres, de redéfinir la classification des maladies, de générer de nouvelles connaissances médicales, ou de prédire les trajectoires de santé des individus en vue d’une meilleure prévention. Différentes applications en santé de la recherche en IA sont envisagées, allant de l’aide à la décision médicale par des systèmes experts à la médecine de précision (ex. ciblage pharmacologique), en passant par la prévention individualisée grâce à des trajectoires de santé élaborées sur la base de marqueurs biologiques. Des préoccupations éthiques pressantes relatives à l’impact de l’IA sur nos sociétés émergent avec le recours grandissant aux algorithmes pour analyser un nombre croissant de données relatives à la santé (souvent personnelles, sinon sensibles) ainsi que la réduction de la supervision humaine de nombreux processus automatisés. Les limites de l’analyse des données massives, la nécessité de partage et l’opacité des décisions algorithmiques sont à la source de différentes préoccupations éthiques relatives à la protection de la vie privée et de l’intimité, au consentement libre et éclairé, à la justice sociale, à la déshumanisation des soins et du patient, ou encore à la sécurité. Pour répondre à ces enjeux, de nombreuses initiatives se sont penchées sur la définition et l’application de principes directeurs en vue d’une gouvernance éthique de l’IA. L’opérationnalisation de ces principes s’accompagne cependant de différentes difficultés de l’éthique appliquée, tant relatives à la portée (universelle ou plurielle) desdits principes qu’à la façon de les mettre en pratique (des méthodes inductives ou déductives). S’il semble que ces difficultés trouvent des réponses dans la démarche éthique (soit une approche sensible aux contextes d’application), cette manière de faire se heurte à différents défis. L’analyse des craintes et des attentes citoyennes qui émanent des discussions ayant eu lieu lors de la coconstruction de la Déclaration de Montréal relativement au développement responsable de l’IA permet d’en dessiner les contours. Cette analyse a permis de mettre en évidence trois principaux défis relatifs à l’exercice de la responsabilité qui pourrait nuire à la mise en place d’une gouvernance éthique de l’IA en santé : l’incapacitation des professionnels de santé et des patients, le problème des mains multiples et l’agentivité artificielle. Ces défis demandent de se pencher sur la création de systèmes d’IA capacitants et de préserver l’agentivité humaine afin de favoriser le développement d’une responsabilité (pragmatique) partagée entre les différentes parties prenantes du développement des systèmes d’IA en santé. Répondre à ces différents défis est essentiel afin d’adapter les mécanismes de gouvernance existants et de permettre le développement d’une innovation numérique en santé responsable, qui doit garder l’humain au centre de ses développements. / The use of artificial intelligence (AI) systems in health is part of the advent of a new "high definition" medicine that is predictive, preventive and personalized, benefiting from the unprecedented amount of data that is today available. At the heart of digital health innovation, the development of AI systems promises to lead to an interconnected and self-learning healthcare system. AI systems could thus help to redefine the classification of diseases, generate new medical knowledge, or predict the health trajectories of individuals for prevention purposes. Today, various applications in healthcare are being considered, ranging from assistance to medical decision-making through expert systems to precision medicine (e.g. pharmacological targeting), as well as individualized prevention through health trajectories developed on the basis of biological markers. However, urgent ethical concerns emerge with the increasing use of algorithms to analyze a growing number of data related to health (often personal and sensitive) as well as the reduction of human intervention in many automated processes. From the limitations of big data analysis, the need for data sharing and the algorithmic decision ‘opacity’ stems various ethical concerns relating to the protection of privacy and intimacy, free and informed consent, social justice, dehumanization of care and patients, and/or security. To address these challenges, many initiatives have focused on defining and applying principles for an ethical governance of AI. However, the operationalization of these principles faces various difficulties inherent to applied ethics, which originate either from the scope (universal or plural) of these principles or the way these principles are put into practice (inductive or deductive methods). These issues can be addressed with context-specific or bottom-up approaches of applied ethics. However, people who embrace these approaches still face several challenges. From an analysis of citizens' fears and expectations emerging from the discussions that took place during the coconstruction of the Montreal Declaration for a Responsible Development of AI, it is possible to get a sense of what these difficulties look like. From this analysis, three main challenges emerge: the incapacitation of health professionals and patients, the many hands problem, and artificial agency. These challenges call for AI systems that empower people and that allow to maintain human agency, in order to foster the development of (pragmatic) shared responsibility among the various stakeholders involved in the development of healthcare AI systems. Meeting these challenges is essential in order to adapt existing governance mechanisms and enable the development of a responsible digital innovation in healthcare and research that allows human beings to remain at the center of its development.

The adoption of digital health technologies has dramatically changed the healthcare sector landscape and thus generates new opportunities to collect, capture, store, access and retrieve electronic personal health information (ePHI). With the introduction of digital health technologies and the digitisation of health data, an increasing number of hospitals and peripheral health facilities across the globe are transitioning from a paper-based environment to an electronic or paper-light environment. However, the growing use of digital health technologies within healthcare facilities has caused ePHI to be exposed to a variety of threats such as cyber security threats, human-related threats, technological threats and environmental threats. These threats have the potential to cause harm to hospital systems and severely compromise the integrity and confidentiality of ePHI. Because of the growing number of security threats, many hospitals, both private and public, are struggling to secure ePHI due to a lack of robust data security plans, systems and security control measures. The purpose of this study was to explore the security of electronic personal health information in a public hospital in South Africa. The study was underpinned by the interpretivism paradigm with qualitative data collected through semi-structured interviews with purposively selected IT technicians, network controllers’, administrative clerks and records management clerks, and triangulated with document and system analysis. Audio-recorded interviews were transcribed verbatim. Data was coded and analysed using ATLAS.ti, version 8 software, to generate themes and codes within the data, from which findings were derived. The key results revealed that the public hospital is witnessing a deluge of sophisticated cyber threats such as worm viruses, Trojan horses and shortcut viruses. This is compounded by technological threats such as power and system failure, network connection failure, obsolete computers and operating systems, and outdated hospital systems. However, defensive security measures such as data encryption, windows firewall, antivirus software and security audit log system exist in the public hospital for securing and protecting ePHI against threats and breaches. The study recommended the need to implement Intrusion Protection System (IPS), and constantly update the Windows firewall and antivirus program to protect hospital computers and networks against newly released viruses and other malicious codes. In addition to the use of password and username to control access to ePHI in the public hospital, the study recommends that the hospital should put in place authentication mechanisms such as biometric system and Radio Frequency Identification (RFID) system restrict access to ePHI, as well as to upgrade hospital computers and the Patient Administration and Billing (PAAB) System. In the absence of security policy, there is a need for the hospital to put in place a clear written security policy aimed at protecting ePHI. The study concluded that healthcare organisations should upgrade the security of their information systems to protect ePHI stored in databases against unauthorised access, malicious codes and other cyber-attacks. / Information Science / M. Inf. (Information Security)

Stroke is a leading cause of disability worldwide, and access to rehabilitation is crucial for recovery. This study examines the potential of digital technologies to improve the rehabilitation experience of stroke survivors in Scania, Sweden. The use of digital tools and telerehabilitation in stroke rehabilitation in Scania remains largely unexplored. Through qualitative interviews with 12 stroke survivors, 1 stroke survivor relative, and 6 healthcare professionals, this study identifies four key themes that play a significant role in the rehabilitation process: Access to care and rehabilitation, Motivation, Psychological and emotional needs, and Social support net. Based on these findings, the study proposes several "digital suggestions" to improve the rehabilitation process, including utilizing digital physio- and occupational therapy and improving alignment between various digital systems within the region. The study emphasizes the importance of individual adaptation in stroke rehabilitation, which aligns with the overarching goal of Swedish healthcare to provide patientcentered care. The findings of this study can inform future work with digital opportunities in Scania's stroke care and rehabilitation, potentially leading to better outcomes for stroke survivors.

Introduktion: Den äldre befolkningen ökar och många känner sig ensamma och isolerade. Det är en folkhälsoutmaning att hitta lösningar till detta problem då ofrivillig ensamhet kan leda till psykisk ohälsa. Ett av de globala målen är att bekämpa ojämlikhet i hälsa, så genom att samhället arbetar med preventiva insatser i gruppen äldre kan det bidra till ökad jämlikhet i samhället. Syfte: Att beskriva de samhälleliga insatserna som kan göras för att motverka ofrivillig ensamhet hos äldre. Metod: En litteraturstudie baserad på 20 vetenskapliga originalartiklar som inhämtats från databaserna PubMed, Medline Ebsco och CINAHL. Artiklarna analyserades med en tematisk analys. De mest använda sökorden var elderly people, loneliness, prevention, intervention och effective. Resultat: Åtta teman på vad som motverkar ofrivillig ensamhet återfanns och som grupperades i tre kategorier, samtliga teman var socialt stöd, digital teknik, kontaktskapande sällskap, fysisk aktivitet, primärvård, sociala interaktioner, psykiskt välbefinnande och digitala sociala interventioner. Slutsats: Studiens resultat visar att samhällets insatser bidrar till att minska ofrivillig ensamhet och isolering bland äldre. Samhället behöver också utveckla arbetet och vara mer lyhörd enligt de äldres önskemål. Fler studier behövs, speciellt hur digitaliseringen kan utvecklas och användes till de äldres fördel. / Introduction: The elderly population is increasing and many feel lonely and isolated. It is a public health challenge to find solutions to this problem as involuntary loneliness can lead to mental illness. One of the global goals is to fight inequality in health, so by society working with preventive measures in the group of older people, it can contribute to increased equality in society. Aim: To describe the social efforts that can be made to counteract involuntary loneliness in the elderly. Method: A literature study based on 20 original scientific articles obtained from the databases PubMed, Medline Ebsco and CINAHL. The articles were analyzed with a thematic analysis. The most used keywords were elderly people, loneliness, prevention, intervention and effective. Results: Eight themes of counteracting involuntary loneliness were found and grouped into three categories, all themes were social support, digital technology, contact-creating societies, physical activity, primary care, social interactions, mental well-being and digital social interventions. Conclusion: The results of the study show that society's efforts contribute to reducing involuntary loneliness and isolation among the elderly. Society also needs to develop its work and be more responsive to the wishes of the elderly. More studies are needed, especially how digitization can be developed and used to the benefit of the elderly.

<p>The rapid expansion of consumer Internet-of-Things (IoT) technology across various application domains has made it one of the most sought-after and swiftly evolving technologies. IoT devices offer numerous benefits, such as enhanced security, convenience, and cost reduction. However, as these devices need access to sensitive aspects of human life to function effectively, their abuse can lead to significant financial, psychological, and physical harm. While previous studies have examined the vulnerabilities of IoT devices, insufficient research has delved into the impact and mitigation of threats to users' privacy and safety. This dissertation addresses the challenge of protecting user safety and privacy against threats posed by IoT device vulnerabilities. We first introduce a novel IWMD architecture, which serves as the last line of defense against unsafe operations of Implantable and Wearable Medical Devices (IWMDs). We demonstrate the architecture's effectiveness through a prototype artificial pancreas. Subsequent chapters emphasize the safety and privacy of smart home device users. First, we propose a unique device activity-based categorization and learning approach for network traffic analysis. Utilizing this technology, we present a new smart home security framework and a device type identification mechanism to enhance transparency and access control in smart home device communication. Lastly, we propose a novel traffic shaping technique that hinders adversaries from discerning user activities through traffic analysis. Experiments conducted on commercially available IoT devices confirm that our solutions effectively address these issues with minimal overhead.</p>

No description available.

This thesis investigates the application of TrueBalance, a conversational agent designed to support young adults vulnerable to eating disorders (EDs). TrueBalance integrates Cognitive Behavioral Therapy (CBT) techniques with biomedical insights, including genetic and neurobiological factors, to provide a more personalized and scientifically grounded support system. It addresses limitations in existing dietary monitoring tools that usually focus on calorie tracking and food intake, often neglecting the nuanced needs of specific groups like young females and elite athletes, who are particularly vulnerable to EDs and disordered eating behaviors.  The study addresses how biomedical determinants can be integrated into a conversational agent, how these agents can utilize CBT principles to support individuals vulnerable to EDs, and what challenges and opportunities arise from the user’s perspective when using such a dialogue model. The research strives to bridge the gap in current dietary self-monitoring tools by offering a more robust and empathetic support system for individuals struggling with EDs. Through iterative development and user testing, TrueBalance has demonstrated its potential as an engaging educational tool. Feedback from both therapists and users has highlighted the tool’s utility in real-world settings. It has led to suggestions for enhancements in personalizing interactions and making response systems more adaptive. The findings suggest conversational agents like TrueBalance have potential in non-clinical support environments for individuals with EDs and function as a potential informative, supportive tool for therapists’ education. / Denna masteruppsats undersöker användningen av TrueBalance, en konversationsagent designad för att stödja unga vuxna som är sårbara för ätstörningar. TrueBalance integrerar tekniker från Kognitiv beteendeterapi (KBT) med biomedicinska insikter, inklusive genetiska och neurobiologiska faktorer, för att tillhandahålla ett mer personligt och vetenskapligt förankrat stödsystem. Den tar itu med begränsningarna i befintliga verktyg för kostövervakning, som vanligtvis fokuserar på kalorispårning och matintag men ofta förbiser de nyanserade behoven hos specifika grupper, såsom unga kvinnor och elitidrottare, som är särskilt sårbara för ätstörningar och ätstörda beteenden. Studien behandlar hur biomedicinska determinanter kan integreras i en konversationsagent, hur dessa agenter kan använda KBT-principer för att stödja individer sårbara för ätstörningar, samt vilka utmaningar och möjligheter som uppstår från användarens perspektiv när de använder en sådan dialogmodell. Forskningen strävar efter att överbrygga klyftan i nuvarande verktyg för kostövervakning genom att erbjuda ett robustare och mer empatiskt stödsystem för individer som kämpar med ätstörningar. Genom iterativ utveckling och användartester har TrueBalance visat sin potential som ett engagerande pedagogiskt verktyg. Återkoppling från både terapeuter och användare har belyst verktygets nytta i verkliga sammanhang. Det har lett till förslag på förbättringar för att personalisera interaktioner och göra responssystemen mer adaptiva. Resultaten tyder på att konversationsagenter som TrueBalance har potential i icke-kliniska stödmiljöer för individer med ätstörningar och kan fungera som ett potentiellt informativt, stödjande verktyg för terapeuters utbildning.