A5033075709- Artificial Intelligence in Healthcare and Education
- Mobile Health and mHealth Applications
- Technology Use by Older Adults
- Telemedicine and Telehealth Implementation
- Ethics in Clinical Research
- Persona Design and Applications
- Ethics and Social Impacts of AI
- Digital Mental Health Interventions
- Open Source Software Innovations
- Privacy, Security, and Data Protection
- Public Relations and Crisis Communication
- COVID-19 Digital Contact Tracing
- Family and Disability Support Research
- Radiomics and Machine Learning in Medical Imaging
- Spinal Cord Injury Research
- Data-Driven Disease Surveillance
- Health Literacy and Information Accessibility
- Patient-Provider Communication in Healthcare
- Explainable Artificial Intelligence (XAI)
- Knowledge Management and Sharing
- Migration, Health and Trauma
- Mental Health and Patient Involvement
- Education and experiences of immigrants and refugees
- Machine Learning in Healthcare
- Adversarial Robustness in Machine Learning
ETH Zurich
2020-2023
Swiss Paraplegic Research
2015-2021
Charité - Universitätsmedizin Berlin
2021
University of Lucerne
2015-2019
Abstract Background Explainability is one of the most heavily debated topics when it comes to application artificial intelligence (AI) in healthcare. Even though AI-driven systems have been shown outperform humans certain analytical tasks, lack explainability continues spark criticism. Yet, not a purely technological issue, instead invokes host medical, legal, ethical, and societal questions that require thorough exploration. This paper provides comprehensive assessment role medical AI makes...
Explainability for artificial intelligence (AI) in medicine is a hotly debated topic. Our paper presents review of the key arguments favor and against explainability AI-powered Clinical Decision Support System (CDSS) applied to concrete use case, namely an CDSS currently used emergency call setting identify patients with life-threatening cardiac arrest. More specifically, we performed normative analysis using socio-technical scenarios provide nuanced account role CDSSs allowing abstractions...
Artificial intelligence (AI) has the potential to transform clinical decision-making as we know it. Powered by sophisticated machine learning algorithms, decision support systems (CDSS) can generate unprecedented amounts of predictive information about individuals' health. Yet, despite these promote proactive and improve health outcomes, their utility impact remain poorly understood due still rare application in practice. Taking example AI-powered CDSS stroke medicine a case point, this...
Governments around the globe have started to develop and deploy digital contact tracing apps gain control over spread of novel coronavirus (Covid-19). The appropriateness usefulness these technologies as a containment measure since sparked political academic discussions globally. present paper contributes this debate through an exploration how national daily newspapers in Germany, Austria, Switzerland reported on development adoption contact-tracing during early after stages lockdown. These...
Involving the public in co-production of research to inform service delivery can help ensure appropriateness services. However, vulnerable groups are often systematically excluded from these activities. To raise awareness and stimulate discussion, this review 1) describes how currently involved aimed at improving services; (2) consolidates challenges researchers encountered instances; (3) produces an overview emergent solutions recommendations for overcoming challenges. The authors conclude...
The Covid-19 pandemic is characterized by uncertainty and constant change, forcing governments health authorities to ramp up risk communication efforts. Consequently, visuality social media platforms like Twitter have come play a vital role in disseminating prevention messages widely. Yet date, only little known about what characterizes visual during the pandemic. To address this gap literature, study's objective was determine how used on promote World Health Organisations (WHO) recommended...
This paper documents how an ethically aligned co-design methodology ensures trustworthiness in the early design phase of artificial intelligence (AI) system component for healthcare. The explains decisions made by deep learning networks analyzing images skin lesions. trustworthy AI developed here used a holistic approach rather than static ethical checklist and required multidisciplinary team experts working with designers their managers. Ethical, legal, technical issues potentially arising...
Spurred by recent advances in machine learning and electronic hardware, digital health promises to profoundly transform medicine. At the same time, however, it raises conspicuous ethical regulatory issues. This has led a growing number of calls for responsible health. Based on stakeholder engagement methods, this paper sets out identify core impediments hindering Switzerland. We developed participatory research methodology access stakeholders' fragmented knowledge health, engaging 46...
Abstract Background Because refugees face significant adversities before, during, and after resettlement, resilience is of central importance to this population. However, strengths-based research on post-migration refugee experiences sparse. Methods We conducted semi-structured interviews with 54 adult participants who arrived in Germany between 2013 2018 their preferred language. analyzed different aspects these using thematic analysis. Results Nine themes were identified. Four manifest...
Artificial Intelligence (AI) has the potential to greatly improve delivery of healthcare and other services that advance population health wellbeing. However, use AI in also brings risks may cause unintended harm. To guide future developments AI, High-Level Expert Group on set up by European Commission (EC), recently published ethics guidelines for what it terms “trustworthy” AI. These are aimed at a variety stakeholders, especially guiding practitioners toward more ethical robust...
This article's main contributions are twofold: 1) to demonstrate how apply the general European Union's High-Level Expert Group's (EU HLEG) guidelines for trustworthy AI in practice domain of healthcare and 2) investigate research question what does "trustworthy AI" mean at time COVID-19 pandemic. To this end, we present results a post-hoc self-assessment evaluate trustworthiness an system predicting multiregional score conveying degree lung compromise patients, developed verified by...
Background Spinal cord injury is a complex chronic health condition that requires individuals to actively self-manage. Therefore, an evidence-based, self-management app would be of value support with spinal in the prevention pressure injuries. Objective The main objectives this study were (1) establish co-design approach for developing high-fidelity prototype injury, (2) design resulted from process, and (3) conduct first usability assessment app. Methods We adopted develop evidence-based...
Abstract Governments around the globe have started to develop and deploy digital contact tracing apps gain control over spread of novel coronavirus (Covid-19). The appropriateness usefulness these technologies as a containment measure since sparked political academic discussions globally. present paper contributes this debate through an exploration how national daily newspapers in Germany, Austria, Switzerland reported on development adoption contact-tracing during early after stages...
Abstract Building artificial intelligence (AI) systems that adhere to ethical standards is a complex problem. Even though multitude of guidelines for the design and development such trustworthy AI exist, these focus on high-level abstract requirements systems, it often very difficult assess if specific system fulfills requirements. The Z-Inspection® process provides holistic dynamic framework evaluate trustworthiness at different stages lifecycle, including intended use, design, development....
The use of online communities to promote end user involvement and co-creation in the product service innovation process is well documented marketing management literature. Whereas are widely used for health care provision peer-to-peer support, only little known about how they could be integrated into process.The overall objective this qualitative study was explore community managers' views on experiences with knowledge people disabilities.A descriptive research design used. Data were...
Mobile health applications can offer tailored self-management support to individuals living with chronic conditions. However, there are several challenges the adoption of these technologies in practice. Co-design is a promising approach overcoming some by enabling development solutions that meet actual needs and preferences relevant stakeholder groups.Taking spinal cord injury as case point, overall objectives this study were identify perceived benefits co-designed app could promote its...
Introduction: Forcibly displaced people are at particular risk of mental health problems and also face specific integration challenges upon resettlement. Existing literature suggests that there may be a bidirectional relationship between integration. The present study seeks to understand the processes or significant negative emotional experiences among adult refugees in Germany. Method: Applying qualitative approach, we conducted 54 semi-structured interviews with asylum seekers who arrived...
Artificial intelligence (AI) has the potential to revolutionize healthcare, for example via decision support systems, computer vision approaches, or AI-based prevention tools. Initial results from AI applications in healthcare show promise but are rarely translated into clinical practice successfully and ethically. This occurs despite an abundance of "Trustworthy AI" guidelines. How can we explain translational gaps healthcare? paper offers a fresh perspective on this problem, showing that...
ABSTRACT One of the more interesting ideas for achieving personalized, preventive, and participatory medicine is concept a digital twin. A twin personalized computer model patient. So far, twins have been constructed using either mechanistic models, which can simulate trajectory physiological biochemical processes in person, or machine learning example be used to estimate risk having stroke given cross-section profile at timepoint. These two modelling approaches complementary strengths...
Qualitative exploratory study.To explore the lived experience of SCI caregivers, with a focus on challenges their role.Caregivers people living in community Switzerland.Data were collected through semi-structured interviews. Thematic analysis was performed.The sample included 22 participants (16 women, 15 life partners) mean age 61 years who had been caregivers for an average 18 years. Caregiving seemed to be characterized by two phases. The first phase relatively short and central becoming...