Suchergebnisse

Aims: In three days at the beginning of the COVID-19 pandemic, the Copenhagen Emergency Medical Services developed a digital diagnostic device. The purpose was to assess and triage potential COVID-19 symptoms and to reduce the number of calls to public health-care helplines. The device was used almost 150,000 times in a few weeks and was described by politicians and administrators as a solution and success. However, high usage cannot serve as the sole criterion of success. What might be adequate criteria? And should digital triage for citizens by default be considered low risk? Methods: This paper reflects on the uncertain aspects of the performance, risks and issues of accountability pertaining to the digital diagnostic device in order to draw lessons for future improvements. The analysis is based on the principles of evidence-based medicine (EBM), the EU and US regulations of medical devices and the taxonomy of uncertainty in health care by Han et al. Results: Lessons for future digital devices are (a) the need for clear criteria of success, (b) the importance of awareness of other severe diseases when triaging, (c) the priority of designing the device to collect data for evaluation and (d) clear allocation of responsibilities. Conclusions: A device meant to substitute triage for citizens according to its own criteria of success should not by default be considered as low risk. In a pandemic age dependent on digitalisation, it is therefore important not to abandon the ethos of EBM, but instead to prepare the ground for new ways of building evidence of effect.

AIMS: In three days at the beginning of the COVID-19 pandemic, the Copenhagen Emergency Medical Services developed a digital diagnostic device. The purpose was to assess and triage potential COVID-19 symptoms and to reduce the number of calls to public health-care helplines. The device was used almost 150,000 times in a few weeks and was described by politicians and administrators as a solution and success. However, high usage cannot serve as the sole criterion of success. What might be adequate criteria? And should digital triage for citizens by default be considered low risk? METHODS: This paper reflects on the uncertain aspects of the performance, risks and issues of accountability pertaining to the digital diagnostic device in order to draw lessons for future improvements. The analysis is based on the principles of evidence-based medicine (EBM), the EU and US regulations of medical devices and the taxonomy of uncertainty in health care by Han et al. RESULTS: Lessons for future digital devices are (a) the need for clear criteria of success, (b) the importance of awareness of other severe diseases when triaging, (c) the priority of designing the device to collect data for evaluation and (d) clear allocation of responsibilities. CONCLUSIONS: A device meant to substitute triage for citizens according to its own criteria of success should not by default be considered as low risk. In a pandemic age dependent on digitalisation, it is therefore important not to abandon the ethos of EBM, but instead to prepare the ground for new ways of building evidence of effect.

AbstractIn contemporary policy discourses, data are presented as key assets for improving health‐care quality: policymakers want health care to become 'data driven'. In this article, we focus on a particular example of this ambition, namely a new Danish national quality development program for general practitioners (GPs) where doctors are placed in so‐called 'clusters'. In these clusters, GPs are obliged to assess their own and colleagues' clinical quality with data derived from their own clinics—using comparisons, averages and benchmarks. Based on semi‐structured interviews with Danish GPs and drawing on Science and Technology Studies, we explore how GPs understand these data, and what makes them trust—or question—a data analysis. The GPs describe how they change clinical practices based on these discussions of data. So, when and how do data for quality assurance come to influence their perceptions of quality? By exploring these issues, we carve out a role for a sociological engagement with evidence in everyday medical practices. In conclusion, we suggest a need to move from the aim of being data driven to one of being data informed.

This paper documents how an ethically aligned co-design methodology ensures trustworthiness in the early design phase of an artificial intelligence (AI) system component for healthcare. The system explains decisions made by deep learning networks analyzing images of skin lesions. The co-design of trustworthy AI developed here used a holistic approach rather than a static ethical checklist and required a multidisciplinary team of experts working with the AI designers and their managers. Ethical, legal, and technical issues potentially arising from the future use of the AI system were investigated. This paper is a first report on co-designing in the early design phase. Our results can also serve as guidance for other early-phase AI-similar tool developments.

Artificial Intelligence (AI) has the potential to greatly improve the delivery of healthcare and other services that advance population health and wellbeing. However, the use of AI in healthcare also brings potential risks that may cause unintended harm. To guide future developments in AI, the High-Level Expert Group on AI set up by the European Commission (EC), recently published ethics guidelines for what it terms "trustworthy" AI. These guidelines are aimed at a variety of stakeholders, especially guiding practitioners toward more ethical and more robust applications of AI. In line with efforts of the EC, AI ethics scholarship focuses increasingly on converting abstract principles into actionable recommendations. However, the interpretation, relevance, and implementation of trustworthy AI depend on the domain and the context in which the AI system is used. The main contribution of this paper is to demonstrate how to use the general AI HLEG trustworthy AI guidelines in practice in the healthcare domain. To this end, we present a best practice of assessing the use of machine learning as a supportive tool to recognize cardiac arrest in emergency calls. The AI system under assessment is currently in use in the city of Copenhagen in Denmark. The assessment is accomplished by an independent team composed of philosophers, policy makers, social scientists, technical, legal, and medical experts. By leveraging an interdisciplinary team, we aim to expose the complex trade-offs and the necessity for such thorough human review when tackling socio-technical applications of AI in healthcare. For the assessment, we use a process to assess trustworthy AI, called 1Z-Inspection® to identify specific challenges and potential ethical trade-offs when we consider AI in practice.