Defining disease severity in atopic dermatitis and psoriasis for the application to biomarker research: an interdisciplinary perspective.

More severe atopic dermatitis and psoriasis are associated with a higher cumulative impact on quality of life, multimorbidity and healthcare costs. Proactive, early intervention in those most at risk of severe disease may reduce this cumulative burden and modify the disease trajectory to limit progression. The lack of reliable biomarkers for this at-risk group represents a barrier to such a paradigm shift in practice. To expedite discovery and validation, the BIOMarkers in Atopic Dermatitis and Psoriasis (BIOMAP) consortium (a large-scale European, interdisciplinary research initiative) has curated clinical and molecular data across diverse study designs and sources including cross-sectional and cohort studies (small-scale studies through to large multicentre registries), clinical trials, electronic health records and large-scale population-based biobanks. We map all dataset disease severity instruments and measures to three key domains (symptoms, inflammatory activity and disease course), and describe important codependencies and relationships across variables and domains. We prioritize definitions for more severe disease with reference to international consensus, reference standards and/or expert opinion. Key factors to consider when analysing datasets across these diverse study types include explicit early consideration of biomarker purpose and clinical context, candidate biomarkers associated with disease severity at a particular point in time and over time and how they are related, taking the stage of biomarker development into account when selecting disease severity measures for analyses, and validating biomarker associations with disease severity outcomes using both physician- and patient-reported measures and across domains. The outputs from this exercise will ensure coherence and focus across the BIOMAP consortium so that mechanistic insights and biomarkers are clinically relevant, patient-centric and more generalizable to current and future research efforts.

Atopic dermatitis (AD), and psoriasis are long-term skin conditions that can significantly affect people's lives, especially when symptoms are severe. Approximately 10% of adults and 20% of children are affected by AD, while psoriasis affects around 5% of people in the UK. Both conditions are associated with debilitating physical symptoms (such as itch) and have been linked to depression and anxiety. Biomarkers are naturally occurring chemicals in the human body and have potential to enhance the longer-term management of AD and psoriasis. Currently, there are no routinely used biomarkers that can identify people who experience or will go on to develop severe AD and psoriasis. For this reason, research is under way to understand which biomarkers are linked to severity. In this study, a multidisciplinary team of skin researchers from across Europe, along with patient groups, discussed the complexities of studying severity-related biomarkers. We identified a number of severity measurement approaches and there were recommendations for future biomarker research, including (i) considering multiple measures as no single measure can encompass all aspects of severity, (ii) exploring severity measures recorded by both healthcare professionals and patients, as each may capture different aspects, and (iii) accounting for influencing factors, such as different treatment approaches, that may impact AD and psoriasis severity, which make it challenging to compare findings across studies. Overall, we anticipate that the insights gained from these discussions will increase the likelihood of biomarkers being effectively applied in real-world settings, to ultimately improve outcomes for people with AD and psoriasis.

Ethical layering in AI-driven polygenic risk scores-New complexities, new challenges.

Researchers aim to develop polygenic risk scores as a tool to prevent and more effectively treat serious diseases, disorders and conditions such as breast cancer, type 2 diabetes mellitus and coronary heart disease. Recently, machine learning techniques, in particular deep neural networks, have been increasingly developed to create polygenic risk scores using electronic health records as well as genomic and other health data. While the use of artificial intelligence for polygenic risk scores may enable greater accuracy, performance and prediction, it also presents a range of increasingly complex ethical challenges. The ethical and social issues of many polygenic risk score applications in medicine have been widely discussed. However, in the literature and in practice, the ethical implications of their confluence with the use of artificial intelligence have not yet been sufficiently considered. Based on a comprehensive review of the existing literature, we argue that this stands in need of urgent consideration for research and subsequent translation into the clinical setting. Considering the many ethical layers involved, we will first give a brief overview of the development of artificial intelligence-driven polygenic risk scores, associated ethical and social implications, challenges in artificial intelligence ethics, and finally, explore potential complexities of polygenic risk scores driven by artificial intelligence. We point out emerging complexity regarding fairness, challenges in building trust, explaining and understanding artificial intelligence and polygenic risk scores as well as regulatory uncertainties and further challenges. We strongly advocate taking a proactive approach to embedding ethics in research and implementation processes for polygenic risk scores driven by artificial intelligence.

You Can't Have AI Both Ways: Balancing Health Data Privacy and Access Fairly.

Artificial intelligence (AI) in healthcare promises to make healthcare safer, more accurate, and more cost-effective. Public and private actors have been investing significant amounts of resources into the field. However, to benefit from data-intensive medicine, particularly from AI technologies, one must first and foremost have access to data. It has been previously argued that the conventionally used "consent or anonymize approach" undermines data-intensive medicine, and worse, may ultimately harm patients. Yet, this is still a dominant approach in European countries and framed as an either-or choice. In this paper, we contrast the different data governance approaches in the EU and their advantages and disadvantages in the context of healthcare AI. We detail the ethical trade-offs inherent to data-intensive medicine, particularly the balancing of data privacy and data access, and the subsequent prioritization between AI and other effective health interventions. If countries wish to allocate resources to AI, they also need to make corresponding efforts to improve (secure) data access. We conclude that it is unethical to invest significant amounts of public funds into AI development whilst at the same time limiting data access through strict privacy measures, as this constitutes a waste of public resources. The "AI revolution" in healthcare can only realise its full potential if a fair, inclusive engagement process spells out the values underlying (trans) national data governance policies and their impact on AI development, and priorities are set accordingly.