Are the European reference networks for rare diseases ready to embrace machine learning? A mixed-methods study.

BACKGROUND: The delay in diagnosis for rare disease (RD) patients is often longer than for patients with common diseases. Machine learning (ML) technologies have the potential to speed up and increase the precision of diagnosis in this population group. We aim to explore the expectations and experiences of the members of the European Reference Networks (ERNs) for RDs with those technologies and their potential for application. METHODS: We used a mixed-methods approach with an online survey followed by a focus group discussion. Our study targeted primarily medical professionals but also other individuals affiliated with any of the 24 ERNs. RESULTS: The online survey yielded 423 responses from ERN members. Participants reported a limited degree of knowledge of and experience with ML technologies. They considered improved diagnostic accuracy the most important potential benefit, closely followed by the synthesis of clinical information, and indicated the lack of training in these new technologies, which hinders adoption and implementation in routine care. Most respondents supported the option that ML should be an optional but recommended part of the diagnostic process for RDs. Most ERN members saw the use of ML limited to specialised units only in the next 5 years, where those technologies should be funded by public sources. Focus group discussions concluded that the potential of ML technologies is substantial and confirmed that the technologies will have an important impact on healthcare and RDs in particular. As ML technologies are not the core competency of health care professionals, participants deemed a close collaboration with developers necessary to ensure that results are valid and reliable. However, based on our results, we call for more research to understand other stakeholders' opinions and expectations, including the views of patient organisations. CONCLUSIONS: We found enthusiasm to implement and apply ML technologies, especially diagnostic tools in the field of RDs, despite the perceived lack of experience. Early dialogue and collaboration between health care professionals, developers, industry, policymakers, and patient associations seem to be crucial to building trust, improving performance, and ultimately increasing the willingness to accept diagnostics based on ML technologies.

Rare diseases' genetic newborn screening as the gateway to future genomic medicine: the Screen4Care EU-IMI project.

Following the reverse genetics strategy developed in the 1980s to pioneer the identification of disease genes, genome(s) sequencing has opened the era of genomics medicine. The human genome project has led to an innumerable series of applications of omics sciences on global health, from which rare diseases (RDs) have greatly benefited. This has propelled the scientific community towards major breakthroughs in disease genes discovery, in technical innovations in bioinformatics, and in the development of patients' data registries and omics repositories where sequencing data are stored. Rare diseases were the first diseases where nucleic acid-based therapies have been applied. Gene therapy, molecular therapy using RNA constructs, and medicines modulating transcription or translation mechanisms have been developed for RD patients and started a new era of medical science breakthroughs. These achievements together with optimization of highly scalable next generation sequencing strategies now allow movement towards genetic newborn screening. Its applications in human health will be challenging, while expected to positively impact the RD diagnostic journey. Genetic newborn screening brings many complexities to be solved, technical, strategic, ethical, and legal, which the RD community is committed to address. Genetic newborn screening initiatives are therefore blossoming worldwide, and the EU-IMI framework has funded the project Screen4Care. This large Consortium will apply a dual genetic and digital strategy to design a comprehensive genetic newborn screening framework to be possibly translated into the future health care.

Genomic newborn screening: Are we entering a new era of screening?

Population newborn screening (NBS) for phenylketonuria began in the United States in 1963. In the 1990s electrospray ionization mass spectrometry permitted an array of pathognomonic metabolites to be identified simultaneously, enabling up to 60 disorders to be recognized with a single test. In response, differing approaches to the assessment of the harms and benefits of screening have resulted in variable screening panels worldwide. Thirty years on and another screening revolution has emerged with the potential for first line genomic testing extending the range of screening conditions recognized after birth to many hundreds. At the annual SSIEM conference in 2022 in Freiburg, Germany, an interactive plenary discussion on genomic screening strategies and their challenges and opportunities was conducted. The Genomics England Research project proposes the use of Whole Genome Sequencing to offer extended NBS to 100 000 babies for defined conditions with a clear benefit for the child. The European Organization for Rare Diseases seeks to include "actionable" conditions considering also other types of benefits. Hopkins Van Mil, a private UK research institute, determined the views of citizens and revealed as a precondition that families are provided with adequate information, qualified support, and that autonomy and data are protected. From an ethical standpoint, the benefits ascribed to screening and early treatment need to be considered in relation to asymptomatic, phenotypically mild or late-onset presentations, where presymptomatic treatment may not be required. The different perspectives and arguments demonstrate the unique burden of responsibility on those proposing new and far-reaching developments in NBS programs and the need to carefully consider both harms and benefits.