Enabling Global Clinical Collaborations on Identifiable Patient Data: The Minerva Initiative

GestaltMatcher Database - A global reference for the facial phenotypic variability of rare human diseases

Dysmorphologists sometimes encounter challenges in recognizing disorders due to phenotypic variability influenced by factors such as age and ethnicity. Moreover, the performance of Next Generation Phenotyping Tools such as GestaltMatcher is dependent on the diversity of the training set. Therefore, we developed GestaltMatcher Database (GMDB) - a global reference for the phenotypic variability of rare diseases that complies with the FAIR-principles. We curated dysmorphic patient images and metadata from 2,224 publications, transforming GMDB into an online dynamic case report journal. To encourage clinicians worldwide to contribute, each case can receive a Digital Object Identifier (DOI), making it a citable micro-publication. This resulted in a collection of 2,312 unpublished images, partly with longitudinal data. We have compiled a collection of 10,189 frontal images from 7,695 patients representing 683 disorders. The web interface enables gene- and phenotype-centered queries for registered users (https://db.gestaltmatcher.org/). Despite the predominant European ancestry of most patients (59%), our global collaborations have facilitated the inclusion of data from frequently underrepresented ethnicities, with 17% Asian, 4% African, and 6% with other ethnic backgrounds. The analysis has revealed a significant enhancement in GestaltMatcher performance across all ethnic groups, incorporating non-European ethnicities, showcasing a remarkable increase in Top-1-Accuracy by 31.56% and Top-5-Accuracy by 12.64%. Importantly, this improvement was achieved without altering the performance metrics for European patients. GMDB addresses dysmorphology challenges by representing phenotypic variability and including underrepresented groups, enhancing global diagnostic rates and serving as a vital clinician reference database.

Computational facial analysis for rare Mendelian disorders

With the advances in computer vision, computational facial analysis has become a powerful and effective tool for diagnosing rare disorders. This technology, also called next-generation phenotyping (NGP), has progressed significantly over the last decade. This review paper will introduce three key NGP approaches. In 2014, Ferry et al. first presented Clinical Face Phenotype Space (CFPS) trained on eight syndromes. After 5 years, Gurovich et al. proposed DeepGestalt, a deep convolutional neural network trained on more than 21,000 patient images with 216 disorders. It was considered a state-of-the-art disorder classification framework. In 2022, Hsieh et al. developed GestaltMatcher to support the ultra-rare and novel disorders not supported in DeepGestalt. It further enabled the analysis of facial similarity presented in a given cohort or multiple disorders. Moreover, this article will present the usage of NGP for variant prioritization and facial gestalt delineation. Although NGP approaches have proven their capability in assisting the diagnosis of many disorders, many limitations remain. This article will introduce two future directions to address two main limitations: enabling the global collaboration for a medical imaging database that fulfills the FAIR principles and synthesizing patient images to protect patient privacy. In the end, with more and more NGP approaches emerging, we envision that the NGP technology can assist clinicians and researchers in diagnosing patients and analyzing disorders in multiple directions in the near future.

Democratising or disrupting diagnosis? Ethical issues raised by the use of AI tools for rare disease diagnosis

Computational phenotyping (CP) technology uses facial recognition algorithms to classify and potentially diagnose rare genetic disorders on the basis of digitised facial images. This AI technology has a number of research as well as clinical applications, such as supporting diagnostic decision-making. Using the example of CP, we examine stakeholders' views of the benefits and costs of using AI as a diagnostic tool within the clinic. Through a series of in-depth interviews (n ​= ​20) with: clinicians, clinical researchers, data scientists, industry and support group representatives, we report stakeholder views regarding the adoption of this technology in a clinical setting. While most interviewees were supportive of employing CP as a diagnostic tool in some capacity we observed ambivalence around the potential for artificial intelligence to overcome diagnostic uncertainty in a clinical context. Thus, while there was widespread agreement amongst interviewees concerning the public benefits of AI assisted diagnosis, namely, its potential to increase diagnostic yield and enable faster more objective and accurate diagnoses by up skilling non specialists and thereby enabling access to diagnosis that is potentially lacking, interviewees also raised concerns about ensuring algorithmic reliability, expunging algorithmic bias and that the use of AI could result in deskilling the specialist clinical workforce. We conclude that, prior to widespread clinical implementation, on-going reflection is needed regarding the trade-offs required to determine acceptable levels of bias and conclude that diagnostic AI tools should only be employed as an assistive technology within the dysmorphology clinic.

The ethical and legal landscape of brain data governance

Neuroscience research is producing big brain data which informs both advancements in neuroscience research and drives the development of advanced datasets to provide advanced medical solutions. These brain data are produced under different jurisdictions in different formats and are governed under different regulations. The governance of data has become essential and critical resulting in the development of various governance structures to ensure that the quality, availability, findability, accessibility, usability, and utility of data is maintained. Furthermore, data governance is influenced by various ethical and legal principles. However, it is still not clear what ethical and legal principles should be used as a standard or baseline when managing brain data due to varying practices and evolving concepts. Therefore, this study asks what ethical and legal principles shape the current brain data governance landscape? A systematic scoping review and thematic analysis of articles focused on biomedical, neuro and brain data governance was carried out to identify the ethical and legal principles which shape the current brain data governance landscape. The results revealed that there is currently a large variation of how the principles are presented and discussions around the terms are very multidimensional. Some of the principles are still at their infancy and are barely visible. A range of principles emerged during the thematic analysis providing a potential list of principles which can provide a more comprehensive framework for brain data governance and a conceptual expansion of neuroethics.

“I don’t think people are ready to trust these algorithms at face value”: trust and the use of machine learning algorithms in the diagnosis of rare disease

Background

As the use of AI becomes more pervasive, and computerised systems are used in clinical decision-making, the role of trust in, and the trustworthiness of, AI tools will need to be addressed. Using the case of computational phenotyping to support the diagnosis of rare disease in dysmorphology, this paper explores under what conditions we could place trust in medical AI tools, which employ machine learning.

Methods

Semi-structured qualitative interviews (n = 20) with stakeholders (clinical geneticists, data scientists, bioinformaticians, industry and patient support group spokespersons) who design and/or work with computational phenotyping (CP) systems. The method of constant comparison was used to analyse the interview data.

Results

Interviewees emphasized the importance of establishing trust in the use of CP technology in identifying rare diseases. Trust was formulated in two interrelated ways in these data. First, interviewees talked about the importance of using CP tools within the context of a trust relationship; arguing that patients will need to trust clinicians who use AI tools and that clinicians will need to trust AI developers, if they are to adopt this technology. Second, they described a need to establish trust in the technology itself, or in the knowledge it provides—epistemic trust. Interviewees suggested CP tools used for the diagnosis of rare diseases might be perceived as more trustworthy if the user is able to vouchsafe for the technology’s reliability and accuracy and the person using/developing them is trusted.

Conclusion

This study suggests we need to take deliberate and meticulous steps to design reliable or confidence-worthy AI systems for use in healthcare. In addition, we need to devise reliable or confidence-worthy processes that would give rise to reliable systems; these could take the form of RCTs and/or systems of accountability transparency and responsibility that would signify the epistemic trustworthiness of these tools. words 294.

Digital/computational phenotyping: What are the differences in the science and the ethics?

The concept of 'digital phenotyping' was originally developed by researchers in the mental health field, but it has travelled to other disciplines and areas. This commentary draws upon our experiences of working in two scientific projects that are based at the University of Oxford's Big Data Institute - The RADAR-AD project and The Minerva Initiative - which are developing algorithmic phenotyping technologies. We describe and analyse the concepts of digital biomarkers and computational phenotyping that underlie these projects, explain how they are linked to other research in digital phenotyping and compare and contrast some of their epistemological and ethical implications. In particular, we argue that the phenotyping paradigm in both projects is grounded on an assumption of 'objectivity' that is articulated in different ways depending on the role that is given to the computational/digital tools. Using the concept of 'affordance', we show how specific functionalities relate to potential uses and social implications of these technologies and argue that it is important to distinguish among them as the concept of digital phenotyping is increasingly being used with a variety of meanings.

Quantitative facial phenotyping for Koolen-de Vries and 22q11.2 deletion syndrome

The Koolen-de Vries syndrome (KdVS) is a multisystem syndrome with variable facial features caused by a 17q21.31 microdeletion or KANSL1 truncating variant. As the facial gestalt of KdVS has resemblance with the gestalt of the 22q11.2 deletion syndrome (22q11.2DS), we assessed whether our previously described hybrid quantitative facial phenotyping algorithm could distinguish between these two syndromes, and whether there is a facial difference between the molecular KdVS subtypes. We applied our algorithm to 2D photographs of 97 patients with KdVS (78 microdeletions, 19 truncating variants (likely) causing KdVS) and 48 patients with 22q11.2DS as well as age, gender and ethnicity matched controls with intellectual disability (n = 145). The facial gestalts of KdVS and 22q11.2DS were both recognisable through significant clustering by the hybrid model, yet different from one another (p = 7.5 × 10^-10 and p = 0.0052, respectively). Furthermore, the facial gestalts of KdVS caused by a 17q21.31 microdeletion and KANSL1 truncating variant (likely) causing KdVS were indistinguishable (p = 0.981 and p = 0.130). Further application to three patients with a variant of unknown significance in KANSL1 showed that these faces do not match KdVS. Our data highlight quantitative facial phenotyping not only as a powerful tool to distinguish syndromes with overlapping facial dysmorphisms but also to establish pathogenicity of variants of unknown clinical significance.

Is Sharing Datasets the Answer to the New Challenges of Reproductive Biology Research?

Data sharing increases the speed of research and saves time and resources while ensuring transparency and reproducibility. We have analyzed this behavior through the reproductive biology community. Our study revealed that Q1 (44%) and Q2 (36%) JCR reproductive biology journals are the most active journals in data sharing.

The case for open science: rare diseases

The premise of Open Science is that research and medical management will progress faster if data and knowledge are openly shared. The value of Open Science is nowhere more important and appreciated than in the rare disease (RD) community. Research into RDs has been limited by insufficient patient data and resources, a paucity of trained disease experts, and lack of therapeutics, leading to long delays in diagnosis and treatment. These issues can be ameliorated by following the principles and practices of sharing that are intrinsic to Open Science. Here, we describe how the RD community has adopted the core pillars of Open Science, adding new initiatives to promote care and research for RD patients and, ultimately, for all of medicine. We also present recommendations that can advance Open Science more globally.

Towards standardization guidelines for in silico approaches in personalized medicine

Despite the ever-progressing technological advances in producing data in health and clinical research, the generation of new knowledge for medical benefits through advanced analytics still lags behind its full potential. Reasons for this obstacle are the inherent heterogeneity of data sources and the lack of broadly accepted standards. Further hurdles are associated with legal and ethical issues surrounding the use of personal/patient data across disciplines and borders. Consequently, there is a need for broadly applicable standards compliant with legal and ethical regulations that allow interpretation of heterogeneous health data through in silico methodologies to advance personalized medicine. To tackle these standardization challenges, the Horizon2020 Coordinating and Support Action EU-STANDS4PM initiated an EU-wide mapping process to evaluate strategies for data integration and data-driven in silico modelling approaches to develop standards, recommendations and guidelines for personalized medicine. A first step towards this goal is a broad stakeholder consultation process initiated by an EU-STANDS4PM workshop at the annual COMBINE meeting (COMBINE 2019 workshop report in same issue). This forum analysed the status quo of data and model standards and reflected on possibilities as well as challenges for cross-domain data integration to facilitate in silico modelling approaches for personalized medicine.

Optimizing Genetic Diagnosis of Neurodevelopmental Disorders in the Clinical Setting

Progress in medical genetics has changed the practice of medicine in general and child neurology in particular. A genetic diagnosis has become critically important in determining optimal management of many neurodevelopmental disorders, making genetic testing a routine consideration of patient care in outpatient and inpatient settings. Today's child neurologists should be familiar with various genetic testing modalities and their appropriate use. Molecular genetic testing of children with unexplained developmental delays and/or congenital anomalies has a 20% to 30% chance of identifying a causative etiology. Newer methods have made genetic testing more widely available and sensitive but also more likely to produce ambiguous results.

Digitizing the Pharma Neurons - A Technological Operation in Progress!

BACKGROUND

Digitization and automation are the buzzwords in clinical research and pharma companies are investigating heavily here. Right from drug discovery to personalized medicine, digital patients and patient engagement, there is great consideration of technology at each step.

METHODS

The published data and online information available is reviewed to give an overview of digitization in pharma, across the drug development cycle, industry collaborations and innovations. The regulatory guidelines, innovative collaborations across industry, academics and thought leadership are presented. Also included are some ideas, suggestions, way forwards while digitizing the pharma neurons, the regulatory stand, benefits and challenges.

RESULTS

The innovations range from discovering personalized medicine to conducting virtual clinical trials, and maximizing data collection from the real-world experience. To address the increasing demand for the real-world data and the needs of tech-savvy patients, the innovations are shaping up accordingly. Pharma companies are collaborating with academics and they are co-innovating the technology for example Massachusetts Institute of Technology's program. This focuses on the modernization of clinical trials, strategic use of artificial intelligence and machine learning using real-world evidence, assess the risk-benefit ratio of deploying digital analytics in medicine, and proactively identifying the solutions.

CONCLUSION

With unfolding data on the impact of science and technology amalgamation, we need shared mindset between data scientists and medical professionals to maximize the utility of enormous health and medical data. To tackle this efficiently, there is a need of cross-collaboration and education, and align with ethical and regulatory requirements. A perfect blend of industry, regulatory, and academia will ensure successful digitization of pharma neurons.