Linked Registries: Connecting Rare Diseases Patient Registries through a Semantic Web Layer

Framework for Multistakeholder Patient Registries in the Field of Rare Diseases: Focus on Neurogenetic Diseases

Progress in genetic diagnosis and orphan drug legislation has opened doors to new therapies in rare neurogenetic diseases (RNDs). Innovative therapies such as gene therapy can improve patients' quality of life but come with academic, regulatory, and financial challenges. Registries can play a pivotal role in generating evidence to tackle these, but their development requires multidisciplinary knowledge and expertise. This study aims to develop a practical framework for creating and implementing patient registries addressing common challenges and maximizing their impact on care, research, drug development, and regulatory decision making with a focus on RNDs. A comprehensive 3-step literature and qualitative research approach was used to develop the framework. A qualitative systematic literature review was conducted, extracting guidance and practices leading to the draft framework. Subsequently, we interviewed representatives of 5 established international RND registries to add learnings from hands-on experiences to the framework. Expert input on the draft framework was sought in digital multistakeholder focus groups to refine the framework. The literature search; interviews with 5 registries; and focus groups with patient representatives (n = 4), clinicians (n = 6), regulators, health technology assessment (HTA) bodies and payers (n = 7), industry representatives (n = 7), and data/information technology (IT) specialists (n = 5) informed development of the framework. It covers the interests of different stakeholders, purposes for data utilization, data aspects, IT infrastructure, governance, and financing of rare disease registries. Key principles include that data should be rapidly accessible, independent, and trustworthy. Governance should involve multiple stakeholders. In addition, data should be highly descriptive, machine-readable, and accessible through a shared infrastructure and not spread over multiple isolated repositories. Sustainable and independent financing of registries is deemed important but remains challenging because of a lack of widely supported funding models. The proposed framework will guide stakeholders in establishing or improving rare disease registries that fulfill requirements of academics and patients as well as regulators, HTA bodies, and commercial parties. There is a need for more clarity regarding quality requirements for registries in regulatory and HTA context. In addition, independent financing models for registries should be developed, as well as well-defined policies on technical uniformity in health data.

Navigating the uncommon: challenges in applying evidence-based medicine to rare diseases and the prospects of artificial intelligence solutions

The study of rare diseases has long been an area of challenge for medical researchers, with agonizingly slow movement towards improved understanding of pathophysiology and treatments compared with more common illnesses. The push towards evidence-based medicine (EBM), which prioritizes certain types of evidence over others, poses a particular issue when mapped onto rare diseases, which may not be feasibly investigated using the methodologies endorsed by EBM, due to a number of constraints. While other trial designs have been suggested to overcome these limitations (with varying success), perhaps the most recent and enthusiastically adopted is the application of artificial intelligence to rare disease data. This paper critically examines the pitfalls of EBM (and its trial design offshoots) as it pertains to rare diseases, exploring the current landscape of AI as a potential solution to these challenges. This discussion is also taken a step further, providing philosophical commentary on the weaknesses and dangers of AI algorithms applied to rare disease research. While not proposing a singular solution, this article does provide a thoughtful reminder that no 'one-size-fits-all' approach exists in the complex world of rare diseases. We must balance cautious optimism with critical evaluation of new research paradigms and technology, while at the same time not neglecting the ever-important aspect of patient values and preferences, which may be challenging to incorporate into computer-driven models.

Scoping review of the recommendations and guidance for improving the quality of rare disease registries

BACKGROUND

Rare disease registries (RDRs) are valuable tools for improving clinical care and advancing research. However, they often vary qualitatively, structurally, and operationally in ways that can determine their potential utility as a source of evidence to support decision-making regarding the approval and funding of new treatments for rare diseases.

OBJECTIVES

The goal of this research project was to review the literature on rare disease registries and identify best practices to improve the quality of RDRs.

METHODS

In this scoping review, we searched MEDLINE and EMBASE as well as the websites of regulatory bodies and health technology assessment agencies from 2010 to April 2023 for literature offering guidance or recommendations to ensure, improve, or maintain quality RDRs.

RESULTS

The search yielded 1,175 unique references, of which 64 met the inclusion criteria. The characteristics of RDRs deemed to be relevant to their quality align with three main domains and several sub-domains considered to be best practices for quality RDRs: (1) governance (registry purpose and description; governance structure; stakeholder engagement; sustainability; ethics/legal/privacy; data governance; documentation; and training and support); (2) data (standardized disease classification; common data elements; data dictionary; data collection; data quality and assurance; and data analysis and reporting); and (3) information technology (IT) infrastructure (physical and virtual infrastructure; and software infrastructure guided by FAIR principles (Findability; Accessibility; Interoperability; and Reusability).

CONCLUSIONS

Although RDRs face numerous challenges due to their small and dispersed populations, RDRs can generate quality data to support healthcare decision-making through the use of standards and principles on strong governance, quality data practices, and IT infrastructure.

Unravelling undiagnosed rare disease cases by HiFi long-read genome sequencing

Solve-RD is a pan-European rare disease (RD) research program that aims to identify disease-causing genetic variants in previously undiagnosed RD families. We utilised 10-fold coverage HiFi long-read sequencing (LRS) for detecting causative structural variants (SVs), single nucleotide variants (SNVs), insertion-deletions (InDels), and short tandem repeat (STR) expansions in extensively studied RD families without clear molecular diagnoses. Our cohort includes 293 individuals from 114 genetically undiagnosed RD families selected by European Rare Disease Network (ERN) experts. Of these, 21 families were affected by so-called 'unsolvable' syndromes for which genetic causes remain unknown, and 93 families with at least one individual affected by a rare neurological, neuromuscular, or epilepsy disorder without genetic diagnosis despite extensive prior testing. Clinical interpretation and orthogonal validation of variants in known disease genes yielded thirteen novel genetic diagnoses due to de novo and rare inherited SNVs, InDels, SVs, and STR expansions. In an additional four families, we identified a candidate disease-causing SV affecting several genes including an MCF2 / FGF13 fusion and PSMA3 deletion. However, no common genetic cause was identified in any of the 'unsolvable' syndromes. Taken together, we found (likely) disease-causing genetic variants in 13.0% of previously unsolved families and additional candidate disease-causing SVs in another 4.3% of these families. In conclusion, our results demonstrate the added value of HiFi long-read genome sequencing in undiagnosed rare diseases.

Increase transparency and reproducibility of real-world evidence in rare diseases through disease-specific Federated Data Networks

PURPOSE

In rare diseases, real-world evidence (RWE) generation is often restricted due to small patient numbers and global geographic distribution. A federated data network (FDN) approach brings together multiple data sources harmonized for collaboration to increase the power of observational research. In this paper, we review how to increase reproducibility and transparency of RWE studies in rare diseases through disease-specific FDNs.

METHOD

To be successful, a multiple stakeholder scientific FDN collaboration requires a strong governance model in place. In such a model, each database owner remains in full control regarding the use of and access to patient-level data and is responsible for data privacy, ethical, and legal compliance. Provided that all this is well documented and good database descriptions are in place, such a governance model results in increased transparency, while reproducibility is achieved through data curation and harmonization, and distributed analytical methods.

RESULTS

Leveraging the OHDSI community set of methods and tools, two rare disease-specific FDNs are discussed in more detail. For multiple myeloma, HONEUR-the Haematology Outcomes Network in Europe-has built a strong community among the data partners dedicated to scientific exchange and research. To advance scientific knowledge in pulmonary hypertension (PH) an FDN, called PHederation, was established to form a partnership of research institutions with PH databases coming from diverse origins.

Data quality and patient characteristics in European ANCA-associated vasculitis registries: data retrieval by federated querying

OBJECTIVES

This study aims to describe the data structure and harmonisation process, explore data quality and define characteristics, treatment, and outcomes of patients across six federated antineutrophil cytoplasmic antibody-associated vasculitis (AAV) registries.

METHODS

Through creation of the vasculitis-specific Findable, Accessible, Interoperable, Reusable, VASCulitis ontology, we harmonised the registries and enabled semantic interoperability. We assessed data quality across the domains of uniqueness, consistency, completeness and correctness. Aggregated data were retrieved using the semantic query language SPARQL Protocol and Resource Description Framework Query Language (SPARQL) and outcome rates were assessed through random effects meta-analysis.

RESULTS

A total of 5282 cases of AAV were identified. Uniqueness and data-type consistency were 100% across all assessed variables. Completeness and correctness varied from 49%-100% to 60%-100%, respectively. There were 2754 (52.1%) cases classified as granulomatosis with polyangiitis (GPA), 1580 (29.9%) as microscopic polyangiitis and 937 (17.7%) as eosinophilic GPA. The pattern of organ involvement included: lung in 3281 (65.1%), ear-nose-throat in 2860 (56.7%) and kidney in 2534 (50.2%). Intravenous cyclophosphamide was used as remission induction therapy in 982 (50.7%), rituximab in 505 (17.7%) and pulsed intravenous glucocorticoid use was highly variable (11%-91%). Overall mortality and incidence rates of end-stage kidney disease were 28.8 (95% CI 19.7 to 42.2) and 24.8 (95% CI 19.7 to 31.1) per 1000 patient-years, respectively.

CONCLUSIONS

In the largest reported AAV cohort-study, we federated patient registries using semantic web technologies and highlighted concerns about data quality. The comparison of patient characteristics, treatment and outcomes was hampered by heterogeneous recruitment settings.

Challenges in mapping European rare disease databases, relevant for ML-based screening technologies in terms of organizational, FAIR and legal principles: scoping review

Background

Given the increased availability of data sources such as hospital information systems, electronic health records, and health-related registries, a novel approach is required to develop artificial intelligence-based decision support that can assist clinicians in their diagnostic decision-making and shorten rare disease patients' diagnostic odyssey. The aim is to identify key challenges in the process of mapping European rare disease databases, relevant to ML-based screening technologies in terms of organizational, FAIR and legal principles.

Methods

A scoping review was conducted based on the PRISMA-ScR checklist. The primary article search was conducted in three electronic databases (MEDLINE/Pubmed, Scopus, and Web of Science) and a secondary search was performed in Google scholar and on the organizations' websites. Each step of this review was carried out independently by two researchers. A charting form for relevant study analysis was developed and used to categorize data and identify data items in three domains - organizational, FAIR and legal.

Results

At the end of the screening process, 73 studies were eligible for review based on inclusion and exclusion criteria with more than 60% (n = 46) of the research published in the last 5 years and originated only from EU/EEA countries. Over the ten-year period (2013-2022), there is a clear cycling trend in the publications, with a peak of challenges reporting every four years. Within this trend, the following dynamic was identified: except for 2016, organizational challenges dominated the articles published up to 2018; legal challenges were the most frequently discussed topic from 2018 to 2022. The following distribution of the data items by domains was observed - (1) organizational (n = 36): data accessibility and sharing (20.2%); long-term sustainability (18.2%); governance, planning and design (17.2%); lack of harmonization and standardization (17.2%); quality of data collection (16.2%); and privacy risks and small sample size (11.1%); (2) FAIR (n = 15): findable (17.9%); accessible sustainability (25.0%); interoperable (39.3%); and reusable (17.9%); and (3) legal (n = 33): data protection by all means (34.4%); data management and ownership (22.9%); research under GDPR and member state law (20.8%); trust and transparency (13.5%); and digitalization of health (8.3%). We observed a specific pattern repeated in all domains during the process of data charting and data item identification - in addition to the outlined challenges, good practices, guidelines, and recommendations were also discussed. The proportion of publications addressing only good practices, guidelines, and recommendations for overcoming challenges when mapping RD databases in at least one domain was calculated to be 47.9% (n = 35).

Conclusion

Despite the opportunities provided by innovation - automation, electronic health records, hospital-based information systems, biobanks, rare disease registries and European Reference Networks - the results of the current scoping review demonstrate a diversity of the challenges that must still be addressed, with immediate actions on ensuring better governance of rare disease registries, implementing FAIR principles, and enhancing the EU legal framework.

Overcoming challenges in rare disease registry integration using the semantic web - a clinical research perspective

The growing number of disease-specific patient registries for rare diseases has highlighted the need for registry interoperability and data linkage, leading to large-scale rare disease data integration projects using Semantic Web based solutions. These technologies may be difficult to grasp for rare disease experts, leading to limited involvement by domain expertise in the data integration process. Here, we propose a data integration framework starting from the perspective of the clinical researcher, allowing for purposeful rare disease registry integration driven by clinical research questions.

A systematic overview of rare disease patient registries: challenges in design, quality management, and maintenance

Patient registries serve to overcome the research limitations inherent in the study of rare diseases, where patient numbers are typically small. Despite the value of real-world data collected through registries, adequate design and maintenance are integral to data quality. We aimed to describe an overview of the challenges in design, quality management, and maintenance of rare disease registries.A systematic search of English articles was conducted in PubMed, Ovid Medline/Embase, and Cochrane Library. Search terms included "rare diseases, patient registries, common data elements, quality, hospital information systems, and datasets". Inclusion criteria were any manuscript type focused upon rare disease patient registries describing design, quality monitoring or maintenance. Biobanks and drug surveillances were excluded.A total of 37 articles, published between 2001 and 2021, met the inclusion criteria. Patient registries covered a wide range of disease areas and covered multiple geographical locations, with a predisposition for Europe. Most articles were methodological reports and described the design and setup of a registry. Most registries recruited clinical patients (92%) with informed consent (81%) and protected the collected data (76%). Whilst the majority (57%) collected patient-reported outcome measures, only few (38%) consulted PAGs during the registry design process. Few reports described details regarding quality management (51%) and maintenance (46%).Rare disease patient registries are valuable for research and evaluation of clinical care, and an increasing number have emerged. However, registries need to be continuously evaluated for data quality and long-term sustainability to remain relevant for future use.

Global Epidemiology of Movement Disorders: Rare or Underdiagnosed?

In this manuscript, we review the epidemiology of movement disorders including Parkinson's disease (PD), atypical parkinsonism, essential tremor, dystonia, functional movement disorders, tic disorders, chorea, and ataxias. We emphasize age-, sex-, and geography-based incidence and prevalence, as well as notable trends including the rising incidence and prevalence of PD. Given the growing global interest in refining clinical diagnostic skills in recognizing movement disorders, we highlight some key epidemiological findings that may be of interest to clinicians and health systems tasked with diagnosing and managing the health of patients with movement disorders.

Identifying congenital generalized lipodystrophy using deep learning-DEEPLIPO

Congenital Generalized Lipodystrophy (CGL) is a rare autosomal recessive disease characterized by near complete absence of functional adipose tissue from birth. CGL diagnosis can be based on clinical data including acromegaloid features, acanthosis nigricans, reduction of total body fat, muscular hypertrophy, and protrusion of the umbilical scar. The identification and knowledge of CGL by the health care professionals is crucial once it is associated with severe and precocious cardiometabolic complications and poor outcome. Image processing by deep learning algorithms have been implemented in medicine and the application into routine clinical practice is feasible. Therefore, the aim of this study was to identify congenital generalized lipodystrophy phenotype using deep learning. A deep learning approach model using convolutional neural network was presented as a detailed experiment with evaluation steps undertaken to test the effectiveness. These experiments were based on CGL patient's photography database. The dataset consists of two main categories (training and testing) and three subcategories containing photos of patients with CGL, individuals with malnutrition and eutrophic individuals with athletic build. A total of 337 images of individuals of different ages, children and adults were carefully chosen from internet open access database and photographic records of stored images of medical records of a reference center for inherited lipodystrophies. For validation, the dataset was partitioned into four parts, keeping the same proportion of the three subcategories in each part. The fourfold cross-validation technique was applied, using 75% (3 parts) of the data as training and 25% (1 part) as a test. Following the technique, four tests were performed, changing the parts that were used as training and testing until each part was used exactly once as validation data. As a result, a mean accuracy, sensitivity, and specificity were obtained with values of [90.85 ± 2.20%], [90.63 ± 3.53%] and [91.41 ± 1.10%], respectively. In conclusion, this study presented for the first time a deep learning model able to identify congenital generalized lipodystrophy phenotype with excellent accuracy, sensitivity and specificity, possibly being a strategic tool for detecting this disease.

Systematic Review: Drug Repositioning for Congenital Disorders of Glycosylation (CDG)

Advances in research have boosted therapy development for congenital disorders of glycosylation (CDG), a group of rare genetic disorders affecting protein and lipid glycosylation and glycosylphosphatidylinositol anchor biosynthesis. The (re)use of known drugs for novel medical purposes, known as drug repositioning, is growing for both common and rare disorders. The latest innovation concerns the rational search for repositioned molecules which also benefits from artificial intelligence (AI). Compared to traditional methods, drug repositioning accelerates the overall drug discovery process while saving costs. This is particularly valuable for rare diseases. AI tools have proven their worth in diagnosis, in disease classification and characterization, and ultimately in therapy discovery in rare diseases. The availability of biomarkers and reliable disease models is critical for research and development of new drugs, especially for rare and heterogeneous diseases such as CDG. This work reviews the literature related to repositioned drugs for CDG, discovered by serendipity or through a systemic approach. Recent advances in biomarkers and disease models are also outlined as well as stakeholders' views on AI for therapy discovery in CDG.

A scoping review of semantic integration of health data and information

OBJECTIVE

We summarized a decade of new research focusing on semantic data integration (SDI) since 2009, and we aim to: (1) summarize the state-of-art approaches on integrating health data and information; and (2) identify the main gaps and challenges of integrating health data and information from multiple levels and domains.

MATERIALS AND METHODS

We used PubMed as our focus is applications of SDI in biomedical domains and followed the Preferred Reporting Items for Systematic Review and Meta-Analyses (PRISMA) to search and report for relevant studies published between January 1, 2009 and December 31, 2021. We used Covidence-a systematic review management system-to carry out this scoping review.

RESULTS

The initial search from PubMed resulted in 5,326 articles using the two sets of keywords. We then removed 44 duplicates and 5,282 articles were retained for abstract screening. After abstract screening, we included 246 articles for full-text screening, among which 87 articles were deemed eligible for full-text extraction. We summarized the 87 articles from four aspects: (1) methods for the global schema; (2) data integration strategies (i.e., federated system vs. data warehousing); (3) the sources of the data; and (4) downstream applications.

CONCLUSION

SDI approach can effectively resolve the semantic heterogeneities across different data sources. We identified two key gaps and challenges in existing SDI studies that (1) many of the existing SDI studies used data from only single-level data sources (e.g., integrating individual-level patient records from different hospital systems), and (2) documentation of the data integration processes is sparse, threatening the reproducibility of SDI studies.

Defining and characterising a toolkit for the development of a successful European registry for rare liver diseases: a model for building a rare disease registry

INTRODUCTION

A rare disease is defined by the European Health Commission as a disorder affecting less than 5/10,000 of the population. There are at least 20 rare liver diseases (RLDs) seen frequently in the adult and paediatric liver clinic, signifying that the hepatology community can be influential in developing such patient databases for registering patients with rare hepatic conditions. The aim of this review was, first, to identify registries for RLDs in Europe, and, second, to design a universal blueprint for the development of a registry for RLD by using lessons learnt from the European registries that have already been established.

METHODS

We searched PubMed, Google Scholar and clinicaltrials.gov using the MESH terms 'registries', 'database management systems', 'database' and the non-MESH terms 'database$', 'registry', 'repository' and 'repositories'. We only included studies in English from countries/consortia of the European Union (EU). Our literature search was performed in 2020.

RESULTS

We identified 37 registries for RLDs in Europe. Using information from the design of these registries we designed a blueprint for the development of a patient registry for an RLD consisting of a theoretical, technical and maintenance phase.

DISCUSSION

It is believed that rare diseases may affect as much as 6-8% of the EU population across its 28 member states. Here we have provided a toolkit for designing a registry for an RLD. Our article will complement the efforts of loco-regional, national and international groups seeking to establish robust systems for data collection and analysis for orphan liver diseases.

Dietary phytochemicals/nutrients as promising protector of breast cancer development: a comprehensive analysis

Genetic change, particularly epigenetic alteration, is one of the imperative factors for sporadic breast cancer development in the worldwide population of women. The DNA methylation process is essential and natural for human cellular renewal and tissue homeostasis, but its dysregulation contributes to many pathological changes, including breast tumorigenesis. Chemopreventive agents mainly protect the abnormal DNA methylation either by hindering the division of pre-malignant cells or looming the DNA damage, which leads to malignancy. The present review article is about understanding the potential role of dietary phytochemicals in breast cancer prevention. Accordingly, a literature search of the published article until August 2021 has been performed. Further, we have investigated the binding affinity of different phytochemicals isolated from diverse dietary sources against the various oncogenic proteins related to breast cancer initiation to understand the common target(s) in breast cancer prevention mechanisms. Various small phytochemicals, especially dietary phytochemicals including sulforaphane, mahanine, resveratrol, linolenic acid, diallyl sulfide, benzyl/phenethyl isothiocyanate, etc. are being investigated as the chemopreventive agent to manage breast cancer development, and some of them have shown promising outcomes in the cited research. In this present review, we discuss the recent advancement in acceptance of such types of potential dietary phytochemicals as a chemopreventive agent against breast cancer development and their inner lining mechanism. The critical clinical trials and cohort studies have also been considered to understand the progress in contemporary perspectives.

Collaborative Research and Development of a Novel, Patient-Centered Digital Platform (MyEyeSite) for Rare Inherited Retinal Disease Data: Acceptability and Feasibility Study

BACKGROUND

Inherited retinal diseases (IRDs) are a leading cause of blindness in children and working age adults in the United Kingdom and other countries, with an appreciable socioeconomic impact. However, by definition, IRD data are individually rare, and as a result, this patient group has been underserved by research. Researchers need larger amounts of these rare data to make progress in this field, for example, through the development of gene therapies. The challenge has been how to find and make these data available to researchers in the most productive way. MyEyeSite is a research collaboration aiming to design and develop a digital platform (the MyEyeSite platform) for people with rare IRDs that will enable patients, doctors, and researchers to aggregate and share specialist eye health data. A crucial component of this platform is the MyEyeSite patient application, which will provide the means for patients with IRD to interact with the system and, in particular, to collate, manage, and share their personal specialist IRD data both for research and their own health care.

OBJECTIVE

This study aims to test the acceptability and feasibility of the MyEyeSite platform in the target IRD population through a collaborative patient-centered study.

METHODS

Qualitative data were generated through focus groups and workshops, and quantitative data were obtained through a survey of patients with IRD. Participants were recruited through clinics at Moorfields Eye Hospital National Health Service (NHS) Foundation Trust and the National Institute for Health Research (NIHR) Moorfields Biomedical Research Centre through their patient and public involvement databases.

RESULTS

Our IRD focus group sample (n=50) highlighted the following themes: frustration with the current system regarding data sharing within the United Kingdom's NHS; positive expectations of the potential benefits of the MyEyeSite patient application, resulting from increased access to this specialized data; and concerns regarding data security, including potentially unethical use of the data outside the NHS. Of the surveyed 80 participants, 68 (85%) were motivated to have a more active role in their eye care and share their data for research purposes using a secure technology, such as a web application or mobile app.

CONCLUSIONS

This study demonstrates that patients with IRD are highly motivated to be actively involved in managing their own data for research and their own eye care. It demonstrates the feasibility of involving patients with IRD in the detailed design of the MyEyeSite platform exemplar, with input from the patient with IRD workshops playing a key role in determining both the functionality and accessibility of the designs and prototypes. The development of a user-centered technological solution to the problem of rare health data has the potential to benefit not only the patient with IRD community but also others with rare diseases.

Opportunities and Challenges for Machine Learning in Rare Diseases

Rare diseases (RDs) are complicated health conditions that are difficult to be managed at several levels. The scarcity of available data chiefly determines an intricate scenario even for experts and specialized clinicians, which in turn leads to the so called “diagnostic odyssey” for the patient. This situation calls for innovative solutions to support the decision process via quantitative and automated tools. Machine learning brings to the stage a wealth of powerful inference methods; however, matching the health conditions with advanced statistical techniques raises methodological, technological, and even ethical issues. In this contribution, we critically point to the specificities of the dialog of rare diseases with machine learning techniques concentrating on the key steps and challenges that may hamper or create actionable knowledge and value for the patient together with some on-field methodological suggestions and considerations.

Learning from disease registries during a pandemic: Moving toward an international federation of patient registries

High-quality dermatology patient registries often require considerable time to develop and produce meaningful data. Development time is influenced by registry complexity and regulatory hurdles that vary significantly nationally and institutionally. The rapid emergence of the coronavirus disease 2019 (COVID-19) global pandemic has challenged health services in an unprecedented manner. Mobilization of the dermatology community in response has included rapid development and deployment of multiple, partially harmonized, international patient registries, reinventing established patient registry timelines. Partnership with patient organizations has demonstrated the critical nature of inclusive patient involvement. This global effort has demonstrated the value, capacity, and necessity for the dermatology community to adopt a more cohesive approach to patient registry development and data sharing that can lead to myriad benefits. These include improved utilization of limited resources, increased data interoperability, improved ability to rapidly collect meaningful data, and shortened response times to generate real-world evidence. We call on the global dermatology community to support the development of an international federation of patient registries to consolidate and operationalize the lessons learned during this pandemic. This will provide an enduring means of applying this knowledge to the maintenance and development of sustainable, coherent, and impactful patient registries of benefit now and in the future.

De-novo FAIRification via an Electronic Data Capture system by automated transformation of filled electronic Case Report Forms into machine-readable data

INTRODUCTION

Existing methods to make data Findable, Accessible, Interoperable, and Reusable (FAIR) are usually carried out in a post hoc manner: after the research project is conducted and data are collected. De-novo FAIRification, on the other hand, incorporates the FAIRification steps in the process of a research project. In medical research, data is often collected and stored via electronic Case Report Forms (eCRFs) in Electronic Data Capture (EDC) systems. By implementing a de novo FAIRification process in such a system, the reusability and, thus, scalability of FAIRification across research projects can be greatly improved. In this study, we developed and implemented a novel method for de novo FAIRification via an EDC system. We evaluated our method by applying it to the Registry of Vascular Anomalies (VASCA).

METHODS

Our EDC and research project independent method ensures that eCRF data entered into an EDC system can be transformed into machine-readable, FAIR data using a semantic data model (a canonical representation of the data, based on ontology concepts and semantic web standards) and mappings from the model to questions on the eCRF. The FAIRified data are stored in a triple store and can, together with associated metadata, be accessed and queried through a FAIR Data Point. The method was implemented in Castor EDC, an EDC system, through a data transformation application. The FAIRness of the output of the method, the FAIRified data and metadata, was evaluated using the FAIR Evaluation Services.

RESULTS

We successfully applied our FAIRification method to the VASCA registry. Data entered on eCRFs is automatically transformed into machine-readable data and can be accessed and queried using SPARQL queries in the FAIR Data Point. Twenty-one FAIR Evaluator tests pass and one test regarding the metadata persistence policy fails, since this policy is not in place yet.

CONCLUSION

In this study, we developed a novel method for de novo FAIRification via an EDC system. Its application in the VASCA registry and the automated FAIR evaluation show that the method can be used to make clinical research data FAIR when they are entered in an eCRF without any intervention from data management and data entry personnel. Due to the generic approach and developed tooling, we believe that our method can be used in other registries and clinical trials as well.

Design, development and deployment of a web-based interoperable registry for inherited retinal dystrophies in Portugal: the IRD-PT

Background

The development of multicenter patient registries promotes the generation of scientific knowledge by using real-world data. A country-wide, web-based registry for inherited retinal dystrophies (IRDs) empowers patients and community organizations, while supporting formal partnerships research. We aim to describe the design, development and deployment of a country-wide, with investigators and stakeholders in the global aim to develop high-value, high-utility web-based, user-friendly and interoperable registry for IRDs—the IRD-PT.

Results

The IRD-PT is a clinical/genetic research registry included in the retina.pt platform (https://www.retina.com.pt), which was developed by the Portuguese Retina Study Group. The retina.pt platform collects data on individuals diagnosed with retinal diseases, from several sites across Portugal, with over 1800 participants and over 30,000 consultations to date. The IRD-PT module interacts with the retina.pt core system which provides a range of basic functions for patient data management, while the IRD-PT module allows data capture for the specific purpose of IRDs. All IRDs are coded accordingly to the International Statistical Classification of Diseases and Related Health Problems (ICD) 9, ICD 10, ICD 11, and Orphanet Rare Disease Ontology (ORPHA codes) to make the IRD-PT interoperable with other IRD registries across the world. Furthermore, the genes are coded according to the Ontology of Genes and Genomes and Online Mendelian Inheritance in Man, whereas signs and symptoms are coded according to the Human Phenotype Ontology. The IRD-PT module pre-launched at Centro Hospitalar e Universitário de Coimbra, the largest reference center for IRDs in Portugal. As of April 1st 2020, finalized data from 537 participants were available for this preliminary analysis.

Conclusions

In the specific field of rare diseases, the use of registries increases research accessibility for individuals, while providing clinicians/investigators with a coherent data ecosystem necessary to boost research. Appropriate design and implementation of patient registries enables rapid decision making and ongoing data mining, ultimately leading to improved patient outcomes. We have described here the principles behind the design, development and deployment of a web-based, user-friendly and interoperable software tool aimed to generate important knowledge and collecting high-quality data on the epidemiology, genomic landscape and natural history of IRDs in Portugal.

SCALEUS-FD: A FAIR Data Tool for Biomedical Applications

The Semantic Web and Linked Data concepts and technologies have empowered the scientific community with solutions to take full advantage of the increasingly available distributed and heterogeneous data in distinct silos. Additionally, FAIR Data principles established guidelines for data to be Findable, Accessible, Interoperable, and Reusable, and they are gaining traction in data stewardship. However, to explore their full potential, we must be able to transform legacy solutions smoothly into the FAIR Data ecosystem. In this paper, we introduce SCALEUS-FD, a FAIR Data extension of a legacy semantic web tool successfully used for data integration and semantic annotation and enrichment. The core functionalities of the solution follow the Semantic Web and Linked Data principles, offering a FAIR REST API for machine-to-machine operations. We applied a set of metrics to evaluate its “FAIRness” and created an application scenario in the rare diseases domain.

Interoperability of population-based patient registries

•

Inter-linkage of patient-registry data provides a rich source of secondary data usage.

•

Mapping of heterogeneous metadata systems can be accomplished via semantic links.

•

Semantic linkage between patient registries provides the basis for interoperability.

•

Semantic metadata registry frameworks can facilitate access back to primary data sources.

Enabling full interoperability within and between population-based patient-registry domains would open up access to a rich and unique source of health data for secondary data usage. Previous attempts to tackle patient-registry interoperability have met with varying degrees of success, but a unifying solution remains elusive. The purpose of this paper is to show by practical example how a solution is attainable via the implementation of an existing framework based of the concept of federated, semantic metadata registries. One important feature motivating the use of this framework is that it can be implemented gradually and independently within each patient-registry domain. By employing linked open data principles, the framework extends the ISO/IEC 11179 standard to provide both syntactic and semantic interoperability of data elements with the means of specifying automated extraction scripts for retrieval of data from different registry content models. The examples provided address the domain of European population-based cancer registries to demonstrate the feasibility of the approach. One of the examples shows how quick gains are derivable by allowing retrieval of aggregated core data sets. The other examples show how aggregated full sets of data and record-level data might also be retrieved from each local registry. An infrastructure of patient-registry domains adhering to the principles of the framework would provide the semantic contexts and inter-linkage of data necessary for automated search and retrieval of registry data. It would thereby also lay the foundation for making registry data serviceable to artificial intelligence (AI) applications.

Videira P, Valadão G. Artificial Intelligence (AI) in Rare Diseases: Is the Future Brighter?

The amount of data collected and managed in (bio)medicine is ever-increasing. Thus, there is a need to rapidly and efficiently collect, analyze, and characterize all this information. Artificial intelligence (AI), with an emphasis on deep learning, holds great promise in this area and is already being successfully applied to basic research, diagnosis, drug discovery, and clinical trials. Rare diseases (RDs), which are severely underrepresented in basic and clinical research, can particularly benefit from AI technologies. Of the more than 7000 RDs described worldwide, only 5% have a treatment. The ability of AI technologies to integrate and analyze data from different sources (e.g., multi-omics, patient registries, and so on) can be used to overcome RDs’ challenges (e.g., low diagnostic rates, reduced number of patients, geographical dispersion, and so on). Ultimately, RDs’ AI-mediated knowledge could significantly boost therapy development. Presently, there are AI approaches being used in RDs and this review aims to collect and summarize these advances. A section dedicated to congenital disorders of glycosylation (CDG), a particular group of orphan RDs that can serve as a potential study model for other common diseases and RDs, has also been included.