RESUMO
For many decades, the clinical unmet needs of primary Sjögren's Syndrome (pSS) have been left unresolved due to the rareness of the disease and the complexity of the underlying pathogenic mechanisms, including the pSS-associated lymphomagenesis process. Here, we present the HarmonicSS cloud-computing exemplar which offers beyond the state-of-the-art data analytics services to address the pSS clinical unmet needs, including the development of lymphoma classification models and the identification of biomarkers for lymphomagenesis. The users of the platform have been able to successfully interlink, curate, and harmonize 21 regional, national, and international European cohorts of 7,551 pSS patients with respect to the ethical and legal issues for data sharing. Federated AI algorithms were trained across the harmonized databases, with reduced execution time complexity, yielding robust lymphoma classification models with 85% accuracy, 81.25% sensitivity, 85.4% specificity along with 5 biomarkers for lymphoma development. To our knowledge, this is the first GDPR compliant platform that provides federated AI services to address the pSS clinical unmet needs.
RESUMO
Goal: To present a framework for data sharing, curation, harmonization and federated data analytics to solve open issues in healthcare, such as, the development of robust disease prediction models. Methods: Data curation is applied to remove data inconsistencies. Lexical and semantic matching methods are used to align the structure of the heterogeneous, curated cohort data along with incremental learning algorithms including class imbalance handling and hyperparameter optimization to enable the development of disease prediction models. Results: The applicability of the framework is demonstrated in a case study of primary Sjögren's Syndrome, yielding harmonized data with increased quality and more than 85% agreement, along with lymphoma prediction models with more than 80% sensitivity and specificity. Conclusions: The framework provides data quality, harmonization and analytics workflows that can enhance the statistical power of heterogeneous clinical data and enables the development of robust models for disease prediction.
RESUMO
Crohn's disease (CD) and ulcerative colitis (UC) have a strong genetic component, contributing to a patient's susceptibility for inflammatory bowl disease (IBD). Linkage analysis has detected an IBD susceptibility locus in a region on chromosome 7q that encompasses the p47 (NCF1) gene and p47 (PsiNCF1) pseudogenes. Involvement of the NCF1 locus in IBD was supported by the observation that chronic inflammation of the bowel is a feature of chronic granulomatous disease caused by NCF1 mutation in 25% of cases. The pseudogenes have a dinucleotide deletion (PsiGT) at the beginning of exon 2, resulting in a frameshift and premature stop codon. APsiNCF1 (DeltaGT) to NCF1 (GTGT) ratio of 2:1 has been proposed as the predominant ratio in humans; but variability may occur after DNA exchange by recombination between PsiNCF1 and NCF1 to produce a potentially functional gene hybrid (type IIPsiNCF1). A preliminary study suggested an association between individuals with a 1:1 ratio and susceptibility to IBD. The possible presence of type IIPsiNCF1 was proposed as a susceptibility factor. We have now established the PsiNCF1 to NCF1 ratio for a significant number of IBD patients (n = 488) and control subjects (n = 181) and show that there is no statistically significant difference between the frequency of the 1:1 ratio in CD (11.2%) or UC (12.2%) patients and controls (13.4%). The 2:1 ratio was identified as the most common ratio (83.3%). Our data show there is no association of the 1:1 ratio with IBD and that susceptibility is unlikely to be a consequence of an inherited 1:1, rather than a 2:1 (PsiNCF1:NCF1) ratio.