Addressing the clinical unmet needs in primary Sjögren's Syndrome through the sharing, harmonization and federated analysis of 21 European cohorts.

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.

Overcoming the Barriers That Obscure the Interlinking and Analysis of Clinical Data Through Harmonization and Incremental Learning.

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.

Enhancing medical data quality through data curation: a case study in primary Sjögren's syndrome.

OBJECTIVES: To address the need for automatically assessing the quality of clinical data in terms of accuracy, relevance, conformity, and completeness, through the concise development and application of an automated method which is able to automatically detect problematic fields and match clinical terms under a specific domain. METHODS: The proposed methodology involves the automated construction of three diagnostic reports that summarise valuable information regarding the types and ranges of each term in the dataset, along with the detected outliers, inconsistencies, and missing values, followed by a set of clinically relevant terms based on a reference model which serves as a set of terms which describes the domain knowledge of a disease of interest. RESULTS: A case study was conducted using anonymised data from 250 patients who were diagnosed with primary Sjögren's syndrome (pSS), yielding reliable outcomes that were highlighted for clinical evaluation. Our method was able to successfully identify 28 features with detected outliers, and unknown data types, as well as, identify outliers, missing values, similar terms, and inconsistencies within the dataset. The data standardisation method was able to match 76 out of 85 (89.41%) pSS-related terms according to a standard pSS reference model which has been introduced by the clinicians. CONCLUSIONS: Our results confirm the clinical value of the data curation method towards the improvement of the dataset quality through the precise identification of outliers, missing values, inconsistencies, and similar terms, as well as, through the automated detection of pSS-related relevant terms towards data standardisation.

Medical data quality assessment: On the development of an automated framework for medical data curation.

Data quality assessment has gained attention in the recent years since more and more companies and medical centers are highlighting the importance of an automated framework to effectively manage the quality of their big data. Data cleaning, also known as data curation, lies in the heart of the data quality assessment and is a key aspect prior to the development of any data analytics services. In this work, we present the objectives, functionalities and methodological advances of an automated framework for data curation from a medical perspective. The steps towards the development of a system for data quality assessment are first described along with multidisciplinary data quality measures. A three-layer architecture which realizes these steps is then presented. Emphasis is given on the detection and tracking of inconsistencies, missing values, outliers, and similarities, as well as, on data standardization to finally enable data harmonization. A case study is conducted in order to demonstrate the applicability and reliability of the proposed framework on two well-established cohorts with clinical data related to the primary Sjögren's Syndrome (pSS). Our results confirm the validity of the proposed framework towards the automated and fast identification of outliers, inconsistencies, and highly-correlated and duplicated terms, as well as, the successful matching of more than 85% of the pSS-related medical terms in both cohorts, yielding more accurate, relevant, and consistent clinical data.

Adherence to follow-up and treatment recommendations in Greek and immigrant patients with chronic hepatitis B in Greece.

BACKGROUND/AIM: Immigrants have multiple barriers to access to health care systems. We evaluated the adherence to follow-up and treatment recommendations of chronic hepatitis B virus (HBV) Greek and immigrant patients. METHODS: In total, 1001 consecutive adult patients with chronic HBV infection who visited our clinics for the first time between 2002 and 2011 were included. All patients born outside Greece were considered immigrants. Diagnosis was considered to be complete if patients could be classified into HBeAg-positive chronic hepatitis B (CHB), inactive carriers, HBeAg-negative CHB, or decompensated cirrhosis. RESULTS: Of the patients, 56% were Greeks and 44% were immigrants. Greeks visited our clinics at a significantly older mean age (50 vs. 35 years, P<0.001) and more frequently with advanced liver disease (11.4 vs. 6.4%, P=0.007). During the first year, Greeks more frequently had several tests and eventually a complete diagnosis (68 vs. 55%, P<0.001). Greeks were more frequently in the phase of HBeAg-negative CHB and less frequently in the phase of inactive carrier or HBeAg-positive CHB, but age was the main determinant for these differences in multivariate analysis. Treatment was initiated more frequently by Greeks than immigrants with treatment indications (86 vs. 65%, P<0.001). Only 30-33% of treated and 4-10% of untreated patients remained under follow-up at year 5, without significant differences between Greeks and immigrants. CONCLUSION: Adherence to follow-up recommendations is rather poor for all chronic HBV patients. Immigrants are lost more frequently during the first year, but only small proportions of treated and particularly untreated Greek or immigrant patients remain under long-term follow-up.

Rheumatoid arthritis is sufficient to cause atheromatosis but not arterial stiffness or hypertrophy in the absence of classical cardiovascular risk factors.

Rheumatoid arthritis (RA) associates with increased cardiovascular disease (CVD) mortality thought to be due to accelerated arterial disease. Different components of arterial disease, namely, atheromatosis, arteriosclerosis, and arterial wall hypertrophy, are differentially affected by classical CVD risk factors, which are highly prevalent in these patients. We hypothesized that RA disease per se may also differentially affect these components. Of 267 consecutive RA patients, we selected specifically those who were free of established CVD and CVD risk factors (18 %); of them, 41 patients (36 women, 49 ± 13 years) could be matched effectively 1:1 for age and gender to healthy controls. Atheromatosis was assessed by the presence of carotid and/or femoral artery plaques, arteriosclerosis by pulse wave velocity and local wall elasticity, and arterial hypertrophy by intima-media thickness and cross-sectional area. More patients had atheromatic plaques than controls (29 vs. 12 %, p = 0.039), and multiarterial atheromatosis was more prevalent in RA (22 vs. 2 %, p = 0.026). Accelerated atheromatosis was not associated with rheumatoid factor, or anti-cyclic citrullinated peptide (CCP) autoantibody status. Plaque burden in patients with less than 5 years disease duration (aged 41 ± 13 years) was comparable to their matched controls. In contrast, all indices of arterial stiffness and hypertrophy were similar between controls and RA patients, even in those with long-standing disease. RA per se is sufficient to cause atheromatosis in the absence of classical CVD risk factors, but has minimal, if any, effect on arteriosclerosis and arterial wall hypertrophy.

Myocardial ischaemia without obstructive coronary artery disease in rheumatoid arthritis: hypothesis-generating insights from a cross-sectional study.

OBJECTIVE: RA is associated with increased cardiovascular events, reportedly to equal diabetes mellitus (DM). The presence of myocardial ischaemia was assessed in asymptomatic high-risk RA patients and compared with patients with DM and a healthy control group. METHODS: Eighteen consecutive non-diabetic RA patients without known cardiovascular disease who developed a new carotid atheromatic plaque during the last 3 years were matched 1:1 for traditional cardiovascular risk factors with asymptomatic type 2 DM patients and 1:2 with asymptomatic non-RA, non-DM control subjects. After dobutamine stress contrast echocardiography with wall-motion and perfusion evaluation, coronary angiography was performed in those with positive stress tests. RESULTS: Ischaemia by echocardiography was found in 67% of RA patients; this was significantly higher than controls (31%, P = 0.019) but comparable to those with DM (78%, P = 0.71). Angiography performed in eight consenting RA patients was normal in four, revealed non-flow-limiting coronary atheromatic lesions in two and significant lesions in two patients. RA patients with ischaemia had CRP serum levels significantly higher by six-fold compared with those with normal stress echocardiography. CONCLUSION: Asymptomatic RA patients may display myocardial ischaemia at similar levels to DM patients but with low prevalence of obstructive coronary artery disease. Microvascular abnormalities associated with increased inflammatory response may account for these findings. Their exact nature and significance require further evaluation.

The role of inflammation, the autonomic nervous system and classical cardiovascular disease risk factors on subendocardial viability ratio in patients with RA: a cross-sectional and longitudinal study.

INTRODUCTION: Evidence indicates that rheumatoid arthritis (RA) patients have increased susceptibility to myocardial ischaemia that contributes to myocardial infarction. The subendocardial viability ratio (SEVR) can be measured using pulse wave analysis and reflects myocardial oxygen supply and demand. The objective of the present study was to examine specific predictors of SEVR in RA patients, with a specific focus on inflammation and classical cardiovascular disease (CVD) risk factors. METHODS: Two patient cohorts were included in the study; a primary cohort consisting of 220 RA patients and a validation cohort of 127 RA patients. All patients underwent assessment of SEVR using pulse wave analysis. Thirty-one patients from the primary cohort who were about to start anti-inflammatory treatment were prospectively examined for SEVR at pretreatment baseline and 2 weeks, 3 months and 1 year following treatment. Systemic markers of disease activity and classical CVD risk factors were assessed in all patients. RESULTS: The SEVR (mean ± standard deviation) for RA in the primary cohort was 148 ± 27 and in the validation cohort was 142 ± 25. Regression analyses revealed that all parameters of RA disease activity were associated with SEVR, along with gender, blood pressure and heart rate. These findings were the same in the validation cohort. Analysis of longitudinal data showed that C-reactive protein (P < 0.001), erythrocyte sedimentation rate (P < 0.005), Disease Activity Score in 28 joints (P < 0.001), mean blood pressure (P < 0.005) and augmentation index (P < 0.001) were significantly reduced after commencing anti-TNFα treatment. Increasing C-reactive protein was found to be associated with a reduction in SEVR (P = 0.02) and an increase in augmentation index (P = 0.001). CONCLUSION: The present findings reveal that the SEVR is associated with markers of disease activity as well as highly prevalent classical CVD risk factors in RA, such as high blood pressure and diabetes. Further prospective studies are required to determine whether the SEVR predicts future cardiac events in RA.

NCF1 (p47phox) and ncf1 pseudogenes are not associated with inflammatory bowel disease.

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.