Health Vision: An interactive web based platform for healthcare data analysis and visualisation

Focus on software

Data clustering is an important technique for data visualization and statistical data analysis. Using data clustering technique for geo-located data analysis and visualization has been shown to be useful in many practical domains. Although there are numerous studies for data clustering algorithms, the implementations and applications based on these algorithms are rare and inadequate, especially for web-based data visualization services. In this research, a new web-based interactive data clustering prototype is proposed for geo-located data visualization. The necessary web-based infrastructure for geo-located data analysis and visualization is designed and implemented at first. And then the new interactive data clustering prototype using multi-dimensional K-Means algorithm is implemented on the existing infrastructure. In order to assess whether the new prototype can contribute meaningfully to architectural design and urban studies, qualified users with urban study or architectural backgrounds are invited to use the prototype and then make their comments and evaluations. To make it clear how this new prototype might apply in real world settings, an application scenario in which the user might interact with the prototype is provided and analyzed.

Lacrimal Gland in Sjögren's Syndrome

OP0079 Salivary Gland Epithelial Cells (SGECS) Promote the Differentiation of B Cells

Salivary glands of patients with Sjögren's syndrome (SS) have been shown to be a site of anti-SS-B/La antibody production. The present study investigated differences in the localization of the SS-B/La antigen in labial salivary gland (LSG) tissue between SS and non-SS patients, which may explain the local antigen-driven anti-SS-B/La response. Distribution of SS-B/La was studied immunohistologically in the LSG biopsy samples of 9 SS patients, 10 non-SS patients, and in normal tissues obtained at autopsy within 2 hours after death, using a mouse monoclonal antibody directed to SS-B/La. In 3 SS and 3 non-SS patients, LSGs were also studied with affinity-purified biotinylated human antibodies directed against SS-B/La. In the non-SS patients, SS-B/La was primarily observed in the nucleoli of acinic cells of the LSGs. Patients with either primary SS or secondary SS showed an accumulation of SS-B/La in the nucleoplasm of acinic cells. In the SS patients, SS-B/La was also detected in the cytoplasm as a diffuse or perinuclear staining. Sometimes, SS-B/La was found along the membrane of acinic cells as well. This aberrant nuclear and cytoplasmic distribution of SS-B/La in SS patients correlated well with abnormalities in the composition of the plasma cell population in the LSGs, but not with a lymphocytic focus score > 1. The accumulation and redistribution of SS-B/La in the LSGs may play an important role in the local antigen-driven anti-SS-B/La response in SS, and can also be used to improve the diagnostic possibilities of the LSG biopsy.

AB0196 MESENCHYMAL STEM CELLS TUNE THE DIFFERENTIATION OF MYELOID-DERIVED SUPPRESSOR CELLS IN SJöGREN’S SYNDROME THROUGH INHIBITING IL-12

Background: A key strength of population sciences and epidemiology is the breadth and depth of the data these studies, especially prospective cohorts, collect over time. However, publications from and websites of these studies tend to present collapsed or aggregate data in traditional tables, often underestimating the true complexity of information in those data. One goal of the NIH Strategic Plan for Data Science is to “support the development and dissemination of advanced data management, analytics, and visualization tools.” We recently developed a robust, innovative, and scalable data visualization environment for the California Teachers Study (CTS), a prospective cancer epidemiology cohort. Methods: We identified the need to eliminate the practice of storing CTS data in a collection of disparate data silos and constructed a data warehouse to compile two decades of study data, eliminating additional harmonization steps. We then developed a data commons, a remotely accessible environment where cohort data could be utilized by our researchers and study collaborators. This allowed questionnaire-based data, cancer registry information, and hospitalization and mortality data from our study participants to be easily accessed in a secure environment. Serving as a single unified source of information, the data warehouse, coupled with the industry-leading data visualization tool Tableau, was configured using the following key epidemiologic cohort activities: reports, cohort selection, calculated values, and exploring and transforming data variables for analysis. Results: With the ability to sort and filter on specific covariates we can define subsets of populations for cohort selection and endpoint-specific analysis. Using interactive reports with drags and drops, and creating calculated variables within Tableau, gives us the ability to visualize time between event data, such as time from study entry to a cancer diagnosis, multiple cancer diagnoses, hospitalizations, or mortality without requiring programmatic back-end coding. Conclusion: The creation of a data warehouse and data commons has given the CTS the ability to visualize information about the demographics and health-related patterns of our study participants, leading to faster answers to complex questions about our data. The interactive data visualizations that we have created allow users the ability to identify new patterns easily, and drill down into the data for a more detailed look. Defining analytic populations through cohort selection and adding geospatial data to our data warehouse has already resulted in the discovery of new patterns that had been unidentified before—simply by providing the same information but utilizing a more accessible and innovative approach to presenting it. As epidemiology uses and shares more of its data, it’s essential to help the widest possible community understand those data in detail. Data visualization can provide specific benefits to key, essential population sciences research activities. Citation Format: Nadia T. Chung, James V. Lacey Jr., Emma Spielfogel, Paul Hughes, Sandeep Chandra, Elena Martinez, Jennifer Benbow. Opportunities for and benefits of incorporating data visualization in population sciences [abstract]. In: Proceedings of the AACR Special Conference on Modernizing Population Sciences in the Digital Age; 2019 Feb 19-22; San Diego, CA. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2020;29(9 Suppl):Abstract nr A01.

Defining the Drivers of Idelalisib-Related Early Autoimmune Toxicity in Chronic Lymphocytic Leukemia

This research concerns the detection of unauthorised access within hospital networks through the real-time analysis of audit logs. Privacy is a primary concern amongst patients due to the rising adoption of Electronic Patient Record (EPR) systems. There is growing evidence to suggest that patients may withhold information from healthcare providers due to lack of Trust in the security of EPRs. Yet, patient record data must be available to healthcare providers at the point of care. Ensuring privacy and confidentiality of that data is challenging. Roles within healthcare organisations are dynamic and relying on access control is not sufficient. Through proactive monitoring of audit logs, unauthorised accesses can be detected and presented to an analyst for review. Advanced data analytics and visualisation techniques can be used to aid the analysis of big data within EPR audit logs to identify and highlight pertinent data points. Employing a human-in-the-loop model ensures that suspicious activity is appropriately investigated and the data analytics is continuously improving. This paper presents a system that employs a Human-in-the-Loop Machine Learning (HILML) algorithm, in addition to a density-based local outlier detection model. The system is able to detect 145 anomalous behaviours in an unlabelled dataset of 1,007,727 audit logs. This equates to 0.014% of the EPR accesses being labelled as anomalous in a specialist Liverpool (UK) hospital.

In a variety of disciplines, from biology and physics to computer science and the social sciences, computational topology has become a potent tool for data analysis and visualisation. This study explores computational topology's uses in data analysis and visualisation, showing its potential for revealing hidden structures and patterns in large, complicated datasets.The paper starts out by giving a general introduction of computational topology and outlining its core ideas and methods. The use of it for extracting important information from big, high-dimensional datasets is then explored in relation to data analysis. Computational topology allows for the discovery of topological properties such as holes, voids, and connection patterns by modelling data as topological structures, such as simplicial complexes or persistent homology diagrams.The study also explores the function of computational topology in data visualisation, highlighting its capacity to offer clear and insightful visual representations of challenging datasets. Computational topology enables the construction of simpler and aesthetically pleasing representations while preserving the fundamental topological properties of the data through methods like topological simplification and dimensionality reduction.The usefulness of computational topology in several application domains, such as genomics, image analysis, and network analysis, is demonstrated through a number of case studies. These instances show how computational topology can improve activities like data exploration, clustering, classification, and anomaly detection, resulting in fresh perceptions and learnings.This study emphasises the enormous potential of computational topology for applications in data processing and visualisation. Computational topology provides a new perspective that complements current approaches by utilising the inherent geometric and topological properties of data. This allows researchers and practitioners to better understand complex datasets and make decisions based on the knowledge gleaned from them.

Data visualization and data mining are transdisciplinary tools for predictive and descriptive analytics. This presentation shows the abundance of data visualization tools currently available that are applicable for multi-disciplinary data. Some examples of visualization are presented as applied for multi-disciplines. Results of applying the most commonly used data visualization tools of Tableau [1] and Power BI [2] are presented as preliminary outputs of a funded Seed Money Grant that applies data for transmissible diseases for humans and also plant pathology. Tableau Software, LLC is an American interactive data visualization software company focused on business intelligence and can be used across all disciplines. Tableau products query relational databases, online analytical processing cubes, cloud databases, and spreadsheets to generate graph-type data visualizations.[1] Power BI (Business Intelligence) is a suite of business analytics tools developed by Microsoft that is widely used across various industries for business reporting, data analysis, and decision-making. [2] Future directions of this research are discussed that include using other data mining and visualization methods such as image processing techniques for applications to data for plant pathology and human diseases.

We read with great interest the article by Erten et al1 entitled “Comparison of plasma vitamin D levels in patients with Sjögren's syndrome and healthy subjects”. Erten et al compared the levels of plasma vitamin D in 107 Sjögren's syndrome (SS) cases and 74 healthy controls. The authors reported that plasma vitamin D levels in patients with SS (20.5 ± 10.5 μg/L) were significantly lower than in the control group (28.4 ± 15.2 μg/L). However, the association between the level of vitamin D and SS remains controversial. Vitamin D deficiency may result in an increased risk of developing some immune-mediated diseases, including SS,2 suggesting a possible role of vitamin D in the pathogenesis of the disease. However, some studies were unable to demonstrate the correlation between low levels of vitamin D and SS. This study aimed to perform a meta-analysis on the association between vitamin D level and SS. We searched PubMed, Embase, Google Scholar and Web of Science using key words for available articles (up to November 2018). The following terms were used: Sjogren's syndrome, SS, 25(OH)D, 1,25(OH)D and vitamin D. We included case-control studies in English that compared vitamin D levels in SS patients and healthy controls. Abstracts, review articles, case reports or conference proceedings were excluded. The strength of the difference of vitamin D between SS and controls was assessed by standard mean differences (SMDs) with 95% confidence intervals (CIs), and median (range) was transformed into mean ± SD.3 The extent of heterogeneity was quantified by I2. If I2 < 50%, it was considered that the variation between studies is small, then a fixed effect model was used; otherwise, a random effect model was used. All the statistical analyses were performed by the RevMan software, version 5.0. All tests were two-sided. A difference of P < 0.05 was considered statistically significant. Of the 159 articles identified from our initial search, nine articles satisfying the inclusion criteria were identified and were included in this meta-analysis.1, 4, 5 Two studies4, 12 included the same individuals13 as control group; according to the Cochrane Reviewers' Handbook, we divided out the control group evenly into two groups to perform the comparison in this meta-analysis. The nine studies were published between 1999 and 2018, and involved 549 SS patients and 1082 healthy controls. Four of the nine studies reported significantly lower vitamin D level in SS patients than in healthy controls, while the other five did not. The I2 value was 93%, then a random effect model was used. Figure 1 showed that the average level of 25(OH)D in SS patients was comparable with that in healthy controls (SMD = −0.43, 95% CI = −0.90 to 0.04, P = 0.07). This result indicated there is no evidence to confirm the different vitamin D levels between SS patients and healthy controls. This meta-analysis has several limitations that need more consideration. First, subgroup analysis and meta-regression were not performed because the number of included studies is relatively small. Second, there were some confounders in this meta-analysis, such as age, ethnicity, season, outdoor activity, diet intake, treatment and so on. However, not all the included studies generated adjusted values, so we could not pool the result by adjusting for confounders. Therefore, further longitudinal, prospective and well-designed cohort studies are needed to elucidate the role of vitamin D in the pathogenesis of SS.

Big data analytics in health is an emerging area due to the urgent need to derive actionable intelligence from the large volumes of healthcare data to efficiently manage the healthcare system and to improve health outcomes. In this paper we present a ‘big’ healthcare data analytics platform—termed as Healthcare Analytics for Intelligence and Learning (HAIL)—that is an end-to-end healthcare data analytics solution to derive data-driven actionable intelligence and situational awareness to inform and transform health decision-making, systems management and policy development. The innovative aspects of HAIL are: (a) the integration of data-driven and knowledge-driven analytics approaches, (b) a sand-box environment for healthcare analysts to develop and test health policy/process models by exploiting a range of data preparation, analytical and visualization methods, (c) the incorporation of specialized healthcare data standards, terminologies and concept maps to support data analytics, and (d) text analytics to analyze unstructured healthcare data. The architecture of HAIL comprises the following four main modules (fig 1): (A) Health Data Integration module that entails a semantics-based metadata manager to synthesize health data originating from a range of healthcare institutions to formulate a rich contextualized data resource. The data integration is achieved through ETL workflows designed by health analysts and researchers, (B) Health Analytics Module provides a range of healthcare analytics capabilities including, (i) Exploratory Analytics using data mining to perform data clustering, classification and association tasks, (ii) Predictive Analytics to predict future trends/outcomes derived from past observations of the healthcare processes, (iii) Text Analytics to analyze unstructured texts (such as clinical notes, discharge summaries, referral notes, clinical guidelines, etc.), (iv) Simulation-based Analytics to simulate what-if questions based on simulation models, (v) Workflow analytics to interact with modeled clinical workflows to understand the affects of various confounding factors, (vi) Semantic Analytics to infer contextualized relationships, anomalies and deviations through reasoning over a semantic health data model, and (vii) Informational Analytics to present summaries, aggregations, charts and reports, (C) Data Visualization Module offers a range of interactive data visualizations, such as geospatial visualizations, causal networks, 2D and 3D graphs, pattern clusters and interactive visualizations to explore high dimensional data, (D) Data Analytics Workbench is an interactive workspace to enable data health analysts to specify and set-up their analytics process in terms of data preparation, selection and set-up of analytical methods and the selection of visualization methods. Using the workbench analysts can design sophisticated data analytics workflows/models using a range of data integration, analytical and visualization methods. The HAIL platform is available via a web portal and the desktop application, and it is deployed on a cloud infrastructure. HAIL can be connected with existing health data sources to provide front-end data analytics. Fig 2 shows the technical architecture. The HAIL platform has been applied to analyze a real-life clinical healthcare situations using actual data from the provincial clinical data warehouse. We will present two case studies of the use of HAIL. In conclusion, the HAIL platform addresses a critical need for healthcare analytics to impact health decision-making, systems management and policy development.

Purpose: To evaluate the ocular surface temperature (OST) using an infrared thermography camera in Sjogren Syndrome (SS) patients compared with healthy subjects and correlate these results with the dry eye symptomatology, tear volume, stability and matrix metalloproteinase 9 (MMP-9) concentrations. Methods: Twelve patients of primary SS (46.64 ± 13.34 years), and twenty volunteers (41.38 ± 9.67 years) without dry eye, participated in this study. OSDI questionnaire, Schirmer test, tear break up time (TFBUT), matrix metalloproteinase 9 (MMP-9) concentrations and OST were evaluated. Results: Central cornea temperature was statistically higher in SS than in control group (p = 0.014), being 34.81 ± 0.37oC and 34.25 ± 0.65oC respectively. In the control group, the temperature increased in the periphery compared with central cornea, limbus and conjunctiva (p 0.05). The SS patients showed a significant lower Schirmer test and TFBUT compared with control group (p<0.005). Also, the OSDI score and MMP-9 concentration were statistically higher in SS patients compared with the control group (p<0.05). No correlation between central cornea temperature and TFBUT, OSDI and Schirmer test was found. However we found a strong positive correlation between central cornea temperature and MMP-9 concentration been 0.628 (p=0.029). Conclusion: Central cornea temperature is higher in SS compared with healthy subjects. The strong positive correlation between MMP-9 concentration and central cornea temperature suggests that the high temperature in SS could be due to ocular surface inflammation

Sirs: Sjogren’s syndrome (SjS) is one of the major autoimmune disorders and is characterized by dry eyes and a dry mouth. A wide variety of extraglandular manifestations has been reported in SjS. Aseptic meningitis is a well-known manifestation of SjS; however, little is known about its pathomechanism [1, 3]. We detected a unique autoantibody in the serum and cerebrospinal fluid (CSF) of an SjS patient with recurrent aseptic meningitis. A 19-year-old female was readmitted to our hospital after the third recurrence of aseptic meningitis. Nine months and five months before this admission, she had experienced the same symptoms, i.e., headache, nausea, and fever. She was diagnosed with aseptic meningitis because of the presence of mononuclear pleocytosis in the CSF. The symptoms subsided spontaneously within a few days. On examination, there were no subjective symptoms of sicca syndrome, and Schirmer’s test was negative. Neurological examination revealed no abnormalities, except stiffness of the neck. Laboratory tests revealed elevated amylase (268 IU/dl) and serum IgG (2920 mg/dl) concentrations; positive rheumatoid factor (2+); accelerated erythrocyte sedimentation rate (30 mm/h); and positive serum antinuclear antibody (ANA) as well as the anti-SS-A and anti-SS-B antibodies at titers of 1:2560, 1:256, and 1:8, respectively. The CSF contained 153 mg/dl protein and 85 mm of cells (81% mononuclear cells); the anti-SS-A and anti-SS-B antibodies were absent. These findings led us to suspect SjS. A sialogram revealed the destruction of the sialoducts, and a salivary gland biopsy revealed abundant lymphocytic infiltration. The patient was diagnosed with SjS and recurrent aseptic meningitis, and she was treated with 50 mg of daily oral prednisolone. Based on the results of the physical and serological examinations, we inferred that the overlapping of other systemic autoimmune diseases with SjS is unlikely. The clinical symptoms resolved immediately without subsequent recurrence. The patient’s serum and CSF were analyzed by using western blotting (WB) and immunohistochemistry as reported previously [4]. WB of bovine tissue samples showed that the CSF reacted with two bands with apparent molecular weights of 56 kD and 44 kD in the cerebral cortex, meningeal tissue, and liver (Fig. 1a). Immunohistochemical analysis by the avidin-biotin-peroxidase method using rat cerebral slices showed that the CSF labeled the nuclei of the neurons and meningeal cells (Fig. 1b). We detected an identical autoantibody in the patient’s serum (data not shown). Mauch et al. reported that approximately 70% SjS patients had neurological complications; of these, one-sixth had aseptic meningitis [3]. Alexander et al reported that from a group of 25 consecutive SjS patients with CNS involvements, 5 (20%) had recurrent aseptic meningitis or meningoencephalitis [1]. Although aseptic meningitis is common in SjS, recurrent aseptic meningitis without other CNS involvements is rare, and its pathoetiology has not been elucidated thus far. Some autoantibodies may be related to the pathogenesis of the CNS involvement in SjS, for example, the possible association of the anti-SS-A antibody with cerebral angiitis [2]. However, the relationship between these autoantibodies and CNS involvement remains unknown. We demonstrated the presence of an autoantibody in the patient’s CSF and serum; this autoantibody recognizes 56and 44-kD nuclear antigens of the CNS neurons, meningeal cells, and cells of other systemic organs. The presence of this autoantibody in the patient’s CSF may imply its causative association with recurrent aseptic meningitis in SjS. We already reported some other autoantibodies in SjS patients with CNS involvements, but this is the first report K. Ishida, MD, PhD T. Uchihara, MD, PhD H. Mizusawa, MD, PhD Dept. of Neurology and Neurological Science, Tokyo Medical and Dental University Graduate School 1-5-45 Yushima, Bunkyo-ku Tokyo 113-8519, Japan