Data Warehouse Research Articles

MPN-203 Anemia Burden in Patients With Myelofibrosis (MF) Treated With Ruxolitinib (RUX): Data From the Veterans Affairs Corporate Data Warehouse (VACDW)

MPN-203 Anemia Burden in Patients With Myelofibrosis (MF) Treated With Ruxolitinib (RUX): Data From the Veterans Affairs Corporate Data Warehouse (VACDW)

Anemia Burden in Patients With Myelofibrosis (MF) Treated With Ruxolitinib (RUX): Data From the Veterans Affairs Corporate Data Warehouse (VACDW)

Anemia Burden in Patients With Myelofibrosis (MF) Treated With Ruxolitinib (RUX): Data From the Veterans Affairs Corporate Data Warehouse (VACDW)

Standardization of Metadata of Analog Cadastral Documents Resulting from Systematic Cadaster Establishment

The systematic approach to the establishment of a cadaster in most European countries has resulted in a variety of cadastral documents. Most official cadastral data are from the 19th and 20th centuries and are stored as hard copies or electronic data in a data warehouse, while the original documents are stored in analog format in separate locations, making the cadastral data difficult to access. The increasing interest in the use of archival cadastral documents has stimulated their digitalization in most countries, allowing users to access cadastral documents through metadata catalogs. Most catalogs use archival metadata standards to describe cadastral documents, with a lack of application of geoinformation metadata standards that represent fundamental spatial datasets. Archival metadata standards do not provide enough information about the origin and quality of cadastral data. The aim of this study was to examine the applicability of the ISO 19115-1 standard for describing cadastral documents. The methodology includes a comparison and an analysis of documents which are stored in different locations. The metadata of archived cadastral documents are recorded in archive inventories, and archives use different terminology for documents with the same content. The scientific contribution of this study is given by the classification of key documents and their associated properties that uniquely described each document. Four types of documents were classified by comparison, and we analyzed the content between documents. Property identification resulted in the semantic mapping to metadata elements of ISO 19115-1 and showed a considerable congruence of elements. It was possible to apply the ISO 19115-1 standard for describing documents of systematic cadaster establishment, with additional extensions for some elements. Proposed extensions to describe the cadastral documents include replacing free text with domains of appropriate values, adding stricter obligations, and restricting the use of domain values. The standardization of metadata for analog cadastral documents in archives has created a prerequisite for the development of a metadata catalog, which would increase the availability and accessibility of cadastral data for different user groups.

Insomnia and unhealthy alcohol use in a National Sample of Women Veterans 50 years and older enrolled in the Veterans Health Administration

In this study, we examined rates of insomnia and co-occurring unhealthy alcohol use in a national sample of women Veterans age 50 years and older. We further explored associations between sociodemographic measures, insomnia-related clinical characteristics, and unhealthy alcohol use, and analyzed whether women with insomnia were more likely to report unhealthy alcohol use. Study aims were evaluated using national Veterans Health Administration (VA) electronic health records data from VA’s Corporate Data Warehouse. Data were extracted for women Veterans ≥50 years old with ≥1 VA primary care visit in each study year (2018: 3/11/18–3/10/19; 2020: 3/11/20–3/10/21; 2022: 3/11/22–3/10/23). Cases of insomnia were identified via diagnostic codes and prescription medications for insomnia. Unhealthy alcohol use was identified via Alcohol Use Disorders Identification Test-Consumption screening scores indicating unhealthy alcohol use. Annual sample sizes ranged from 240,420–302,047. Over the study timeframe, insomnia rates (diagnosis or medication) among women ≥50 years old ranged from 18.11–19.29%; co-occurring insomnia and unhealthy alcohol use rates ranged from 2.02–2.52%. Insomnia and unhealthy alcohol use rates were highest among women aged 50–59 years old. Depression and physical health comorbidities were consistently associated with insomnia; associations by race and ethnicity were less consistent. Compared to women without insomnia, women Veterans with either concurrent or unremitting insomnia were more likely to endorse unhealthy alcohol use. Findings signal a potential need for assessment and preventative efforts aimed at addressing insomnia and unhealthy alcohol use among women Veterans.

Impact of Terrorism on the Use of Healthcare Services in Burkina Faso Between 2015 and 2022.

Burkina Faso has been facing a security crisis due to terrorism since 2015. This study aims to assess the impact of the attacks on the use of healthcare services. This is a secondary study on data from the country's health data warehouse and the ACLED security data warehouse. After a description, generalized additive models were used to assess the impact of attacks on the use of health services. Between January 2015 and December 2022, 2449 kidnap/disappearance attacks, armed attacks, bombings and landmine explosions were perpetrated, causing 4965 deaths. The Sahel region was the most targeted (36.37% of attacks and 50.57% of deaths). Only population density had a significant impact on the use of health services (p<5%). The models were valid. Our study has shown that, despite the persistent insecurity in Burkina Faso, people are resilient and, above all, continue to seek out the most important healthcare services. It is therefore important to work to maintain the supply of these services.

Synthesizing Clinical Data Warehouse Content for Enhanced External Collaboration: A Preliminary Proposal.

This paper introduces a novel approach aimed at enhancing the accessibility of clinical data warehouses (CDWs) for external users, particularly researchers and biomedical companies interested in developing and testing their solutions. The primary focus is on proposing a clinical data catalogue designed to elucidate the contents of CDWs, facilitating biomedical project launch and completion. The catalogue is designed to address three fundamental inquiries that external users may have regarding CDWs: "What data is available, how much data is present, and how was it generated?" Additionally, the paper showcases a prototype of the catalogue through a visualization example, utilizing data from the CDW of Rennes University Hospital.

Performance of a NLP Tool for Text Classification from Orthopaedic Operative Reports, Using Data from the Large Network of Clinical Data Warehouses of the West of France: The HACRO-HUGORTHO Project.

Electronic health data concerning implantable medical devices (IMD) opens opportunities for dynamic real-world monitoring to assess associated risks related to implanted materials. Due to population ageing and expanding demands, total hip, knee, and shoulder arthroplasties are increasing. Automating the collection and analysis of orthopedic device features could benefit physicians and public health policies enabling early issue detection, IMD monitoring and patient safety assessment. A machine learning tool using natural language processing (NLP) was developed for the automated extraction of operation information from medical reports in orthopedics. A corpus of 959 orthopaedic operative reports from 5 centres was manually annotated using the Prodigy software® with a strong inter-annotator agreement of 0.80. Data to extract concerned key clinical and procedure information (n= 9) selected by a multidisciplinary group based on the French health authority checklist. Performances parameters of the NLP model estimated an overall strong precision and recall of respectively 97.0 and 96.0 with a F1-score 96.3. Systematic monitoring of orthopedic devices could be ensured by an automated tool, leveraging clinical data warehouses. Traceability of medical devices with implantation modalities will allow detection of implant factors leading to complications. The evidence from real-world data could provide concrete and dynamic insights to surgeons and infectious disease specialists concerning implant follow-up, guiding therapeutic decision-making, and informing public health policymakers. The tool will be applied on clinical data warehouses to automate information extraction and presentation, providing feedback on mandatory information completion and contents of operative reports to support improvements, and thereafter implant research projects.

The Effect of Antidepressants on Withdrawal in Patients with Alcohol Dependence: A Retrospective Study.

The use of electronic health records has expanded in the past decades, with healthcare entities storing terabytes of patient health data. In this study, we investigated how these databases can be utilized to generate clinically relevant information. We used the Office of Addiction Services and Supports Client Data Systems data merged with the NYS Medicaid Data Warehouse to study the relationship of certain antidepressants on alcohol withdrawal (AW) rates in patients with alcohol dependence (AD). We found that in patients with AD, bupropion was associated with a significantly reduced rate of AW compared to selective serotonin reuptake inhibitors (SSRIs). This may be due to the ability of bupropion to inhibit dopaminergic reuptake. This retrospective study provides the advantage of being faster and less expensive than randomized controlled trials (RCTs).

An Integrated Pipeline for Phenotypic Characterization, Clustering and Visualization of Patient Cohorts in a Rare Disease-Oriented Clinical Data Warehouse.

Rare diseases pose significant challenges due to their heterogeneity and lack of knowledge. This study develops a comprehensive pipeline interoperable with a document-oriented clinical data warehouse, integrating cohort characterization, patient clustering and interpretation. Leveraging NLP, semantic similarity, machine learning and visualization, the pipeline enables the identification of prevalent phenotype patterns and patient stratification. To enhance interpretability, discriminant phenotypes characterizing each cluster are provided. Users can visually test hypotheses by marking patients exhibiting specific keywords in the EHR like genes, drugs and procedures. Implemented through a web interface, the pipeline enables clinicians to navigate through different modules, discover intricate patterns and generate interpretable insights that may advance rare diseases understanding, guide decision-making, and ultimately improve patient outcomes.

The Ouest Data Hub: An Interregional Health Data Sharing Ecosystem for Research.

The Ouest Data Hub (ODH) a project lead by GCS HUGO which is a cooperation group of University Hospitals in the French Grand Ouest region represents a groundbreaking initiative in this territory, advancing health data sharing and reuse to support research driven by real-world health data. Central to its structure are the Clinical Data Warehouses (CDWs) and Clinical Data Centers (CDCs), essential for analytics and as the linchpin of the ODH's status as an interregional Learning Health System. Aimed at fostering innovation and research, the ODH's collaborative and multi-institutional model effectively utilizes both local and shared resources. Yet, the path is not without challenges, especially in data quality and interoperability, where ongoing harmonization and standard adherence are critical. In 2023, this facilitated access to extensive health data from over 9.3 million patient records, demonstrating the ODH's capacity for both monocentric and multicentric research across various clinical fields, in close collaboration with physicians. The integration of healthcare professionals is crucial, ensuring data's clinical relevance and guiding accurate interpretations. Future expansions of the ODH to new hospitals and data types promise to enhance its model further, already inspiring similar frameworks across France. This scalable model for health data ecosystems showcases the ODH's potential as a foundation for national and supranational data sharing efforts.

Monitoring Variability of Laboratory Results in a Clinical Data Warehouse Using Automatic Dashboard.

Hospital laboratory results are a significant data source in Clinical Data Ware-houses (CDW). To ensure comparability across healthcare organizations and for use in research studies, the results need to be interoperable. The LOINC (Logical Observation Identifiers, Names, and Codes) terminology provides a unique identifier for local codes for lab tests, enabling interoperability. However, in real-world, events occur over time and can disrupt the distribution of lab result values. For example, new equipment may be added to the analysis pipeline, a machine may be replaced, formulas may evolve due to new scientific knowledge, and legacy terminologies may be adopted. This article proposes a pipeline for creating an automated dashboard to monitor these events and data quality. We used automatic change point detection methods such as PELT for event detection in lab results. For a given LOINC code, we create a dashboard that summarizes the number of local codes mapped, and the number of patients (by sex, age, and hospital service) associated with the code. Finally, the dashboard enables the visualization of time events that disrupt the signal distribution. The biologists were able to explain to us the changes for several biological assays.

Assessing Health Data Science Internships: A Comprehensive Study at the University of Lille.

Data Science emerged as a new cross-disciplinary discipline at the intersection of statistics, computer science, and expertise in a specific domain, such as health and biology. The data science field, alongside other data-related professions, is continuously evolving. We conducted a study examining tasks assigned to first-year internship students pursuing a Master's degree in Health Data Science, exploring the missions, technologies employed and skills required, and internship alignment with students' training through semi-structured interviews with 32 participants. Three quarters of the students were placed in teams within the public sector. Among these entities, there were 11 hospitals and 12 universities. Although the majority of students did their internship as part of a methodological team, they often had a healthcare professional on their team. Nearly half of the missions involved descriptive analysis, followed by 9 missions focused on etiology or prediction and 8 missions on implementing a data warehouse. The majority of students had to perform data management and produce graphs, while only half conducted statistical analysis. The findings highlighted that data management remains a major challenge, and it should be taken into consideration when designing training programs. In future, it remains to determine whether this trend will continue with second-year students or if, with experience, they are more often assigned statistical analyses.

Risk of Major Bleeding, Stroke/Systemic Embolism, and Death Associated With Different Oral Anticoagulants in Patients With Atrial Fibrillation and Severe Chronic Kidney Disease.

Patients with atrial fibrillation and severe chronic kidney disease have higher risks of bleeding, thromboembolism, and mortality. However, optimal anticoagulant choice in these high-risk patients remains unclear. Using deidentified electronic health records from the Optum Labs Data Warehouse, adults with atrial fibrillation and severe chronic kidney disease (estimated glomerular filtration rate <30 mL/min per 1.73 m2) initiating warfarin, apixaban, or rivaroxaban between 2011 and 2021 were included. Using inverse probability of treatment weighting, adjusted risks of major bleeding, stroke/systemic embolism, and death were compared among agents. A total of 6794 patients were included (mean age, 78.5 years; mean estimated glomerular filtration rate, 24.7 mL/min per 1.73 m2; 51% women). Apixaban versus warfarin was associated with a lower risk of major bleeding (incidence rate, 1.5 versus 2.9 per 100 person-years; subdistribution hazard ratio [sub-HR], 0.53 [95% CI, 0.39-0.70]), and similar risks for stroke/systemic embolism (incidence rate, 1.9 versus 2.4 per 100 person-years; sub-HR, 0.80 [95% CI, 0.59-1.09]) and death (incidence rate, 4.6 versus 4.5 per 100 person-years; HR, 1.03 [95% CI, 0.82-1.29]). Rivaroxaban versus warfarin was associated with a higher risk of major bleeding (incidence rate, 4.9 versus 2.9 per 100 person-years; sub-HR, 1.65 [95% CI, 1.10-2.48]), with no difference in risks for stroke/systemic embolism and death. Apixaban versus rivaroxaban was associated with a lower risk of major bleeding (sub-HR, 0.53 [95% CI, 0.36-0.78]). These real-world findings are consistent with potential safety advantages of apixaban over warfarin and rivaroxaban for patients with atrial fibrillation and severe chronic kidney disease. Further randomized trials comparing individual oral anticoagulants are warranted.

E-COMMERCE OPERATIONS WITH AI-POWERED DATA WAREHOUSES: A CASE STUDY ON CUSTOMER BEHAVIOR ANALYSIS

This paper presents a comprehensive systematic review of the impact of AI-powered data warehouses on e-commerce operations, with a particular focus on customer behavior analysis and operational efficiency. Leveraging the PRISMA methodology, the study synthesizes findings from 70 research articles spanning multiple countries, including the United States, China, India, the United Kingdom, and Germany. The review highlights the transformative role of AI-driven data warehouses in enabling real-time, predictive analytics, which significantly enhances the ability of e-commerce businesses to understand and respond to customer preferences, optimize inventory management, and implement dynamic pricing strategies. While the benefits of AI integration are substantial, the study also identifies persistent challenges, such as data privacy concerns, high implementation costs, and integration complexities, that may hinder widespread adoption. The paper concludes with recommendations for businesses to strategically approach the implementation of AI-powered data warehouses, emphasizing the need for scalable solutions, robust data governance, and ongoing investment in technology and training. This research underscores the potential of AI-powered data warehouses to drive innovation and growth in the e-commerce sector, while also calling for continued exploration of solutions to address the existing challenges.

The Hemodynamic Effects of Bolus Dose Calcium in Patients Undergoing Pulmonary Artery Reconstruction and Unifocalization Surgery: A Pilot Study

Objectives: To determine if bolus administration of calcium increases pulmonary artery pressures after unifocalization procedures or pulmonary artery reconstruction surgery. Design: Retrospective cohort study using Stanford University's data warehouse. Setting: A large pediatric heart center within an academic quaternary care facility. Participants: All patients undergoing pulmonary artery reconstruction or unifocalization procedure identifiable within the data warehouse. Interventions: We collected data from Stanford University's data repository; we formatted it and analyzed it using RStudio (v 2023.06.1+524). Measurements and Main Results: Our primary outcome is the change in pulmonary artery systolic pressure (PASP) after a bolus administration of calcium. Secondary endpoints include changes in pulmonary arterial to systemic arterial pressure ratio, mean arterial pressure, right sided filling pressure, and left atrial pressure. We used the Friedman test to assess differences and the Durbin-Conover rank-sum for pairwise comparisons. We found a difference in PASP after a bolus dose of calcium (Friedman X2 = 13.67, p = 0.003), with a higher PASP five minutes after calcium administration when compared to two minutes before the administration (35 mmHg versus 33 mmHg, p = 0.01), and a higher PASP 10 minutes after calcium administration when compared to two minutes before the administration (35 mmHg versus 33 mmHg, p = 0.008). Conclusions: Calcium bolus administration led to an increase in pulmonary arterial pressure in patients after pulmonary artery reconstruction or unifocalization surgeries. It may be prudent to avoid bolus administration in this patient population immediately after repair or in patients with right ventricular dysfunction.

Abated crowding by fast-tracking the Throughput component of the ED for patients in no need of hospitalization with competency managed personnel

BackgroundEmergency department (ED) crowding is a major patient safety concern and has a negative impact on healthcare systems and healthcare providers. We hypothesized that it would be feasible to control crowding by employing a multifaceted approach consisting of systematically fast-tracking patients who are mostly not in need of a hospital stay as assessed by an initial nurse and treated by decision competent physicians.MethodsData from 120,901 patients registered in a secondary care ED from the 4tth quarter of 2021 to the 1st quarter of 2024 was drawn from the electronic health record’s data warehouse using the SAP Web Intelligence tool and processed in the Python programming language. Crowding was compared before and after ED transformation from a uniform department into a high flow (α) and a low flow (β) section with patient placement in gurneys/chairs or beds, respectively. Patients putatively not in need of hospitalization were identified by nurse, placed in in the α setting and assessed and treated by decision competent physicians. Incidence of crowding, number of patients admitted per day and readmittances within 72 h following ED admission before and after changes were determined. Values are number of patients, mean ± SEM and mean differences with 95% CIs. Statistical significance was ascertained using Student’s two tailed t-test for unpaired values.ResultsBefore and after ED changes crowding of 130% amounted to 123.8 h and 19.3 h in the latter. This is a difference of -104.6 ± 23.9 h with a 95% CI of -159.9 to -49.3, Δ% -84 (p = 0.002).There was the same amount of patients / day amounting to 135.8 and 133.5 patients / day Δ% = -1.7 patients 95% CI -6.3 to 1.6 (p = 0.21).There was no change in readmittances within 72 h before and after changes amounting to 9.0% versus 9.5%, Δ% = 0.5, 95%, CI -0.007 to 1.0 (p > 0.052).ConclusionIt appears feasible to abate crowding with unchanged patient admission and without an increase in readmittances by fast-track assessment and treatment of patients who are not in need of hospitalization.

SSF-CDW: achieving scalable, secure, and fast OLAP query for encrypted cloud data warehouse

Implementing a cloud-based data warehouse to store sensitive or critical strategic data presents challenges primarily related to the security of the stored information and the exchange of OLAP queries between the cloud server and users. Although encryption is a viable solution for safeguarding outsourced data, applying it to OLAP queries involving multidimensional data, measures, and Multidimensional Expressions (MDX) operations on encrypted data poses difficulties. Existing searchable encryption solutions are inadequate for handling such complex queries, which complicates the use of business intelligence tools that rely on efficient and secure data processing and analysis.This paper proposes a new privacy-preserving cloud data warehouse scheme called SSF-CDW which facilitates a secure and scalable solution for an encrypted cloud data warehouse. Our SSF-CDW improves the OLAP queries accessible only to authorized users who can decrypt the query results with improved query performance compared to traditional OLAP tools. The approach involves utilizing symmetric encryption and Ciphertext Policy Attribute-Based Encryption (CP-ABE) to protect the privacy of the dimension and fact data modeled in Multidimensional OLAP (MOLAP). To support efficient OLAP query execution, we proposed a new data cube retrieval mechanism using a Redis schema which is an in-memory database. This technique dynamically compiles queries by disassembling them down into multiple levels and consolidates the results mapped to the corresponding encrypted data cube. The caching of dimensional and fact data associated with the encrypted cube is also implemented to improve the speed of frequently queried data. Experimental comparisons between our proposed indexed search strategy and other indexing schemes demonstrate that our approach surpasses alternative techniques in terms of search speed for both ad-hoc and repeated OLAP queries, all while preserving the privacy of the query results.

Specifics of Data Collection and Data Processing during Formation of RailVista Dataset for Machine Learning- and Deep Learning-Based Applications.

This paper presents the methodology and outcomes of creating the Rail Vista dataset, designed for detecting defects on railway tracks using machine and deep learning techniques. The dataset comprises 200,000 high-resolution images categorized into 19 distinct classes covering various railway infrastructure defects. The data collection involved a meticulous process including complex image capture methods, distortion techniques for data enrichment, and secure storage in a data warehouse using efficient binary file formats. This structured dataset facilitates effective training of machine/deep learning models, enhancing automated defect detection systems in railway safety and maintenance applications. The study underscores the critical role of high-quality datasets in advancing machine learning applications within the railway domain, highlighting future prospects for improving safety and reliability through automated recognition technologies.

Generalizability of heat-related health risk associations observed in a large healthcare claims database of patients with commercial health insurance.

Extreme ambient heat is unambiguously associated with higher risk of illness and death. The Optum Labs Data Warehouse (OLDW), a database of medical claims from US-based patients with commercial or Medicare Advantage health insurance, has been used to quantify heat-related health impacts. Whether results for the insured sub-population are generalizable to the broader population has to our knowledge not been documented. We sought to address this question, for the US population in California from 2012 to 2019. We examined changes in daily rates of emergency department (ED) encounters and in-patient hospitalization encounters for all-causes, heat-related outcomes, renal disease, mental/behavioral disorders, cardiovascular disease, and respiratory disease. OLDW was the source for health data for insured individuals in California, and health data for the broader population were gathered from the California Department of Health Care Access and Information (HCAI). We defined extreme heat exposure as any day in a group of 2 or more days with maximum temperatures exceeding the county-specific 97.5 th percentile and used a space-time-stratified case-crossover design to assess and compare the impacts of heat on health. Average incidence rates of medical encounters differed by dataset. However, rate ratios for ED encounters were similar across datasets for all causes (ratio of incidence rate ratios (rIRR) = 0.989; 95% confidence interval (CI) = 0.973, 1.011), heat-related causes (rIRR = 1.080; 95% CI = 0.999, 1.168), renal disease (rIRR = 0.963; 95% CI = 0.718, 1.292), and mental health disorders (rIRR = 1.098; 95% CI = 1.004, 1.201). Rate ratios for inpatient encounters were also similar. This work presents evidence that OLDW can continue to be a resource for estimating the health impacts of extreme heat.

PENERAPAN TEKNIK ETL PADA KOMENTAR APLIKASI FLIP.ID DI APLIKASI PLAYSTORE DENGAN APLIKASI PENTAHO

User comments on the Play Store are crucial sources for developers to understand user feedback on their applications. In this research, we introduce the application of Extract, Transform, Load (ETL) Technique to analyze user comments on the Flip.id application on the Play Store using the Pentaho application. The ETL method is utilized to extract comment data, transform it into a suitable format, and load it into a data warehouse for further analysis. This process involves systematic and structured data processing steps. We identify common patterns in user comments to gain valuable insights for application developers in enhancing the quality and user experience of their applications. The research findings indicate that the application of ETL Technique using the Pentaho application can be an effective approach for analyzing user comments on the Play Store platform, as well as providing valuable insights for application developers for data-driven decision-making. This research can serve as a foundation for further research in sentiment analysis and user-driven product improvement