Global Data Sharing in Alzheimer Disease Research.

Many investigators recognize the importance of data sharing; however, they lack the capability to share data. Research efforts could be vastly expanded if Alzheimer disease data from around the world was linked by a global infrastructure that would enable scientists to access and utilize a secure network of data with thousands of study participants at risk for or already suffering from the disease. We discuss the benefits of data sharing, impediments today, and solutions to achieving this on a global scale. We introduce the Global Alzheimer's Association Interactive Network (GAAIN), a novel approach to create a global network of Alzheimer disease data, researchers, analytical tools, and computational resources to better our understanding of this debilitating condition. GAAIN has addressed the key impediments to Alzheimer disease data sharing with its model and approach. It presents practical, promising, yet, data owner-sensitive data-sharing solutions.

The Global Alzheimer's Association Interactive Network.

INTRODUCTION: The Global Alzheimer's Association Interactive Network (GAAIN) is consolidating the efforts of independent Alzheimer's disease data repositories around the world with the goals of revealing more insights into the causes of Alzheimer's disease, improving treatments, and designing preventative measures that delay the onset of physical symptoms. METHODS: We developed a system for federating these repositories that is reliant on the tenets that (1) its participants require incentives to join, (2) joining the network is not disruptive to existing repository systems, and (3) the data ownership rights of its members are protected. RESULTS: We are currently in various phases of recruitment with over 55 data repositories in North America, Europe, Asia, and Australia and can presently query >250,000 subjects using GAAIN's search interfaces. DISCUSSION: GAAIN's data sharing philosophy, which guided our architectural choices, is conducive to motivating membership in a voluntary data sharing network.

Identifying appropriate reference data models for comparative effectiveness research (CER) studies based on data from clinical information systems.

INTRODUCTION: The need for a common format for electronic exchange of clinical data prompted federal endorsement of applicable standards. However, despite obvious similarities, a consensus standard has not yet been selected in the comparative effectiveness research (CER) community. METHODS: Using qualitative metrics for data retrieval and information loss across a variety of CER topic areas, we compare several existing models from a representative sample of organizations associated with clinical research: the Observational Medical Outcomes Partnership (OMOP), Biomedical Research Integrated Domain Group, the Clinical Data Interchange Standards Consortium, and the US Food and Drug Administration. RESULTS: While the models examined captured a majority of the data elements that are useful for CER studies, data elements related to insurance benefit design and plans were most detailed in OMOP's CDM version 4.0. Standardized vocabularies that facilitate semantic interoperability were included in the OMOP and US Food and Drug Administration Mini-Sentinel data models, but are left to the discretion of the end-user in Biomedical Research Integrated Domain Group and Analysis Data Model, limiting reuse opportunities. Among the challenges we encountered was the need to model data specific to a local setting. This was handled by extending the standard data models. DISCUSSION: We found that the Common Data Model from the OMOP met the broadest complement of CER objectives. Minimal information loss occurred in mapping data from institution-specific data warehouses onto the data models from the standards we assessed. However, to support certain scenarios, we found a need to enhance existing data dictionaries with local, institution-specific information.

Medical data transformation using rewriting.

This paper presents a system for declaratively transforming medical subjects' data into a common data model representation. Our work is part of the "GAAIN" project on Alzheimer's disease data federation across multiple data providers. We present a general purpose data transformation system that we have developed by leveraging the existing state-of-the-art in data integration and query rewriting. In this work we have further extended the current technology with new formalisms that facilitate expressing a broader range of data transformation tasks, plus new execution methodologies to ensure efficient data transformation for disease datasets.

The GAAIN Entity Mapper: An Active-Learning System for Medical Data Mapping.

This work is focused on mapping biomedical datasets to a common representation, as an integral part of data harmonization for integrated biomedical data access and sharing. We present GEM, an intelligent software assistant for automated data mapping across different datasets or from a dataset to a common data model. The GEM system automates data mapping by providing precise suggestions for data element mappings. It leverages the detailed metadata about elements in associated dataset documentation such as data dictionaries that are typically available with biomedical datasets. It employs unsupervised text mining techniques to determine similarity between data elements and also employs machine-learning classifiers to identify element matches. It further provides an active-learning capability where the process of training the GEM system is optimized. Our experimental evaluations show that the GEM system provides highly accurate data mappings (over 90% accuracy) for real datasets of thousands of data elements each, in the Alzheimer's disease research domain. Further, the effort in training the system for new datasets is also optimized. We are currently employing the GEM system to map Alzheimer's disease datasets from around the globe into a common representation, as part of a global Alzheimer's disease integrated data sharing and analysis network called GAAIN. GEM achieves significantly higher data mapping accuracy for biomedical datasets compared to other state-of-the-art tools for database schema matching that have similar functionality. With the use of active-learning capabilities, the user effort in training the system is minimal.

GEM: The GAAIN Entity Mapper.

We present a software system solution that significantly simplifies data sharing of medical data. This system, called GEM (for the GAAIN Entity Mapper), harmonizes medical data. Harmonization is the process of unifying information across multiple disparate datasets needed to share and aggregate medical data. Specifically, our system automates the task of finding corresponding elements across different independently created (medical) datasets of related data. We present our overall approach, detailed technical architecture, and experimental evaluations demonstrating the effectiveness of our approach.

The clinical translation gap in child health exercise research: a call for disruptive innovation.

In children, levels of play, physical activity, and fitness are key indicators of health and disease and closely tied to optimal growth and development. Cardiopulmonary exercise testing (CPET) provides clinicians with biomarkers of disease and effectiveness of therapy, and researchers with novel insights into fundamental biological mechanisms reflecting an integrated physiological response that is hidden when the child is at rest. Yet the growth of clinical trials utilizing CPET in pediatrics remains stunted despite the current emphasis on preventative medicine and the growing recognition that therapies used in children should be clinically tested in children. There exists a translational gap between basic discovery and clinical application in this essential component of child health. To address this gap, the NIH provided funding through the Clinical and Translational Science Award (CTSA) program to convene a panel of experts. This report summarizes our major findings and outlines next steps necessary to enhance child health exercise medicine translational research. We present specific plans to bolster data interoperability, improve child health CPET reference values, stimulate formal training in exercise medicine for child health care professionals, and outline innovative approaches through which exercise medicine can become more accessible and advance therapeutics across the broad spectrum of child health.

University of California, Irvine-Pathology Extraction Pipeline: the pathology extraction pipeline for information extraction from pathology reports.

We describe Pathology Extraction Pipeline (PEP)--a new Open Health Natural Language Processing pipeline that we have developed for information extraction from pathology reports, with the goal of populating the extracted data into a research data warehouse. Specifically, we have built upon Medical Knowledge Analysis Tool pipeline (MedKATp), which is an extraction framework focused on pathology reports. Our particular contributions include additional customization and development on MedKATp to extract data elements and relationships from cancer pathology reports in richer detail than at present, an abstraction layer that provides significantly easier configuration of MedKATp for extraction tasks, and a machine-learning-based approach that makes the extraction more resilient to deviations from the common reporting format in a pathology reports corpus. We present experimental results demonstrating the effectiveness of our pipeline for information extraction in a real-world task, demonstrating performance improvement due to our approach for increasing extractor resilience to format deviation, and finally demonstrating the scalability of the pipeline across pathology reports for different cancer types.

Neuroscience Data Integration through Mediation: An (F)BIRN Case Study.

We describe an application of the BIRN mediator to the integration of neuroscience experimental data sources. The BIRN mediator is a general purpose solution to the problem of providing integrated, semantically-consistent access to biomedical data from multiple, distributed, heterogeneous data sources. The system follows the mediation approach, where the data remains at the sources, providers maintain control of the data, and the integration system retrieves data from the sources in real-time in response to client queries. Our aim with this paper is to illustrate how domain-specific data integration applications can be developed quickly and in a principled way by using our general mediation technology. We describe in detail the integration of two leading, but radically different, experimental neuroscience sources, namely, the human imaging database, a relational database, and the eXtensible neuroimaging archive toolkit, an XML web services system. We discuss the steps, sources of complexity, effort, and time required to build such applications, as well as outline directions of ongoing and future research on biomedical data integration.