Dataset Information

An extensible big data software architecture managing a research resource of real-world clinical radiology data linked to other health data from the whole Scottish population.

ABSTRACT: AIM:To enable a world-leading research dataset of routinely collected clinical images linked to other routinely collected data from the whole Scottish national population. This includes more than 30 million different radiological examinations from a population of 5.4 million and >2 PB of data collected since 2010. METHODS:Scotland has a central archive of radiological data used to directly provide clinical care to patients. We have developed an architecture and platform to securely extract a copy of those data, link it to other clinical or social datasets, remove personal data to protect privacy, and make the resulting data available to researchers in a controlled Safe Haven environment. RESULTS:An extensive software platform has been developed to host, extract, and link data from cohorts to answer research questions. The platform has been tested on 5 different test cases and is currently being further enhanced to support 3 exemplar research projects. CONCLUSIONS:The data available are from a range of radiological modalities and scanner types and were collected under different environmental conditions. These real-world, heterogenous data are valuable for training algorithms to support clinical decision making, especially for deep learning where large data volumes are required. The resource is now available for international research access. The platform and data can support new health research using artificial intelligence and machine learning technologies, as well as enabling discovery science.

SUBMITTER: Nind T

PROVIDER: S-EPMC7523405 | biostudies-literature | 2020 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

An extensible big data software architecture managing a research resource of real-world clinical radiology data linked to other health data from the whole Scottish population.

Nind Thomas T Sutherland James J McAllister Gordon G Hardy Douglas D Hume Ally A MacLeod Ruairidh R Caldwell Jacqueline J Krueger Susan S Tramma Leandro L Teviotdale Ross R Abdelatif Mohammed M Gillen Kenny K Ward Joe J Scobbie Donald D Baillie Ian I Brooks Andrew A Prodan Bianca B Kerr William W Sloan-Murphy Dominic D Herrera Juan F R JFR McManus Dan D Morris Carole C Sinclair Carol C Baxter Rob R Parsons Mark M Morris Andrew A Jefferson Emily E

GigaScience 20200901 10

<h4>Aim</h4>To enable a world-leading research dataset of routinely collected clinical images linked to other routinely collected data from the whole Scottish national population. This includes more than 30 million different radiological examinations from a population of 5.4 million and >2 PB of data collected since 2010.<h4>Methods</h4>Scotland has a central archive of radiological data used to directly provide clinical care to patients. We have developed an architecture and platform to securel ...[more]

PMID: 32990744

Similar Datasets

Project description:BackgroundNew "next generation" DNA sequencing technologies offer individual researchers the ability to rapidly generate large amounts of genome sequence data at dramatically reduced costs. As a result, a need has arisen for new software tools for storage, management and analysis of genome sequence data. Although bioinformatic tools are available for the analysis and management of genome sequences, limitations still remain. For example, restrictions on the submission of data and use of these tools may be imposed, thereby making them unsuitable for sequencing projects that need to remain in-house or proprietary during their initial stages. Furthermore, the availability and use of next generation sequencing in industrial, governmental and academic environments requires biologist to have access to computational support for the curation and analysis of the data generated; however, this type of support is not always immediately available.ResultsTo address these limitations, we have developed DraGnET (Draft Genome Evaluation Tool). DraGnET is an open source web application which allows researchers, with no experience in programming and database management, to setup their own in-house projects for storing, retrieving, organizing and managing annotated draft and complete genome sequence data. The software provides a web interface for the use of BLAST, allowing users to perform preliminary comparative analysis among multiple genomes. We demonstrate the utility of DraGnET for performing comparative genomics on closely related bacterial strains. Furthermore, DraGnET can be further developed to incorporate additional tools for more sophisticated analyses.ConclusionsDraGnET is designed for use either by individual researchers or as a collaborative tool available through Internet (or Intranet) deployment. For genome projects that require genome sequencing data to initially remain proprietary, DraGnET provides the means for researchers to keep their data in-house for analysis using local programs or until it is made publicly available, at which point it may be uploaded to additional analysis software applications. The DraGnET home page is available at http://www.dragnet.cvm.iastate.edu and includes example files for examining the functionalities, a link for downloading the DraGnET setup package and a link to the DraGnET source code hosted with full documentation on SourceForge.

Dataset Information

An extensible big data software architecture managing a research resource of real-world clinical radiology data linked to other health data from the whole Scottish population.

Publications

An extensible big data software architecture managing a research resource of real-world clinical radiology data linked to other health data from the whole Scottish population.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets