@misc{Adamska2015,
title = {Challenges of linking to routine healthcare records in UK Biobank},
author = { Ligia Adamska, Naomi Allen, Robin Flaig, Cathie Sudlow, Michael Lay and Martin Landray },
url = {http://www.trialsjournal.com/content/16/S2/O68},
year = {2015},
date = {2015-11-16},
abstract = {

Increased availability of electronic healthcare records (EHR) has transformed how health research is conducted in the UK by enabling linkages between various health-related datasets.

UK Biobank is a prospective cohort study of 500,000 men and women aged 40-69 years recruited throughout the UK between 2006 and 2010. To follow participants' health over time, UK Biobank has linked to national death and cancer registries and hospital admissions data, with linkage to primary care data under development. This exercise involves linking to separate data providers, determining which data-fields are of most value to research, mapping changes in clinical coding systems over time, and distinguishing which data can be standardised from those that should remain specific to the dataset of origin, before integration into a single dataset amenable to analysis by external researchers.

Data linkage for a national cohort poses several challenges including different regulatory processes across each of the devolved data providers, as well as differences in matching algorithms, data formats and coding schema, in addition to the sheer volume of data to be processed. One of the biggest challenges is defining rules for handling data ambiguities whilst preserving data integrity and provenance. UK Biobank is the first study to map hospital episode records across England, Scotland and Wales. These datasets vary in terms of content, data quality, geographical and temporal coverage and considerable expertise is required to integrate, document and present these data in an accessible way to researchers.
},
keywords = {By UK Biobank, linkage},
pubstate = {published},
tppubtype = {presentation}
}

@article{Sudlow2015,
title = {UK Biobank: An Open Access Resource for Identifying the Causes of a Wide Range of Complex Diseases of Middle and Old Age},
author = {Cathie Sudlow and John Gallacher and Naomi Allen and Valerie Beral and Paul Burton and John Danesh and Paul Downey and Paul Elliott and Jane Green and Martin Landray and Bette Liu and Paul Matthews and Giok Ong and Jill Pell and Alan Silman and Alan Young and Tim Sprosen and Tim Peakman and Rory Collins },
url = {http://journals.plos.org/plosmedicine/article?id=10.1371/journal.pmed.1001779},
year = {2015},
date = {2015-03-31},
journal = {PLOS Medicine},
abstract = {The challenge of understanding the determinants of common life-threatening and disabling conditions is substantial. These conditions are typically caused by a combination of lifestyle, environmental, and genomic factors, with individually modest effects and complex interactions, the detection and quantification of which require studies with large numbers of disease cases. While retrospective case-control studies of particular diseases [1] or existing prospective studies of particular risk factors can help to address this challenge [2,3], a complementary approach is to establish large prospective cohorts designed to study a much wider range of known and novel risk factors for a wide range of diseases [4]. Prospective studies can assess exposures before the onset and treatment of disease, diseases that are not readily investigated by retrospective studies, and both the adverse and beneficial effects of a specific exposure on the lifetime risks of different diseases.

UK (United Kingdom) Biobank is a very large, population-based prospective study, established to allow detailed investigations of the genetic and nongenetic determinants of the diseases of middle and old age [5,6]. It aims to combine extensive and precise assessment of exposures with comprehensive follow-up and characterisation of many different health-related outcomes, as well as to promote innovative science by maximising access to the resource. Recruitment of 500,000 participants and the collection of an unprecedented wealth of baseline data and samples were completed in 2010. Activity is now focused on further phenotyping of participants and their health outcomes and on providing access to researchers from around the world.},
keywords = {About UKBiobank, By UK Biobank, methodology, Open Access},
pubstate = {published},
tppubtype = {article}
}

@article{Gaye2014,
title = {Understanding the impact of pre-analytic variation in haematological and clinical chemistry analytes on the power of association studies},
author = {Amadou Gaye and Tim Peakman and Martin D Tobin and Paul R Burton},
url = {http://ije.oxfordjournals.org/content/early/2014/07/31/ije.dyu127.short?rss=1},
year = {2014},
date = {2014-08-01},
journal = {International Journal of Epidemiology},
volume = {10.1093/ije/dyu127},
abstract = {Background: Errors, introduced through poor assessment of physical measurement or because of inconsistent or inappropriate standard operating procedures for collecting, processing, storing or analysing haematological and biochemistry analytes, have a negative impact on the power of association studies using the collected data. A dataset from UK Biobank was used to evaluate the impact of pre-analytical variability on the power of association studies.

Methods: First, we estimated the proportion of the variance in analyte concentration that may be attributed to delay in processing using variance component analysis. Then, we captured the proportion of heterogeneity between subjects that is due to variability in the rate of degradation of analytes, by fitting a mixed model. Finally, we evaluated the impact of delay in processing on the power of a nested case-control study using a power calculator that we developed and which takes into account uncertainty in outcome and explanatory variables measurements.

Results: The results showed that (i) the majority of the analytes investigated in our analysis, were stable over a period of 36 h and (ii) some analytes were unstable and the resulting pre-analytical variation substantially decreased the power of the study, under the settings we investigated.

Conclusions: It is important to specify a limited delay in processing for analytes that are very sensitive to delayed assay. If the rate of degradation of an analyte varies between individuals, any delay introduces a bias which increases with increasing delay. If pre-analytical variation occurring due to delays in sample processing is ignored, it affects adversely the power of the studies that use the data.},
keywords = {analytes, By UK Biobank},
pubstate = {published},
tppubtype = {article}
}

@article{Biobank2014,
title = {UK BIOBANK DATA: COME AND GET IT},
author = {UK Biobank},
url = {http://stm.sciencemag.org/content/6/224/224ed4.short},
issn = {1946-6234},
year = {2014},
date = {2014-02-19},
journal = {Science Translational Medicine},
volume = {6},
number = {224},
pages = {224},
keywords = {By UK Biobank, methodology},
pubstate = {published},
tppubtype = {article}
}

@article{Allena2012,
title = {UK Biobank: Current status and what it means for epidemiology},
author = {Naomi Allena and Cathie Sudlowa and Paul Downey and Tim Peakman and John Danesh and Paul Elliott and John Gallacher and Jane Green and Paul Matthews and Jill Pell and Tim Sprosen and Rory Collins},
url = {http://www.sciencedirect.com/science/article/pii/S2211883712000597},
year = {2012},
date = {2012-09-01},
journal = {Health Policy and Technology},
volume = {1},
number = {3},
pages = {123–126},
abstract = {UK Biobank is a very large prospective study which aims to provide a resource for the investigation of the genetic, environmental and lifestyle determinants of a wide range of diseases of middle age and later life. Between 2006 and 2010, over 500,000 men and women aged 40 to 69 years were recruited and extensive data on participants' lifestyles, environment, medical history and physical measures, along with biological samples, were collected. The health of the participants is now being followed long-term, principally through linkage to a wide range of health-related records, with validation and characterisation of health-related outcomes. Further enhancements are also underway to improve phenotype characterisation, including internet-based dietary assessment, biomarker measurements on the baseline blood samples and, in sub-samples of the cohort, physical activity monitoring and proposals for extensive brain and body imaging. UK Biobank is now available for use by all researchers, without exclusive or preferential access, for any health-related research that is in the public interest. The open-access nature of the resource will allow researchers from around the world to conduct research that leads to better strategies for the prevention, diagnosis and treatment of a wide range of life-threatening and disabling conditions.},
keywords = {By UK Biobank, epidemiology, imaging, methodology},
pubstate = {published},
tppubtype = {article}
}

@article{Collins2012,
title = {What makes UK Biobank special?},
author = {Rory Collins},
url = {http://www.thelancet.com/journals/lancet/article/PIIS0140-6736(12)60404-8/fulltext},
year = {2012},
date = {2012-03-29},
journal = {The Lancet },
volume = {379},
number = {9822},
pages = {1173 - 1174},
abstract = {In a prescient move more than a decade ago, the Medical Research Council and Wellcome Trust decided to establish the large UK Biobank prospective cohort to support the investigation of risk factors for the major diseases of middle and old age. 1 , 2 Recruitment of more than 500 000 men and women aged 40—69 years was successfully achieved during 2006—10 and their health is being followed long term. On March 30, 2012, the UK Biobank resource is launched for use by all researchers—without exclusive or pr ..},
keywords = {By UK Biobank, methodology},
pubstate = {published},
tppubtype = {article}
}

@article{Downey2008,
title = {Design and implementation of a high-throughput biological sample processing facility using modern manufacturing principles.},
author = {Paul Downey and Tim Peakman},
url = {http://www.ncbi.nlm.nih.gov/pubmed/18381393},
year = {2008},
date = {2008-04-01},
journal = {International Journal of Epidemiology},
volume = {37},
number = {1},
pages = {46-50},
keywords = {By UK Biobank, methodology},
pubstate = {published},
tppubtype = {article}
}

@article{Elliott2008,
title = {The UK Biobank sample handling and storage validation studies},
author = {Paul Elliott and Tim C Peakman},
url = {http://www.ncbi.nlm.nih.gov/pubmed/18381389},
year = {2008},
date = {2008-04-01},
journal = {International Journal of Epidemiology},
volume = {37},
number = {1},
pages = {i2-i6},
abstract = {Background and aims UK Biobank is a large prospective study in the United Kingdom to investigate the role of genetic factors, environmental exposures and lifestyle in the causes of major diseases of late and middle age. It involves the collection of blood and urine from 500 000 individuals aged between 40 and 69 years. How the samples are collected, processed and stored will have a major impact on the future scientific usefulness of the UK Biobank resource. A series of validation studies was recommended to test the robustness of the draft sample handling and storage protocol.

Methods Samples of blood and urine were collected from 40 healthy volunteers and either processed immediately according to the protocol or maintained at specified temperatures (4°C for all tubes with the exception of vacutainers containing acid citrate dextrose that were maintained at 18°C) for 12, 24 or 36 h prior to processing. A further sample was maintained for 24 h at 4°C, processed and the aliquots frozen at −80°C for 20 days and then thawed under controlled conditions. The stability of the samples was compared for the different times in a wide variety of assays.

Results The samples maintained at 4°C were stable for at least 24 h after collection for a wide range of assays. Small but significant changes were observed in metabonomic studies in samples maintained at 4°C for 36 h. There was no degradation of the samples for a range of biochemical assays after short-term freezing and thawing under controlled conditions. Whole blood maintained at 18°C for 24 h in vacutainers containing acid citrate dextrose is suitable for viral immortalization techniques.

Conclusions The validation studies reported in this supplement provide justification for the sample handling and storage procedures adopted in the UK Biobank project.},
keywords = {By UK Biobank, methodology, storage},
pubstate = {published},
tppubtype = {article}
}