Search

MotivationIn multi-cohort machine learning studies, it is critical to differentiate between effects that are reproducible across cohorts and those that are cohort-specific. Multi-task learning (MTL) is a machine learning approach that facilitates this differentiation through the simultaneous learning of prediction tasks across cohorts. Since multi-cohort data can often not be combined into a single storage solution, there would be the substantial utility of an MTL application for geographically distributed data sources.ResultsHere, we describe the development of ‘dsMTL’, a computational framework for privacy-preserving, distributed multi-task machine learning that includes three supervised and one unsupervised algorithms. First, we derive the theoretical properties of these methods and the relevant machine learning workflows to ensure the validity of the software implementation. Second, we implement dsMTL as a library for the R programming language, building on the DataSHIELD platform that supports the federated analysis of sensitive individual-level data. Third, we demonstrate the applicability of dsMTL for comorbidity modeling in distributed data. We show that comorbidity modeling using dsMTL outperformed conventional, federated machine learning, as well as the aggregation of multiple models built on the distributed datasets individually. The application of dsMTL was computationally efficient and highly scalable when applied to moderate-size (n Availability and implementationdsMTL is freely available at https://github.com/transbioZI/dsMTLBase (server-side package) and https://github.com/transbioZI/dsMTLClient (client-side package).Supplementary informationSupplementary data are available at Bioinformatics online.

Objectives: Existing individual-level human data cover large populations on many dimensions such as lifestyle, demography, laboratory measures, clinical parameters, etc. Recent years have seen large investments in data catalogues to FAIRify data descriptions to capitalise on this great promise, i.e. make catalogue contents more Findable, Accessible, Interoperable and Reusable. However, their valuable diversity also created heterogeneity, which poses challenges to optimally exploit their richness.Methods: In this opinion review, we analyse catalogues for human subject research ranging from cohort studies to surveillance, administrative and healthcare records.Results: We observe that while these catalogues are heterogeneous, have various scopes, and use different terminologies, still the underlying concepts seem potentially harmonizable. We propose a unified framework to enable catalogue data sharing, with catalogues of multi-center cohorts nested as a special case in catalogues of real-world data sources. Moreover, we list recommendations to create an integrated community of metadata catalogues and an open catalogue ecosystem to sustain these efforts and maximise impact.Conclusions: We propose to embrace the autonomy of motivated catalogue teams and invest in their collaboration via minimal standardisation efforts such as clear data licensing, persistent identifiers for linking same records between catalogues, minimal metadata ‘common data elements’ using shared ontologies, symmetric architectures for data sharing (push/pull) with clear provenance tracks to process updates and acknowledge original contributors. And most importantly, we encourage the creation of environments for collaboration and resource sharing between catalogue developers, building on international networks such as OpenAIRE and research data alliance, as well as domain specific ESFRIs such as BBMRI and ELIXIR. OBJECTIVES: Existing individual-level human data cover large populations on many dimensions such as lifestyle, demography, laboratory measures, clinical parameters, etc. Recent years have seen large investments in data catalogues to FAIRify data descriptions to capitalise on this great promise, i.e. make catalogue contents more Findable, Accessible, Interoperable and Reusable. However, their valuable diversity also created heterogeneity, which poses challenges to optimally exploit their richness. METHODS: In this opinion review, we analyse catalogues for human subject research ranging from cohort studies to surveillance, administrative and healthcare records. RESULTS: We observe that while these catalogues are heterogeneous, have various scopes, and use different terminologies, still the underlying concepts seem potentially harmonizable. We propose a unified framework to enable catalogue data sharing, with catalogues of multi-center cohorts nested as a special case in catalogues of real-world data sources. Moreover, we list recommendations to create an integrated community of metadata catalogues and an open catalogue ecosystem to sustain these efforts and maximise impact. CONCLUSIONS: We propose to embrace the autonomy of motivated catalogue teams and invest in their collaboration via minimal standardisation efforts such as clear data licensing, persistent identifiers for linking same records between catalogues, minimal metadata 'common data elements' using shared ontologies, symmetric architectures for data sharing (push/pull) with clear provenance tracks to process updates and acknowledge original contributors. And most importantly, we encourage the creation of environments for collaboration and resource sharing between catalogue developers, building on international networks such as OpenAIRE and research data alliance, as well as domain specific ESFRIs such as BBMRI and ELIXIR.

Background The lack of accessible and structured documentation creates major barriers for investigators interested in understanding, properly interpreting and analyzing cohort data and biological samples. Providing the scientific community with open information is essential to optimize usage of these resources. A cataloguing toolkit is proposed by Maelstrom Research to answer these needs and support the creation of comprehensive and user-friendly study- and network-specific web-based metadata catalogues. Methods Development of the Maelstrom Research cataloguing toolkit was initiated in 2004. It was supported by the exploration of existing catalogues and standards, and guided by input from partner initiatives having used or pilot tested incremental versions of the toolkit. Results The cataloguing toolkit is built upon two main components: a metadata model and a suite of open-source software applications. The model sets out specific fields to describe study profiles; characteristics of the subpopulations of participants; timing and design of data collection events; and datasets/variables collected at each data collection event. It also includes the possibility to annotate variables with different classification schemes. When combined, the model and software support implementation of study and variable catalogues and provide a powerful search engine to facilitate data discovery. Conclusions The Maelstrom Research cataloguing toolkit already serves several national and international initiatives and the suite of software is available to new initiatives through the Maelstrom Research website. With the support of new and existing partners, we hope to ensure regular improvements of the toolkit.

Motivation Improving the dissemination of information on existing epidemiological studies and facilitating the interoperability of study databases are essential to maximizing the use of resources and accelerating improvements in health. To address this, Maelstrom Research proposes Opal and Mica, two inter-operable open-source software packages providing out-of-the-box solutions for epidemiological data management, harmonization and dissemination. Implementation Opal and Mica are two standalone but inter-operable web applications written in Java, JavaScript and PHP. They provide web services and modern user interfaces to access them. General features Opal allows users to import, manage, annotate and harmonize study data. Mica is used to build searchable web portals disseminating study and variable metadata. When used conjointly, Mica users can securely query and retrieve summary statistics on geographically dispersed Opal servers in real-time. Integration with the DataSHIELD approach allows conducting more complex federated analyses involving statistical models. Availability Opal and Mica are open-source and freely available at [www.obiba.org] under a General Public License (GPL) version 3, and the metadata models and taxonomies that accompany them are available under a Creative Commons licence.

Gaye, Amadou Marcon, Yannick Isaeva, Julia LaFlamme, Philippe Turner, Andrew Jones, Elinor M Minion, Joel Boyd, Andrew W Newby, Christopher J Nuotio, Marja-Liisa Wilson, Rebecca Butters, Oliver Murtagh, Barnaby Demir, Ipek Doiron, Dany Giepmans, Lisette Wallace, Susan E Budin-Ljosne, Isabelle Oliver Schmidt, Carsten Boffetta, Paolo Boniol, Mathieu Bota, Maria Carter, Kim W deKlerk, Nick Dibben, Chris Francis, Richard W Hiekkalinna, Tero Hveem, Kristian Kvaloy, Kirsti Millar, Sean Perry, Ivan J Peters, Annette Phillips, Catherine M Popham, Frank Raab, Gillian Reischl, Eva Sheehan, Nuala Waldenberger, Melanie Perola, Markus van den Heuvel, Edwin Macleod, John Knoppers, Bartha M Stolk, Ronald P Fortier, Isabel Harris, Jennifer R Woffenbuttel, Bruce H R Murtagh, Madeleine J Ferretti, Vincent Burton, Paul R eng MC_UP_A540₁021/Medical Research Council/United Kingdom MR/K006525/1/Medical Research Council/United Kingdom Medical Research Council/United Kingdom Wellcome Trust/United Kingdom Research Support, Non-U.S. Gov't England 2014/09/30 06:00 Int J Epidemiol. 2014 Dec;43(6):1929-44. doi: 10.1093/ije/dyu188. Epub 2014 Sep 26.; International audience; BACKGROUND: Research in modern biomedicine and social science requires sample sizes so large that they can often only be achieved through a pooled co-analysis of data from several studies. But the pooling of information from individuals in a central database that may be queried by researchers raises important ethico-legal questions and can be controversial. In the UK this has been highlighted by recent debate and controversy relating to the UK's proposed 'care.data' initiative, and these issues reflect important societal and professional concerns about privacy, confidentiality and intellectual property. DataSHIELD provides a novel technological solution that can circumvent some of the most basic challenges in facilitating the access of researchers and other healthcare professionals to individual-level data. METHODS: Commands are sent from a central analysis computer (AC) to several data computers (DCs) storing the data to be co-analysed. The data sets are analysed simultaneously but in parallel. The separate parallelized analyses are linked by non-disclosive summary statistics and commands transmitted back and forth between the DCs and the AC. This paper describes the technical implementation of DataSHIELD using a modified R statistical environment linked to an Opal database deployed behind the computer firewall of each DC. Analysis is controlled through a standard R environment at the AC. RESULTS: Based on this Opal/R implementation, DataSHIELD is currently used by the Healthy Obese Project and the Environmental Core Project (BioSHaRE-EU) for the federated analysis of 10 data sets across eight European countries, and this illustrates the opportunities and challenges presented by the DataSHIELD approach. CONCLUSIONS: DataSHIELD facilitates important research in settings where: (i) a co-analysis of individual-level data from several studies is scientifically necessary but governance restrictions prohibit the release or sharing of some of the required data, and/or render data access unacceptably slow; (ii) a research group (e.g. in a developing nation) is particularly vulnerable to loss of intellectual property-the researchers want to fully share the information held in their data with national and international collaborators, but do not wish to hand over the physical data themselves; and (iii) a data set is to be included in an individual-level co-analysis but the physical size of the data precludes direct transfer to a new site for analysis.