Suchergebnisse

ObjectivesCO-CONNECT is making UK COVID-19 data Findable, Accessible, Interoperable and Reusable (FAIR) through a federated platform, which supports secure, anonymised research at scale and pace. This interdisciplinary project, spanning 22 organisations, is connecting data from >50 large research cohorts and data collected through routine healthcare provision across the UK.
ApproachAcross the UK, data has been collected that can help us answer key questions about COVID-19. As the data are in many places with many different processes it is difficult and complex for public health groups, researchers, policymakers, and government to find and access lots of high-quality data quickly and efficiently to make decisions. In collaboration with Health Data Research UK, CO-CONNECT is streamlining processes of accessing data for research.
Results1) Discovering data and meta-analysis: CO-CONNECT enables researchers to determine how many people meet their research criteria within the various datasets across the UK through the Health Data Research Innovation Gateway Cohort Discovery tool e.g. "How many people in each dataset have had a PCR test which was positive and were under the age of 40?" Only summary level, anonymous data are provided so researchers can answer such questions rapidly without requiring multiple data governance permissions and directly contacting each data source. The tool also supports aggregate level meta-analysis of the data.
2) Detailed analysis: With data governance approvals, researchers can analyse detailed level, standardised, linked, pseudonymised data in a Trusted Research Environment. The common format reduces the effort on each research project, supporting rapid research.
ConclusionProviding data in this de-identifiable, safe way enables rapid, robust research e.g., COVID-19 results from a test centre can be linked to hospital records along with prescriptions from pharmacies enabling researchers to understand whether people with different existing health conditions are more or less susceptible to COVID-19. If you want to know more visit https://co-connect.ac.uk.

Objectives To develop a new approval process for federated data custodians to install and support a new platform which enables researchers to run from one website, instantaneous, aggregate-level queries to determine the number of patients in each dataset which meet their research criteria.
To agree security controls across data custodians which protect patient confidentiality whilst also providing this new automated capability for researchers and reducing the burden on each data custodian to manually provide the information.
ApproachThe COVID - Curated and Open aNalysis aNd rEsearCh plaTform (CO-CONNECT) has integrated a Cohort Discovery Tool into the Health Data Research (HDR) UK Innovation Gateway website and is connecting >50 different federated datasets. The underpinning architecture is novel, without precedent at such a scale in the UK. We found that although each data custodian recognised the benefits of the platform, many were unclear of the process to formally approve this new model. We have worked across data custodians to co-develop the required new processes and document the security controls.
ResultsWe found vast differences in technical knowledge and infrastructures across different data custodians, especially across small research groups hosting data on consented research cohorts verses larger organisations who host and manage routinely collected data. A model for approvals evolved for these 2 separate groups:
Consented research cohorts: a 2-stage process of a pre-assessment for the need for a DPIA and/or completed DPIA. All returned a positive outcome which deemed no personal identifiable information was being used.
Unconsented population level data: 4 different documents were required each being approved by different committees within each data custodian: DPIA, Data Access Application, Security Risk Assessment, Disclosure Control Assessment.
As the model was novel to many data custodians, we developed many different explainer videos and detailed step by step instructions.
ConclusionWe recommend a new approvals process for new technologies/models is developed to support initiatives which are not covered by the traditional data access request process. Increased investment in teams which approve data governance and IT security applications which have been overwhelmed by the increased demand for their services to review COVID-19 related projects would be welcomed.

ObjectivesBuilding upon the Scottish Safe Haven Network's (SSHN) collaborative experience to develop an exemplar dataset on Scottish national level laboratory tests within the SSHN. To test the feasibility of a federated safe haven network in Scotland for clinical laboratory data using existing federation solutions.
ApproachConsiderations were given to the clinical tests that are being commonly used across Scotland. An investigation of laboratory data structure was conducted using SQL with the assistance of White Rabbit which captures the metadata information from each safe haven. Data heterogeneity or commonalities were investigated in detail in R. We examined the inter-relationships among clinical laboratories from different regions of NHS Scotland. A common data structure was proposed to facilitate the sharing of clinical test results. We investigated multiple existing federation solutions to streamline access to data across the SSHN.
ResultsA dataset of all laboratory tests for patients registered with the Scottish Health Research Register and Biobank (SHARE) from laboratory data sources within the network (Grampian Data Safe Haven, Health Informatics Center, Glasgow Safe Haven & Lothian/DataLoch Safe Haven) were developed. An open-source toolkit that includes SQL scripts to harmonise laboratory data from multiple safe haven and R scripts to conduct heterogeneity investigation to streamline the sharing and the analysis was created. We have shown a working model for federation within Scotland for the first time with the view to expand into more routine projects. The project has developed a systematic concept mapping of data available across the SSHN to aid cohort discovery.
ConclusionsThe exemplar national level laboratory data together with the toolkit will help provide researchers with information such as which data are available to access. It will also support and improve national-level research studies at a faster pace. The work has demonstrated the feasibility of a common process for federated data discovery and sharing across the SSHN.

Scotland has more than five million people within a single health system, using a single central Picture Archiving and Commication System (PACS) for radiography data. This enabled the project team to build a research resource exceeding a petabyte of imaging from 2010 onwards, with open-source tooling to collate and de-identify images on demand. Image metadata, treatment and diagnostic records can be used to define large cohorts of patients then make the data available remotely to researchers in a Trusted Research Environment (TRE).
Original identifiable images are stored in one of three isolated zones with controlled data transfer to protect patient privacy and prevent inadvertent disclosure. Linkage to other records is performed in the second zone on de-identified images using encrypted patient identifiers. Automated screening with optical character recognition and natural language processing was implemented to identify and redact personally identifiable information before release to researchers in the third zone.
A recent extension to this system has provided an ongoing feed of routine imaging, which is securely shared with regional counterparts to ensure the minimal possible additional load is placed on clinical PACS resources and avoid duplicate requests.
The project launched in April 2022 and since then a variety of research projects have already used this environment and data representing millions of pounds of funding, some using large cohorts with historical data up to 14 years old, re-assessing historical scans with the benefit of subsequent diagnosis to investigate possible early warning signs of conditions including dementia and pre-cancerous lung nodules.

IntroductionTrusted research environments (TREs) provide secure access to very sensitive data for research. All TREs operate manual checks on outputs to ensure there is no residual disclosure risk. Machine learning (ML) models require very large amount of data; if this data is personal, the TRE is a well-established data management solution. However, ML models present novel disclosure risks, in both type and scale.
ObjectivesAs part of a series on ML disclosure risk in TREs, this article is intended to introduce TRE managers to the conceptual problems and work being done to address them.
MethodsWe demonstrate how ML models present a qualitatively different type of disclosure risk, compared to traditional statistical outputs. These arise from both the nature and the scale of ML modelling.
ResultsWe show that there are a large number of unresolved issues, although there is progress in many areas. We show where areas of uncertainty remain, as well as remedial responses available to TREs.
ConclusionsAt this stage, disclosure checking of ML models is very much a specialist activity. However, TRE managers need a basic awareness of the potential risk in ML models to enable them to make sensible decisions on using TREs for ML model development.

ObjectiveThe global COVID pandemic has highlighted the need for the reporting of enhanced serology data from laboratory testing data. Qualitative results alone do not provide detailed data to understand levels of SARS-CoV-2 seroprevalence within a populace. To enable this, a minimum data set is required to support standardised data reporting.
ApproachThe CO-CONNECT project is concerned with the response to COVID within the UK and how datasets can be made Findable, Accessible, Interoperable and Reusable (FAIR). One aspect of this is a focus upon improving granular levels of COVID serology testing data being reported by national laboratories to the National Pathology Exchange (NPEx). A study was conducted to ascertain the essential data elements that could formulate a COVID Serology Data Standard (CSDS). Three NHS laboratories acting as pilot studies and NPEx have been actively involved with the development of the CSDS, together with clinicians and academics from the CO-CONNECT project.
ResultsFeedback from clinicians, academics and NPEx has been collected, together with NHS laboratory feasibility analysis to derive a minimum set of data elements that form a proposed data standard to standardise the reporting of laboratory COVID serology data for the UK. The proposed CSDS comprises twelve data elements in total, grouped into four main areas, (1) subject identifier and test date and time, (2) analyser types, test kits and samples, (3) qualitative results and (4) quantitative results. To further support the standardisation effort, a proposed Health Level Seven (HL7) message structure has been created to enable the reporting of the CSDS data elements to NPEx.
ConclusionThe CSDS has been created to help augment levels of reported granular data for laboratory COVID serology testing. If adopted, this could enable healthcare professionals to better understand the calibration of assays across multiple analyser types and thus antibody response levels.

ObjectiveThe HDRUK Phenotype Library (phenotypes.healthdatagateway.org) shares definitions used to measure concepts of interest (such as diagnoses or treatments) within health datasets. It already holds more than 1000 phenotypes, with researchers able to contribute their work via an API. We aimed to create a more user-friendly method of contributing to the Library.
ApproachWe designed a phenotype creation workflow enabling users to create and submit new content via web interface. Goals included clarity and ease of use for a broad range of users.
ResultsA home page shows researchers' own content. Researchers can create new phenotypes using a web form, entering metadata such as name, authors, description, and publications. Code lists are defined via one or more rules, including search terms or referring to another phenotype, or by CSV upload. Users can make their phenotypes accessible to a research group or to all authenticated users, as well as publish content on the web. Publication requests are reviewed to ensure content is complete and appropriate. Editing, with full history and version control, is also supported.
ConclusionsWe implemented and released the new features. We are currently engaging researchers to get feedback and invite content submission.
ImplicationsThe benefit of tools to support research transparency and repeatability is only realized when they are adopted. We hope that a GUI to support phenotype creation will broaden the Library's user base help it serve as an enabler of higher-quality, more efficient research across the worldwide health data research community.

ObjectivesTo assess a range of tools and methods to support Trusted Research Environments (TREs) to assess output from AI methods for potentially identifiable information, investigate the legal and ethical implications and controls, and produce a set of guidelines and recommendations to support all TREs with export controls of AI algorithms.
ApproachTREs provide secure facilities to analyse confidential personal data, with staff checking outputs for disclosure risk before publication. Artificial intelligence (AI) has high potential to improve the linking and analysis of population data, and TREs are well suited to supporting AI modelling. However, TRE governance focuses on classical statistical data analysis. The size and complexity of AI models presents significant challenges for the disclosure-checking process. Models may be susceptible to external hacking: complicated methods to reverse engineer the learning process to find out about the data used for training, with more potential to lead to re-identification than conventional statistical methods.
ResultsGRAIMatter is:

Quantitatively assessing the risk of disclosure from different AI models exploring different models, hyper-parameter settings and training algorithms over common data types
Evaluating a range of tools to determine effectiveness for disclosure control
Assessing the legal and ethical implications of TREs supporting AI development and identifying aspects of existing legal and regulatory frameworks requiring reform.
Running 4 PPIE workshops to understand their priorities and beliefs around safeguarding and securing data
Developing a set of recommendations including

suggested open-source toolsets for TREs to use to measure and reduce disclosure risk
descriptions of the technical and legal controls and policies TREs should implement across the 5 Safes to support AI algorithm disclosure control
training implications for both TRE staff and how they validate researchers



ConclusionGRAIMatter is developing a set of usable recommendations for TREs to use to guard against the additional risks when disclosing trained AI models from TREs.

ObjectivesTo research and develop tools and methods for building cohorts of images linked to longitudinal healthcare records from real-world clinical images from the whole Scottish population. To provide this capability for the Scottish Medical Imaging service (provided by the Scottish National Safe Haven) to support research and AI projects.
ApproachClinical images, especially when linked to routinely collected health data, are extremely useful for many types of research and AI development. However, finding and using clinical images for research data is challenging because:
1) Existing software used to search for images are designed for clinical care rather than research making it easy to find images for a particular patient. They are not designed to search for all images with particular characteristics e.g. slice thickness/scanning protocol/contrast agent/patient medication.
2) Reuse of clinical images for research requires de-identification, yet identifiable data can be present in many areas of the associated image file.
ResultsThe PICTURES (InterdisciPlInary Collaboration for efficienT and effective Use of clinical images in big data health care RESearch) 5-year programme has developed an architecture for building cohorts of images based upon research criteria and providing these in a di-identifiable form within a Safe Haven environment. There are 3 zones:

An identifiable zone which stores the raw image data and a MongoDB database which captures the metadata
A de-identified zone which provides a database and tools for cohort building which do not require imaging data expertise
Several Project Private Zones (PPZs) where researchers can install custom software and access the de-identified images for their project

The architecture supports cohort building based upon features within pixel data, image metadata and linking to longitudinal health care records.
ConclusionPICTURES is currently enhancing the cohort building user interface used by the National Safe Haven and supporting exemplar projects. The SMI service is live and accepting requests for more information. The software is open source and we welcome the use of the platform by other Safe Havens/research groups.

ObjectivesThe Scottish Medical Imaging (SMI) service provides linkable, population based, "research-ready" real-world medical images for researchers to develop or validate AI algorithms within the Scottish National Safe Haven. The PICTURES research programme is developing novel methods to enhance the SMI service offering through research in cybersecurity and software/data/infrastructure engineering.
ApproachAdditional technical and governance controls were required to enable safe access to medical images.
The researcher is isolated from the rest of the trusted research environment (TRE) using a Project Private Zone (PPZ). This enables researchers to build and install their own software stack, and protects the TRE from malicious code.
Guidelines are under development for researchers on the safe development of algorithms and the expected relationship between the size of the model and the training dataset. There is associated work on the statistical disclosure control of models to enable safe release of trained models from the TRE.
ResultsA policy enabling the use of "Non-standard software" based on prior research, domain knowledge and experience gained from two contrasting research studies was developed. Additional clauses have been added to the legal control – the eDRIS User Agreement – signed by each researcher and their Head of Department. Penalties for attempting to import or use malware, remove data within models or any attempt to deceive or circumvent such controls are severe, and apply to both the individual and their institution. The process of building and deploying a PPZ has been developed allowing researchers to install their own software.
No attempt has yet been made to add additional ethical controls; however, a future service development could be validating the performance of researchers' algorithms on our training dataset.
ConclusionThe availability to conduct research using images poses new challenges and risks for those commissioning and operating TREs. The Private Project Zone and our associated governance controls are a huge step towards supporting the needs of researchers in the 21st century.

The prevalence of the coronavirus SARS-CoV-2 disease has resulted in the unprecedented collection of health data to support research. Historically, coordinating the collation of such datasets on a national scale has been challenging to execute for several reasons, including issues with data privacy, the lack of data reporting standards, interoperable technologies, and distribution methods. The coronavirus SARS-CoV-2 disease pandemic has highlighted the importance of collaboration between government bodies, healthcare institutions, academic researchers and commercial companies in overcoming these issues during times of urgency. The National COVID-19 Chest Imaging Database, led by NHSX, British Society of Thoracic Imaging, Royal Surrey NHS Foundation Trust and Faculty, is an example of such a national initiative. Here, we summarise the experiences and challenges of setting up the National COVID-19 Chest Imaging Database, and the implications for future ambitions of national data curation in medical imaging to advance the safe adoption of artificial intelligence in healthcare.

The prevalence of the coronavirus SARS-CoV-2 disease has resulted in the unprecedented collection of health data to support research. Historically, coordinating the collation of such datasets on a national scale has been challenging to execute for several reasons, including issues with data privacy, the lack of data reporting standards, interoperable technologies, and distribution methods. The coronavirus SARS-CoV-2 disease pandemic has highlighted the importance of collaboration between government bodies, healthcare institutions, academic researchers and commercial companies in overcoming these issues during times of urgency. The National COVID-19 Chest Imaging Database, led by NHSX, British Society of Thoracic Imaging, Royal Surrey NHS Foundation Trust and Faculty, is an example of such a national initiative. Here, we summarise the experiences and challenges of setting up the National COVID-19 Chest Imaging Database, and the implications for future ambitions of national data curation in medical imaging to advance the safe adoption of artificial intelligence in healthcare.