PRJ4201- Department for Science, Innovation & Technology (DSIT). Requirement for a skilled digital team to create privacy-preserving, cross-border data sharing technology/platform between UK and US medical researchers.

Description

Summary of work Effective research into rare paediatric cancers is currently limited by the scarcity of data available to researchers. This pilot aims to develop a single, proof-of-concept solution to enable cross-border data collaboration on rare paediatric cancer datasets between a US and UK medical data partner. It builds on previous work carried out under the UK-US Privacy Enhancing Technologies (PETs) Prize Challenges, but aims to apply techniques demonstrated in that project to an example with real data, and demonstrate data protection compliance to data owners and regulators. Where the supplied staff will work No specific location (for example they can work remotely) Who the organisation using the products or services is Department for Science, Innovation & Technology (DSIT) Why the work is being done Effective research into rare paediatric cancers is currently limited by the scarcity of data available to researchers. This pilot aims to develop a single, proof-of-concept solution to enable cross-border data collaboration on rare paediatric cancer datasets between a US and UK medical data partner. It builds on previous work carried out under the UK-US Privacy Enhancing Technologies (PETs) Prize Challenges, but aims to apply techniques demonstrated in that project to an example with real data, and demonstrate data protection compliance to data owners and regulators. The business problem Sharing health-related data across borders is technically and legally challenging. Privacy Enhancing Technologies (PETs) could provide an effective solution, enabling researchers to securely access a larger pool of relevant data, whilst protecting patient privacy and mitigating the associated legal and ethical risks. Federated learning has been identified as a particularly useful PET for this pilot. Federated learning enables cross-border collaboration by allowing researchers to train machine learning models on locally hosted data while only sharing model parameters, ensuring compliance with privacy regulations like UK GDPR and US HIPAA. This preserves data sovereignty and privacy, as sensitive data remains within its jurisdiction, addressing the legal and ethical challenges of international data sharing. This project aims to demonstrate the effectiveness of PETs in protecting patient privacy while allowing medical researchers to gain access to a larger pool of data to enhance their work. This pilot will provide a proof of concept to regulators and data owners, showing that privacy and research functionality can coexist under strict regulatory frameworks. The people who will use the product or service User type: The primary users are medical researchers employed by the medical research organisations we are partnering with in the US and UK respectively Definition: These researchers require secure, privacy-preserving access to paediatric cancer data from both regions to carry out meaningful medical analyses and contribute to cross-border insights. To accomplish this, the platform will provide secure data access through a federated learning model. Researchers will be able to run queries and analyses on the data stored within their respective jurisdictions, using advanced PETs to ensure compliance with both UK GDPR and US HIPAA regulations. The system will be low-tech, requiring minimal training for the medical research teams, and designed for flexibility to accommodate future expansions. Which phase the project is in Not applicable Existing team • DSIT function: ~FTE 2 • Medical data/research partners function: resource is variable but expert collaborators (~10-20) from a prominent US and UK cancer research group. Additional ad-hoc support from tech teams at medical partners also available. Address where the work will be done We will consider collaborating in or around any UK-based location. Our headquarters are at 100 Parliament Street, SW1A 2BQ, London. Working arrangements The PETs operates in our London address on a hybrid basis: Monday to Friday based in our offices in central London starting work by 9.30am, 7.5 hours per day + lunch time. There is no explicit requirement to work from 100 Parliament Street for this contract. Security and vetting requirements Baseline Personnel Security Standard (BPSS) More information about the Security requirements: BPSS as a minimum Latest start date 11 November 2024 Expected contract length Contract length: 0 years 6 months 0 days Budget Indicative maximum: £210000 Indicative minimum: £195000 Contracted out service or supply of resource? Contracted out service: the off-payroll rules do not apply