eprintid: 10199444 rev_number: 7 eprint_status: archive userid: 699 dir: disk0/10/19/94/44 datestamp: 2024-11-04 10:41:19 lastmod: 2024-11-04 10:41:19 status_changed: 2024-11-04 10:41:19 type: article metadata_visibility: show sword_depositor: 699 creators_name: Qian, Zhaozhi creators_name: Callender, Thomas creators_name: Cebere, Bogdan creators_name: Janes, Sam M creators_name: Navani, Neal creators_name: van der Schaar, Mihaela title: Synthetic data for privacy-preserving clinical risk prediction ispublished: pub divisions: UCL divisions: B02 divisions: C10 divisions: D17 divisions: K71 keywords: Synthetic data, Machine learning, Risk-prediction, Outcomes research, Translational research note: © The Author(s), 2024. This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/. abstract: Synthetic data promise privacy-preserving data sharing for healthcare research and development. Compared with other privacy-enhancing approaches—such as federated learning—analyses performed on synthetic data can be applied downstream without modification, such that synthetic data can act in place of real data for a wide range of use cases. However, the role that synthetic data might play in all aspects of clinical model development remains unknown. In this work, we used state-of-the-art generators explicitly designed for privacy preservation to create a synthetic version of ever-smokers in the UK Biobank before building prognostic models for lung cancer under several data release assumptions. We demonstrate that synthetic data can be effectively used throughout the medical prognostic modeling pipeline even without eventual access to the real data. Furthermore, we show the implications of different data release approaches on how synthetic biobank data could be deployed within the healthcare system. date: 2024-10-27 date_type: published publisher: Springer Science and Business Media LLC official_url: https://doi.org/10.1038/s41598-024-72894-y oa_status: green full_text_type: pub language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 2332204 doi: 10.1038/s41598-024-72894-y medium: Electronic pii: 10.1038/s41598-024-72894-y lyricists_name: Janes, Samuel lyricists_name: Callender, Thomas lyricists_id: SMJAN15 lyricists_id: TCALL19 actors_name: Callender, Thomas actors_id: TCALL19 actors_role: owner funding_acknowledgements: EICEDAAP\100012 [Cancer Research UK] full_text_status: public publication: Scientific Reports volume: 14 article_number: 25676 event_location: England issn: 2045-2322 citation: Qian, Zhaozhi; Callender, Thomas; Cebere, Bogdan; Janes, Sam M; Navani, Neal; van der Schaar, Mihaela; (2024) Synthetic data for privacy-preserving clinical risk prediction. Scientific Reports , 14 , Article 25676. 10.1038/s41598-024-72894-y <https://doi.org/10.1038/s41598-024-72894-y>. Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/10199444/1/s41598-024-72894-y.pdf