Three layers and two revelations: a multidisciplinary framework for curating real-world data from electronic patient records reveals a decade of breast screening performance
British Journal of Radiology · 2026
DOI: 10.1093/bjr/tqag226 ↗Kurz gefasst
Fachartikel in der Zeitschrift British Journal of Radiology, 2026. Verfasst von Richard Sidebottom und 14 weiteren Autor:innen. Beteiligte Einrichtung: Radiology, AI Imaging Hub, The Royal Marsden, Sutton, Surrey SM2 5PT, United Kingdom. Hauptthemen laut MEDLINE: Electronic Health Records, Breast Neoplasms, Mammography, Early Detection of Cancer. Die Arbeit nennt 9 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Institute for Health Research, Biomedical Research Center at the Royal Marsden NHS Foundation Trust and the Institute of Cancer Research, NIHR or the Department of Health and Social Care.
Abstract (Originalsprache)
Objectives
To develop and validate a scalable, semi-automated framework for extracting high-granularity research data from legacy electronic patient records (EPR), using a decade of family history breast screening as the exemplar.
Methods
Our multidisciplinary team developed a 3-layer architecture distinguishing raw EPR data, a context layer holding a structured patient journey, and analysis-ready output variables. The context layer was implemented in structured query language (SQL) with explicit rules for cohort identification, exclusions, imaging-event linkage, and outcome derivation. Validation comprised a cohort inclusion audit and an independent patient-journey audit of 904 attendances.
Results
The framework distilled 1 276 903 events in 7781 women into a final cohort of 5392 women comprising 26 483 screening attendances between 2010 and 2019. The inclusion audit found no missed cases. The journey audit returned 7 errors (0.77%); 4 shared a systematic pattern of clinical recall with normal mammographic coding. Encoding this pattern as an additional SQL rule flagged 82 additional recalls and reduced the effective error rate to 0.33%. Screening performance (cancer detection rate 0.5%, recall rate 4.1%) reproduced the FH01 benchmark.
Conclusion
Our 3-layer framework combining programmatic extraction with iterative clinician validation, and limited manual curation transformed inaccessible real-world EPR data into an audit-ready research dataset at scale. Advances in knowledge Our study provides a practical approach to overcome the technical barriers and utilize EPR data at a scale not feasible manually. It demonstrates that semi-automated curation can benchmark clinical performance and validate new technologies like DBT in real-world settings where prospective data collection is absent.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Radiology, AI Imaging Hub, The Royal Marsden, Sutton, Surrey SM2 5PT, United Kingdom.
- Radiology, The Royal Marsden, Sutton, Surrey SM2 5PT, United Kingdom.
- Performance and Information, The Royal Marsden, Sutton, Surrey SM2 5PT, United Kingdom.
- Research and Development, The Royal Marsden, Sutton, Surrey SM2 5PT, United Kingdom.
- Breast Unit, The Royal Marsden, Sutton, Surrey SM2 5PT, United Kingdom.
- Velindre Cancer Centre, Wales CF14 2TL, United Kingdom.
ORCID-Profile: Richard Sidebottom, Emily Greenlay, Christina Messiou
Förderung
- National Institute for Health Research
- Biomedical Research Center at the Royal Marsden NHS Foundation Trust and the Institute of Cancer Research
- NIHR or the Department of Health and Social Care
- Biomedical Research Center
- Royal Marsden NHS Foundation Trust and the Institute of Cancer Research
- Royal Marsden Cancer Charity
- NIHR
- Department of Health and Social Care
Zitieren
APA
Sidebottom, R., Webb, D., Campbell, D., Satchwell, L., Greenlay, E., England, S., Gagliardi, T., Allen, S., Bhaludin, B., Pope, R., Elwood, E., Scudder, J., Sinett, V., Messiou, C., & Koh, D. M. (2026). Three layers and two revelations: a multidisciplinary framework for curating real-world data from electronic patient records reveals a decade of breast screening performance. British Journal of Radiology. https://doi.org/10.1093/bjr/tqag226
Vancouver
Sidebottom R, Webb D, Campbell D, Satchwell L, Greenlay E, England S, et al. Three layers and two revelations: a multidisciplinary framework for curating real-world data from electronic patient records reveals a decade of breast screening performance. British Journal of Radiology. 2026. doi:10.1093/bjr/tqag226
BibTeX
@article{Sidebottom2026,
author = {Sidebottom, Richard and Webb, Donna and Campbell, Des and Satchwell, Laura and Greenlay, Emily and England, Suzanne and Gagliardi, Tanja and Allen, Steve and Bhaludin, Basrull and Pope, Romney and Elwood, Elliot and Scudder, Julie and Sinett, Victoria and Messiou, Christina and Koh, Dow-Mu},
title = {Three layers and two revelations: a multidisciplinary framework for curating real-world data from electronic patient records reveals a decade of breast screening performance},
journal = {British Journal of Radiology},
year = {2026},
doi = {10.1093/bjr/tqag226}
}
EUVIMED