A pipeline to further enhance quality, integrity and reusability of the NCCID clinical data

Sci Data. 2023 Jul 27;10(1):493. doi: 10.1038/s41597-023-02340-7.

Authors

Anna Breger^#^{1

2}, Ian Selby^#^{3

4}, Michael Roberts^{5

6}, Judith Babar^{7

8}, Effrossyni Gkrania-Klotsas^{8

9}, Jacobus Preller^{8

9}, Lorena Escudero Sánchez^{7

10}; AIX-COVNET Collaboration; James H F Rudd⁶, John A D Aston¹¹, Jonathan R Weir-McCall^{7

8

12}, Evis Sala^{13

14}, Carola-Bibiane Schönlieb⁵

Collaborators

AIX-COVNET Collaboration:
Sören Dittmer, Matthew Thorpe, Julian Gilbey, Anna Korhonen, Emily Jefferson, Georg Langs, Guang Yang, Xiaodan Xing, Yang Nan, Ming Li, Helmut Prosch, Jan Stanczuk, Jing Tang, Philip Teare, Mishal Patel, Marcel Wassink, Markus Holzer, Eduardo González Solares, Nicholas Walton, Pietro Liò, Tolou Shadbahr

Affiliations

¹ Department of Applied Mathematics and Theoretical Physics, University of Cambridge, Cambridge, UK. ab2864@cam.ac.uk.
² Center of Medical Physics and Biomedical Engineering, Medical University of Vienna, Vienna, Austria. ab2864@cam.ac.uk.
³ Department of Radiology, University of Cambridge, Cambridge, UK. ias49@cam.ac.uk.
⁴ Cambridge University Hospitals NHS Trust, Cambridge, UK. ias49@cam.ac.uk.
⁵ Department of Applied Mathematics and Theoretical Physics, University of Cambridge, Cambridge, UK.
⁶ Department of Medicine, University of Cambridge, Cambridge, UK.
⁷ Department of Radiology, University of Cambridge, Cambridge, UK.
⁸ Cambridge University Hospitals NHS Trust, Cambridge, UK.
⁹ School of Clinical Medicine, University of Cambridge, Cambridge, UK.
¹⁰ Cancer Research UK (CRUK) Cambridge Centre, Cambridge, UK.
¹¹ Department of Pure Mathematics and Mathematical Statistics, University of Cambridge, Cambridge, UK.
¹² Department of Radiology, Royal Papworth Hospital, Cambridge, UK.
¹³ Advanced Radiodiagnostics Centre, Fondazione Policlinico Universitario Agostino Gemelli, Rome, Italy.
¹⁴ Università Cattolica del Sacro Cuore, Rome, Italy.

^# Contributed equally.

Abstract

The National COVID-19 Chest Imaging Database (NCCID) is a centralized UK database of thoracic imaging and corresponding clinical data. It is made available by the National Health Service Artificial Intelligence (NHS AI) Lab to support the development of machine learning tools focused on Coronavirus Disease 2019 (COVID-19). A bespoke cleaning pipeline for NCCID, developed by the NHSx, was introduced in 2021. We present an extension to the original cleaning pipeline for the clinical data of the database. It has been adjusted to correct additional systematic inconsistencies in the raw data such as patient sex, oxygen levels and date values. The most important changes will be discussed in this paper, whilst the code and further explanations are made publicly available on GitLab. The suggested cleaning will allow global users to work with more consistent data for the development of machine learning tools without being an expert. In addition, it highlights some of the challenges when working with clinical multi-center data and includes recommendations for similar future initiatives.

Publication types

Dataset
Research Support, Non-U.S. Gov't

MeSH terms

Artificial Intelligence
COVID-19*
Humans
Machine Learning
Radiography, Thoracic
State Medicine
Thorax* / diagnostic imaging

Grants and funding

WT_/Wellcome Trust/United Kingdom