EUVIMEDEUVIMED entdecken
StudienprotokollOpen Access · CC BY-NC 4.0

AI-assisted detection for chest X-rays (AID-CXR): a multi-reader multi-case study protocol

Farhaan Khan iD, Indrajeet Das, Marusa Kotnik, Louise Wing, Edwin Van Beek, John Murchison, Jong Seok Ahn, Sang Hyup Lee, Ambika Seth, Abdala Trinidad Espinosa Morgado iD, Howell Fu iD, Alex Novak iD und 5 weitere

BMJ Open · 2024-12 · 14 (12) · e080554

DOI: 10.1136/bmjopen-2023-080554 ↗

Kurz gefasst

Studienprotokoll in der Zeitschrift BMJ Open, online erschienen am 20.12.2024. Verfasst von Farhaan Khan und 16 weiteren Autor:innen. Beteiligte Einrichtung: Oxford University Hospitals NHS Foundation Trust, Oxford, UK farhaan.a.khan@outlook.com. Hauptthemen laut MEDLINE: Artificial Intelligence, Lung Diseases, Radiographic Image Interpretation, Computer-Assisted, Radiography, Thoracic. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 11 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Lunit.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

A chest X-ray (CXR) is the most common imaging investigation performed worldwide. Advances in machine learning and computer vision technologies have led to the development of several artificial intelligence (AI) tools to detect abnormalities on CXRs, which may expand diagnostic support to a wider field of health professionals. There is a paucity of evidence on the impact of AI algorithms in assisting healthcare professionals (other than radiologists) who regularly review CXR images in their daily practice.

Aims

To assess the utility of an AI-based CXR interpretation tool in assisting the diagnostic accuracy, speed and confidence of a varied group of healthcare professionals. Methods and analysis The study will be conducted using 500 retrospectively collected inpatient and emergency department CXRs from two UK hospital trusts. Two fellowship-trained thoracic radiologists with at least 5 years of experience will independently review all studies to establish the ground truth reference standard with arbitration from a third senior radiologist in case of disagreement. The Lunit INSIGHT CXR tool (Seoul, Republic of Korea) will be applied and compared against the reference standard. Area under the receiver operating characteristic curve (AUROC) will be calculated for 10 abnormal findings: pulmonary nodules/mass, consolidation, pneumothorax, atelectasis, calcification, cardiomegaly, fibrosis, mediastinal widening, pleural effusion and pneumoperitoneum. Performance testing will be carried out with readers from various clinical professional groups with and without the assistance of Lunit INSIGHT CXR to evaluate the utility of the algorithm in improving reader accuracy (sensitivity, specificity, AUROC), confidence and speed (paired sample t-test). The study is currently ongoing with a planned end date of 31 December 2024. Ethics and dissemination The study has been approved by the UK Healthcare Research Authority. The use of anonymised retrospective CXRs has been authorised by Oxford University Hospital’s information governance teams. The results will be presented at relevant conferences and published in a peer-reviewed journal. Trial registration number Protocol ID 310995-B (awaiting approval), ClinicalTrials.gov

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligenceLung DiseasesRadiographic Image Interpretation, Computer-AssistedRadiography, ThoracicHumansAlgorithmsResearch DesignRetrospective StudiesROC CurveMulticenter Studies as TopicRandomized Controlled Trials as Topic

Stichwörter der Autor:innen

Chest imagingDiagnostic ImagingRESPIRATORY MEDICINE (see Thoracic Medicine)

Autor:innen und Institutionen

  • Oxford University Hospitals NHS Foundation Trust, Oxford, UK farhaan.a.khan@outlook.com.
  • University Hospitals of Leicester NHS Trust, Leicester, UK.
  • Addenbrooke's Hospital, Cambridge, UK.
  • Oxford University Hospitals NHS Foundation Trust, Oxford, UK.
  • Edinburgh Imaging, Queen's Medical Research Institute, University of Edinburgh, Edinburgh, UK.
  • Royal Infirmary of Edinburgh, Edinburgh, UK.

ORCID-Profile: Farhaan Khan, Abdala Trinidad Espinosa Morgado, Howell Fu, Alex Novak, Sarim Ather

Förderung

  • Lunit

Zitieren

APA

Khan, F., Das, I., Kotnik, M., Wing, L., Van Beek, E., Murchison, J., Ahn, J. S., Lee, S. H., Seth, A., Espinosa Morgado, A. T., Fu, H., Novak, A., Salik, N., Campbell, A., Shah, R., Gleeson, F., & Ather, S. (2024). AI-assisted detection for chest X-rays (AID-CXR): a multi-reader multi-case study protocol. BMJ Open, 14(12), e080554. https://doi.org/10.1136/bmjopen-2023-080554

Vancouver

Khan F, Das I, Kotnik M, Wing L, Van Beek E, Murchison J, et al. AI-assisted detection for chest X-rays (AID-CXR): a multi-reader multi-case study protocol. BMJ Open. 2024;14(12):e080554. doi:10.1136/bmjopen-2023-080554

BibTeX
@article{Khan2024,
  author = {Khan, Farhaan and Das, Indrajeet and Kotnik, Marusa and Wing, Louise and Van Beek, Edwin and Murchison, John and Ahn, Jong Seok and Lee, Sang Hyup and Seth, Ambika and Espinosa Morgado, Abdala Trinidad and Fu, Howell and Novak, Alex and Salik, Nabeeha and Campbell, Alan and Shah, Ruchir and Gleeson, Fergus and Ather, Sarim},
  title = {AI-assisted detection for chest X-rays (AID-CXR): a multi-reader multi-case study protocol},
  journal = {BMJ Open},
  year = {2024},
  volume = {14},
  number = {12},
  pages = {e080554},
  doi = {10.1136/bmjopen-2023-080554}
}
Kostenlos starten →