TY - JOUR
T1 - AI-assisted detection for chest X-rays (AID-CXR)
T2 - a multi-reader multi-case study protocol
AU - Khan, Farhaan
AU - Das, Indrajeet
AU - Kotnik, Marusa
AU - Wing, Louise
AU - Van Beek, Edwin
AU - Murchison, John
AU - Ahn, Jong Seok
AU - Lee, Sang Hyup
AU - Seth, Ambika
AU - Espinosa Morgado, Abdala Trinidad
AU - Fu, Howell
AU - Novak, Alex
AU - Salik, Nabeeha
AU - Campbell, Alan
AU - Shah, Ruchir
AU - Gleeson, Fergus
AU - Ather, Sarim
N1 - © Author(s) (or their employer(s)) 2024. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ.
PY - 2024/12/20
Y1 - 2024/12/20
N2 - 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.
AB - 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.
KW - Humans
KW - Artificial Intelligence
KW - Radiography, Thoracic/methods
KW - Retrospective Studies
KW - Algorithms
KW - ROC Curve
KW - Research Design
KW - Radiologists
KW - United Kingdom
KW - Lung Diseases/diagnostic imaging
U2 - 10.1136/bmjopen-2023-080554
DO - 10.1136/bmjopen-2023-080554
M3 - Article
C2 - 39806695
SN - 2044-6055
VL - 14
JO - BMJ Open
JF - BMJ Open
IS - 12
M1 - e080554
ER -