Khan Farhaan, Das Indrajeet, Kotnik Marusa, Wing Louise, Van Beek Edwin, Murchison John, Ahn Jong Seok, Lee Sang Hyup, Seth Ambika, Espinosa Morgado Abdala Trinidad, Fu Howell, Novak Alex, Salik Nabeeha, Campbell Alan, Shah Ruchir, Gleeson Fergus, Ather Sarim
Oxford University Hospitals NHS Foundation Trust, Oxford, UK
University Hospitals of Leicester NHS Trust, Leicester, UK.
BMJ Open. 2024 Dec 20;14(12):e080554. doi: 10.1136/bmjopen-2023-080554.
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.
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.
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.
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.
Protocol ID 310995-B (awaiting approval), ClinicalTrials.gov.
胸部X光（CXR）是全球范围内最常用的影像学检查方法。机器学习和计算机视觉技术的进步促使了多种人工智能（AI）工具的开发，用于检测CXR上的异常情况，这可能会将诊断支持扩展到更广泛的卫生专业人员领域。关于AI算法对日常工作中定期审查CXR图像的卫生专业人员（放射科医生除外）的影响，证据较少。
评估基于AI的CXR解读工具对不同卫生专业人员诊断准确性、速度和信心的辅助作用。
本研究将使用从英国两家医院信托机构回顾性收集的500份住院患者和急诊科CXR。两名经过 fellowship 培训、经验至少5年的胸科放射科医生将独立审查所有研究，以确立基本事实参考标准，如有分歧将由第三位资深放射科医生进行仲裁。将应用Lunit INSIGHT CXR工具（韩国首尔）并与参考标准进行比较。将针对10种异常发现计算受试者操作特征曲线下面积（AUROC）：肺结节/肿块、实变、气胸、肺不张、钙化、心脏扩大、纤维化、纵隔增宽、胸腔积液和气腹。将在有和没有Lunit INSIGHT CXR辅助的情况下，对来自不同临床专业组的读者进行性能测试，以评估该算法在提高读者准确性（敏感性、特异性、AUROC）、信心和速度（配对样本t检验）方面的效用。该研究目前正在进行，计划结束日期为2024年12月31日。
该研究已获得英国医疗保健研究管理局的批准。牛津大学医院的信息治理团队已授权使用匿名回顾性CXR。研究结果将在相关会议上展示，并发表在同行评审期刊上。
方案ID 310995 - B（待批准），ClinicalTrials.gov。
