AI is increasingly being integrated into the clinical setting, with impressive accuracies noted across many modalities, including plain radiography. Chest x-rays are a commonly conducted, first line investigation in patients presenting with symptoms which may indicate cancer (and/or other conditions), however, 90% of undetected lung cancers are missed by clinicians on initial chest x-rays, meaning that these patients may not be sent for further investigation and/or treatment.
AI has been proposed as a way to increase accuracy and decrease error, whilst allowing for time efficiencies for clinicians. No study has determined the use of AI for detection of additional (incidental findings) on any imaging modality. This study aims to discover if AI applied to a retrospective sample of images will detect additional findings, not reported at the time of the initial radiological report. Patient and clinician perspectives of the use of the technology for this purpose will be investigated. Clinical outcome of the patients/service users will be investigated and the relevance of any additional findings on eventual diagnoses and/or clinical outcome will be determined.
Aim: to determine if a commercially available AI model, trained to provide diagnosis on plain chest radiographs, can detect additional pathology not detected at initial report and determine the potential clinical impact of any additional findings.
To gain public/service user and clinician perception on the detection of incidental findings from imaging studies
To determine if a CE approved AI model can detect additional findings on chest radiographs, not detected at initial report.
To investigate the prevalence and nature of any additional findings and their clinical relevance
To follow to patient journey to determine their health outcomes