21 February 2022 in Journal of Medical Imaging and Radiation Oncology
Introduction: Incorporating artificial intelligence (AI) in diagnostic medical imaging reports has the potential to improve efficiency. Although perception of radiologists, radiographers, medical students and patients on AI use in image reporting has been explored, there is limited literature on non‐radiologist clinicians' opinion on this topic.Method: Single‐centre online survey targeting non‐radiologist medical staff conducted from May to August 2021 at a tertiary referral hospital in Melbourne, Australia. Survey questions revolved around clinicians' level of comfort acting on AI‐generated reports with varying levels of radiologist involvement and scan complexity, opinion on medicolegal responsibility for erroneous AI‐issued reports and perception of data privacy and security.Results: Eighty‐eight responses were collected, including 47.9% of consultants. Non‐radiologist clinicians across all seniorities and specialties felt significantly less comfortable acting on AI‐issued reports compared with radiologist‐issued reports (mean comfort radiologist 6.44/7, mean comfort AI 3.35/7, P < 0.001) but felt equally comfortable with an AI‐hybrid model of care (mean comfort hybrid 6.38/7, P = 0.676). Non‐radiologist clinicians believed that medicolegal responsibility with errors in AI‐issued reports mostly lay with hospitals or health service providers (65.9%) and radiologists (54.5%). Regarding data privacy and security, non‐radiologist clinicians felt significantly less comfortable with AI issuing image reports instead of radiologists (P < 0.001).Conclusion: A hybrid AI‐generated radiologist‐confirmed method of image reporting may be the ideal way of integrating AI into clinical practice based on the perception of our referring non‐radiologist medical colleagues. Formal guidelines on medicolegal responsibility and data privacy should be established prior to utilising AI in the clinical setting.
3 August 2021 in Journal of Medical Radiation Sciences
Introduction: Peripherally inserted central catheters (PICCs) offer a convenient long‐term intravenous access option. Different methods exist for insertion including the use of continuous fluoroscopy for guidance, or bedside insertion techniques. The blind pushing technique is a bedside approach which involves advancing a PICC through the access sheath without imaging guidance, before taking a mobile chest radiograph to confirm tip position. Obtaining optimal position is a critical aim of PICC placement as malpositioned lines have been associated with higher complications including death. We aimed to assess the accuracy of PICC placement by comparing the tip position and complications for lines placed under fluoroscopic guidance to those placed without fluoroscopic guidance.Methods: The Radiology Information System was used to identify 100 continuous PICC insertions in each group (fluoroscopic and blind pushing) between 1 January and 12 May 2019. Patients were excluded if there was a known history of central venous occlusion/stenosis.Results: In the fluoroscopic‐guided group, 0% of the lines were malpositioned compared with 60% of the lines placed using the blind pushing technique, P < 0.001.Fluoroscopic‐guided PICC insertions were in place for a total of 2446 days and demonstrated 6 complications (2.45 complications per 1000 catheter days). This compared with blind pushing technique PICC insertions which were in place for a total of 1521 days and demonstrated 18 complications (11.83 complications per 1000 catheter days), P = 0.004.Conclusion: The use of fluoroscopy for PICC placement leads to significant improvements in tip accuracy than for PICCs placed using the blind pushing technique. While the use of these imaging resources incurs cost and time, these factors should be balanced in order to offer patients the safest and most accurate method of line insertion.
20 March 2020 in Journal of Medical Imaging and Radiation Oncology
27 April 2022 in Journal of Vascular and Interventional Radiology