Interventional Radiology Peer Learning Platform and Adverse Event Reporting (IR-PEER): Initial Experience Implementing a Team-based Novel Peer Learning System in Interventional Radiology.

Although the transition from peer review to peer learning has had favorable outcomes in diagnostic radiology, experience with implementing a team-based peer review system in interventional radiology (IR) remains limited. Peer learning systems benefit diverse IR teams composed of multiple clinical roles and could contribute value in archiving events that have potential educational value. With multiple stakeholder input from clinical roles within the IR division at our institution (ie, radiologic technologists, nurses, advanced practice providers, residents, fellows, and attending physicians), we launched a HIPAA-compliant secure IR complication and learning opportunity reporting platform in April 2022. Case submissions were monitored over the subsequent 24 weeks, with monthly dashboard reports provided to departmental leadership. Preintervention and postintervention surveys were used to assess the impact of the peer learning platform and adverse event reporting in IR (IR-PEER) on perceptions of complication reporting in the IR division across clinical roles. Ninety-two peer learning submissions were collected for a weekly average ± standard error of 3.8 ± 0.6 submissions per week, and an additional 26 submissions were collected as part of the division's ongoing monthly complication review conference, for a total of 98 unique total case references. A total of 64.1% of submissions (59 of 92) involved a complication and/or adverse event, and 35.9% of submissions (33 of 92) identified a learning opportunity (no complication or adverse event). Nurses reported that IR-PEER made the complication-reporting process easier (P = .01), and all clinical roles reported that IR-PEER improved the overall process of complication reporting. Peer learning frameworks such as IR-PEER provide a more equitable communication platform for multidisciplinary teams to capture and archive learning opportunities that support quality and safety improvement efforts.

The Role of Artificial Intelligence in the Detection and Implementation of Biomarkers for Hepatocellular Carcinoma: Outlook and Opportunities.

Liver cancer is a leading cause of cancer-related death worldwide, and its early detection and treatment are crucial for improving morbidity and mortality. Biomarkers have the potential to facilitate the early diagnosis and management of liver cancer, but identifying and implementing effective biomarkers remains a major challenge. In recent years, artificial intelligence has emerged as a promising tool in the cancer sphere, and recent literature suggests that it is very promising in facilitating biomarker use in liver cancer. This review provides an overview of the status of AI-based biomarker research in liver cancer, with a focus on the detection and implementation of biomarkers for risk prediction, diagnosis, staging, prognostication, prediction of treatment response, and recurrence of liver cancers.