Journal of the American College of Radiology : JACR最新文献

Purpose: To identify the published standards for the classification and communication of critical actionable findings in emergency radiology, and the associated facilitators and barriers to communication and message management/dissemination of such findings.

Materials and methods: Search terms for resources pertaining to critical findings (CFs) in emergency radiology were applied to 2 databases (PubMed, Embase). Screening of hits using the following pre-established inclusion and exclusion criteria were performed by 3 analysts with subsequent consensus discussion for discrepancies: 1) The resources include any standards for the classification and/or communication of imaging findings as critical OR 2) The resource discusses any facilitators to the communication of CFs OR 3) The resource discusses any barriers to the communication of CFs. Resources with explicit focus on a pediatric population or predominant focus on artificial intelligence/natural language processing were omitted. Accompanying gray literature search was used to expand included resources. Data extraction included: year, country, resource type, scope/purpose, participants, context, standards to identifying/communicating CFs, facilitators/barriers, method type, recommendations, applicability, and disclosures.

Results: Seventy-six resources were included in the final analysis, including 16 societal/commission guidelines. Among the guidelines, no standardized list of CFs was identified, with typical recommendations suggesting application of a local policy. Communication standards included direct closed-loop communication for high acuity findings, with more flexible communication channels for less acute findings. Applied interventions for CFs management, most frequently fell into 4 categories: electronic (n=10), hybrid i.e., electronic/administrative (n = 3), feedback/education (n=5), and administrative (n=4).

Conclusion: There are published standards, policies and interventions for the management of CFs in emergency radiology. 3-tier stratification (e.g. critical/urgent/incidental) based on time-sensitivity and severity is most common with most critical findings necessitating closed-loop communication. Awareness of systemic facilitators and barriers should inform local policy development. Electronic and administrative communication pathways are useful adjuncts. Further research should offer comparative analyses of different CF interventions with regards to cost-effectiveness, notification time, and user feedback.

Objective: This study explores radiology program directors' perspectives on the impact of large language model (LLM) use among residency applicants to craft personal statements.

Methods: Eight program directors from the Radiology Residency Education Research Alliance (RRERA) participated in a mixed-methods study, which included a survey regarding impressions of AI-generated personal statements and focus group discussions (July 2023). Each director reviewed four personal statement variations for five applicants, blinded to author type: the original and three ChatGPT-4.0 versions generated with varying prompts, aggregated for analysis. A 5-point Likert scale surveyed the writing quality, including voice, clarity, engagement, organization, and the perceived origin of each statement. An experienced qualitative researcher facilitated focus group discussions. Data analysis was performed using a rapid analytic approach with a coding template capturing key areas related to residency applications.

Results: GPT-generated statement (GPT) ratings were more often average or worse in quality (56%, 268/475) than ratings of human-authored statements (Hu) (29% [45/160]). Although reviewers were not confident in their ability to distinguish the origin of personal statements, they did so reliably and consistently, identifying the human-authored personal statements at 95% (38/40) as probably or definitely original. Focus group discussions highlighted the inevitable use of AI in crafting personal statements and concerns about its impact on the authenticity and the value of the personal statement in residency selections. Program directors were divided on the appropriate use and regulation of AI.

Discussion: Radiology residency program directors rated LLM-generated personal statements as lower in quality and expressed concern about the loss of the applicant's voice but acknowledged the inevitability of increased AI use in the generation of application statements.

Purpose: To assess the ability of the Annalise Enterprise CXR Triage Trauma artificial intelligence model to identify vertebral compression fractures on chest radiographs and its potential to address undiagnosed osteoporosis and its treatment.

Materials and methods: This retrospective study used a consecutive cohort of 596 chest radiographs from four U.S. hospitals between 2015 and 2021. Each radiograph included both frontal (anteroposterior or posteroanterior) and lateral projections. These radiographs were assessed for the presence of vertebral compression fracture in a consensus manner by up to three thoracic radiologists. The model then performed inference on the cases. A chart review was also performed for the presence of osteoporosis-related ICD-10 diagnostic codes and medication use for the study period and an additional year of follow up.

Results: The model successfully completed inference on 595 cases (99.8%); these cases included 272 positive cases and 323 negative cases. The model performed with area under the receiver operating characteristic curve of 0.955 (95% CI: 0.939 to 0.968), sensitivity 89.3% (95% CI: 85.7 to 92.7%) and specificity 89.2% (95% CI: 85.4 to 92.3%). Out of the 236 true-positive cases (i.e., correctly identified vertebral compression fractures by the model) with available chart information, only 86 (36.4%) had a diagnosis of vertebral compression fracture and 140 (59.3%) had a diagnosis of either osteoporosis or osteopenia; only 78 (33.1%) were receiving a disease modifying medication for osteoporosis.

Conclusion: The model identified vertebral compression fracture accurately with a sensitivity 89.3% (95% CI: 85.7 to 92.7%) and specificity of 89.2% (95% CI: 85.4 to 92.3%). Its automated use could help identify patients who have undiagnosed osteoporosis and who may benefit from taking disease modifying medications.