Retrospectively assessing evaluation and management of artificial-intelligence detected nodules on uninterpreted chest radiographs in the era of radiologists shortage.

PURPOSE: High volumes of chest radiographs (CXR) remain uninterpreted due to severe shortage of radiologists. These CXRs may be informally reported by non-radiologist physicians, or not reviewed at all. Artificial intelligence (AI) software can aid lung nodule detection. Our aim was to assess evaluation and management by non-radiologists of uninterpreted CXRs with AI detected nodules, compared to retrospective radiology reports. MATERIALS AND METHODS: AI detected nodules on uninterpreted CXRs of adults, performed 30/6/2022-31/1/2023, were evaluated. Excluded were patients with known active malignancy and duplicate CXRs of the same patient. The electronic medical records (EMR) were reviewed, and the clinicians' notes on the CXR and AI detected nodule were documented. Dedicated thoracic radiologists retrospectively interpreted all CXRs, and similarly to the clinicians, they had access to the AI findings, prior imaging and EMR. The radiologists' interpretation served as the ground truth, and determined if the AI-detected nodule was a true lung nodule and if further workup was required. RESULTS: A total of 683 patients met the inclusion criteria. The clinicians commented on 386 (56.5%) CXRs, identified true nodules on 113 CXRs (16.5%), incorrectly mentioned 31 (4.5%) false nodules as real nodules, and did not mention the AI detected nodule on 242 (35%) CXRs, of which 68 (10%) patients were retrospectively referred for further workup by the radiologist. For 297 patients (43.5%) there were no comments regarding the CXR in the EMR. Of these, 77 nodules (11.3%) were retrospectively referred for further workup by the radiologist. CONCLUSION: AI software for lung nodule detection may be insufficient without a formal radiology report, and may lead to over diagnosis or misdiagnosis of nodules.

Restructuring an internal medicine rotation to take on a fully virtual experience in a resource-limited setting: A mixed-methods study.

BACKGROUND: During the coronavirus disease 2019 (COVID-19) pandemic, medical schools in the Philippines accelerated the adoption of virtual learning. Course developers were challenged to provide equal opportunities for clinical exposure given the differential access of students to technology. This study describes the modifications in the course design of an internal medicine rotation for third-year medical students and the perceptions of the faculty and students toward these changes. MATERIALS AND METHODS: Course evaluations by students and faculty were reviewed. Using a concurrent mixed-methods approach, we analyzed the quantitative and qualitative responses and triangulated the results of the faculty and student surveys. RESULTS: Shifting to a virtual learning platform decreased the number of student-patient interactions. Observing a telemedicine consultation done by faculty substituted for real patient encounters. In consideration of students with limited Internet access, synchronous activities were made nongraded. The survey response rate was 51% (93/181) for students and 34% (32/94) for faculty. Survey participants indicated high overall satisfaction toward the virtual course with a general agreement between students and faculty respondents in most domains. Recurrent themes were the demand for more patient encounters, more synchronous activities, and better evaluation tools. Only the faculty were critical of technical issues, such as audibility and Internet connectivity. CONCLUSION: The experiences of a single institution in redesigning and implementing an undergraduate medical course in internal medicine for a fully virtual platform were described. Strategies for augmenting patient exposure and tailored clinical assessment tools are needed to improve stakeholder satisfaction. In resource-limited settings, access to appropriate technology must be considered to ensure equitable learning.