Canonical text (the exact bytes fingerprinted)

TRUVACE RECORD VERSION
record: TRV-2026-1007
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-09-07T06:07:09.744773Z
status: published
lens: trace
sector: education
headline: Hands-on Artificial Intelligence Education for Radiology Residents: A Three-year Feasibility and Curriculum Implementation Study
dek: Rationale and objectives Artificial intelligence (AI) has rapidly transformed radiology practice, yet structured and practical AI education remains inconsistently integrated into radiology residency training. We developed and implemented a hands-on AI curriculum designed to integrate core computational principles with clinically relevant imaging applications. This study describes the curriculum design and evaluates its feasibility, reproducibility, and preliminary educational outcomes over three consecutive year…
gain_title: An 8-hour hands-on AI rotation delivered to 27 radiology residents over three years was completed by all participants with consistent structure, yielding approximate 80-90% post-training quiz performance and favorable ratings for overall value.
problem_title: Learner survey showed mixed perceptions with half of respondents reporting technical complexity did not match their training level, prompting requests for a more introductory primer and greater clinical emphasis.
trace_subject: 8-hour hands-on AI curriculum for diagnostic radiology residents at a single academic institution
gain_reading: An 8-hour hands-on AI rotation delivered to 27 radiology residents over three years was completed by all participants with consistent structure, yielding approximate 80-90% post-training quiz performance and favorable ratings for overall value.
gain_evidence: A structured, hands-on AI curriculum integrated into residency training is feasible and sustainable across independent cohorts | all residents completed the rotation and post-rotation assessment, and curricular structure and duration remained consistent across cohorts, supporting feasibility and reproducibility | Estimated aggregate post-training assessment performance was approximately 80-90% correct responses
problem_reading: Learner survey showed mixed perceptions with half of respondents reporting technical complexity did not match their training level, prompting requests for a more introductory primer and greater clinical emphasis.
problem_evidence: 50% of respondents disagreed that complexity matched their training level | Free-text feedback consistently recommended a more introductory primer for learners without prior AI/coding exposure and greater emphasis on clinical application
quick_read: Between 2023 and 2025, educators at a single academic institution integrated an 8-hour interactive AI rotation into diagnostic radiology residency, combining didactics with lab modules on convolution, radiomics, machine learning, deep learning, evaluation, bias, and clinical cases for 27 residents across three cohorts.

The study matters because it provides early feasibility evidence for practical AI training in a clinical specialty, but by September 2026 the evidence remains limited to one site, approximate retrospective quiz estimates without archived individual scores, and a 16-of-27 survey response showing split views on technical complexity, leaving scalability and validated competency gains uncertain.
limitation: Single-institution design with small cohorts, retrospective approximate performance estimate without centrally archived individual scores, and survey response from only 16 of 27 residents limits generalizability; authors note need for multi-institutional prospective validation.
tag: Dual reading
key_points: 8-hour interactive rotation implemented 2023-2025 at a single academic institution covering convolution, radiomics, machine learning, deep learning, model evaluation, bias, and case-based applications. | Total N=27 across cohorts of 9, 8, and 10 residents; evaluation used post-rotation written quizzes and a 9-item Likert survey with 16 of 27 responding. | Survey showed 62% agree/strongly agree for overall value and awareness of AI limitations, but 50% disagreed that technical complexity matched training level.
rundown: From 2023 through 2025, an 8-hour rotation combining brief didactics with lab modules on convolution, radiomics, machine learning, deep learning, model evaluation, bias, and case-based applications was delivered to cohorts of 9, 8, and 10 residents at one academic center.

By the September 2026 publication date, authors reported all 27 residents completed the rotation, with an approximate retrospective estimate of 80-90% correct on post-rotation quizzes and a survey of 16 responders showing 62% positive for overall value and for awareness of AI limitations, alongside 50% disagreement on appropriateness of technical complexity.
sources:
- peer_reviewed | Academic Radiology | https://doi.org/10.1016/j.acra.2026.08.095 | 2026-09-05
prev: 0000000000000000000000000000000000000000000000000000000000000000

sha256

1e6fe06248dbc2bfe73a180a2975c97d305fe0a2050033745fecefcb75fdee53

previous

0000000000000000000000000000000000000000000000000000000000000000