Agentic Artificial Intelligence for the Automated Generation of Accurate Summary Podcasts of Radiology Research Papers

Jeong Hyun Lee, Kyowon Gu, Jaeseung Shin, Ji Hye Min, Jeong Ah Hwang, Ji Yoon Ban, Jihwan Choi, Taewon Han, Dong Young Jeong, Kyung A Kang, Haejung Kim, Harim Kim, Hyun Su Kim, Min Je Kim, Myoung Kyoung Kim, Sanghee Kim, Min Hwan Kwak, Ji Hyun Lee, Sang Yub Lee, Chang Hoon Oh, Sung Goo Park, Yun Hwa · 2026

Read Agentic Artificial Intelligence for the Automated Generation of Accurate Summary Podcasts of Radiology Research Papers by Jeong Hyun Lee, Kyowon Gu, Jaeseung Shin, Ji Hye Min, Jeong Ah Hwang, Ji Yoon Ban, Jihwan Choi, Taewon Han, Dong Young Jeong, Kyung A Kang, Haejung Kim, Harim Kim, Hyun Su Kim, Min Je Kim, Myoung Kyoung Kim, Sanghee Kim, Min Hwan Kwak, Ji Hyun Lee, Sang Yub Lee, Chang Hoon Oh, Sung Goo Park, Yun Hwa (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13333226.txt.

Description

Jeong Hyun Lee and colleagues test a 2026 agentic AI pipeline for generating accurate podcast summaries of radiology research papers. The goal was to see whether a custom multi-agent pipeline could beat a generic commercial tool, Google NotebookLM, on factual accuracy. Twenty-two original research articles from the April 2025 issue of Radiology were processed through both systems, yielding 44 audio episodes. The custom pipeline, called P5, used separate agents for script writing, quality assurance, pronunciation, and audio synthesis.

Four radiologists from a pool of 25 evaluated each blinded episode, giving 176 total evaluations. Primary outcomes were hallucinations per episode and the share of hallucination-free episodes, with secondary outcomes detailed in the full paper. The study asks whether purpose-built agent workflows can curb the factual errors that plague generic podcast tools. For radiology educators, it offers head-to-head evidence on a fast-growing way to consume research.

Catalog record

CREATORJeong Hyun Lee, Kyowon Gu, Jaeseung Shin, Ji Hye Min, Jeong Ah Hwang, Ji Yoon Ban, Jihwan Choi, Taewon Han, Dong Young Jeong, Kyung A Kang, Haejung Kim, Harim Kim, Hyun Su Kim, Min Je Kim, Myoung Kyoung Kim, Sanghee Kim, Min Hwan Kwak, Ji Hyun Lee, Sang Yub Lee, Chang Hoon Oh, Sung Goo Park, Yun Hwa
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE27 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13333226

Browse the full library · About the Tower of Babel