Comment on “Artificial intelligence construction: a review of the bridge between CT imaging features of lung ground-glass nodules adenocarcinoma and carcinogenic driver genes”
Year: 2026
Type: article
Abstract: Xue and Chen et al.'s review connects AI-derived CT features of lung ground-glass nodule adenocarcinoma to driver gene status. Three aspects are missing. There is no stated search strategy no databases, date range, or inclusion criteria despite drawing on more than 150 references, so readers cannot tell whether weaker or null results were sought out or just left aside. Individual studies are cited by their best accuracy or AUC figures, from approximately 0.64 to above 0.95, with no attempt to weigh them by sample size, design, or validation status. The framing does not match the evidence the review cites: the text calls AI transformative, but a systematic review it references reports a mean AUC of only ~0.64 for driver gene prediction from imaging. None of this undercuts the review's usefulness as a starting map of the field, but a stated search process, some quality-weighting of the cited numbers, and framing that matches the aggregate evidence would make it more reliable.
Authors: V. P. Abel Jopaul, M. Lingaraj
Language: English
Subfield: Radiology, Nuclear Medicine and Imaging
Field: Medicine
Domain: Health Sciences
Open Access status: gold
Estimated APC paid: $4,390
OpenAlex ID: W7204482994