Kahi, Charles J.

Abstract Citation-prediction studies often estimate citation counts using information unavailable at publication. We evaluated whether citation-risk outcomes can be predicted using only publication-time information: metadata, references, author history, and text available on or before publication. We assembled 9,424 original-research articles published from 2017 to 2022 across seven clinical gastroenterology journals using OpenAlex and PubMed. The primary reference-observed cohort included 8,409 articles with a parsed reference list. The primary outcome was ≤ 3 citations within 2 years; secondary outcomes were 0 citations within 3 years, ≤ 3 citations within 3 years, and > 20 citations within 2 years. Models compared a nonsemantic citation/reference/context baseline, author-history variables, whole-document title/abstract embeddings, role-segmented source-text embeddings, and reference-context distributional features. Evaluation used two held-out publication-year folds with PR-AUC, or area under the precision-recall curve, F1, and precision among the top-ranked 10% of predictions. For the primary outcome, the nonsemantic baseline achieved PR-AUC 0.818, F1 0.722, and precision@10% 0.935. Adding whole-document embeddings improved performance to 0.828, 0.735, and 0.962, respectively. Structure-aware features did not improve the primary outcome but provided endpoint-specific gains for secondary outcomes. Author-history features showed standalone signal but did not improve the baseline. Pooled performance exceeded journal-local performance, indicating that citation-risk signal operated at the corpus level. These findings support publication-time-valid citation-risk modeling as a reproducible framework for studying evidence visibility within bounded literatures and motivate replication across other journal sets, specialties, and publication eras.

SummaryBackgroundNeoplasia detection rate, the proportion of Barrett's oesophagus patients with high‐grade dysplasia or oesophageal adenocarcinoma detected at index surveillance endoscopy has been proposed as a quality metric. However, the correlation between neoplasia detection rate and a clinically relevant outcome like post‐endoscopy Barrett's neoplasia remains unknown. Post‐endoscopy Barrett's neoplasia refers to the rate of high‐grade dysplasia or oesophageal adenocarcinoma on repeat endoscopy within one year of an index screening examination revealing non‐dysplastic Barrett's oesophagus or low‐grade dysplasia.AimTo assess correlation between neoplasia detection rate and post‐endoscopy Barrett's neoplasia.MethodsWe performed a systematic search of multiple databases from date of inception to June 2021 to identify cohort studies reporting both neoplasia detection rate and post‐endoscopy Barrett's neoplasia. Data from each study were pooled using a random effects model, and their correlation assessed using meta‐regression. Heterogeneity was assessed and a priori planned subgroup analyses were conducted.ResultsTen studies with 27 894 patients with Barrett's oesophagus were included. The pooled neoplasia detection rate and post‐endoscopy Barrett's neoplasia were 5.0% (95% CI: 3.4%‐7.1%, I2 = 97%) and 19.6% (95% CI: 10.1%‐34.7%, I2 = 96%), respectively. Meta‐regression revealed a statistically significant inverse relationship between the two variables (coefficient −3.50, 95% CI: −4.63 to −2.37, P < 0.01). With every 1% increase of neoplasia detection rate, post‐endoscopy Barrett's neoplasia decreased by 3.50%. Heterogeneity was high despite adjusting for study quality and performing several subgroup analyses.ConclusionWe observed a statistically significant inverse correlation between neoplasia detection rate and post‐endoscopy Barrett's neoplasia. Additional studies are needed to further validate this correlation.