{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T11:24:07Z","timestamp":1786965847124,"version":"build-2736575974"},"reference-count":28,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2026,8,15]],"date-time":"2026-08-15T00:00:00Z","timestamp":1786752000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background: Infertility is a common reproductive health disorder that affects roughly 10\u201315% of couples during their reproductive period. Hysterosalpingography (HSG) is a widely utilized imaging modality for assessing uterine cavity morphology and fallopian tube patency and continues to play a central role in infertility investigations. Nevertheless, the interpretation of HSG findings may vary according to the experience and expertise of the evaluator, potentially leading to inconsistencies in clinical decision-making. Although artificial intelligence (AI) has demonstrated considerable potential in medical image analysis across various specialties, evidence regarding its application in the interpretation of HSG examinations remains scarce. Therefore, this study aimed to evaluate the level of agreement among radiologists, gynecologists, and an AI-based system in the assessment of identical HSG images. Methods: In this retrospective study, a total of 1443 HSG images obtained from 414 women who underwent hysterosalpingography as part of an infertility evaluation between January 2021 and January 2025 were reviewed. Cases with incomplete clinical records or suboptimal image quality were excluded from the analysis. All examinations were independently assessed by an experienced radiologist, a gynecologist specializing in infertility management, and a multimodal artificial intelligence system based on ChatGPT-5, with each evaluator blinded to the assessments of the others and to the patients\u2019 clinical information. Image interpretation included the evaluation of contrast distribution, peritoneal spill, uterine cavity findings, tubal patency, and overall HSG impression, which were categorized according to predefined diagnostic criteria. The primary outcome was the degree of interobserver agreement among the evaluators. Agreement analyses were performed using Cohen\u2019s kappa (\u03ba) and Gwet\u2019s AC1 coefficients. Analyses were conducted using IBM SPSS Statistics (version 30.0; IBM Corp., Armonk, NY, USA) and R statistical software (version 4.4.0; R Foundation for Statistical Computing, Vienna, Austria). Statistical significance was set at p &lt; 0.05 (two-sided). Results: A total of 1443 HSG images obtained from 414 women were included in the final analysis. The mean age of the study population was 30.97 \u00b1 5.59 years, and primary infertility accounted for 87.9% of cases. The average number of images acquired per examination was 3.49 \u00b1 1.05. According to Cohen\u2019s kappa analysis, the highest levels of agreement were observed for the assessment of image artifacts and contrast medium distribution. Agreement between the AI system and the radiologist was particularly strong for contrast medium distribution (\u03ba = 0.757). For the overall interpretation of HSG findings, AI demonstrated substantial agreement with the radiologist (\u03ba = 0.637), exceeding the level of agreement observed between the radiologist and the gynecologist (\u03ba = 0.363). In contrast, concordance involving AI was lower for the evaluation of uterine abnormalities, intrauterine filling defects, and tubal patency. When agreement was reassessed using Gwet\u2019s AC1 statistic, concordance coefficients were consistently higher than the corresponding kappa values across all evaluator pairs. Near-perfect agreement between AI and the radiologist was identified for contrast medium distribution (AC1 = 0.954), peritoneal spill (AC1 = 0.893), and patterns of peritoneal contrast passage (AC1 = 0.841). Procedures performed under local anesthesia yielded a significantly greater number of images than those conducted under general anesthesia (3.86 \u00b1 0.86 vs. 3.08 \u00b1 1.10, p &lt; 0.001). No significant associations were detected between abnormal HSG findings and either infertility type or anesthetic technique. In multivariable analysis, the use of general anesthesia was independently associated with a lower image count, whereas the presence of tubal pathology emerged as an independent predictor of acquiring a greater number of images during the examination. Conclusions: Our findings indicate that AI-assisted interpretation of HSG images has the potential to complement expert assessment, showing substantial concordance in several key diagnostic domains. While the technology appears promising as a decision-support tool in infertility evaluation, further research and refinement are warranted, particularly regarding the assessment of tubal and uterine pathologies.<\/jats:p>","DOI":"10.3390\/diagnostics16162576","type":"journal-article","created":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T10:04:36Z","timestamp":1786961076000},"page":"2576","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Interobserver Agreement Between Artificial Intelligence, Radiologist, and Gynecologist in Hysterosalpingography Interpretation: A Retrospective Comparative Study"],"prefix":"10.3390","volume":"16","author":[{"given":"Deniz","family":"Ta\u015fk\u0131ran","sequence":"first","affiliation":[{"name":"Department of Obstetrics and Gynecolog, Faculty of Medicine, Giresun University, 28100 Giresun, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2950-8767","authenticated-orcid":false,"given":"Serdar","family":"Aslan","sequence":"additional","affiliation":[{"name":"Departments of Radiology, Faculty of Medicine, Giresun University, 28100 Giresun, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Salih","family":"Kolsuz","sequence":"additional","affiliation":[{"name":"Giresun Maternity and Children\u2019s Hospital, Training and Research Hospital, 28100 Giresun, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4060-2781","authenticated-orcid":false,"given":"Mesut","family":"Al\u00e7\u0131","sequence":"additional","affiliation":[{"name":"Department of Obstetrics and Gynecolog, Faculty of Medicine, Giresun University, 28100 Giresun, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Esra","family":"Yazgan Yi\u011fitba\u015f","sequence":"additional","affiliation":[{"name":"Departments of Radiology, Faculty of Medicine, Giresun University, 28100 Giresun, Turkey"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,15]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1255","DOI":"10.1016\/j.fertnstert.2021.08.038","article-title":"Fertility evaluation of infertile women: A committee opinion","volume":"116","author":"Penzias","year":"2021","journal-title":"Fertil. Steril."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"107180","DOI":"10.1016\/j.crad.2025.107180","article-title":"Ultrasound O-RADS and Modified Ultrasound Simple Rules Comparison in Evaluation of Surgically Proven Adnexal Masses","volume":"92","author":"Kajal","year":"2025","journal-title":"Clin. Radiol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1511","DOI":"10.5664\/jcsm.11732","article-title":"Artificial intelligence in sleep medicine: Assessing the diagnostic precision of ChatGPT-4","volume":"21","author":"Patel","year":"2025","journal-title":"J. Clin. Sleep Med."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1038\/s41586-023-06555-x","article-title":"A foundation model for generalizable disease detection from retinal images","volume":"622","author":"Zhou","year":"2023","journal-title":"Nature"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"421","DOI":"10.1148\/radiol.2019191293","article-title":"Chest radiograph interpretation with deep learning models: Assessment with radiologist-adjudicated reference standards and population-adjusted evaluation","volume":"294","author":"Majkowska","year":"2020","journal-title":"Radiology"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1046\/j.1469-0705.1999.13010017.x","article-title":"Artificial neural network models for the preoperative discrimination between malignant and benign adnexal masses","volume":"13","author":"Timmerman","year":"1999","journal-title":"Ultrasound Obstet. Gynecol. Off. J. Int. Soc. Ultrasound Obstet. Gynecol."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1002\/uog.20181","article-title":"Deep learning enables automatic quantitative assessment of puborectalis muscle and urogenital hiatus in plane of minimal hiatal dimensions","volume":"54","author":"Grob","year":"2019","journal-title":"Ultrasound Obstet. Gynecol."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1002\/uog.13441","article-title":"Quantitative ultrasound texture analysis of fetal lungs to predict neonatal respiratory morbidity","volume":"45","author":"Palacio","year":"2015","journal-title":"Ultrasound Obstet. Gynecol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1038\/s42256-019-0139-8","article-title":"Validity of machine learning in biology and medicine increased through collaborations across fields of expertise","volume":"2","author":"Littmann","year":"2020","journal-title":"Nat. Mach. Intell."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","article-title":"Large language models encode clinical knowledge","volume":"620","author":"Singhal","year":"2023","journal-title":"Nature"},{"key":"ref_11","first-page":"133","article-title":"Of regulating healthcare AI and robots","volume":"21","author":"Terry","year":"2019","journal-title":"Yale JL Tech"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1476","DOI":"10.1016\/j.jacr.2017.07.007","article-title":"Artificial intelligence: Threat or boon to radiologists?","volume":"14","author":"Recht","year":"2017","journal-title":"J. Am. Coll. Radiol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"R139","DOI":"10.1530\/REP-18-0523","article-title":"Artificial intelligence in reproductive medicine","volume":"158","author":"Wang","year":"2019","journal-title":"Reproduction"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"25076","DOI":"10.1038\/s41598-024-77313-w","article-title":"Repeatability and reproducibility of artificial intelligence-acquired fetal brain measurements (SonoCNS) in the second and third trimesters of pregnancy","volume":"14","author":"Mlodawski","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"3429","DOI":"10.2147\/IJWH.S555065","article-title":"Interobserver Variability in Hysterosalpingography Interpretation: Radiologists vs Gynecologists","volume":"17","author":"Karadag","year":"2025","journal-title":"Int. J. Womens Health"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1016\/S0015-0282(97)81903-6","article-title":"Observer variability in the diagnosis and management of the hysterosalpingogram","volume":"67","author":"Glatstein","year":"1997","journal-title":"Fertil. Steril."},{"key":"ref_17","first-page":"1280","article-title":"HSG-Assistant: AI-Driven Framework for Enhanced Hysterosalpingography Analysis","volume":"327","author":"Yi","year":"2025","journal-title":"Stud. Health Technol. Inf."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1876","DOI":"10.1148\/rg.2021210033","article-title":"Evaluating Fallopian Tube Patency: What the Radiologist Needs to Know","volume":"41","author":"Grigovich","year":"2021","journal-title":"Radiographics"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1067\/j.cpradiol.2008.02.003","article-title":"Hysterosalpingography: Technique and applications","volume":"38","author":"Chalazonitis","year":"2009","journal-title":"Curr. Probl. Diagn. Radiol."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2152","DOI":"10.1093\/bjr\/tqaf199","article-title":"Intravasation is not only a complication but also a radiological finding for tubal pathologies in hysterosalpingography","volume":"98","author":"Yavuz","year":"2025","journal-title":"Br. J. Radiol."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1111\/1754-9485.13619","article-title":"Assessment of contrast intravasation in patients investigated by fluoroscopic hysterosalpingograms: A two-year retrospective audit in Western Australia","volume":"68","author":"Chia","year":"2024","journal-title":"J. Med. Imaging Radiat. Oncol."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"3045","DOI":"10.1038\/s41467-019-11069-0","article-title":"Integrating biomedical research and electronic health records to create knowledge-based biologically meaningful machine-readable embeddings","volume":"10","author":"Nelson","year":"2019","journal-title":"Nat. Commun."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1016\/j.acra.2015.10.004","article-title":"Big Data and the Future of Radiology Informatics","volume":"23","author":"Kansagra","year":"2016","journal-title":"Acad. Radiol."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1155\/2015\/306248","article-title":"Comparison of four different pain relief methods during hysterosalpingography: A randomized controlled study","volume":"20","author":"Unlu","year":"2015","journal-title":"Pain Res. Manag"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"762","DOI":"10.1016\/j.jmig.2014.02.014","article-title":"Comparison of nonsteroidal anti-inflammatory drugs and misoprostol for pain relief during and after hysterosalpingography: Prospective, randomized, controlled trial","volume":"21","author":"Hassa","year":"2014","journal-title":"J. Minim. Invasive Gynecol."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1348\/000711006X126600","article-title":"Computing inter-rater reliability and its variance in the presence of high agreement","volume":"61","author":"Gwet","year":"2008","journal-title":"Br. J. Math. Stat. Psychol."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Wongpakaran, N., Wongpakaran, T., Wedding, D., and Gwet, K.L. (2013). A comparison of Cohen\u2019s Kappa and Gwet\u2019s AC1 when calculating inter-rater reliability coefficients: A study conducted with personality disorder samples. BMC Med. Res. Methodol., 13.","DOI":"10.1186\/1471-2288-13-61"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"16857","DOI":"10.1038\/s41598-025-01249-y","article-title":"Reproducibility of quantitative cervical strain elastography in nonpregnant patients and the effect of vaginal misoprostol on measured parameters","volume":"15","author":"Mlodawski","year":"2025","journal-title":"Sci. Rep."}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/16\/2576\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T10:25:05Z","timestamp":1786962305000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/16\/2576"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,15]]},"references-count":28,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["diagnostics16162576"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics16162576","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,15]]}}}