{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T05:36:32Z","timestamp":1782970592258,"version":"3.54.5"},"reference-count":24,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T00:00:00Z","timestamp":1782950400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Endocrinol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>The assessment of menopausal status is crucial for individualized health management and risk stratification of chronic diseases in women. The traditional assessment of menopause mainly relies on serum reproductive hormone tests, such as FSH, AMH, etc., whose test results are stable and reliable and are the gold standard for clinical diagnosis. Meanwhile, ultrasound is a routine gynecological examination method. But the unstructured information in its report has not been systematically used for predictive modeling.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This study included 713 Chinese women from Hangzhou Red Cross Hospital as the training set and another 284 from the Second Affiliated Hospital of Zhejiang University as the independent external validation set. Three morphological features of ovarian atrophy (OA), endometrial atrophy (EA) and uterine atrophy (UA) were automatically extracted from unstructured ultrasound report text by using large language model (LLM), and fused with anthropometric features to construct a multimodal prediction model. Eight machine learning models were trained and their predictive performances were compared.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The highest AUC of 0.984 was obtained by integrating anthropometric and hormone features in the validation set. The AUC is 0.935, which combines anthropometric features and ultrasound morphological features. The qwen-plus with the largest number of LLM parameters has the best feature extraction performance and is closest to the labeling results of human experts.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>LLM can effectively extract structured morphological features from ultrasound report text. The fusion of ultrasound morphological features and anthropometric features can provide supplementary evaluation methods for assessing menopausal status. This method is particularly suitable for clinical scenarios where hormone data is temporarily missing or unavailable.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fendo.2026.1869205","type":"journal-article","created":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T04:24:11Z","timestamp":1782966251000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Multimodal machine learning for menopause status prediction using LLM-extracted ultrasound features"],"prefix":"10.3389","volume":"17","author":[{"given":"Weiwei","family":"Yin","sequence":"first","affiliation":[{"name":"Department of Obstetrics and Gynecology, Hangzhou Red Cross Hospital","place":["Hangzhou, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengyuan","family":"Shen","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology and College of Software, Zhejiang University of Technology","place":["Hangzhou, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chun","family":"Feng","sequence":"additional","affiliation":[{"name":"The Second Affiliated Hospital Zhejiang University School of Medicine","place":["Hangzhou, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xia","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology and College of Software, Zhejiang University of Technology","place":["Hangzhou, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sihao","family":"Shen","sequence":"additional","affiliation":[{"name":"Department of Obstetrics and Gynecology, Hangzhou Red Cross Hospital","place":["Hangzhou, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiyue","family":"Jiang","sequence":"additional","affiliation":[{"name":"The Second Affiliated Hospital Zhejiang University School of Medicine","place":["Hangzhou, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenbo","family":"Cheng","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology and College of Software, Zhejiang University of Technology","place":["Hangzhou, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lihui","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Obstetrics and Gynecology, Hangzhou Red Cross Hospital","place":["Hangzhou, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ling","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Obstetrics and Gynecology, Hangzhou Red Cross Hospital","place":["Hangzhou, Zhejiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,2]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1016\/j.maturitas.2015.07.019","article-title":"Menopause prediction and potential implications","volume":"82","author":"Daan","year":"2015","journal-title":"Maturitas"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1210\/clinem\/dgac461","article-title":"Risk prediction models of natural menopause onset: a systematic review","volume":"107","author":"Raeisi-Dehkordi","year":"2022","journal-title":"J Clin Endocrinol Metab"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1002\/med.22081","article-title":"Estrogen deficiency-mediated osteoimmunity in postmenopausal osteoporosis","volume":"45","author":"Yao","year":"2025","journal-title":"Med Res Rev"},{"key":"B4","doi-asserted-by":"publisher","first-page":"106773","DOI":"10.1016\/j.neubiorev.2026.106773","article-title":"The brain in transition: Perimenopause through a translational lens","volume":"187","author":"Hynd","year":"2026","journal-title":"Neurosci Biobehav Rev"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.3389\/fpubh.2025.1528718","article-title":"Depression symptoms in perimenopausal women with somatic pain: nomogram construction based on a logistic regression model","volume":"13","author":"Gao","year":"2025","journal-title":"Front Public Health"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1093\/humupd\/dmac045","article-title":"Anti-m\u00fcllerian hormone for the diagnosis and prediction of menopause: a systematic review","volume":"29","author":"Nelson","year":"2023","journal-title":"Hum Reprod Update"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.3109\/13697137.2011.650656","article-title":"Executive summary of the stages of reproductive aging workshop+ 10: addressing the unfinished agenda of staging reproductive aging","volume":"15","author":"Harlow","year":"2012","journal-title":"Climacteric"},{"key":"B8","doi-asserted-by":"publisher","first-page":"P1","DOI":"10.1530\/eje-14-0253","article-title":"The polycystic ovary syndrome: a position statement from the european society of endocrinology","volume":"171","author":"Conway","year":"2014","journal-title":"Eur J Endocrinol"},{"key":"B9","doi-asserted-by":"publisher","first-page":"915","DOI":"10.7490\/f1000research.1114157.1","article-title":"A terrible beauty: A short history of nice the national institute for health and care excellence","volume":"6","author":"Timmins","year":"2017","journal-title":"F1000Research"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.3109\/01443615.2014.920794","article-title":"Royal college of obstetricians and gynaecologists guidelines: how evidence-based are they","volume":"34","author":"Prusova","year":"2014","journal-title":"J Obstetrics Gynaecology"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1093\/humupd\/dmt062","article-title":"The physiology and clinical utility of anti-mullerian\u00a8 hormone in women","volume":"20","author":"Dewailly","year":"2014","journal-title":"Hum Reprod Update"},{"key":"B12","doi-asserted-by":"publisher","first-page":"425","DOI":"10.1016\/j.ogc.2011.05.002","article-title":"The timing of the age at which natural menopause occurs","volume":"38","author":"Gold","year":"2011","journal-title":"Obstetrics Gynecology Clinics North America"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1210\/er.2009-0006","article-title":"Ovarian aging: mechanisms and clinical consequences","volume":"30","author":"Broekmans","year":"2009","journal-title":"Endocr Rev"},{"key":"B14","first-page":"195","article-title":"Transvaginal sonography of the endometrium in postmenopausal women","volume":"78","author":"Varner","year":"1991","journal-title":"Obstetrics Gynecology"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1001\/jama.280.17.1510","article-title":"Endovaginal ultrasound to exclude endometrial cancer and other endometrial abnormalities","volume":"280","author":"Smith-Bindman","year":"1998","journal-title":"Jama"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1016\/0378-5122(91)90214-b","article-title":"Transvaginal sonography of postmenopausal ovaries with pathologic correlation","volume":"9","author":"Fleischer","year":"1990","journal-title":"J Ultrasound Med"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1006\/gyno.2000.5783","article-title":"Ovarian volume related to age","volume":"77","author":"Pavlik","year":"2000","journal-title":"Gynecologic Oncol"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1002\/path.6232","article-title":"Extracting structured information from unstructured histopathology reports using generative pre-trained transformer 4 (gpt-4)","volume":"262","author":"Truhn","year":"2024","journal-title":"J Pathol"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1007\/s11547-023-01651-4","article-title":"Large language models for structured reporting in radiology: performance of gpt-4, chatgpt-3.5, perplexity and bing","volume":"128","author":"Mallio","year":"2023","journal-title":"La Radiologia Med"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1002\/9781119548911.ch14","article-title":"Feasibility of using the privacypreserving large language model vicuna for labeling radiology reports","volume":"309","author":"Mukherjee","year":"2023","journal-title":"Radiology"},{"key":"B21","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Lundberg","year":"2017"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1210\/endocr\/bqaf137","article-title":"The hypothalamic-pituitary-ovarian axis, ovarian disorders, and brain aging","volume":"166","author":"Valera","year":"2025","journal-title":"Endocrinology"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1016\/j.beem.2023.101774","article-title":"New advances in menopause symptom management","volume":"38","author":"Koysombat","year":"2024","journal-title":"Best Pract Res Clin Endocrinol Metab"},{"key":"B24","doi-asserted-by":"publisher","first-page":"117805","DOI":"10.1016\/j.bone.2026.117805","article-title":"Calcium, fsh, and the changing bones of menopause: A longitudinal look at the silent transformation","volume":"205","author":"Puranda","year":"2026","journal-title":"Bone"}],"container-title":["Frontiers in Endocrinology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2026.1869205\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T04:24:12Z","timestamp":1782966252000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2026.1869205\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,2]]},"references-count":24,"alternative-id":["10.3389\/fendo.2026.1869205"],"URL":"https:\/\/doi.org\/10.3389\/fendo.2026.1869205","relation":{},"ISSN":["1664-2392"],"issn-type":[{"value":"1664-2392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,2]]},"article-number":"1869205"}}