{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T15:42:51Z","timestamp":1791906171038,"version":"4.3.4"},"reference-count":23,"publisher":"Wiley","license":[{"start":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T00:00:00Z","timestamp":1791504000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"},{"start":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T00:00:00Z","timestamp":1791504000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["obgyn.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Intl J Gynecology &amp; Obste"],"abstract":"Abstract<\/jats:title>\n \n Introduction<\/jats:title>\n For patients requiring hysterectomy, uterine weight is an important factor affecting surgical complexity and surgical outcomes. However, uterine weight is not readily available for analysis in administrative databases. In the present study, we use natural language processing to extract uterine weight from narrative pathology text.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n Pathology text was obtained for 5000 patients sampled \u00b13\u2009days of hysterectomy from hospital administrative datasets. The gross pathology subsections that describe the submitted tissues were retained for analysis. Manual annotation was performed to create a gold standard dataset. The texts were pre\u2010processed, tokenized (split into words and punctuation), and tagged with parts\u2010of\u2010speech (e.g., noun, verb, number, adverb). Numeric tokens were retained for analysis. Feature engineering (e.g., variable construction and selection) included creating subspecimen flags, three tokens before and after the numeric tokens, weight units, and the prefix \u201cweigh.\u201d Models included classification and regression trees (CART), extreme gradient boosting (XGB), and CatBoost, trained on 75%, validated on 15%, and tested in a 10% hold\u2010out dataset. Performance on a real\u2010world application was assessed for all hysterectomies performed over a 4\u2010year period.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n Trained on all numeric tokens using features determined a priori, CART had 99.1% precision and 100% recall, with eight false positives. XGB performed similarly (99.3% precision; 99.9% recall). Performance was best using CatBoost's ordered target encoding and all values of the previous and subsequent three tokens (99.8% precision; 100% recall). Applied to the test dataset, CART slightly outperformed CatBoost with two fewer false positives. Summing all weights in the test set reports (\n n\u2009=<\/jats:italic>\n \u2009474), the extracted total specimen weight was a mean 9.4\u2009g higher than the truth, owing predominantly to duplicate weights (22\/37 discrepant reports). Application in the real\u2010world dataset (\n n\u2009=<\/jats:italic>\n \u200957\u2009546) identified a small number of reports with data quality issues specific to low\u2010weight specimens that should be excluded (\u226410\u2009g) or subjected to manual adjudication (>10 to \u226415\u2009g).\n <\/jats:p>\n <\/jats:sec>\n \n Conclusion<\/jats:title>\n Natural language processing followed by simple CART can accurately extract total uterine weight from narrative pathology reports. Further work is needed to extract specific anatomic weights.<\/jats:p>\n <\/jats:sec>","DOI":"10.1002\/ijgo.71384","type":"journal-article","created":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T10:15:08Z","timestamp":1791540908000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Use of natural language processing to extract uterine weight from pathology reports"],"prefix":"10.1002","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9650-9105","authenticated-orcid":false,"given":"Steven","family":"Habbous","sequence":"first","affiliation":[{"name":"Ontario Health Toronto Ontario Canada"},{"name":"Schulich School of Medicine and Dentistry Western University London Ontario Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alinah","family":"Surani","sequence":"additional","affiliation":[{"name":"Department of Obstetrics and Gynaecology University of Toronto Toronto Ontario Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ally","family":"Murji","sequence":"additional","affiliation":[{"name":"Department of Obstetrics and Gynaecology University of Toronto Toronto Ontario Canada"},{"name":"Institute for Better Health Trillium Health Partners Mississauga Ontario Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erik","family":"Hellsten","sequence":"additional","affiliation":[{"name":"Ontario Health Toronto Ontario Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,10,9]]},"reference":[{"issue":"1","key":"e_1_2_11_2_1","article-title":"Surgical outcomes of robotic hysterectomy for large uterus weighing more than 1000 g: a retrospective study from a high\u2010volume center","volume":"19","author":"Zhao L","year":"2025","journal-title":"J Robot Surg"},{"issue":"1","key":"e_1_2_11_3_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.4293\/JSLS.2014.00251","article-title":"Feasibility and safety of outpatient total laparoscopic hysterectomy","volume":"19","author":"Maheux\u2010Lacroix S","year":"2015","journal-title":"JSLS"},{"issue":"5","key":"e_1_2_11_4_1","doi-asserted-by":"crossref","first-page":"e2026","DOI":"10.1002\/rcs.2026","article-title":"Impact of uterine weight on robotic hysterectomy: analysis of 500 cases in a single institute","volume":"15","author":"Akazawa M","year":"2019","journal-title":"Int J Med Robot"},{"issue":"6","key":"e_1_2_11_5_1","first-page":"435","article-title":"Morbidity of vaginal hysterectomy for benign tumors as a function of uterine weight","volume":"48","author":"Deval B","year":"2003","journal-title":"J Reprod Med"},{"issue":"5","key":"e_1_2_11_6_1","doi-asserted-by":"crossref","first-page":"480.e1","DOI":"10.1016\/j.ajog.2018.06.015","article-title":"Uterine weight and complications after abdominal, laparoscopic, and vaginal hysterectomy","volume":"219","author":"Louie M","year":"2018","journal-title":"Am J Obstet Gynecol"},{"issue":"3","key":"e_1_2_11_7_1","doi-asserted-by":"crossref","first-page":"276","DOI":"10.4103\/jmas.jmas_125_24","article-title":"Impact\u00a0of\u00a0uterine weight on surgical outcomes in robotic hysterectomy: an ambispective analysis","volume":"21","author":"Bahadur A","year":"2024","journal-title":"J Minim Access Surg"},{"issue":"3","key":"e_1_2_11_8_1","article-title":"Effect of uterine weight on the surgical outcomes of robot\u2010assisted hysterectomy in benign indications","volume":"16","author":"Higuchi N","year":"2024","journal-title":"Cureus"},{"key":"e_1_2_11_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajog.2026.09.018"},{"issue":"3","key":"e_1_2_11_10_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1200\/CCI.19.00008","article-title":"Obtaining knowledge in pathology reports through a natural language processing approach with classification, named\u2010entity recognition, and relation\u2010extraction heuristics","volume":"3","author":"Oliwa T","year":"2019","journal-title":"JCO Clin Cancer Inform"},{"key":"e_1_2_11_11_1","doi-asserted-by":"crossref","first-page":"104510","DOI":"10.1016\/j.ijmedinf.2021.104510","article-title":"The need to separate the wheat from the chaff in medical informatics: introducing a comprehensive checklist for the (self)\u2010assessment of medical AI studies","volume":"153","author":"Cabitza F","year":"2021","journal-title":"Int J Med Inform"},{"key":"e_1_2_11_12_1","volume-title":"Ensemble Methods for Machine Learning","author":"Kunapuli G","year":"2023"},{"issue":"1","key":"e_1_2_11_13_1","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1186\/s40537-020-00369-8","article-title":"CatBoost for big data: an interdisciplinary review","volume":"7","author":"Hancock JT","year":"2020","journal-title":"J Big Data"},{"key":"e_1_2_11_14_1","doi-asserted-by":"crossref","first-page":"e59251","DOI":"10.2196\/59251","article-title":"Exploring named entity recognition potential and the value of tailored natural language processing pipelines for radiology, pathology, and Progress notes in clinical decision support: quantitative study","volume":"4","author":"Kocaman V","year":"2025","journal-title":"JMIR Ai"},{"issue":"1","key":"e_1_2_11_15_1","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1016\/j.gie.2022.07.009","article-title":"Validation of a natural language processing algorithm to identify adenomas and measure adenoma detection rates across a health system: a population\u2010level study","volume":"97","author":"Tinmouth J","year":"2023","journal-title":"Gastrointest Endosc"},{"key":"e_1_2_11_16_1","doi-asserted-by":"crossref","first-page":"27","DOI":"10.2196\/70315","article-title":"Large language model architectures in health care: scoping review of research perspectives","volume":"27","author":"Leiser F","year":"2025","journal-title":"J Med Internet Res"},{"issue":"3","key":"e_1_2_11_17_1","doi-asserted-by":"crossref","first-page":"310","DOI":"10.1002\/path.6232","article-title":"Extracting structured information from unstructured histopathology reports using generative pre\u2010trained transformer 4 (GPT\u20104)","volume":"262","author":"Truhn D","year":"2024","journal-title":"J Pathol"},{"key":"e_1_2_11_18_1","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2025.110665","article-title":"From BERT to generative AI \u2010 comparing encoder\u2010only vs. large language models in a cohort of lung cancer patients for named entity recognition in unstructured medical reports","volume":"195","author":"Arzideh K","year":"2025","journal-title":"Comput Biol Med"},{"key":"e_1_2_11_19_1","article-title":"Improving information extraction from pathology reports using named entity recognition","author":"Zeng KG","year":"2023","journal-title":"Res Sq"},{"key":"e_1_2_11_20_1","doi-asserted-by":"crossref","first-page":"104731","DOI":"10.1016\/j.jbi.2024.104731","article-title":"Augmenting biomedical named entity recognition with general\u2010domain resources","volume":"159","author":"Yin Y","year":"2024","journal-title":"J Biomed Inform"},{"issue":"7","key":"e_1_2_11_21_1","doi-asserted-by":"crossref","first-page":"1208","DOI":"10.1093\/jamia\/ocac040","article-title":"CancerBERT: a cancer domain\u2010specific language model for extracting breast cancer phenotypes from electronic health records","volume":"29","author":"Zhou S","year":"2022","journal-title":"J Am Med Inform Assoc"},{"key":"e_1_2_11_22_1","doi-asserted-by":"crossref","DOI":"10.7717\/peerj-cs.2245","article-title":"Trade\u2010off between training and testing ratio in machine learning for medical image processing","volume":"10","author":"Sivakumar M","year":"2024","journal-title":"PeerJ Comput Sci"},{"key":"e_1_2_11_23_1","doi-asserted-by":"crossref","DOI":"10.57187\/4942","article-title":"A qualitative assessment of the use of artificial intelligence in public sector health organizations in Ontario, Canada","volume":"156","author":"Habbous S","year":"2025","journal-title":"Swiss Med Wkly"},{"issue":"4","key":"e_1_2_11_24_1","first-page":"400","article-title":"Size matters in planning hysterectomy approach","volume":"12","author":"Mohan Y","year":"2016","journal-title":"Womens Health"}],"container-title":["International Journal of Gynecology & Obstetrics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/obgyn.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/ijgo.71384","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/obgyn.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/ijgo.71384","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/obgyn.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/ijgo.71384","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T10:15:11Z","timestamp":1791540911000},"score":1,"resource":{"primary":{"URL":"https:\/\/obgyn.onlinelibrary.wiley.com\/doi\/10.1002\/ijgo.71384"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,9]]},"references-count":23,"alternative-id":["10.1002\/ijgo.71384"],"URL":"https:\/\/doi.org\/10.1002\/ijgo.71384","archive":["Portico"],"relation":{},"ISSN":["0020-7292","1879-3479"],"issn-type":[{"value":"0020-7292","type":"print"},{"value":"1879-3479","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,9]]},"assertion":[{"value":"2026-06-08","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-04","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-10-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"ijgo.71384"}}