{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T18:04:11Z","timestamp":1788458651160,"version":"build-2803163510"},"reference-count":44,"publisher":"BMJ","issue":"1","license":[{"start":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T00:00:00Z","timestamp":1768521600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"Shenzhen Key Medical Discipline Construction Fund","award":["SZXK038"],"award-info":[{"award-number":["SZXK038"]}]},{"DOI":"10.13039\/501100012151","name":"Sanming Project of Medicine in Shenzen Municipality","doi-asserted-by":"publisher","award":["SZSM202311018"],"award-info":[{"award-number":["SZSM202311018"]}],"id":[{"id":"10.13039\/501100012151","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2022A1515140141"],"award-info":[{"award-number":["2022A1515140141"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2023A1515010674"],"award-info":[{"award-number":["2023A1515010674"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Medical Research Fund","award":["C2301005"],"award-info":[{"award-number":["C2301005"]}]},{"name":"Shenzhen Fund for Guangdong Provincial High Level Clinical Key Specialties","award":["SZGSP014"],"award-info":[{"award-number":["SZGSP014"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82271103"],"award-info":[{"award-number":["82271103"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Open Ophth"],"accepted":{"date-parts":[[2025,12,29]]},"published-print":{"date-parts":[[2026,3]]},"abstract":"<jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>Retinopathy of prematurity (ROP) is a leading cause of blindness in children worldwide, requiring more efficient models to help predict treatment-requiring ROP. Our study aimed to develop a new prediction model for ROP occurrence and severity, named NLP-ROPCare, using natural language processing (NLP).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods and analysis<\/jats:title>\n                    <jats:p>A retrospective observational study. Infants with a gestational age \u226432 weeks or birth weight \u22642000 g were collected in Guangdong Women and Children Hospital from 2013 to 2022, including 3922 preterm infants with 1106 patients with ROP. Four pretrained language models - BERT (Bidirectional Encoder Representations from Transformers), RoBERTa (Robustly Optimized BERT pretraining Approach), MC-BERT (language pre-training via a Meta Controller) and NEZHA (NEural contextualiZed representation for CHinese lAnguage understanding) - were used for development of NLP prediction models based on free-form texts in the admission notes. For comparison, two machine learning methods (Random Forest and Support Vector Machine) were used to construct prediction models based on 20 structured characteristics previously extracted from the admission notes. Performance evaluating metrics included accuracy, precision, recall, F1 score and area under the curve (AUC).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The NLP prediction models for ROP occurrence outperformed those for severity. The NEZHA model demonstrated the highest accuracy in predicting ROP occurrence, achieving an F1 score of 89.35% and an AUC of 0.90. Its performance was also better than two machine learning models whose highest F1 was 78% with an AUC equal to 0.87. In addition, the F1 score of RoBERTa (78.44%) was slightly higher than that of NEZHA (77.81%) for predicting ROP severity, and the AUC of RoBERTa also achieved the highest 0.91.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The NLP-ROPCare combines language models NEZHA and RoBERTa to enable early prediction of ROP occurrence and severity based on unstructured free-form texts in the admission notes of preterm infants, highlighting its value in early prevention of ROP. Further external validation should be carried out to better adjust the model.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjophth-2025-002385","type":"journal-article","created":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T18:55:18Z","timestamp":1768589718000},"page":"e002385","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":1,"title":["NLP-ROPCare: predicting retinopathy of prematurity with admission notes using natural language processing"],"prefix":"10.1136","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1828-1077","authenticated-orcid":false,"given":"Yulin","family":"Zhang","sequence":"first","affiliation":[{"name":"Shenzhen Eye Hospital, Shenzhen Eye Medical Center, Southern Medical University, Shenzhen, Guangdong, China"},{"name":"Department of Ophthalmology, Huizhou First Hospital, Huizhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuai","family":"Zhao","sequence":"additional","affiliation":[{"name":"College of Computing and Data Science, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianbing","family":"Ren","sequence":"additional","affiliation":[{"name":"National Key Clinical Specialty Construction Project\/Department of Neonatology, Guangdong Women and Children Hospital, Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuwen","family":"Li","sequence":"additional","affiliation":[{"name":"College of Sciences, Northeastern University, Shenyang, Liaoning, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyu","family":"Zhao","sequence":"additional","affiliation":[{"name":"Shenzhen Eye Hospital, Shenzhen Eye Medical Center, Southern Medical University, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4423-7855","authenticated-orcid":false,"given":"Jie","family":"Sun","sequence":"additional","affiliation":[{"name":"Shenzhen Eye Hospital, Shenzhen Eye Medical Center, Southern Medical University, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuan","family":"Nie","sequence":"additional","affiliation":[{"name":"National Key Clinical Specialty Construction Project\/Department of Neonatology, Guangdong Women and Children Hospital, Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Suzhen","family":"Xie","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Guangdong Women and Children Hospital, Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuelin","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Guangdong Women and Children Hospital, Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinming","family":"Wen","sequence":"additional","affiliation":[{"name":"School of Mathematics, Jilin University, Changchun, Jilin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianqiong","family":"Luo","sequence":"additional","affiliation":[{"name":"National Key Clinical Specialty Construction Project\/Department of Neonatology, Guangdong Women and Children Hospital, Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2123-8125","authenticated-orcid":false,"given":"Guoming","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shenzhen Eye Hospital, Shenzhen Eye Medical Center, Southern Medical University, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2026,1,16]]},"reference":[{"key":"2026011610551166000_11.1.e002385.1","doi-asserted-by":"publisher","DOI":"10.1007\/s10456-007-9066-0"},{"key":"2026011610551166000_11.1.e002385.2","doi-asserted-by":"crossref","DOI":"10.1542\/peds.2018-3061","article-title":"Screening Examination of Premature Infants for Retinopathy of Prematurity","volume":"142","author":"Fierson","year":"2018","journal-title":"Pediatrics"},{"key":"2026011610551166000_11.1.e002385.3","doi-asserted-by":"publisher","DOI":"10.1136\/archdischild-2020-319767"},{"key":"2026011610551166000_11.1.e002385.4","doi-asserted-by":"publisher","DOI":"10.1136\/bjophthalmol-2013-304018"},{"key":"2026011610551166000_11.1.e002385.5","doi-asserted-by":"publisher","DOI":"10.1136\/bjophthalmol-2020-316401"},{"key":"2026011610551166000_11.1.e002385.6","doi-asserted-by":"crossref","DOI":"10.1186\/s12886-018-0708-3","article-title":"A systematic study on the prevention and treatment of retinopathy of prematurity in China","volume":"18","author":"Xu","year":"2018","journal-title":"BMC Ophthalmol"},{"key":"2026011610551166000_11.1.e002385.7","doi-asserted-by":"crossref","first-page":"725","DOI":"10.1016\/j.pcl.2020.04.012","article-title":"Workforce Shortage for Retinopathy of Prematurity Care and Emerging Role of Telehealth and Artificial Intelligence","volume":"67","author":"Barrero-Castillero","year":"2020","journal-title":"Pediatr Clin North Am"},{"key":"2026011610551166000_11.1.e002385.8","doi-asserted-by":"crossref","first-page":"1034","DOI":"10.1001\/jamaophthalmol.2018.2753","article-title":"Development of Modified Screening Criteria for Retinopathy of Prematurity: Primary Results From the Postnatal Growth and Retinopathy of Prematurity Study","volume":"136","author":"Binenbaum","year":"2018","journal-title":"JAMA Ophthalmol"},{"key":"2026011610551166000_11.1.e002385.9","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1016\/j.jaapos.2015.10.017","article-title":"The Colorado-retinopathy of prematurity model (CO-ROP): postnatal weight gain screening algorithm","volume":"20","author":"Cao","year":"2016","journal-title":"J AAPOS"},{"key":"2026011610551166000_11.1.e002385.10","doi-asserted-by":"crossref","DOI":"10.1001\/jamanetworkopen.2022.17447","article-title":"Development and Validation of a Deep Learning Model to Predict the Occurrence and Severity of Retinopathy of Prematurity","volume":"5","author":"Wu","year":"2022","journal-title":"JAMA Netw Open"},{"key":"2026011610551166000_11.1.e002385.11","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1007\/s13167-024-00363-7","article-title":"Multi-risk factors joint prediction model for risk prediction of retinopathy of prematurity","volume":"15","author":"Chen","year":"2024","journal-title":"EPMA J"},{"key":"2026011610551166000_11.1.e002385.12","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(13)60178-6"},{"key":"2026011610551166000_11.1.e002385.13","doi-asserted-by":"publisher","DOI":"10.1542\/peds.2004-1309"},{"key":"2026011610551166000_11.1.e002385.14","doi-asserted-by":"publisher","DOI":"10.1016\/j.jaci.2019.12.897"},{"key":"2026011610551166000_11.1.e002385.15","doi-asserted-by":"publisher","DOI":"10.1126\/science.aaa8685"},{"key":"2026011610551166000_11.1.e002385.16","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-021-80985-3","article-title":"Predicting adult neuroscience intensive care unit admission from emergency department triage using a retrospective, tabular-free text machine learning approach","volume":"11","author":"Klang","year":"2021","journal-title":"Sci Rep"},{"key":"2026011610551166000_11.1.e002385.17","doi-asserted-by":"crossref","first-page":"511","DOI":"10.1016\/j.ajog.2022.04.008","article-title":"Natural language processing of admission notes to predict severe maternal morbidity during the delivery encounter","volume":"227","author":"Clapp","year":"2022","journal-title":"Am J Obstet Gynecol"},{"key":"2026011610551166000_11.1.e002385.18","first-page":"1","article-title":"From Softmax to Nucleusmax: A Novel Sparse Language Model for Chinese Radiology Report Summarization","volume":"22","author":"Zhao","year":"2023","journal-title":"ACM Trans Asian Low-Resour Lang Inf Process"},{"key":"2026011610551166000_11.1.e002385.19","doi-asserted-by":"publisher","DOI":"10.1158\/2159-8290.CD-20-0419"},{"key":"2026011610551166000_11.1.e002385.20","doi-asserted-by":"crossref","unstructured":"Liu C , Zhang W , Chen G , et al . Zero-Shot Text Classification via Self-Supervised Tuning. arXiv 2023. Available: https:\/\/arxiv.org\/abs\/2305.11442","DOI":"10.18653\/v1\/2023.findings-acl.110"},{"key":"2026011610551166000_11.1.e002385.21","unstructured":"Devlin J , Chang MW , Lee K , et al . BERT: pre-training of deep bidirectional transformers for language understanding."},{"key":"2026011610551166000_11.1.e002385.22","unstructured":"Liu YH , Ott M , Goyal N , et al . RoBERTa: A Robustly Optimized BERT Pretraining Approach. arXiv 2019. Available: https:\/\/arxiv.org\/abs\/1907.11692"},{"key":"2026011610551166000_11.1.e002385.23","unstructured":"Zhang N , Jia Q , Yin K , et al . Conceptualized Representation Learning for Chinese Biomedical Text Mining. arXiv [csCL 2020. Available: https:\/\/arxiv.org\/abs\/2008.10813"},{"key":"2026011610551166000_11.1.e002385.24","unstructured":"Wei J , Ren X , Li X , et al . NEZHA: Neural Contextualized Representation for Chinese Language Understanding. arXiv 2021. Available: https:\/\/arxiv.org\/abs\/1909.00204"},{"key":"2026011610551166000_11.1.e002385.25","unstructured":"Vaswani A , Shazeer N , Parmar N , et al . Attention is All you Need. arXiv 2023. Available: https:\/\/arxiv.org\/abs\/1706.03762"},{"key":"2026011610551166000_11.1.e002385.26","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"2026011610551166000_11.1.e002385.27","doi-asserted-by":"crossref","unstructured":"Zhao S , Wen J , Tuan LA , et al . Prompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models. arXiv 2023. Available: https:\/\/arxiv.org\/abs\/2305.01219","DOI":"10.18653\/v1\/2023.emnlp-main.757"},{"key":"2026011610551166000_11.1.e002385.28","unstructured":"Hu EJ , Shen Y , Wallis P , et al . LoRA: Low-Rank Adaptation of Large Language Models. arXiv 2021. Available: https:\/\/arxiv.org\/abs\/2106.09685"},{"key":"2026011610551166000_11.1.e002385.29","doi-asserted-by":"publisher","DOI":"10.1016\/j.survophthal.2018.04.002"},{"key":"2026011610551166000_11.1.e002385.30","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"2026011610551166000_11.1.e002385.31","doi-asserted-by":"publisher","DOI":"10.1039\/b918972f"},{"key":"2026011610551166000_11.1.e002385.32","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.92.22.9977"},{"key":"2026011610551166000_11.1.e002385.33","doi-asserted-by":"crossref","DOI":"10.3389\/fpubh.2022.772592","article-title":"A Transfer Learning Method for Detecting Alzheimer\u2019s Disease Based on Speech and Natural Language Processing","volume":"10","author":"Liu","year":"2022","journal-title":"Front Public Health"},{"key":"2026011610551166000_11.1.e002385.34","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocy173"},{"key":"2026011610551166000_11.1.e002385.35","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.106649"},{"key":"2026011610551166000_11.1.e002385.36","doi-asserted-by":"crossref","DOI":"10.1038\/s41746-022-00742-2","article-title":"A large language model for electronic health records","volume":"5","author":"Yang","year":"2022","journal-title":"NPJ Digit Med"},{"key":"2026011610551166000_11.1.e002385.37","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2012.12.005"},{"key":"2026011610551166000_11.1.e002385.38","doi-asserted-by":"crossref","first-page":"797","DOI":"10.1001\/jamaoncol.2016.0213","article-title":"Natural Language Processing in Oncology: A Review","volume":"2","author":"Yim","year":"2016","journal-title":"JAMA Oncol"},{"key":"2026011610551166000_11.1.e002385.39","doi-asserted-by":"crossref","DOI":"10.2196\/medinform.4732","article-title":"Creation of an Accurate Algorithm to Detect Snellen Best Documented Visual Acuity from Ophthalmology Electronic Health Record Notes","volume":"4","author":"Mbagwu","year":"2016","journal-title":"JMIR Med Inform"},{"key":"2026011610551166000_11.1.e002385.40","doi-asserted-by":"publisher","DOI":"10.1007\/s11136-008-9399-1"},{"key":"2026011610551166000_11.1.e002385.41","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1111\/ceo.13340","article-title":"Using natural language processing for identification of herpes zoster ophthalmicus cases to support population-based study","volume":"47","author":"Zheng","year":"2019","journal-title":"Clin Exp Ophthalmol"},{"key":"2026011610551166000_11.1.e002385.42","doi-asserted-by":"publisher","DOI":"10.1001\/jamaophthalmol.2018.7051"},{"key":"2026011610551166000_11.1.e002385.43","doi-asserted-by":"crossref","DOI":"10.1016\/j.xops.2022.100127","article-title":"Deep Learning Approaches for Predicting Glaucoma Progression Using Electronic Health Records and Natural Language Processing","volume":"2","author":"Wang","year":"2022","journal-title":"Ophthalmol Sci"},{"key":"2026011610551166000_11.1.e002385.44","doi-asserted-by":"crossref","first-page":"105844","DOI":"10.1016\/j.earlhumdev.2023.105844","article-title":"Risk factors in the development of retinopathy of prematurity: A 10-year retrospective study","volume":"185","author":"Di Pietro","year":"2023","journal-title":"Early Hum Dev"}],"container-title":["BMJ Open Ophthalmology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjophth-2025-002385","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T18:55:27Z","timestamp":1768589727000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjophth.bmj.com\/lookup\/doi\/10.1136\/bmjophth-2025-002385"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,16]]},"references-count":44,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1,16]]},"published-print":{"date-parts":[[2026,3]]}},"alternative-id":["10.1136\/bmjophth-2025-002385"],"URL":"https:\/\/doi.org\/10.1136\/bmjophth-2025-002385","relation":{},"ISSN":["2397-3269"],"issn-type":[{"value":"2397-3269","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,16]]}}}