{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T20:19:41Z","timestamp":1777580381752,"version":"3.51.4"},"reference-count":26,"publisher":"SAGE Publications","issue":"3","license":[{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["European Journal of Ophthalmology"],"published-print":{"date-parts":[[2026,5]]},"abstract":"\n Purpose<\/jats:title>\n \n To evaluate the utility of\n CataractBot<\/jats:italic>\n , an LLM (Large Language Model)-powered chatbot that provides doctor-verified answers to patient questions about cataract surgery. We examine its use by both end-users (patients and attendants) and medical experts.\n <\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n \n A 24-week study was conducted to evaluate\n CataractBot<\/jats:italic>\n among patients, their attendants, doctors, and patient coordinators. The bot responded instantly to questions by querying a knowledge base curated by medical professionals. Each response was asynchronously verified by an ophthalmologist (for medical questions) or a patient coordinator (for logistical questions), and their edits contributed to updating the knowledge base, thereby minimizing future expert intervention. A mixed-methods analysis was conducted on interaction logs, including patient and attendant questions, chatbot answers, and expert verifications.\n <\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n A total of 318 patients and attendants sent 1,992 messages, and LLM-generated answers were verified by five doctors and two coordinators. Questions asked pre-surgery were significantly more than post-surgery\n \n \n (<\/mml:mo>\n p<\/mml:mi>\n <<\/mml:mo>\n 0.001<\/mml:mn>\n )<\/mml:mo>\n <\/mml:math>\n <\/jats:inline-formula>\n . Participants asked significantly more medical than logistical questions\n \n \n (<\/mml:mo>\n \n t<\/mml:mi>\n 309<\/mml:mn>\n <\/mml:msub>\n =<\/mml:mo>\n 7.3<\/mml:mn>\n ,<\/mml:mo>\n p<\/mml:mi>\n <<\/mml:mo>\n 0.001<\/mml:mn>\n )<\/mml:mo>\n <\/mml:math>\n <\/jats:inline-formula>\n . Doctors rated 84.5% of\n CataractBot<\/jats:italic>\n \u2019s answers to medical questions as accurate and complete. Their edits, which mainly involved adding information, increased the acceptance of the bot\u2019s answers by 19.0% over time.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusion<\/jats:title>\n \n CataractBot<\/jats:italic>\n was predominantly used to address medical questions. It incorporated expert corrections to improve its answers and reduce the experts\u2019 bot-related workload over time. This study highlights the potential of LLM-powered chatbots to support patient-provider communication in ophthalmology.\n <\/jats:p>\n <\/jats:sec>","DOI":"10.1177\/11206721251396664","type":"journal-article","created":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T15:11:24Z","timestamp":1765206684000},"page":"561-568","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":1,"title":["Utility of an LLM-powered experts-in-the-loop chatbot for pre- and post-operative care of cataract surgery patients"],"prefix":"10.1177","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-1946-684X","authenticated-orcid":false,"given":"Bhuvan","family":"Sachdeva","sequence":"first","affiliation":[{"name":"Microsoft Research"},{"name":"Sankara Eye Hospital"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0061-2624","authenticated-orcid":false,"given":"Pragnya","family":"Ramjee","sequence":"additional","affiliation":[{"name":"Microsoft Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7533-1794","authenticated-orcid":false,"given":"Rahul","family":"Sharma","sequence":"additional","affiliation":[{"name":"Microsoft Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0623-4612","authenticated-orcid":false,"given":"Mithun","family":"Thulasidas","sequence":"additional","affiliation":[{"name":"Sankara Eye Hospital"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1037-3583","authenticated-orcid":false,"given":"Sowmya","family":"Raveendra Murthy","sequence":"additional","affiliation":[{"name":"Sankara Eye Hospital"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2358-810X","authenticated-orcid":false,"given":"Geeta","family":"Fulari","sequence":"additional","affiliation":[{"name":"Sankara Eye Hospital"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1385-3227","authenticated-orcid":false,"given":"Kaushik","family":"Murali","sequence":"additional","affiliation":[{"name":"Sankara Eye Hospital"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7106-164X","authenticated-orcid":false,"given":"Mohit","family":"Jain","sequence":"additional","affiliation":[{"name":"Microsoft Research"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2025,12,8]]},"reference":[{"key":"e_1_3_4_2_2","article-title":"ChatGPT is the fastest-growing app in the history of web applications","author":"Gordon C","year":"2023","unstructured":"Gordon C. ChatGPT is the fastest-growing app in the history of web applications. Forbes 2023. https:\/\/www.forbes.com\/sites\/cindygordon\/2023\/02\/02\/chatgpt-is-the-fastest-growing-ap-in-the\/-history-of-web-applications\/.","journal-title":"Forbes"},{"key":"e_1_3_4_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3659625"},{"key":"e_1_3_4_4_2","doi-asserted-by":"publisher","DOI":"10.1177\/11206721241272251"},{"key":"e_1_3_4_5_2","doi-asserted-by":"publisher","DOI":"10.1177\/11206721251321197"},{"key":"e_1_3_4_6_2","first-page":"112067212513372","article-title":"Evaluating the novel role of ChatGPT-4 in addressing corneal ulcer queries: An AI-powered insight","volume":"0","author":"Gurnani B","year":"2025","unstructured":"Gurnani B, Kaur K, Gireesh P, et al. Evaluating the novel role of ChatGPT-4 in addressing corneal ulcer queries: An AI-powered insight. Eur J Ophthalmol 2025; 0: 11206721251337290.","journal-title":"Eur J Ophthalmol"},{"key":"e_1_3_4_7_2","unstructured":"Sharma R Ramjee P Murali K et al. Editing with AI: How doctors refine LLM-generated answers to patient queries. In: The second workshop on GenAI for health: Potential trust and policy compliance. https:\/\/openreview.net\/forum?id=WyaJ7jBTed."},{"key":"e_1_3_4_8_2","doi-asserted-by":"crossref","unstructured":"Danilov G Kotik K Shevchenko E et al. Length of stay prediction in neurosurgery with Russian GPT-3 language model compared to human expectations. In: Informatics and technology in clinical care and public health 2022 pp.156\u2013159. IOS press.","DOI":"10.3233\/SHTI210882"},{"key":"e_1_3_4_9_2","first-page":"112067212513183","article-title":"Artificial intelligence in the diagnosis and management of refractive errors","volume":"0","author":"Nguyen T","year":"2025","unstructured":"Nguyen T, Ong J, Jonnakuti V, et al. Artificial intelligence in the diagnosis and management of refractive errors. Eur J Ophthalmol 2025; 0: 11206721251318384.","journal-title":"Eur J Ophthalmol"},{"key":"e_1_3_4_10_2","doi-asserted-by":"publisher","DOI":"10.1177\/11206721211073442"},{"key":"e_1_3_4_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2022.104864"},{"key":"e_1_3_4_12_2","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.210258"},{"key":"e_1_3_4_13_2","doi-asserted-by":"publisher","DOI":"10.1177\/11206721231215862"},{"key":"e_1_3_4_14_2","doi-asserted-by":"crossref","unstructured":"Ramjee P Chhokar M Sachdeva B et al. ASHABot: An LLM-powered chatbot to support the informational needs of community health workers. In: Proceedings of the 2025 CHI conference on human factors in computing systems. CHI \u201925 New York NY USA: Association for Computing Machinery. DOI: https:\/\/doi.org\/10.1145\/3706598.3713680.","DOI":"10.1145\/3706598.3713680"},{"key":"e_1_3_4_15_2","doi-asserted-by":"publisher","DOI":"10.3389\/fdgth.2023.1161098"},{"key":"e_1_3_4_16_2","doi-asserted-by":"publisher","DOI":"10.2196\/52399"},{"key":"e_1_3_4_17_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-017-0012-2"},{"key":"e_1_3_4_18_2","unstructured":"Microsoft. BYOeB: Build Your Own expert Bot. https:\/\/github.com\/microsoft\/byoeb (2024 accessed 18 June 2024)."},{"key":"e_1_3_4_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3729479"},{"key":"e_1_3_4_20_2","doi-asserted-by":"crossref","unstructured":"Dell N Vaidyanathan V Medhi I et al. \u201cYours is better!\u201d: Participant response bias in HCI. In: Proceedings of the SIGCHI conference on human factors in computing systems CHI \u201912 2012 pp.1321\u20131330. New York NY USA: Association for Computing Machinery. DOI: https:\/\/doi.org\/10.1145\/2207676.2208589.","DOI":"10.1145\/2207676.2208589"},{"key":"e_1_3_4_21_2","doi-asserted-by":"crossref","unstructured":"Ayala O Bechard P. Reducing hallucination in structured outputs via retrieval-augmented generation. In: Proceedings of the 2024 conference of the north american chapter of the association for computational linguistics: Human language technologies (Volume 6: Industry Track) 2024 p.228\u2013238. Association for Computational Linguistics. DOI: 10.18653\/v1\/2024.naacl-industry.19.","DOI":"10.18653\/v1\/2024.naacl-industry.19"},{"key":"e_1_3_4_22_2","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2023.30320"},{"key":"e_1_3_4_23_2","doi-asserted-by":"publisher","DOI":"10.1136\/bmjophth-2024-001824"},{"key":"e_1_3_4_24_2","doi-asserted-by":"publisher","DOI":"10.1007\/s40123-024-01066-y"},{"key":"e_1_3_4_25_2","article-title":"Large language models and their impact in ophthalmology","volume":"5","author":"Betzler BK","year":"2023","unstructured":"Betzler BK, Chen H, Cheng CY, et al. Large language models and their impact in ophthalmology. Lancet Digit Health 2023; 5: e917\u2013e924.","journal-title":"Lancet Digit Health"},{"key":"e_1_3_4_26_2","doi-asserted-by":"publisher","DOI":"10.1097\/j.jcrs.0000000000001622"},{"key":"e_1_3_4_27_2","doi-asserted-by":"publisher","DOI":"10.3390\/jpm13121679"}],"container-title":["European Journal of Ophthalmology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/11206721251396664","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/11206721251396664","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/11206721251396664","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T19:41:56Z","timestamp":1777405316000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/11206721251396664"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":26,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,5]]}},"alternative-id":["10.1177\/11206721251396664"],"URL":"https:\/\/doi.org\/10.1177\/11206721251396664","relation":{},"ISSN":["1120-6721","1724-6016"],"issn-type":[{"value":"1120-6721","type":"print"},{"value":"1724-6016","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,8]]}}}