{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T09:10:10Z","timestamp":1790327410888,"version":"4.1.0"},"reference-count":25,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T00:00:00Z","timestamp":1790294400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Clin. Med.","JCM"],"abstract":"<jats:p>Objectives: To evaluate a general-purpose large language model (LLM)\u2019s ability to perform surgeon-level decision-making in choosing an intraocular lens (IOL) power when provided the same preoperative data. Methods: This study included 293 eyes (174 patients) that underwent monofocal or toric cataract surgery performed by a single surgeon. GPT-5.2 analyzed the same biometric printouts, topographic displays, and preoperative data used in surgical planning. Postoperative refraction for GPT-5.2-selected IOLs was simulated from the measured postoperative refraction using a fixed conversion factor. The mean refractive deviation from target, mean absolute error (MAE), and number of eyes within \u00b10.25 D and \u00b10.50 D of target refraction were calculated. A subgroup analysis evaluated toric IOL cylinder magnitude and axis. Results: GPT-5.2-selected IOL power differed significantly from that of the surgeon (19.24 \u00b1 4.01 vs. 19.64 \u00b1 4.07 D [mean \u00b1 SD], p &lt; 0.001). Using simulated refractive outcomes for GPT-5.2, MAE was higher than for surgeon-selected IOLs (0.45 \u00b1 0.03 vs. 0.35 \u00b1 0.02 D [mean \u00b1 SE], p = 0.002), and a greater percentage of eyes fell within \u00b10.25 D of target refraction for the surgeon (51.9% vs. 44.7%, p &lt; 0.01), with no difference within \u00b10.50 D (p = 0.06). In toric eyes, the cylinder magnitude did not differ, but simulated residual astigmatism was higher for GPT-5.2 (0.78 \u00b1 0.55 vs. 0.58 \u00b1 0.47 D, p &lt; 0.001), with an axis flip in 47.1% versus 39.2% of eyes. Conclusions: GPT-5.2 synthesized clinical data and approximated surgeon IOL selection, but its simulated refractive outcomes were less accurate than the surgeon\u2019s measured outcomes. These findings suggest that a domain-specific LLM may serve as a support tool in IOL selection and cataract surgery planning.<\/jats:p>","DOI":"10.3390\/jcm15197463","type":"journal-article","created":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T08:09:02Z","timestamp":1790323742000},"page":"7463","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Retrospective Assessment of LLM Decision-Making for IOL Power Selection in Cataract Surgery in Comparison with Surgeon Performance"],"prefix":"10.3390","volume":"15","author":[{"given":"Randle M.","family":"Uyeda","sequence":"first","affiliation":[{"name":"College of Medicine\u2014Phoenix, University of Arizona, Phoenix, AZ 85004, USA"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"}]},{"given":"Josh","family":"Zhe","sequence":"additional","affiliation":[{"name":"College of Medicine\u2014Phoenix, University of Arizona, Phoenix, AZ 85004, USA"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"}]},{"given":"Mina M.","family":"Sitto","sequence":"additional","affiliation":[{"name":"John A. Moran Eye Center, University of Utah Health, Salt Lake City, UT 84132, USA"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4984-3348","authenticated-orcid":false,"given":"Sanjana","family":"Molleti","sequence":"additional","affiliation":[{"name":"Hoopes Moshirfar Research Center, Hoopes Vision, Draper, UT 84020, USA"},{"name":"Department of Ophthalmology and Visual Neurosciences, University of Minnesota, Minneapolis, MN 55455, USA"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"}]},{"given":"Hanna","family":"Pawlowski","sequence":"additional","affiliation":[{"name":"Hoopes Moshirfar Research Center, Hoopes Vision, Draper, UT 84020, USA"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2567-8331","authenticated-orcid":false,"given":"Phillip C.","family":"Hoopes","sequence":"additional","affiliation":[{"name":"Hoopes Moshirfar Research Center, Hoopes Vision, Draper, UT 84020, USA"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1024-6250","authenticated-orcid":false,"given":"Majid","family":"Moshirfar","sequence":"additional","affiliation":[{"name":"John A. Moran Eye Center, University of Utah Health, Salt Lake City, UT 84132, USA"},{"name":"Hoopes Moshirfar Research Center, Hoopes Vision, Draper, UT 84020, USA"},{"name":"Utah Lions Eye Bank, Murray, UT 84107, USA"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,25]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1097\/j.jcrs.0000000000001804","article-title":"Spherical equivalent prediction analysis in intraocular lens power calculations using Barrett Universal II formula variations","volume":"52","author":"Figueiredo","year":"2026","journal-title":"J. Cataract Refract. Surg."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"e1240","DOI":"10.3928\/1081597X-20250826-04","article-title":"Impact of Biometric Parameters on the Predictive Accuracy of Intraocular Lens Power Calculation Formulas Included in the ESCRS IOL Power Calculator","volume":"41","author":"Skrzypecki","year":"2025","journal-title":"J. Refract. Surg."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1186\/s40662-021-00265-z","article-title":"Machine learning adaptation of intraocular lens power calculation for a patient group","volume":"8","author":"Mori","year":"2021","journal-title":"Eye Vis."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"368","DOI":"10.1016\/j.jcrs.2007.10.031","article-title":"Sources of error in intraocular lens power calculation","volume":"34","author":"Norrby","year":"2008","journal-title":"J. Cataract Refract. Surg."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"472","DOI":"10.1111\/j.1755-3768.2007.00879.x","article-title":"Calculation of intraocular lens power: A review","volume":"85","author":"Olsen","year":"2007","journal-title":"Acta Ophthalmol. Scand."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1097\/j.jcrs.0000000000000370","article-title":"Review and recommendations for univariate statistical analysis of spherical equivalent prediction error for IOL power calculations","volume":"47","author":"Holladay","year":"2021","journal-title":"J. Cataract Refract. Surg."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"e115","DOI":"10.1016\/j.ophtha.2020.07.005","article-title":"Update on Intraocular Lens Power Calculation Study Protocols: The Better Way to Design and Report Clinical Trials","volume":"128","author":"Hoffer","year":"2021","journal-title":"Ophthalmology"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Ottonelli, G., De Rosa, G., Celada Ballanti, J., Gaeta, A., Vinciguerra, P., and Di Maria, A. (2025). Does DeepSeek Provide Clinically Acceptable Intraocular Lens (IOL) Power Predictions in Cataract Surgery? A Proof-of-Concept Study. J. Clin. Med., 14.","DOI":"10.3390\/jcm14248870"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"100324","DOI":"10.1016\/j.xops.2023.100324","article-title":"Evaluating the Performance of ChatGPT in Ophthalmology: An Analysis of Its Successes and Shortcomings","volume":"3","author":"Antaki","year":"2023","journal-title":"Ophthalmol. Sci."},{"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","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1136\/bjophthalmol-2018-313173","article-title":"Artificial intelligence and deep learning in ophthalmology","volume":"103","author":"Ting","year":"2019","journal-title":"Br. J. Ophthalmol."},{"key":"ref_12","first-page":"351","article-title":"Using a large language model to process biometry reports and select intraocular lens for cataract surgery","volume":"51","author":"Tan","year":"2025","journal-title":"J. Cataract Refract. Surg."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Liu, Y., Zhang, C., Yuan, Y., Elken, K., Lai, J., Wen, Y., Song, L., Wang, X., Zhang, M., and Chen, Z. (2026). Assessing GPT-4o in cataract surgery decision-making: Appropriateness, consistency, and clinical implications. Front. Artif. Intell., 9.","DOI":"10.3389\/frai.2026.1810899"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"20552076261444617","DOI":"10.1177\/20552076261444617","article-title":"Comparison of three large language models in recognizing ophthalmological examination and supporting preoperative toric IOL planning","volume":"12","author":"Lin","year":"2026","journal-title":"Digit. Health"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Khan, A.M., Waldner, D.M., Luong, M., Sanders, E., Crichton, A.C.S., and Ford, B.A. (2022). Stabilization of refractive error and associated factors following small incision phacoemulsification cataract surgery. BMC Ophthalmol., 22.","DOI":"10.1186\/s12886-021-02221-w"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"e72644","DOI":"10.2196\/72644","article-title":"Prompt Engineering in Clinical Practice: Tutorial for Clinicians","volume":"27","author":"Liu","year":"2025","journal-title":"J. Med. Internet Res."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1371","DOI":"10.1136\/bjo-2023-324438","article-title":"Capabilities of GPT-4 in ophthalmology: An analysis of model entropy and progress towards human-level medical question answering","volume":"108","author":"Antaki","year":"2024","journal-title":"Br. J. Ophthalmol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"2443","DOI":"10.1016\/j.ophtha.2015.08.037","article-title":"Comparison of Newer Intraocular Lens Power Calculation Methods for Eyes after Corneal Refractive Surgery","volume":"122","author":"Wang","year":"2015","journal-title":"Ophthalmology"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"2181","DOI":"10.1016\/j.jcrs.2011.06.028","article-title":"Simulation of toric intraocular lens results: Manual keratometry versus dual-zone automated keratometry from an integrated biometer","volume":"37","author":"Hill","year":"2011","journal-title":"J. Cataract Refract. Surg."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"2080","DOI":"10.1016\/j.jcrs.2012.08.036","article-title":"Contribution of posterior corneal astigmatism to total corneal astigmatism","volume":"38","author":"Koch","year":"2012","journal-title":"J. Cataract Refract. Surg."},{"key":"ref_21","first-page":"CD015522","article-title":"Artificial intelligence for diagnosing exudative age-related macular degeneration","volume":"10","author":"Kang","year":"2024","journal-title":"Cochrane Database Syst. Rev."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Aramberri, J., Hoffer, K.J., Olsen, T., Savini, G., and Shammas, H.J. (2024). Hill-RBF: Improving IOL Power Selection by Artificial Intelligence. Intraocular Lens Calculations. Essentials in Ophthalmology, Springer International Publishing.","DOI":"10.1007\/978-3-031-50666-6"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1930","DOI":"10.1038\/s41591-023-02448-8","article-title":"Large language models in medicine","volume":"29","author":"Thirunavukarasu","year":"2023","journal-title":"Nat. Med."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1001\/jamaophthalmol.2025.2918","article-title":"DeepSeek-R1 vs. OpenAI o1 for Ophthalmic Diagnoses and Management Plans","volume":"143","author":"Mikhail","year":"2025","journal-title":"JAMA Ophthalmol."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1038\/s41591-024-03425-5","article-title":"The TRIPOD-LLM reporting guideline for studies using large language models","volume":"31","author":"Gallifant","year":"2025","journal-title":"Nat. Med."}],"container-title":["Journal of Clinical Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2077-0383\/15\/19\/7463\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T08:34:40Z","timestamp":1790325280000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2077-0383\/15\/19\/7463"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,25]]},"references-count":25,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2026,10]]}},"alternative-id":["jcm15197463"],"URL":"https:\/\/doi.org\/10.3390\/jcm15197463","relation":{},"ISSN":["2077-0383"],"issn-type":[{"value":"2077-0383","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,25]]}}}