<HashMap><database>biostudies-literature</database><scores/><additional><omics_type>Unknown</omics_type><volume>15(2)</volume><submitter>Xiong J</submitter><pubmed_abstract>&lt;h4>Purpose&lt;/h4>To develop and validate a machine learning system for the preoperative prediction of small effective optical zone (EOZ; diameter &lt; 5.5 mm) after small incision lenticule extraction (SMILE).&lt;h4>Methods&lt;/h4>In this multicenter cohort study, 1030 multimodal combinations of preoperative parameters (PP), anterior corneal curvature maps (AACM), surgery video frames, and three-month postoperative EOZ diameter from 1030 eyes (634 patients) undergoing SMILE were divided: 677 for training, 85 for primary validation, 85 for internal test, and 183 for external test. The AACM-PP-Model integrating AACM and PP was developed and compared against parameter-only or image-only models, with primary performance evaluated by the area under the receiver operating characteristic curve (AUROC) and </pubmed_abstract><journal>Translational vision science &amp; technology</journal><pagination>26</pagination><full_dataset_link>https://www.ebi.ac.uk/biostudies/studies/S-EPMC12927424</full_dataset_link><repository>biostudies-literature</repository><pubmed_title>Predicting Small Effective Optical Zone After SMILE via Multimodal Machine Learning Integrating Corneal Topography and Clinical Parameters.</pubmed_title><pmcid>PMC12927424</pmcid><pubmed_authors>Li W</pubmed_authors><pubmed_authors>Xiong J</pubmed_authors><pubmed_authors>Huang F</pubmed_authors><pubmed_authors>Ai C</pubmed_authors><pubmed_authors>Ma L</pubmed_authors><pubmed_authors>Zhang X</pubmed_authors><pubmed_authors>Ling L</pubmed_authors><pubmed_authors>Gao W</pubmed_authors><pubmed_authors>Dai D</pubmed_authors><pubmed_authors>Cen G</pubmed_authors><pubmed_authors>Gui F</pubmed_authors></additional><is_claimable>false</is_claimable><name>Predicting Small Effective Optical Zone After SMILE via Multimodal Machine Learning Integrating Corneal Topography and Clinical Parameters.</name><description>&lt;h4>Purpose&lt;/h4>To develop and validate a machine learning system for the preoperative prediction of small effective optical zone (EOZ; diameter &lt; 5.5 mm) after small incision lenticule extraction (SMILE).&lt;h4>Methods&lt;/h4>In this multicenter cohort study, 1030 multimodal combinations of preoperative parameters (PP), anterior corneal curvature maps (AACM), surgery video frames, and three-month postoperative EOZ diameter from 1030 eyes (634 patients) undergoing SMILE were divided: 677 for training, 85 for primary validation, 85 for internal test, and 183 for external test. The AACM-PP-Model integrating AACM and PP was developed and compared against parameter-only or image-only models, with primary performance evaluated by the area under the receiver operating characteristic curve (AUROC) and </description><dates><release>2026-01-01T00:00:00Z</release><publication>2026 Feb</publication><modification>2026-07-16T17:45:16.025Z</modification><creation>2026-07-09T11:09:44.542Z</creation></dates><accession>S-EPMC12927424</accession><cross_references><pubmed>41718660</pubmed><doi>10.1167/tvst.15.2.26</doi></cross_references></HashMap>