[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123930-en":3,"doc-seo-123930-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},123930,5909877438554,"Maeve","https://ap-avatar.wpscdn.com/avatar/5600025385ad2bf12a7?_k=1778553567797529272",8,"Research & Report","Predicting Choroidal Nevus Transformation to Melanoma Using Machine Learning","Purpose: develop and validate machine learning models to predict choroidal nevus transformation to melanoma using multimodal imaging at initial presentation. Design: retrospective multicenter study with internal training and testing (80%/20%) and external validation between Wills Eye Hospital and Mayo Clinic Rochester cohorts. Methods: fundus photography, fundus autofluorescence, spectral domain OCT, and B-scan ultrasonography; models (XGBoost, LGBM, Random Forest, Extra Tree) evaluated by AUROC and AUPRC, with SHAP interpretation of conversion features. Conclusions: demonstrates accurate, generalizable prediction and identifies top predictive imaging features.","Thomas Jefferson University  \nJefferson Digital Commons  \n\n| Wills Eye Hospital Papers | Wills Eye Hospital |\n| --- | --- |\n| 7-20-2024\u003Cbr>Predicting Choroidal Nevus Transformation to Melanoma Using Machine Learning\u003Cbr>Prashant D. Tailor Piotr K. Kopinski Haley S. D'Souza David A. Leske Timothy W. Olsen\u003Cbr>See next page for additional authors\u003Cbr>Follow this and additional works at: [https://jdc.jefferson.edu/willsfp](https://jdc.jefferson.edu/willsfp)\u003Cbr> Part of the Artificial Intelligence and Robotics Commons, Ophthalmology Commons, and the Theory and Algorithms Commons\u003Cbr>Let us know how access to this document benefits you |  |\n\nThis Article is brought to you for free and open access by the Jefferson Digital Commons. The Jefferson Digital Commons is a service of Thomas Jefferson University's Center for Teaching and Learning (CTL) . The Commons is a showcase for Jefferson books and journals, peer-reviewed scholarly publications, unique historical collections from the University archives, and teaching tools. The Jefferson Digital Commons allows researchers and interested readers anywhere in the world to learn about and keep up to date with Jefferson scholarship. This article has been accepted for inclusion in Wills Eye Hospital Papers by an authorized administrator of the Jefferson Digital Commons. For more information, please contact: [JeffersonDigitalCommons@jefferson.edu](JeffersonDigitalCommons@jefferson.edu).  \nAuthors  \nPrashant D. Tailor, Piotr K. Kopinski, Haley S. D'Souza, David A. Leske, Timothy W. Olsen, Carol L. Shields, Jerry A. Shields, and Lauren A. Dalvin  \nPredicting Choroidal Nevus Transformation to Melanoma Using Machine Learning  \nPrashant D. Tailor, MD, Timothy W. Olsen, MD,  \n1 1  \nPiotr K. Kopinski, MD, PhD, 1 Haley S. D’Souza, MD, 1 David A. Leske, MS, 1 Carol L. Shields, MD,2 Jerry A. Shields, MD,2 Lauren A. Dalvin, MD 1  \nPurpose: To develop and validate machine learning (ML) models to predict choroidal nevus transformation to melanoma based on multimodal imaging at initial presentation.  \nDesign: Retrospective multicenter study.  \nParticipants: Patients diagnosed with choroidal nevus on the Ocular Oncology Service at Wills Eye Hospital (2007e2017) or Mayo Clinic Rochester (2015e2023) .  \nMethods: Multimodal imaging was obtained, including fundus photography, fundus autofluorescence, spectral domain OCT, and B-scan ultrasonography. Machine learning models were created (XGBoost, LGBM, Random Forest, Extra Tree) and optimized for area under receiver operating characteristic curve (AUROC) . The Wills Eye Hospital cohort was used for training and testing (80% traininge20% testing) with fivefold cross validation. The Mayo Clinic cohort provided external validation. Model performance was characterized by AUROC and area under precisionerecall curve (AUPRC) . Models were interrogated using SHapley Additive exPlanations (SHAP) to identify the features most predictive of conversion from nevus to melanoma. Differences in AUROC and AUPRC between models were tested using 10 000 bootstrap samples with replacement and results.  \nMain Outcome Measures: Area under receiver operating curve and AUPRC for each ML model.  \nResults: There were 2870 nevi included in the study, with conversion to melanoma confirmed in 128 cases. Simple AI Nevus Transformation System (SAINTS; XGBoost) was the top-performing model in the test cohort [pooled AUROC 0.864 (95% confidence interval (CI): 0.864e0.865), pooled AUPRC 0.244 (95% CI: 0.243e0.246)] and in the external validation cohort [pooled AUROC 0.931 (95% CI: 0.930e0.931), pooled AUPRC 0.533 (95% CI: 0.531e0.535)] . Other models also had good discriminative performance: LGBM (test set pooled AUROC 0.831, validation set pooled AUROC 0.815), Random Forest (test set pooled AUROC 0.812, validation set pooled AUROC 0 .866), and Extra Tree (test set pooled AUROC 0 .826, validation set pooled AUROC 0 .915) . A model including only nevi with at least 5 years of follow-up demonstrated the best","cbCaicMotNsvWJJR","https://ap.wps.com/l/cbCaicMotNsvWJJR","pdf",1869458,1,15,"English","en",105,"# Purpose\n# Design\n# Participants\n# Methods\n# Main Outcome Measures\n# Results\n# Conclusions","[{\"question\":\"What was the study’s primary purpose?\",\"answer\":\"To develop and validate machine learning models that predict choroidal nevus transformation to melanoma using multimodal imaging at initial presentation.\"},{\"question\":\"Which imaging modalities were used to build the models?\",\"answer\":\"The study used fundus photography, fundus autofluorescence, spectral domain OCT, and B-scan ultrasonography.\"},{\"question\":\"How was model performance evaluated and validated?\",\"answer\":\"Models were assessed using AUROC and AUPRC, trained and tested with fivefold cross validation in the Wills Eye Hospital cohort, and then externally validated using the Mayo Clinic cohort.\"}]","Predicting Choroidal Nevus Transformation to Melanoma Using Machine Learning | PDF",1785819299,38,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"predicting-choroidal-nevus-transformation-to-melanoma-using-machine-learning","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/predicting-choroidal-nevus-transformation-to-melanoma-using-machine-learning/123930/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What was the study’s primary purpose?","Question",{"text":75,"@type":76},"To develop and validate machine learning models that predict choroidal nevus transformation to melanoma using multimodal imaging at initial presentation.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which imaging modalities were used to build the models?",{"text":80,"@type":76},"The study used fundus photography, fundus autofluorescence, spectral domain OCT, and B-scan ultrasonography.",{"name":82,"@type":73,"acceptedAnswer":83},"How was model performance evaluated and validated?",{"text":84,"@type":76},"Models were assessed using AUROC and AUPRC, trained and tested with fivefold cross validation in the Wills Eye Hospital cohort, and then externally validated using the Mayo Clinic cohort.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]