[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127770-en":3,"doc-seo-127770-105":30,"detail-sidebar-cat-0-en-105":92},{"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":20,"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},127770,1099523882182,"Eliana","https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8",8,"Research & Report","Performance of Automated Machine Learning in Predicting Outcomes of Pneumatic Retinopexy - Research","Automated machine learning (AutoML) is evaluated as an accessible approach for clinicians without coding expertise to predict treatment outcomes in pneumatic retinopexy (PR) for rhegmatogenous retinal detachment (RRD). A retrospective multicenter study analyzes 539 consecutive primary RRD patients treated across six training hospitals from 2002 to 2022. Two AutoML platforms (MATLAB Classification Learner and Google Cloud AutoML) are compared with custom ML models. Model performance is assessed using F2 score and AUROC, highlighting reliable results with balanced data and misleading metrics under data imbalance.","Thomas Jefferson University  \nJefferson Digital Commons  \n\n| Wills Eye Hospital Papers | Wills Eye Hospital |\n| --- | --- |\n| 1-19-2024\u003Cbr>Performance of Automated Machine Learning in Predicting Outcomes of Pneumatic Retinopexy\u003Cbr>Arina Nisanova\u003Cbr>Arefeh Yavary Jordan Deaner\u003Cbr>Thomas Jefferson University Ferhina Ali\u003Cbr>Priyanka Gogte\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 Health Services Research Commons, and the Ophthalmology Commons\u003Cbr>Let us know how access to this document benefits you |  |\n\nRecommended Citation  \nNisanova, Arina; Yavary, Arefeh; Deaner, Jordan; Ali, Ferhina; Gogte, Priyanka; Kaplan, Richard; Chen, Kevin; Nudleman, Eric; Grewal, Dilraj; Gupta, Meenakashi; Wolfe, Jeremy; Klufas, Michael; Yiu, Glenn; Soltani, Iman; and Emami-Naeini, Parisa, \"Performance of Automated Machine Learning in Predicting Outcomes of Pneumatic Retinopexy \" (2024) . Wills Eye Hospital Papers. Paper 221.  \n[https://jdc.jefferson.edu/willsfp/221](https://jdc.jefferson.edu/willsfp/221)  \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  \nArina Nisanova, Arefeh Yavary, Jordan Deaner, Ferhina Ali, Priyanka Gogte, Richard Kaplan, Kevin Chen, Eric Nudleman, Dilraj Grewal, Meenakashi Gupta, Jeremy Wolfe, Michael Klufas, Glenn Yiu, Iman Soltani, and Parisa Emami-Naeini  \nThis article is available at Jefferson Digital Commons: [https://jdc.jefferson.edu/willsfp/221](https://jdc.jefferson.edu/willsfp/221)  \nPerformance of Automated Machine Learning in Predicting Outcomes of Pneumatic Retinopexy  \nArina Nisanova, BA, 1 Arefeh Yavary, MSc,2 Jordan Deaner, MD,3 Ferhina S. Ali, MD, MPH,4 Priyanka Gogte, MD,5 Richard Kaplan, MD,6 Kevin C. Chen, MD,7 Eric Nudleman, MD, PhD,8 Dilraj Grewal, MD,9 Meenakashi Gupta, MD,6 Jeremy Wolfe, MD,5 Michael Klufas, MD, 10 Glenn Yiu, MD, PhD, 11 Iman Soltani, PhD, 12 Parisa Emami-Naeini, MD, MPH 11  \nPurpose: Automated machine learning (AutoML) has emerged as a novel tool for medical professionals lacking coding experience, enabling them to develop predictive models for treatment outcomes. This study evaluated the performance of AutoML tools in developing models predicting the success of pneumatic retinopexy (PR) in treatment of rhegmatogenous retinal detachment (RRD) . These models were then compared with custom models created by machine learning (ML) experts.  \nDesign: Retrospective multicenter study.  \nParticipants: Five hundred and thirty nine consecutive patients with primary RRD that underwent PR by avitreoretinal fellow at 6 training hospitals between 2002 and 2022 .  \nMethods: We used 2 AutoML platforms: MATLAB Classification Learner and Google Cloud AutoML. Additional models were developed by computer scientists. We included patient demographics and baseline characteristics, including lens and macula status, RRD size, number and location of breaks, presence of vitreous hemorrhage and lattice degeneration, and physicians’ experience. The dataset was split into a training (n ¼ 483) and test set (n ¼ 56) . The training set, with a 2:1 success-to-failure ratio, was used to train the MATLAB models. Because Google Cloud AutoML requires a min","cbCaisTi3s7JSCbe","https://ap.wps.com/l/cbCaisTi3s7JSCbe","pdf",576175,1,12,"English","en",105,"# Study purpose\n## Study design and participants\n## Methods and datasets\n## Outcome measures and metrics\n## Results and conclusions","[{\"question\":\"What was the purpose of using AutoML in this study?\",\"answer\":\"To evaluate how well AutoML tools can build predictive models for the success of pneumatic retinopexy in patients with rhegmatogenous retinal detachment.\"},{\"question\":\"How was model performance measured and compared?\",\"answer\":\"Performance was compared using F2 scores and AUROC to evaluate the predicted single-procedure anatomic success rate against custom ML models.\"},{\"question\":\"What effect did dataset imbalance have on AutoML results?\",\"answer\":\"Imbalanced training data produced misleadingly high AUROC despite very low F2 score and sensitivity, indicating unreliable outcome predictions without proper data handling.\"}]","Performance of Automated Machine Learning in Predicting Outcomes of Pneumatic Retinopexy - Research | PDF",1785941516,30,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"performance-of-automated-machine-learning-in-predicting-outcomes-of-pneumatic-retinopexy-research","",{"@graph":36,"@context":86},[37,54,69],{"@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/performance-of-automated-machine-learning-in-predicting-outcomes-of-pneumatic-retinopexy-research/127770/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-22","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What was the purpose of using AutoML in this study?","Question",{"text":76,"@type":77},"To evaluate how well AutoML tools can build predictive models for the success of pneumatic retinopexy in patients with rhegmatogenous retinal detachment.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How was model performance measured and compared?",{"text":81,"@type":77},"Performance was compared using F2 scores and AUROC to evaluate the predicted single-procedure anatomic success rate against custom ML models.",{"name":83,"@type":74,"acceptedAnswer":84},"What effect did dataset imbalance have on AutoML results?",{"text":85,"@type":77},"Imbalanced training data produced misleadingly high AUROC despite very low F2 score and sensitivity, indicating unreliable outcome predictions without proper data handling.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":29,"slug":122},"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":107,"slug":138},19,"General","general"]