[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127678-en":3,"doc-seo-127678-105":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},127678,962084925782,"Ava Thompson","https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc",8,"Research & Report","Clinical performance of automated machine learning - A systematic review","Automated machine learning (autoML) lowers technical barriers to building artificial intelligence models, enabling broader clinical adoption. A systematic review summarizes clinical applications of autoML, evaluates capabilities of the tested platforms, and assesses the quality of evidence from trials using autoML compared with conventional models. Searches in major databases (from inception to 11 July 2022) identified 26 platforms across 82 studies, reporting highly variable performance and generally poor reporting quality.","Ann Acad Med Singap 2024;53:Online First [https://doi.org/10.47102/annals-acadmedsg.2023113](https://doi.org/10.47102/annals-acadmedsg.2023113)  \nREVIEW ARTICLE  \nClinical performance of automated machine learning:  \nA systematic review  \nArun James Thirunavukarasu*1,2 MB BChir, Kabilan Elangovan1 BEng, Laura Gutierrez1 MD, Refaat Hassan2 MB BChir, Yong Li1,3 MD, Ting Fang Tan1 MBBS, Haoran Cheng1,3,4 MPH, Zhen Ling Teo5 FRCOphth, Gilbert Lim1 PhD, Daniel Shu Wei Ting*1,3,5 PhD  \nABSTRACT  \nIntroduction: Automated machine learning (autoML) removes technical and technological barriers to building artificial intelligence models. We aimed to summarise the clinical applications of autoML, assess the capabilities of utilised platforms, evaluate the quality of the evidence trialling autoML, and gauge the performance of autoML platforms relative to conventionally developed models, as well as eachother.  \nMethod: This review adhered to prospectively registered protocol (PROSPERO identifier CRD42022344427) . The Cochrane Library, Embase, MEDLINE and Scopus were searched from inception to 11 July 2022. Two researchers screened abstractsand full texts, extracted data and conducted quality assessment. Disagreement was resolved through discussion and if required, arbitration by a third researcher.  \nResults: There were 26 distinct autoML platforms featured in 82 studies. Brain and lung disease were the most common fields of study of 22 specialties. AutoML exhibited variable performance: area under the receiver operator characteristic curve (AUCROC) 0.35–1. 00, F1-score 0.16–0. 99, area under the precision-recall curve (AUPRC) 0.51–1.00. AutoML exhibited the highest AUCROC in 75.6% trials; the highest F1-score in 42.3% trials; and the highest AUPRC in 83.3% trials. In auto ML platform comparisons, AutoPrognosis and Amazon Rekognition performed strongest with unstructured and structured data, respectively. Quality of reporting was poor, with a median DECIDE-AI score of 14 of 27.  \nConclusion: A myriad of autoML platforms have been applied in a variety of clinical contexts. The performance of autoML compares well to bespoke computational and clinical benchmarks. Further work is required to improve the quality of validation studies. AutoML may facilitate a transition to data-centric development, and integration with large language  \nmodels may enable AI to build itself to fulfil userdefined goals.  \nAnn Acad Med Singap 2024;53:Online First  \nKeywords: AI, artificial intelligence, automated machine learning, autoML, machine learning, deep learning  \nCLINICAL IMPACT  \nWhat is New  \n• This systematic review identified 26 distinct autoML platforms that have been trialled and/or applied in a clinical context.  \n• AutoML exhibited variable performance; in head-to-head comparisons, AutoPrognosis and Amazon Rekognition performed the strongest with unstructured and structured  \ndata, respectively.  \nClinical Implications  \n• The performance of autoML compares well tobespoke computational and clinical benchmarks across clinical tasks ranging from diagnosis to prognostication.  \n• Exemplar use cases include identifying pathology on common imaging modalities (e.g. chest X-ray) and predicting hospitalisation and mortality based on tabulated demographics and blood test results.  \n• AutoML may facilitate a transition from model-centric to data-centric development, and integration with large language models may enable automated development of AI applications to fulfil user-defined goals.  \nThe Annals is an open access journal, allowing non-commercial use under CC BY-NC-SA 4.0.  \n1 Artificial Intelligence and Digital Innovation Research Group, Singapore Eye Research Institute, Singapore  \n2 University of Cambridge School of Clinical Medicine, University of Cambridge, Cambridge, United Kingdom  \n3 Duke-NUS Medical School, National University of Singapore, Singapore  \n4 Rollins School of Public Health, Emory University, Atlanta, Georgia, USA  \n5 Singapore Nation","cbCaitUjrDAFzzQQ","https://ap.wps.com/l/cbCaitUjrDAFzzQQ","pdf",962219,1,21,"English","en",105,"# Abstract\n## Introduction\n## Method\n## Results\n## Clinical Impact\n## Introduction\n## Method\n## Results\n## Conclusion","[{\"question\":\"What clinical areas were most frequently studied using autoML?\",\"answer\":\"Brain and lung diseases were the most common fields of study across 22 specialties included in the review.\"},{\"question\":\"How did autoML performance compare across different evaluations?\",\"answer\":\"Performance varied widely, with reported AUCROC ranging from 0.35 to 1.00, F1-score from 0.16 to 0.99, and AUPRC from 0.51 to 1.00, with different platforms achieving the best metrics in different proportions of trials.\"},{\"question\":\"Which platforms showed stronger performance in comparisons, and what about reporting quality?\",\"answer\":\"AutoPrognosis and Amazon Rekognition performed strongest for unstructured and structured data respectively. Reporting quality was poor, with a median DECIDE-AI score of 14 out of 27.\"}]","Clinical performance of automated machine learning - A systematic review | PDF",1785940765,53,{"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},"clinical-performance-of-automated-machine-learning-a-systematic-review","",{"@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/clinical-performance-of-automated-machine-learning-a-systematic-review/127678/",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","2026-08-23","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 clinical areas were most frequently studied using autoML?","Question",{"text":76,"@type":77},"Brain and lung diseases were the most common fields of study across 22 specialties included in the review.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How did autoML performance compare across different evaluations?",{"text":81,"@type":77},"Performance varied widely, with reported AUCROC ranging from 0.35 to 1.00, F1-score from 0.16 to 0.99, and AUPRC from 0.51 to 1.00, with different platforms achieving the best metrics in different proportions of trials.",{"name":83,"@type":74,"acceptedAnswer":84},"Which platforms showed stronger performance in comparisons, and what about reporting quality?",{"text":85,"@type":77},"AutoPrognosis and Amazon Rekognition performed strongest for unstructured and structured data respectively. Reporting quality was poor, with a median DECIDE-AI score of 14 out of 27.","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},[94,98,102,106,111,116,121,124,129,132,136],{"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":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]