[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-363686-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-363686-en":130},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","evaluating-the-diagnostic-accuracy-of-neural-network-models-in-detecting-oral-potentially-malignant-disorders-and-oral-cancer-using-mobile-photographs-an-umbrella-review","Evaluating the diagnostic accuracy of neural network models in detecting oral potentially malignant disorders and oral cancer using mobile photographs: An umbrella review","","Oral cancer and oral potentially malignant disorders remain major global public health challenges, especially where healthcare infrastructure is limited and timely diagnosis is constrained. Early detection improves prognosis, and AI-enabled mobile phone–based diagnostic systems provide an accessible alternative, yet comparative performance across real-world settings is uncertain. This umbrella review evaluates different AI models using six systematic reviews up to October 2024 and appraises risk of bias via Joanna Briggs Institute tools.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/evaluating-the-diagnostic-accuracy-of-neural-network-models-in-detecting-oral-potentially-malignant-disorders-and-oral-cancer-using-mobile-photographs-an-umbrella-review/363686/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/evaluating-the-diagnostic-accuracy-of-neural-network-models-in-detecting-oral-potentially-malignant-disorders-and-oral-cancer-using-mobile-photographs-an-umbrella-review/363686.png","ImageObject",300,407,{"name":42,"@type":43},"Mary Man","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-23","2026-09-23",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",8,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What is the main purpose of the umbrella review?","Question",{"text":63,"@type":64},"To evaluate and compare the diagnostic performance of different AI models for detecting oral cancer and oral potentially malignant disorders using mobile photographs.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"Which study sources and time window were included in the analysis?",{"text":68,"@type":64},"Six systematic reviews were identified from databases including Medline (via PubMed), Web of Science, Scopus, and EMBASE, covering studies up to October 2024.",{"name":70,"@type":61,"acceptedAnswer":71},"What diagnostic performance ranges were reported across included reviews?",{"text":72,"@type":64},"Pooled sensitivity and specificity for AI-based detection ranged from 88% to 92%, with diagnostic odds ratios reported from 114 to 2549.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},363686,1790655434,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,114,119,122,126],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":112,"slug":113},30,"research-report",{"id":115,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":55,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":123,"language":139,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":12,"update_tm":143,"read_time":144,"preview_page_count":33,"preview_urls":145},7421720224475,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","|  | Dental Research Journal |\n| --- | --- |\n|  |  |\n\nReview Article  \nEvaluating the diagnostic accuracy of neural network models in detecting oral potentially malignant disorders and oral cancer using mobile photographs:An umbrella review  \nP. D. Madan Kumar1, Rajeshwari Selvam2, Sasidharan Sivakumar3, Lavanya C4, Ranganathan Kannan4  \nDepartments of 1Public Health Dentistry, 2ICMR Project Research Scientist and 4Oral and Maxillofacial Pathology, Ragas Dental College and Hospital, Chennai, Tamil Nadu, 3Discovery Research Division, Indian Council of Medical Research, ICMR Headquarters, New Delhi, India  \nReceived: 01‑Apr‑2025  \nRevised: 03‑Jan‑2026  \nAccepted: 20‑Mar‑2026  \nPublished: 15‑May‑2026  \nAddress for correspondence:  \nDr. P. D. Madan Kumar, Department of Public Health Dentistry, Ragas Dental College and Hospital, Chennai ‑ 600 119,  \nTamil Nadu, India.  \nE‑mail: madankumar21@ [yahoo.co.in](yahoo.co.in)  \nABSTRACT  \n.  \nwas  \nBackground: Oral cancer (OC) and oral potentially malignant disorders (OPMDs) remain major global public health challenges, particularly in low‑and middle‑income countries. Although early detection substantially improves prognosis, limited healthcare infrastructure restricts timely diagnosis. Artificial intelligence (AI) enabled, mobile phone‑based diagnostic systems offer a promising, accessible solution, and multiple systematic reviews have demonstrated their potential However, uncertainty persists regarding the comparative performance of AI models across diverse real‑world settings.  \nAim: An umbrella review was aimed at evaluating the comparative performance of different AI models in detecting OC and OPMD.  \nMaterials and Methods: This research identified six systematic reviews from databases such as Medline (via PubMed),Web of Science, Scopus, and EMBASE through October 2024 which were checked at the title, abstract, and full‑text levels. The risk of bias (ROB) was then assessed using the Joanna Briggs Institute’s ROB assessment tool.  \nResults: Across included reviews, pooled sensitivity and specificity for AI‑based detection ranged from 88% to 92%, with reported diagnostic odds ratios ranging from 114 to 2549, indicating strong discriminatory performance. Deep learning architectures such as EfficientNet and ResNet consistently demonstrated high diagnostic accuracy, while hybrid approaches (e.g., MLSO + SVM) showed promising performance in selected analyses. However, substantial heterogeneity observed across studies (I2 often >85%), reflecting variability in populations, image acquisition protocols, and model architectures.  \nConclusion: Deep learning models like EfficientNet and ResNet are favored in clinical diagnostics for their exceptional performance and adaptability. Hybrid approaches, such as MLSO + SVM, also show great potential by combining the strengths of traditional and modern methods effectively.  \nKey Words: Artificial intelligence, deep learning, early diagnosis, intraoral photography, mobile health, oral cancer  \n\n| Access this article online |  |\n| --- | --- |\n| | [Website:](Website: www.drj.ir)[ www.drj.ir](Website: www.drj.ir)\u003Cbr>[www.drjjournal.net](www.drjjournal.net)[ ](www.drjjournal.net)[www.ncbi.nlm.nih.gov/pmc/journals/1480](www.ncbi.nlm.nih.gov/pmc/journals/1480)[ ](www.ncbi.nlm.nih.gov/pmc/journals/1480)[DOI:](DOI: 10.4103/drj.drj_172_25)[ 10.4103/drj.drj_172_25](DOI: 10.4103/drj.drj_172_25) |\n\n© 2026 Dental Research Journal | Published by Wolters Kluwer-Medknow  1   \nKumar, et al.: Neural network models in OPMD and oral cancer  \nINTRODUCTION  \nOral cancer (OC) and oral potentially malignant disorders (OPMDs) pose significant global health challenges due to high incidence rates, delayed diagnosis, and associated mortality.[1] Early detection of these conditions is vital, as timely intervention greatly improves survival rates and reduces the need for invasive treatments associated with advanced disease stages.[2,3] Access to specialized diagnostics for OC remains","cbCairBKSItRdpIo","https://ap.wps.com/l/cbCairBKSItRdpIo","pdf",1320722,"English","# Abstract\n## Background\n## Aim\n## Materials and Methods\n## Results\n## Conclusion\n# Introduction\n## Public health challenge and need for screening\n## Role of artificial intelligence and deep learning\n## Smartphone-based neural network approaches and limitations","[{\"question\":\"What is the main purpose of the umbrella review?\",\"answer\":\"To evaluate and compare the diagnostic performance of different AI models for detecting oral cancer and oral potentially malignant disorders using mobile photographs.\"},{\"question\":\"Which study sources and time window were included in the analysis?\",\"answer\":\"Six systematic reviews were identified from databases including Medline (via PubMed), Web of Science, Scopus, and EMBASE, covering studies up to October 2024.\"},{\"question\":\"What diagnostic performance ranges were reported across included reviews?\",\"answer\":\"Pooled sensitivity and specificity for AI-based detection ranged from 88% to 92%, with diagnostic odds ratios reported from 114 to 2549.\"}]","Evaluating the diagnostic accuracy of neural network models in detecting oral potentially malignant disorders and oral cancer using mobile photographs: An umbrella review | PDF",1790152660,25,[146,150,154,158],{"page_no":22,"url":147,"width":148,"height":149},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/fc57fee5eeda1c1a5117d2996b7869de.webp",983,1272,{"page_no":26,"url":151,"width":152,"height":153},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/3e6eecc7af96f8d2779f6f0457a72954.webp",982,1270,{"page_no":30,"url":155,"width":156,"height":157},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/0e76886f47d36e5716a63e2b46340826.webp",981,1269,{"page_no":33,"url":159,"width":160,"height":161},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/d5070157b544108657d9f4e30053de28.webp",980,1268]