[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127997-en":3,"doc-seo-127997-105":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},127997,962084928904,"Asher","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",7,"Healthcare","Glaucoma detection - Binocular approach and clinical data in machine learning","Early glaucoma detection is crucial because the disease causes irreversible damage and often remains asymptomatic until advanced stages. This work proposes a multimodal machine learning pipeline that combines ocular fundus images from both eyes with additional patient clinical data to improve diagnostic accuracy. It evaluates monocular and binocular modes using the PAPILA dataset, integrating GBDT and CNN models and interpreting results via SHAP to explain model outputs, achieving competitive performance with AUC 0.796.","Artiϧcial Intelligence In Medicine 160 (2025) 103050  \n| Glaucoma detection: Binocular approach and clinical data in machine learning\u003Cbr>Oleksandr Kovalyk-Borodyak ∗, Juan Morales-Sánchez ∗, Rafael Verdú-Monedero ∗, José -Luis Sancho-Gómez\u003Cbr>\u003Cbr>Universidad Politécnica de Cartagena, 30202 Cartagena, Spain |  |  |\n| --- | --- | --- |\n| A R T I C L E I N F O |  | A B S T R A C T |\n| Keywords:\u003Cbr>Glaucoma diagnosis Ocular fundus imaging CNN\u003Cbr>Deep learning\u003Cbr>Gradient-boosting decision trees Both eyes\u003Cbr>Clinical data SHAP |  | In this work, we present a multi-modal machine learning method to automate early glaucoma diagnosis. The proposed methodology introduces two novel aspects for automated diagnosis not previously explored in the literature: simultaneous use of ocular fundus images from both eyes and integration with the patient’s additional clinical data. We begin by establishing a baseline, termed monocular mode, which adheres to the traditional approach of considering the data from each eye as a separate instance. We then explore the binocular mode, investigating how combining information from both eyes of the same patient can enhance glaucoma diagnosis accuracy. This exploration employs the PAPILA dataset, comprising information from both eyes, clinical data, ocular fundus images, and expert segmentation of these images. Additionally, we compare two image-derived data modalities: direct ocular fundus images and morphological data from manual expert segmentation. Our method integrates Gradient-Boosted Decision Trees (GBDT) and Convolutional Neural Networks (CNN), specifically focusing on the MobileNet, VGG16, ResNet-50, and Inception models. SHAP values are used to interpret GBDT models, while the Deep Explainer method is applied in conjunction with SHAP to analyze the outputs of convolutional-based models. Our findings show the viability of considering both eyes, which improves the model performance. The binocular approach, incorporating information from morphological and clinical data yielded an AUC of 0.796 (±0 .003 at a 95% confidence interval), while the CNN, using the same approach (both eyes), achieved an AUC of 0.764 (±0 .005 at a 95% confidence interval). |\n\n1. Introduction  \nGlaucoma is the leading cause of irreversible blindness worldwide [1–5]. The risk of glaucoma increases with age [6], affecting one in 200 people under the age of 50 and one in 10 people over the age of 80. Due to the latest medical advances, human life expectancy has increased, meaning that glaucoma is expected to become a major public health problem. It is estimated that, in 2040, 111.8 million people between 40–80 years old will suffer from glaucoma [1]. Glaucoma is a disease that affects the Optic Nerve Head (ONH). It is characterized by a progressive and irreversible loss of the visual field, usually caused by high intraocular pressure. In the later stages of the disease, the visual field decreases and, if left unattended, the disease can cause severe damage to the visual field and even total blindness [7].  \nGiven that there is no cure for the damage glaucoma causes, early detection is crucial to minimize the risk of vision loss. At present, the early and accurate detection of glaucoma poses numerous challenges. First, experts are required to perform adequate tests and evaluate the results. Secondly, glaucoma is a silent, initially asymptomatic disease,  \noften detected only in its advanced stages. It is estimated that 90% of glaucoma patients in the world are undiagnosed [8–12]. Therefore, developing new tools that improve the efficiency of the current diagnosis methods is vital for the early detection of glaucoma.  \nAlthough glaucoma is asymptomatic, indicators of the disease appear years before damage to the visual field occurs. The main procedures for the diagnosis of glaucoma are tonometry, which measures Intraocular Pressure (IOP), campimetry for the study of the visual field, Optical Coherence Tomography (OCT) to study the thic","cbCaijlyIZ614RhU","https://ap.wps.com/l/cbCaijlyIZ614RhU","pdf",3254857,1,12,"English","en",105,"# Introduction\n## Glaucoma burden and need for early detection\n## Current diagnostic procedures and limitations\n## Ocular fundus imaging and extracted features\n# Methodology Overview\n## Monocular vs binocular modes\n## Multimodal integration of images and clinical data\n## Model architectures and interpretability (SHAP)","[{\"question\":\"What is the key idea of the proposed glaucoma detection method?\",\"answer\":\"The method uses a binocular approach by simultaneously leveraging ocular fundus images from both eyes and integrating them with the patient’s additional clinical data.\"},{\"question\":\"How does the binocular mode differ from the monocular mode?\",\"answer\":\"Monocular mode treats each eye as a separate instance, while binocular mode combines information from both eyes of the same patient to improve diagnostic accuracy.\"},{\"question\":\"Which models and interpretability tools are used in the study?\",\"answer\":\"The pipeline combines Gradient-Boosted Decision Trees (GBDT) with CNNs such as MobileNet, VGG16, ResNet-50, and Inception, using SHAP (including Deep Explainer) to interpret outputs.\"}]","Glaucoma detection - Binocular approach and clinical data in machine learning | PDF",1785943740,30,{"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},"glaucoma-detection-binocular-approach-and-clinical-data-in-machine-learning","",{"@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/healthcare/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/glaucoma-detection-binocular-approach-and-clinical-data-in-machine-learning/127997/",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","2026-08-24","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 is the key idea of the proposed glaucoma detection method?","Question",{"text":76,"@type":77},"The method uses a binocular approach by simultaneously leveraging ocular fundus images from both eyes and integrating them with the patient’s additional clinical data.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the binocular mode differ from the monocular mode?",{"text":81,"@type":77},"Monocular mode treats each eye as a separate instance, while binocular mode combines information from both eyes of the same patient to improve diagnostic accuracy.",{"name":83,"@type":74,"acceptedAnswer":84},"Which models and interpretability tools are used in the study?",{"text":85,"@type":77},"The pipeline combines Gradient-Boosted Decision Trees (GBDT) with CNNs such as MobileNet, VGG16, ResNet-50, and Inception, using SHAP (including Deep Explainer) to interpret outputs.","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},[94,98,102,106,111,116,119,123,128,131,135],{"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":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":117,"slug":118},40,"healthcare",{"id":120,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":29,"slug":122},8,"Research & Report","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"]