[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-125518-en":3,"doc-seo-125518-105":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":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},125518,7971461741311,"Ophelia","https://ap-avatar.wpscdn.com/avatar/74000253aff267980c6?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779345379180704826",8,"Research & Report","Enhancing mortality prediction in patients with spontaneous intracerebral hemorrhage - Radiomics and supervised machine learning on non-contrast computed tomography - Article abstract","Radiomics-based supervised machine-learning models are developed to predict mortality during hospital admission in patients with spontaneous intracerebral hemorrhage (sICH) using non-contrast computed tomography (NCCT). A retrospective analysis of a prospectively collected registry includes 105 patients and an in-depth assessment of 105 radiomic features. After missing-value handling and scaling radiomic values to 0–1, multiple classifiers are trained and evaluated with an 80–20 stratified split and tenfold stratified cross-validation. Random Forest, KNN, and SVM are compared with feature selection and hyperparameter strategies, showing highest validation performance with simplified models.","European Journal of Radiology Open 13 (2024) 100618  \nContents lists available at ScienceDirect  \nEuropean Journal of Radiology Open  \njournal [homepage:](homepage: www.elsevier.com/locate/ejro)[ www.elsevier.com/locate/ejro](homepage: www.elsevier.com/locate/ejro)  \n| Enhancing mortality prediction in patients with spontaneous intracerebral   hemorrhage: Radiomics and supervised machine learning on non-contrast computed tomography\u003Cbr>Antonio L´opez-Rueda a,b,*,1,2, María-´Angeles Rodríguez-S´anchez c, Elena Serrano d, Javier Moreno b, Alejandro Rodríguez e, Laura Llulle, Sergi Amaroe, Laura Oleagab\u003Cbr>a Clinical Informatics Department, Hospital Clínic de Barcelona, Barcelona, Spain b Radiology Department, Hospital Clínic de Barcelona, Barcelona, Spain\u003Cbr>c Valencian Research Institute for Artificial Intelligence (VRAIN), Universitat Polit`ecnica de Val`encia, Valencia, Spain d Radiology Department, Hospital Universitario de Bellvitge, Barcelona, Spain\u003Cbr>e Neurology Department, Hospital Clínic de Barcelona, Barcelona, 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>Radiomics\u003Cbr>Machine learning Intracerebral hemorrhage Computed tomography Stroke |  | Purpose: This study aims to develop a Radiomics-based Supervised Machine-Learning model to predict mortality in patients with spontaneous intracerebral hemorrhage (sICH).\u003Cbr>Methods: Retrospective analysis of a prospectively collected clinical registry of patients with sICH consecutively admitted at a single academic comprehensive stroke center between January-2016 and April-2018. We conducted an in-depth analysis of 105 radiomic features extracted from 105 patients. Following the identification and handling of missing values, radiomics values were scaled to 0–1 to train different classifiers. The sample was split into 80–20 % training-test and validation cohort in a stratified fashion. Random Forest(RF), K-Nearest Neighbor(KNN), and Support Vector Machine(SVM) classifiers were evaluated, along with several feature selection methods and hyperparameter optimization strategies, to classify the binary outcome of mortality or survival during hospital admission. A tenfold stratified cross-validation method was used to train the models, and average metrics were calculated.\u003Cbr>Results: RF, KNN, and SVM, with the \"DropOut+SelectKBest\" feature selection strategy and no hyperparameter optimization, demonstrated the best performances with the least number of radiomic features and the most simplified models, achieving a sensitivity range between 0.90 and 0.95 and AUC range from 0.97 to 1 on the validation dataset. Regarding the confusion matrix, the SVM model did not predict any false negative test (negative predicted value 1).\u003Cbr>Conclusion: Radiomics-based Supervised Machine Learning models can predict mortality during admission inpatients with sICH. SVM with the \"DropOut+SelectKBest\" feature selection strategy and no hyperparameter optimization was the best simplified model to detect mortality during admission in patients with sICH. |\n\n1. Introduction  \nCerebrovascular disease is the second leading cause of death worldwide. After ischemic stroke, spontaneous intracerebral hemorrhage (sICH) is the second most common subtype accounting for 10–20 % of all cases [1,2].  \nNon-contrast head computed tomography (NCCT) is the first-line diagnostic test for the emergency evaluation of acute stroke [3]. Multiple radiological signs, representing irregularity and/or heterogeneity of the hematoma, had been defined on NCCT as predictors of expansion or clinical outcome of the patients with sICH [4–10].The limitations of these radiological signs include their low inter- and intra-observer  \n* Correspondence to: 170 Villarroel Street, Barcelona 08036, Spain.  \nE-mail address: [alrueda81@hotmail.com](alrueda81@hotmail.com) (A. L´opez-Rueda).  \n1 Twitter: @AntonioLR81  \n2 ORCID: 0000–0001-7914–9948  \n[https://doi.org/10.1016/j.ejro.2024.100618](https://doi.or","cbCaimctuUQWUenm","https://ap.wps.com/l/cbCaimctuUQWUenm","pdf",4110629,1,7,"English","en",105,"# Introduction\n## Clinical background and diagnostic role of NCCT\n## Limitations of qualitative radiological signs\n# Materials and methods\n## Study design and dataset\n## Radiomic feature extraction and preprocessing\n## Model training, feature selection, and validation\n# Results\n## Comparative performance of RF, KNN, and SVM\n## Sensitivity and AUC on validation\n# Conclusion","[{\"question\":\"What is the study’s primary goal for patients with spontaneous intracerebral hemorrhage (sICH)?\",\"answer\":\"To develop radiomics-based supervised machine-learning models that predict in-hospital mortality in sICH patients using non-contrast computed tomography (NCCT).\"},{\"question\":\"How were radiomic features and data preparation handled in the study?\",\"answer\":\"An in-depth analysis extracted 105 radiomic features from 105 patients; missing values were handled, and radiomic values were scaled to 0–1 before training.\"},{\"question\":\"Which model performed best and under what feature-selection setting?\",\"answer\":\"The best simplified performance on the validation dataset was achieved by Random Forest, KNN, and SVM using the “DropOut+SelectKBest” feature selection strategy without hyperparameter optimization, with sensitivity around 0.90–0.95 and AUC from 0.97 to 1.\"}]","Enhancing mortality prediction in patients with spontaneous intracerebral hemorrhage - Radiomics and supervised machine learning on non-contrast computed tomography - Article abstract | PDF",1785899589,18,{"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},"enhancing-mortality-prediction-in-patients-with-spontaneous-intracerebral-hemorrhage-radiomics-and-supervised-machine-learning-on-non-contrast-computed-tomography-article-abstract","",{"@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/enhancing-mortality-prediction-in-patients-with-spontaneous-intracerebral-hemorrhage-radiomics-and-supervised-machine-learning-on-non-contrast-computed-tomography-article-abstract/125518/",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","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is the study’s primary goal for patients with spontaneous intracerebral hemorrhage (sICH)?","Question",{"text":75,"@type":76},"To develop radiomics-based supervised machine-learning models that predict in-hospital mortality in sICH patients using non-contrast computed tomography (NCCT).","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How were radiomic features and data preparation handled in the study?",{"text":80,"@type":76},"An in-depth analysis extracted 105 radiomic features from 105 patients; missing values were handled, and radiomic values were scaled to 0–1 before training.",{"name":82,"@type":73,"acceptedAnswer":83},"Which model performed best and under what feature-selection setting?",{"text":84,"@type":76},"The best simplified performance on the validation dataset was achieved by Random Forest, KNN, and SVM using the “DropOut+SelectKBest” feature selection strategy without hyperparameter optimization, with sensitivity around 0.90–0.95 and AUC from 0.97 to 1.","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},[93,97,101,105,110,115,119,122,127,130,134],{"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":21,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]