[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128661-en":3,"doc-seo-128661-105":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":4,"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},128661,962084925782,"Ava Thompson","https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc",8,"Research & Report","Machine Learning Prediction of Cardiovascular Risk in Type 1 Diabetes Mellitus Patients Using Radiomics Features Extracted from Eye Images - Master Thesis","Cardiovascular diseases remain the leading cause of mortality in patients with type 1 diabetes mellitus, making reliable risk prediction essential for early intervention. This thesis applies machine learning to predict cardiovascular risk in T1DM using radiomics features extracted from eye images combined with clinical data. Key parameters are identified, including diabetes duration and smoking status plus complementary variables. After feature selection, trained models perform classification tasks with high mean AUC values across multiple risk-separation scenarios.","Machine Learning Prediction of Cardiovascular Risk in Type 1 Diabetes Mellitus Patients Using Radiomics Features Extracted from Eye Images  \nMaster Thesis submitted to the Faculty of the Escola T`ecnica d’Enginyeria de Telecomunicaci´o de Barcelona Universitat Polit`ecnica de Catalunya by  \nAriadna Toh`a Dalmau  \nIn partial fulfillment of the requirements for the master in  \nENGINEERING PHYSICS  \nAdvisors:  \nEnrique Romero Merino  \nFerran Mazzanti Castrillejo  \nBarcelona, June 27, 2024  \nContents  \nList of Figures 3  \nList of Tables 3  \n1 Introduction 6  \n2 Theoretical Background 9  \n2.1 Type 1 Diabetes Mellitus and Cardiovascular Risk .............. 9  \n2.2 OCT, OCTA and Retinal Fundus Images ................... 9  \n2.3 Machine Learning Techniques ......................... 10  \n2.3.1 Quantum Machine Learning ...................... 12  \n3 State of the Art 14  \n3.1 ML Prediction of CV Risk in Diabetic Patients ............... 14  \n3.2 ML Prediction of CV Risk from Eye Images ................. 15  \n4 Methodology and Results 16  \n4.1 Dataset Description and Preprocessing .................... 16  \n4.2 Machine Learning Models ........................... 18  \n4.2.1 Hyperparameters Selection for the Initial Models .......... 18  \n4.2.2 Feature Selection ............................ 20  \n4.2.3 Final Models .............................. 21  \n4.2.4 Relevance of specific data ....................... 26  \n4.3 Statistical Analysis ............................... 27  \n5 Budget 30  \n6 Conclusions and Future Development 31  \nReferences 32  \nAppendices 34  \nList of Figures  \n1 Retinal images included in the dataset for each individual eye........ 10  \n2 AUC values obtained with data from 1 or 2 eyes per patient, using the Random Forest model and performing the classification between high and very high risk................................... 18  \n3 ML models performance for the three classification problems approached,  \nafter performing the initial hyperparameters selection and showing in dif  \nferent colors the data combinations used to train the model. The data  \ncombinations are the ones presented in Section 4.1 and the corresponding  \ncolors are, going from 1 to 8, blue, orange, green, red, purple, brown, pink and grey...................................... 19  \n4 ML models performance for the three classification problems approached,  \nafter performing the feature selection and showing in different colors the  \ndata combinations used to train the model. All the data combinations are the ones and the corresponding colors are, going from 1 to 8, blue, orange, green, red, purple, brown, pink and grey.................... 21  \n5 Final ML models performance for the three classification problems ap  \nproached, showing in different colors the data combinations used to train  \nthe model. The data combinations are the ones presented in Section 4.1 and the corresponding colors are, going from 1 to 8, blue, orange, green, red, purple, brown, pink and grey........................ 22  \n6 ML models performance for the three classification problems approached, evaluating them with a k-fold cross-validation technique........... 24  \nList of Tables  \n1 Mean test AUC, accuracy, sensitivity and specificity of the models obtained for each classification problem.......................... 23  \n2 Key parameters for each group of data in the different classifications.... 25  \n3 Mean test AUC values for each combination of data considered relevant for performing the different classifications..................... 26  \n4 Mean test AUC values for each problem and situation studied........ 26  \n5 Statistical data obtained for problem 1, being a the control cases and b the ones with a certain cardiovascular risk..................... 28  \n6 Statistical data obtained for problem 2, being a the cases with moderate risk and b the ones with high or very high risk................. 28  \n7 Statistical data obtained for problem 3, being a the cases with high risk and b the ones","cbCain6S9ZeUPr6S","https://ap.wps.com/l/cbCain6S9ZeUPr6S","pdf",2556369,1,35,"English","en",105,"# 1 Introduction\n# 2 Theoretical Background\n## 2.1 Type 1 Diabetes Mellitus and Cardiovascular Risk\n## 2.2 OCT, OCTA and Retinal Fundus Images\n## 2.3 Machine Learning Techniques\n# 3 State of the Art\n## 3.1 ML Prediction of CV Risk in Diabetic Patients\n## 3.2 ML Prediction of CV Risk from Eye Images\n# 4 Methodology and Results\n## 4.1 Dataset Description and Preprocessing\n## 4.2 Machine Learning Models\n## 4.3 Statistical Analysis\n# 5 Budget\n# 6 Conclusions and Future Development\n# References\n# Appendices","[{\"question\":\"What is the main goal of this thesis?\",\"answer\":\"To predict cardiovascular risk in type 1 diabetes mellitus patients using machine learning models that incorporate radiomics features extracted from eye images together with clinical data.\"},{\"question\":\"Which data sources are used for the risk prediction?\",\"answer\":\"Radiomics features from eye images (including OCT/OCTA and retinal fundus information) are used alongside other clinical parameters such as diabetes duration and smoking status.\"},{\"question\":\"How are the models evaluated and what performance is reported?\",\"answer\":\"Models are trained using different data combinations, and after feature selection their classification performance is reported using mean AUC values across several risk-separation problems.\"}]","Machine Learning Prediction of Cardiovascular Risk in Type 1 Diabetes Mellitus Patients Using Radiomics Features Extracted from Eye Images - Master Thesis | PDF",1786002411,88,{"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},"machine-learning-prediction-of-cardiovascular-risk-in-type-1-diabetes-mellitus-patients-using-radiomics-features-extracted-from-eye-images-master-thesis","",{"@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/machine-learning-prediction-of-cardiovascular-risk-in-type-1-diabetes-mellitus-patients-using-radiomics-features-extracted-from-eye-images-master-thesis/128661/",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","2026-08-06",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is the main goal of this thesis?","Question",{"text":75,"@type":76},"To predict cardiovascular risk in type 1 diabetes mellitus patients using machine learning models that incorporate radiomics features extracted from eye images together with clinical data.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which data sources are used for the risk prediction?",{"text":80,"@type":76},"Radiomics features from eye images (including OCT/OCTA and retinal fundus information) are used alongside other clinical parameters such as diabetes duration and smoking status.",{"name":82,"@type":73,"acceptedAnswer":83},"How are the models evaluated and what performance is reported?",{"text":84,"@type":76},"Models are trained using different data combinations, and after feature selection their classification performance is reported using mean AUC values across several risk-separation problems.","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},[93,97,101,105,110,115,120,123,128,131,135],{"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":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"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":106,"slug":138},19,"General","general"]