[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118318-en":3,"doc-seo-118318-105":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},118318,7971461740909,"Levi","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Applied Artificial Intelligence - Generative Machine Learning for Precision Medicine","This thesis investigates the application of generative machine learning models to address missing data in healthcare datasets, with the goal of improving patient outcome prediction accuracy. The study evaluates probabilistic and generative approaches, including Conditional Gaussian Mixture Models (cGMM), Variational Autoencoders (VAE), and Generative Adversarial Imputation Networks (GAIN), across different healthcare scenarios. Systematic experiments analyze strengths and limitations related to imputation quality and downstream classification reliability. Findings indicate that these methods show promise, but the complexity of healthcare data and generative-modelling challenges require careful implementation and ongoing refinement.","ACIT5900 MASTER THESIS in  \nApplied Computer and Information Technology (ACIT)  \nMay 2024  \nApplied Artificial Intelligence  \nGenerative Machine Learning for Precision Medicine  \nOskar Pieniak  \nDepartment of Computer Science  \nFaculty of Technology, Art and Design  \nContents  \n1 Introduction 7  \n1.1 Motivation ......................................... 7  \n1.2 Problem statement ..................................... 7  \n1.3 Scope and limitations ................................... 8  \n1.4 Research methods ..................................... 9  \n1.5 Ethical considerations ................................... 10  \n1.6 Main contributions ..................................... 10  \n1.7 Thesis outline ........................................ 10  \n2 Background 12  \n2.1 Healthcare .......................................... 12  \n2.1.1 Precision medicine ................................. 12  \n2.1.2 Clinical decision support system ......................... 13  \n2.1.3 Missing data .................................... 14  \n2.2 Machine Learning ...................................... 15  \n2.2.1 Supervised learning ................................ 15  \n2.2.2 Unsupervised learning ............................... 16  \n2.3 Generative Models ..................................... 16  \n2.3.1 Variational Autoencoder .............................. 17  \n2.3.2 Generative Adversarial Network ......................... 18  \n2.4 Evaluation metrics ..................................... 18  \n2.5 Related works ........................................ 20  \n2.6 Summary .......................................... 20  \n3 Methodology 22  \n3.1 Research Design ...................................... 22  \n3.2 Proposed method ...................................... 22  \n3.3 Data acquisition ...................................... 24  \n3.3.1 Datasets ....................................... 24  \n3.4 Implementation ....................................... 27  \n3.4.1 Data manipulation ................................. 27  \n3.4.2 Introducing missingness .............................. 28  \n3.4.3 Preparation ..................................... 29  \n3.4.4 Imputation ..................................... 29  \n3.4.5 Post-imputation .................................. 30  \n3.4.6 Classification .................................... 31  \n3.5 Technical Setup ....................................... 31  \n3.6 Summary .......................................... 33  \n4 Results 34  \n4.1 Removing outliers ..................................... 34  \n4.2 Visualization ........................................ 34  \n4.3 Introducing missingness .................................. 38  \n4.4 Determining the optimal number of Mixture components ................ 38  \n4.5 Conditional GMM data distribution ........................... 39  \n4.6 VAE latent space dimensionality ............................. 41  \n4.7 Classifiers .......................................... 43  \n4.8 Post-imputation scoring .................................. 44  \n4.9 Classification ........................................ 47  \n4.10 Summary .......................................... 50  \n5 Discussion 51  \n6 Conclusions 53  \n6.1 Thesis summary ...................................... 53  \n6.2 Main Contributions ..................................... 53  \n6.3 Future work ......................................... 53  \nList of Figures  \n1 The basic scheme of a Variational Autoencoder [54] ................... 17  \n2 The basic scheme of a Generative Adversarial network [55] ............... 18  \n3 Internal structure (implementation) of the proposed classifier.............. 23  \n4 Density plot of Cardiovascular Disease dataset...................... 34  \n5 Correlation matrix of Cardiovascular Disease dataset.................. 35  \n6 Density plot of HAD dataset................................ 36  \n7 Correlation matrix of HAD dataset............................ 37  \n8 Computed BIC values.................................... 39  \n9 Imputed value data","cbCaibNqDPlzlCey","https://ap.wps.com/l/cbCaibNqDPlzlCey","pdf",1867715,1,59,"English","en",105,"# Contents\n## 1 Introduction\n## 1.1 Motivation\n## 1.2 Problem statement\n## 1.3 Scope and limitations\n## 1.4 Research methods\n## 1.5 Ethical considerations\n## 1.6 Main contributions\n## 1.7 Thesis outline\n## 2 Background\n## 2.1 Healthcare\n## 2.1.1 Precision medicine\n## 2.1.2 Clinical decision support system\n## 2.1.3 Missing data\n## 2.2 Machine Learning\n## 2.2.1 Supervised learning\n## 2.2.2 Unsupervised learning\n## 2.3 Generative Models\n## 2.3.1 Variational Autoencoder\n## 2.3.2 Generative Adversarial Network\n## 2.4 Evaluation metrics\n## 2.5 Related works\n## 2.6 Summary\n## 3 Methodology\n## 3.1 Research Design\n## 3.2 Proposed method\n## 3.3 Data acquisition\n## 3.3.1 Datasets\n## 3.4 Implementation\n## 3.4.1 Data manipulation\n## 3.4.2 Introducing missingness\n## 3.4.3 Preparation\n## 3.4.4 Imputation\n## 3.4.5 Post-imputation\n## 3.4.6 Classification\n## 3.5 Technical Setup\n## 3.6 Summary\n## 4 Results\n## 4.1 Removing outliers\n## 4.2 Visualization\n## 4.3 Introducing missingness\n## 4.4 Determining the optimal number of Mixture components\n## 4.5 Conditional GMM data distribution\n## 4.6 VAE latent space dimensionality\n## 4.7 Classifiers\n## 4.8 Post-imputation scoring\n## 4.9 Classification\n## 4.10 Summary\n## 5 Discussion\n## 6 Conclusions\n## 6.1 Thesis summary\n## 6.2 Main Contributions\n## 6.3 Future work","[{\"question\":\"Which generative models are evaluated for missing data imputation in healthcare datasets?\",\"answer\":\"The thesis evaluates Conditional Gaussian Mixture Models (cGMM), Variational Autoencoders (VAE), and Generative Adversarial Imputation Networks (GAIN). These models are assessed for their effectiveness in imputing missing data across healthcare scenarios.\"},{\"question\":\"How does the research connect missing data handling to precision medicine outcomes?\",\"answer\":\"The study targets missing data as a key challenge in healthcare datasets and focuses on improving the accuracy of patient outcome predictions. By evaluating how imputation affects downstream reliability, the work supports data-quality refinement relevant to precision medicine.\"},{\"question\":\"What do the results suggest about the practical use of generative modelling for clinical predictions?\",\"answer\":\"The results indicate promise, but also highlight that healthcare data complexity and generative-modelling challenges require careful implementation and continuous refinement. This impacts both imputation quality and the dependability of clinical prediction workflows.\"}]","Applied Artificial Intelligence - Generative Machine Learning for Precision Medicine | PDF",1785683034,149,{"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},"applied-artificial-intelligence-generative-machine-learning-for-precision-medicine","",{"@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/applied-artificial-intelligence-generative-machine-learning-for-precision-medicine/118318/",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","2026-08-05","2026-08-02",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},"Which generative models are evaluated for missing data imputation in healthcare datasets?","Question",{"text":76,"@type":77},"The thesis evaluates Conditional Gaussian Mixture Models (cGMM), Variational Autoencoders (VAE), and Generative Adversarial Imputation Networks (GAIN). These models are assessed for their effectiveness in imputing missing data across healthcare scenarios.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does the research connect missing data handling to precision medicine outcomes?",{"text":81,"@type":77},"The study targets missing data as a key challenge in healthcare datasets and focuses on improving the accuracy of patient outcome predictions. By evaluating how imputation affects downstream reliability, the work supports data-quality refinement relevant to precision medicine.",{"name":83,"@type":74,"acceptedAnswer":84},"What do the results suggest about the practical use of generative modelling for clinical predictions?",{"text":85,"@type":77},"The results indicate promise, but also highlight that healthcare data complexity and generative-modelling challenges require careful implementation and continuous refinement. This impacts both imputation quality and the dependability of clinical prediction workflows.","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"]