[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-290827-105":59,"doc-detail-290827-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","predicting-heart-attacks-using-machine-learning-report","Predicting Heart Attacks Using Machine Learning - Report","","Heart attacks remain one of the most pressing global health challenges, causing millions of deaths each year. Reliable risk prediction is essential for prevention, yet traditional scoring systems often fail to represent the combined clinical, behavioral, and socioeconomic influences. This project applies the Knowledge Discovery in Databases (KDD) framework and machine learning methods to predict heart attack risk from a synthetic dataset of 8,763 patient records and 26 health-related features.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/predicting-heart-attacks-using-machine-learning-report/290827/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/predicting-heart-attacks-using-machine-learning-report/290827.png","ImageObject",300,407,{"name":92,"@type":93},"Skyler","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-20","2026-09-17",true,{"@type":102,"interactionType":103,"userInteractionCount":52},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What framework guides the project’s data handling and model development?","Question",{"text":112,"@type":113},"The project uses the Knowledge Discovery in Databases (KDD) framework to structure goal definition, dataset selection, cleaning/preprocessing, transformation, modeling, evaluation, and documentation.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"Which machine learning models are implemented and compared?",{"text":117,"@type":113},"The study builds and compares Logistic Regression, K-Nearest Neighbors, Decision Trees, Random Forest, and XGBoost, evaluating them with multiple performance metrics.",{"name":119,"@type":110,"acceptedAnswer":120},"What is the main finding about model performance?",{"text":121,"@type":113},"Ensemble methods show superior performance, with XGBoost performing particularly well, while simpler models act as useful baselines.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},290827,1789642677,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":52,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":129,"read_time":144,"preview_page_count":4},2336464648746,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","Predicting Heart Attacks Using Machine Learning  \nA project report submitted for the Subject Module Project  \nin Computer Science by  \nMads Degn  \nJulia Lundager Daniel Holst Pedersen Jonas Pheiffer  \nMagnus Stilling Østergaard  \nPeople and Technology Roskilde University Denmark  \n2025  \nAbstract  \nHeart attacks remain one of the most pressing global health challenges, accounting for millions of deaths each year. Accurate risk prediction is vital for prevention, yet traditional scoring systems often struggle to capture the complexity of clinical, behavioural, and socioeconomic factors. This project investigates the use of machine learning to predict heart attack risk, applying the Knowledge Discovery in Databases framework to guide systematic data handling and model development.  \nUsing the synthetic Heart Attack Risk Prediction Dataset consisting of 8,763 patient records and 26 heart health related features, we conducted extensive preprocessing, Exploratory Data Analysis, and feature engineering to prepare the data for supervised learning. Multiple models were implemented and compared, including Logistic Regression, K-Nearest Neighbors, Decision Trees, Random Forest, and XGBoost. Multiple evaluation metrics were used to assess the performance of said models.  \nResults highlight the superior performance of ensemble methods, particularly XGBoost, while simpler models served as useful baselines. Although synthetic data limits clinical generalizability, the study demonstrates the methodological value of ML pipelines in healthcare prediction and provides a foundation for future work with real patient datasets.  \nContents  \n1 Introduction 7  \n1.1 Report Structure .......................... 10  \n2 Literature Review 12  \n2.1 Summary .............................. 14  \n3 Methodology 15  \n3.1 Tools ................................. 16  \n3.2 Knowledge Discovery in Databases ................ 17  \n3.2.1 Defining the Goal ...................... 18  \n3.2.2 Dataset Selection ...................... 19  \n3.2.3 Data Cleaning and Preprocessing ............. 19  \n3.2.4 Reducing and Transforming the Data ........... 21  \n3.2.5 Matching Dataset with Data Mining Methods ...... 22  \n3.2.6 Algorithms and Parameters for Selected Methods .... 22  \n3.2.7 Performing Data Mining from Transformed Data .... 27  \n3.2.8 Evaluating Discovered Patterns .............. 28  \n3.2.9 Documenting and Reporting the Results ......... 30  \n3.3 Summary .............................. 31  \n4 Data Analysis 33  \n4.1 Data Cleaning and Preprocessing ................. 33  \n4.2 Exploratory Data Analysis ..................... 35  \n4.2.1 Non-Graphical EDA .................... 36  \n4.2.2 Graphical EDA ....................... 39  \n4.3 Feature Engineering ......................... 42  \n4.4 Summary .............................. 43  \n5 Implementation 44  \n5.1 From Exploration to Implementation ............... 46  \n5.1.1 Libraries and Frameworks ................. 46  \n5.2 Data Preprocessing Pipeline .................... 47  \n5.3 Model Training ........................... 48  \n5.4 Entry Point and Model Comparison ................ 50  \n5.5 Results ................................ 50  \n5.5.1 Baseline Results ....................... 51  \n5.5.2 Dropping One-Hot Encoded Columns ........... 52  \n5.5.3 Adding Engineered Features ................ 53  \n5.6 Visual Results ............................ 54  \n5.6.1 ROC Curve ......................... 55  \n5.6.2 Precision–Recall Curve ................... 56  \n5.6.3 Confusion Matrix ...................... 57  \n5.7 Prediction .............................. 58  \n5.8 Summary .............................. 59  \n6 Discussion 60  \n7 Conclusion 63  \nList of Figures  \n3.1 Flowchart of our KDD process................... 15  \n3.2 (Fayyad et al., 1996b) Visual overview of steps in the KDD process. 17  \n4.1 Histogram and boxplot showing the distribution of cholesterol.. 40  \n4.2 Histograms showing the distribution of selected non-binary variables....................","cbCaig0gn6yrmvwV","https://ap.wps.com/l/cbCaig0gn6yrmvwV","pdf",692991,69,"English","# Introduction\n## Report Structure\n# Literature Review\n## Summary\n# Methodology\n## Tools\n## Knowledge Discovery in Databases\n### Defining the Goal\n### Dataset Selection\n### Data Cleaning and Preprocessing\n### Reducing and Transforming the Data\n### Matching Dataset with Data Mining Methods\n### Algorithms and Parameters for Selected Methods\n### Performing Data Mining from Transformed Data\n### Evaluating Discovered Patterns\n### Documenting and Reporting the Results\n## Summary\n# Data Analysis\n## Data Cleaning and Preprocessing\n## Exploratory Data Analysis\n### Non-Graphical EDA\n### Graphical EDA\n## Feature Engineering\n## Summary\n# Implementation\n## From Exploration to Implementation\n## Data Preprocessing Pipeline\n## Model Training\n## Entry Point and Model Comparison\n## Results\n### Baseline Results\n### Dropping One-Hot Encoded Columns\n### Adding Engineered Features\n## Visual Results\n### ROC Curve\n### Precision–Recall Curve\n### Confusion Matrix\n## Prediction\n## Summary\n# Discussion\n# Conclusion","[{\"question\":\"What framework guides the project’s data handling and model development?\",\"answer\":\"The project uses the Knowledge Discovery in Databases (KDD) framework to structure goal definition, dataset selection, cleaning/preprocessing, transformation, modeling, evaluation, and documentation.\"},{\"question\":\"Which machine learning models are implemented and compared?\",\"answer\":\"The study builds and compares Logistic Regression, K-Nearest Neighbors, Decision Trees, Random Forest, and XGBoost, evaluating them with multiple performance metrics.\"},{\"question\":\"What is the main finding about model performance?\",\"answer\":\"Ensemble methods show superior performance, with XGBoost performing particularly well, while simpler models act as useful baselines.\"}]","Predicting Heart Attacks Using Machine Learning - Report | PDF",174]