[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-127406-113":3,"detail-sidebar-cat-0-id-113":85,"doc-detail-127406-id":132},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":78,"head_meta":80,"extra_data":82,"updated_unix":84},113,"id","comparison-of-machine-learning-algorithms-for-heart-failure-detection-based-on-rfecv-feature-selection-and-smote-data-balancing","Perbandingan Algoritma Machine Learning Untuk Deteksi Gagal Jantung Berbasis Seleksi Fitur RFECV dan Penyeimbangan Data SMOTE","","Deteksi dini gagal jantung merupakan tantangan signifikan dalam dunia medis karena kompleksitas faktor risiko. Penelitian ini membandingkan kinerja enam algoritma machine learning untuk memprediksi risiko gagal jantung menggunakan kerangka CRISP-DM. Dataset klinis 299 pasien diproses melalui seleksi fitur dengan Recursive Feature Elimination with Crossvalidation (RFECV) dan penyeimbangan kelas menggunakan Synthetic Minority Over-sampling Technique (SMOTE). Evaluasi memakai validasi silang berstrata dengan metrik akurasi, presisi, recall, dan F1-score. Random Forest memberi performa terbaik (akurasi dan F1-score 91,20%), diikuti Gradient Boosting (90,20%), sementara SMOTE meningkatkan deteksi kelas minoritas.",{"@graph":14,"@context":77},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/id/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/id/document/penelitian-laporan/","Penelitian & Laporan",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/id/document/comparison-of-machine-learning-algorithms-for-heart-failure-detection-based-on-rfecv-feature-selection-and-smote-data-balancing/127406/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/comparison-of-machine-learning-algorithms-for-heart-failure-detection-based-on-rfecv-feature-selection-and-smote-data-balancing/127406.png","ImageObject",300,407,{"name":42,"@type":43},"Theodora","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-09-19","2026-08-05",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",12,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69,73],{"name":60,"@type":61,"acceptedAnswer":62},"Apa tujuan utama penelitian ini?","Question",{"text":63,"@type":64},"Menampilkan dan membandingkan kinerja enam algoritma machine learning untuk mendeteksi risiko gagal jantung, dengan pipeline yang menggabungkan RFECV dan SMOTE dalam kerangka CRISP-DM.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"Bagaimana data dipersiapkan sebelum pemodelan?",{"text":68,"@type":64},"Dataset 299 pasien diproses melalui seleksi fitur menggunakan RFECV, standarisasi dengan StandardScaler, serta penyeimbangan kelas menggunakan SMOTE.",{"name":70,"@type":61,"acceptedAnswer":71},"Algoritma apa yang menghasilkan performa terbaik dan bagaimana metriknya?",{"text":72,"@type":64},"Random Forest memberikan performa terbaik dengan akurasi dan F1-score sebesar 91,20%, diikuti Gradient Boosting dengan 90,20%.",{"name":74,"@type":61,"acceptedAnswer":75},"Mengapa penggunaan SMOTE penting pada penelitian ini?",{"text":76,"@type":64},"SMOTE terbukti meningkatkan kemampuan model, terutama dalam mendeteksi kelas minoritas pada data yang tidak seimbang.","https://schema.org",{"og:url":32,"og:type":79,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":81,"canonical":32},"index,follow",{"doc_id":83,"site_id":7},127406,1785938719,{"code":4,"msg":86,"data":87},"success",[88,93,97,101,105,109,112,116,120,124,128],{"id":89,"doc_module":4,"doc_module_name":25,"category_name":90,"show_sort_weight":91,"slug":92},55,"Agama & Spiritualitas",60,"religion-spirituality",{"id":94,"doc_module":4,"doc_module_name":25,"category_name":95,"show_sort_weight":91,"slug":96},48,"Cerita & Novel","story-novel",{"id":98,"doc_module":4,"doc_module_name":25,"category_name":99,"show_sort_weight":91,"slug":100},56,"Gaya Hidup","lifestyle",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":91,"slug":104},51,"Komik","comic",{"id":106,"doc_module":4,"doc_module_name":25,"category_name":107,"show_sort_weight":91,"slug":108},53,"Layanan Kesehatan","healthcare",{"id":110,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":91,"slug":111},54,"research-report",{"id":113,"doc_module":4,"doc_module_name":25,"category_name":114,"show_sort_weight":91,"slug":115},49,"Sastra","literature",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":118,"show_sort_weight":91,"slug":119},52,"Teknologi","technology",{"id":121,"doc_module":4,"doc_module_name":25,"category_name":122,"show_sort_weight":91,"slug":123},50,"Ujian","exam",{"id":125,"doc_module":4,"doc_module_name":25,"category_name":126,"show_sort_weight":91,"slug":127},57,"Umum","general",{"id":129,"doc_module":4,"doc_module_name":25,"category_name":130,"show_sort_weight":4,"slug":131},181,"Formulir","formulir",{"code":4,"msg":86,"data":133},{"doc_id":83,"user_id":134,"nickname":42,"user_avatar":135,"doc_module":4,"category_id":110,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":136,"file_id":137,"file_url":138,"file_type":139,"file_size":140,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":141,"language":142,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":143,"faqs":144,"seo_title":145,"seo_description":12,"update_tm":84,"read_time":146},962085571259,"https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0","Perbandingan Algoritma Machine Learning Untuk Deteksi Gagal Jantung Berbasis Seleksi Fitur RFECV dan Penyeimbangan Data SMOTE  \nAri Setyawan, Neny Sulistianingsih, Ria Rismayati  \nUniversitas Bumigora, Mataram, Indonesia  \nCorrespondence : e-mail: [arisetyawanari7921@gmail.com](arisetyawanari7921@gmail.com)  \nAbstrak  \nDeteksi dini gagal jantung merupakan tantangan signifikan dalam dunia medis karena kompleksitasfaktor risikonya. Penelitian ini bertujuan membandingkan kinerja enam algoritma machine learning dalam memprediksi risiko gagal jantung dengan pendekatan CRISP-DM. Data klinis sebanyak 299 pasien diproses melalui seleksi fitur menggunakan Recursive Feature Elimination with Crossvalidation (RFECV) serta penyeimbangan kelas dengan Synthetic Minority Over-sampling Technique (SMOTE). Algoritma yang dievaluasi meliputi Logistic Regression, K-Nearest Neighbors, Support Vector Machine, Decision Tree, Random Forest, dan Gradient Boosting. Evaluasi dilakukan menggunakan validasi silang berstrata dengan metrik akurasi, presisi, recall, dan F1-score. Hasil menunjukkan Random Forest mencapai performa terbaik dengan akurasi danF1-scoresebesar 91,20%, diikuti Gradient Boosting dengan 90,20%. Implementasi SMOTE terbukti meningkatkan kemampuan model, terutama dalam mendeteksi kelas minoritas. Temuan ini menegaskan bahwa metode ensemble seperti Random Forest, dikombinasikan dengan RFECV dan SMOTE, efektif untuk klasifikasi risiko gagal jantung secara akurat dan andal.  \nKata kunci: gagal jantung, machine learning, Random Forest, Gradient Boosting, SMOTE.  \nAbstract  \nEarly detection of heart failure remains a significant challenge in the medical field due to the complexity of its risk factors. This study aims to compare the performance of six machine learning algorithms in predicting heart failure risk using the CRISP-DM framework. A clinical dataset of 299 patients was processed through feature selection with Recursive Feature Elimination with Cross-validation (RFECV) and class balancing using the Synthetic Minority Over-sampling Technique (SMOTE). The evaluated algorithms include Logistic Regression, K-Nearest Neighbors, Support Vector Machine, Decision Tree, Random Forest, and Gradient Boosting. Model performance was assessed using stratified cross-validation with accuracy, precision, recall, and F1-score as evaluation metrics. Results indicate that Random Forest achieved the best performance with an accuracy and F1-score of 91.20%, followed by Gradient Boosting with 90.20%. The implementation of SMOTE significantly improved model performance, particularly in detecting the minority class. These findings confirm that ensemble methods such as Random Forest, combined with RFECVand SMOTE, provide an effective and reliable solution for accurate heart failure risk classification.  \nKeywords: heart failure, machine learning, Random Forest, Gradient Boosting, SMOTE.  \n1. Pendahuluan  \nGagal jantung merupakan salah satu penyakit kardiovaskular dengan prevalensi global yang terus meningkat dan saat ini menjangkit lebih dari 64 juta orang di seluruh dunia [1] . Kondisi ini tidak hanya menyebabkan morbiditas tinggi tetapi juga menjadi salah satu penyebab utama kematian, dengan sekitar 50% pasien dilaporkan meninggal dalam lima tahun setelah diagnosis [2] . Deteksi dini menjadi kunci untuk meningkatkan kualitas hidup pasien, namun gejalanya sering tumpang tindih dengan penyakit lain dandipengaruhi oleh kompleksitas faktor risiko. Seiring dengan meningkatnya ketersediaan data klinis,  \nUNIVERSITAS BUMIGORA – 12 SEPTEMBER 2025  \nmachine learning (ML) telah muncul sebagai pendekatan yang menjanjikan untuk mengidentifikasi polapola kompleks yang sulit dikenali metode diagnostik tradisional [3] [4] .  \nPenelitian terdahulu menunjukkan bahwa teknik penyeimbangan data seperti Synthetic Minority Over-sampling Technique (SMOTE) dapat meningkatkan akurasi algoritma ensemble pada data yang tidakseimbang [4] [5] . Selain itu, seleksi fitur menggunakan Recur","cbCaihjsRuqTEXLl","https://ap.wps.com/l/cbCaihjsRuqTEXLl","pdf",366739,7,"Indonesian","# Pendahuluan\n## Latar belakang dan kontribusi penelitian\n# Metode Penelitian\n## Kerangka CRISP-DM dan tahapan yang digunakan\n## Dataset dan alur penelitian","[{\"question\":\"Apa tujuan utama penelitian ini?\",\"answer\":\"Menampilkan dan membandingkan kinerja enam algoritma machine learning untuk mendeteksi risiko gagal jantung, dengan pipeline yang menggabungkan RFECV dan SMOTE dalam kerangka CRISP-DM.\"},{\"question\":\"Bagaimana data dipersiapkan sebelum pemodelan?\",\"answer\":\"Dataset 299 pasien diproses melalui seleksi fitur menggunakan RFECV, standarisasi dengan StandardScaler, serta penyeimbangan kelas menggunakan SMOTE.\"},{\"question\":\"Algoritma apa yang menghasilkan performa terbaik dan bagaimana metriknya?\",\"answer\":\"Random Forest memberikan performa terbaik dengan akurasi dan F1-score sebesar 91,20%, diikuti Gradient Boosting dengan 90,20%.\"},{\"question\":\"Mengapa penggunaan SMOTE penting pada penelitian ini?\",\"answer\":\"SMOTE terbukti meningkatkan kemampuan model, terutama dalam mendeteksi kelas minoritas pada data yang tidak seimbang.\"}]","Perbandingan Algoritma Machine Learning Untuk Deteksi Gagal Jantung Berbasis Seleksi Fitur RFECV dan Penyeimbangan Data SMOTE | PDF",11]