[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120614-en":3,"doc-seo-120614-105":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},120614,13056703020460,"Valentina","https://ap-avatar.wpscdn.com/avatar/be000253dac470eee5d?_k=1778207105932848923",8,"Research & Report","Comparative Analysis of Machine Learning Models for LDL Cholesterol Estimation","Accurate low-density lipoprotein cholesterol (LDL-C) estimation underpins cardiovascular risk assessment and treatment decision-making. Traditional formula-based approaches such as Friedewald, Sampson, and Martin lose accuracy when triglycerides (TG) are high and when LDL-C is very low, and they may require fasting samples. This study compares nine machine learning models with conventional formulas using a large cohort of 120,174 subjects, using key predictors (TC, TG, HDL-C, and age) and 5-fold cross-validation. LightGBM achieves the strongest internal and external performance, with robust behavior across TG strata, particularly in hypertriglyceridemia, and reduced prediction errors near clinically relevant LDL-C thresholds.","Comparative Analysis of Machine Learning Models for LDL Cholesterol Estimation  \nBarthi Dasan  \nUniversitas Nusa Mandiri, Indonesia  \n[E-mail: barthi77@gmail.com](E-mail: barthi77@gmail.com)  \nAbstrak. Estimasi low-density lipoprotein cholesterol (LDL-C) yang akurat sangat penting dalampenilaian risiko kardiovaskular dan pengambilan keputusan terapi. Metode estimasi LDL-C berbasis formula tradisional, seperti persamaan Friedewald, Sampson, dan Martin, menunjukkan penurunanakurasi pada kadar trigliserida (TG) yang tinggi. Studi ini membandingkan sembilan model machine learning (ML) dengan formula konvensional menggunakan dataset besar yang terdiri dari 120.174 subjek. Setelah prapemrosesan data dan seleksi fitur, empat prediktor utama (TC, TG, HDL-C, dan usia) digunakan untuk melatih model ML dengan validasi silang 5-fold. Di antara seluruh model, Light Gradient Boosting Machine (LightGBM) menunjukkan kinerja terbaik dengan R² = 0,8749, MSE = 204,53 mg²/dL², dan PCC = 0,935 pada internal test set. Kinerja superior yang serupa jugadiamati pada external validation cohort (n = 10.183), terutama pada kategori hypertriglyceridemia (TG ≥ 200 mg/dL), di mana formula konvensional mengalami penurunan performa yang signifikan. Model ML, khususnya pendekatan berbasis ensemble, mempertahankan akurasi prediksi yang stabil di seluruh rentang TG dan secara nyata mengurangi kesalahan prediksi pada ambang klinis LDL-Cyang relevan (70, 100, dan 130 mg/dL) . Temuan ini mendukung integrasi estimasi LDL-C berbasis ML ke dalam alur kerja laboratorium rutin dan menyoroti potensinya dalam mendukung pengambilan keputusan klinis.  \nKata kunci: Lipid; Kolesterol LDL; Machine Learning; Trigliserida  \nAbstract. Accurate estimation of low-density lipoprotein cholesterol (LDL-C) is essential for cardiovascular risk assessment and treatment decision-making. Traditional formula-based LDL-C estimations, such as Friedewald, Sampson, and Martin equations, show decreasing accuracy at higher triglyceride (TG) levels. This study compares nine machine learning (ML) models against conventional formulas using a large dataset of 120,174 subjects. After data preprocessing and feature selection, four predictors (TC, TG, HDL-C, and age) were used to train ML models with 5-fold cross-validation. Among all models, Light Gradient Boosting Machine (LightGBM) demonstrated the best performance, achieving R² = 0.8749, MSE = 204.53 mg²/dL², and PCC = 0.935 on the internal test set. Similar superiority was observed in the external validation cohort (n = 10,183), particularly in hypertriglyceridemic ranges (TG ≥ 200 mg/dL), where classical equations showed substantial performance degradation. Machine learning models, especially ensemble-based approaches, maintain robust predictive ability across TG strata and significantly reduce error around clinically relevant LDL-C thresholds (70, 100, and 130 mg/dL). These findings support the integration of ML-assisted LDL-C estimation into routine laboratory workflows and highlight its potential contribution to clinical decision support.  \nKeywords: Lipids; LDL cholesterol; Machine learning; Triglyceride  \n1. Introduction  \nAtherosclerotic cardiovascular disease (ASCVD) is a leading cause of global morbidity and mortality, with elevated low-density lipoprotein cholesterol (LDL-C) being a major and extensively validated risk factor. Consequently, LDL-C reduction has been established as a primary target for both primary and secondary cardiovascular prevention in clinical practice and guidelines. Traditionally, LDL-C has been estimated using equations such as the Friedewald formula, developed in 1972, which calculates LDL-C from total cholesterol (TC), high-density lipoprotein cholesterol (HDL-C), and triglycerides (TG) . However, this formula has known limitations, including limited accuracy in scenarios with high triglycerides (TG >400 mg/dL) or very low LDL-C (LDL-C \u003C70 mg/dL), and it typically requires a fasting sample. The MartinHopkins equa","cbCaijzmrMI6X7ak","https://ap.wps.com/l/cbCaijzmrMI6X7ak","pdf",941570,1,21,"English","en",105,"# Introduction\n## Background on LDL-C as a risk factor\n## Limitations of traditional LDL-C formulas\n## Motivation for machine learning approaches","[{\"question\":\"Why is accurate LDL-C estimation important in clinical practice?\",\"answer\":\"LDL-C is a validated risk factor for atherosclerotic cardiovascular disease, and precise estimation supports cardiovascular prevention strategies and individualized treatment decisions.\"},{\"question\":\"What limitations affect traditional LDL-C estimation formulas?\",\"answer\":\"Formulas like Friedewald and Martin-Hopkins show reduced accuracy at high triglyceride levels and at very low LDL-C concentrations, and Friedewald typically requires a fasting sample.\"},{\"question\":\"Which machine learning model performed best and how was it evaluated?\",\"answer\":\"LightGBM performed best, evaluated using 5-fold cross-validation on 120,174 subjects and further assessed on an external validation cohort of 10,183 participants.\"}]","Comparative Analysis of Machine Learning Models for LDL Cholesterol Estimation | PDF",1785730901,53,{"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},"comparative-analysis-of-machine-learning-models-for-ldl-cholesterol-estimation","",{"@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/comparative-analysis-of-machine-learning-models-for-ldl-cholesterol-estimation/120614/",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","2026-08-03",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},"Why is accurate LDL-C estimation important in clinical practice?","Question",{"text":75,"@type":76},"LDL-C is a validated risk factor for atherosclerotic cardiovascular disease, and precise estimation supports cardiovascular prevention strategies and individualized treatment decisions.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What limitations affect traditional LDL-C estimation formulas?",{"text":80,"@type":76},"Formulas like Friedewald and Martin-Hopkins show reduced accuracy at high triglyceride levels and at very low LDL-C concentrations, and Friedewald typically requires a fasting sample.",{"name":82,"@type":73,"acceptedAnswer":83},"Which machine learning model performed best and how was it evaluated?",{"text":84,"@type":76},"LightGBM performed best, evaluated using 5-fold cross-validation on 120,174 subjects and further assessed on an external validation cohort of 10,183 participants.","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"]