P, PANWASTO SAMOSIR (2025) PERBANDINGAN PERFORMA ALGORITMA XGBOOST, CATBOOST DAN GBM DALAM PREDIKSI PENYAKIT KARDIOVASKULAR. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
01 Cover.pdf Download (319kB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (BAB I)
02 Bab 1.pdf Restricted to Registered users only Download (33kB) |
|
|
Text (BAB II)
03 Bab 2.pdf Restricted to Registered users only Download (237kB) |
|
|
Text (BAB III)
04 Bab 3.pdf Restricted to Registered users only Download (53kB) |
|
|
Text (BAB IV)
05 Bab 4.pdf Restricted to Registered users only Download (380kB) |
|
|
Text (BAB V)
06 Bab 5.pdf Restricted to Registered users only Download (28kB) |
|
|
Text (DAFTAR PUSTAKA)
07 Daftar Pustaka.pdf Restricted to Registered users only Download (131kB) |
|
|
Text (LAMPIRAN)
08 Lampiran.pdf Restricted to Registered users only Download (494kB) |
Abstract
Cardiovascular disease is the leading cause of death worldwide, involving disorders of the heart and blood vessels, such as coronary artery disease and hypertension. Risk factors for cardiovascular disease include unhealthy lifestyle choices as well as non-modifiable factors such as age and family history. To address the challenges in early detection and prediction of cardiovascular disease, machine learning approaches, particularly boosting algorithms, have shown significant potential. This study aims to compare the performance of three main boosting algorithms: XGBoost, CatBoost, and Gradient Boosting, in predicting the risk of cardiovascular disease using publicly available datasets. The results indicate that CatBoost outperforms the other models with an accuracy of 75%, Precision of 0.83, and ROC AUC of 0.81, demonstrating its superior ability to generate accurate predictions. Gradient Boosting achieves an accuracy of 70% and demonstrates a good balance between Recall and Precision, while XGBoost has the lowest performance with an accuracy of 63.3% across all evaluation metrics. Based on these findings, CatBoost is the most effective model for predicting the risk of cardiovascular disease. Keywords: Cardiovascular Diseases, Boosting Algorithms, XGBoost, CatBoost, Gradient Boosting Machine (GBM) Penyakit kardiovaskular merupakan penyebab utama kematian di seluruh dunia, melibatkan gangguan pada jantung dan pembuluh darah, seperti penyakit jantung koroner dan hipertensi. Faktor risiko penyakit kardiovaskular mencakup gaya hidup tidak sehat serta faktor non-modifikasi seperti usia dan riwayat keluarga. Untuk mengatasi tantangan dalam deteksi dini dan prediksi penyakit kardiovaskular, pendekatan machine learning, khususnya algoritma boosting, telah menunjukkan potensi yang signifikan. Penelitian ini bertujuan untuk membandingkan kinerja tiga algoritma boosting utama, yaitu XGBoost, CatBoost, dan Gradient Boosting, dalam memprediksi risiko penyakit kardiovaskular menggunakan dataset yang tersedia secara online. Hasil penelitian menunjukkan bahwa CatBoost memiliki performa terbaik dengan akurasi sebesar 75%, Precision 0.83, dan ROC AUC 0.81, yang mengindikasikan kemampuannya dalam menghasilkan prediksi yang lebih akurat. Gradient Boosting memiliki akurasi 70% dan menunjukkan keseimbangan yang baik antara Recall dan Precision, sementara XGBoost memiliki kinerja terendah dengan akurasi 63.3% di semua metrik evaluasi. Berdasarkan hasil ini, CatBoost adalah model yang paling efektif untuk memprediksi risiko penyakit kardiovaskular. Kata Kunci: Kardiovaskular, Boosting Algorithms, XGBoost, CatBoost, Gradient Boosting Machine (GBM)
Actions (login required)
 |
View Item |
