ANGGANA, WAHYU (2026) SISTEM PENDUKUNG KEPUTUSAN DIAGNOSIS RISIKO PENYAKIT JANTUNG MENGGUNAKAN ALGORITMA NAIVE BAYES DENGAN OPTIMASI HYPERPARAMETER TREE-STRUCTURED PARZEN ESTIMATOR (TPE). S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
Cover.pdf Download (517kB) | Preview |
|
![[img]](https://repository.mercubuana.ac.id/style/images/fileicons/text.png) |
Text (BAB I)
BAB 1.pdf Restricted to Registered users only Download (34kB) |
|
|
Text (BAB II)
BAB 2.pdf Restricted to Registered users only Download (416kB) |
|
|
Text (BAB III)
BAB 3.pdf Restricted to Registered users only Download (136kB) |
|
|
Text (BAB IV)
BAB 4.pdf Restricted to Registered users only Download (712kB) |
|
|
Text (BAB V)
BAB 5.pdf Restricted to Registered users only Download (28kB) |
|
|
Text (DAFTAR PUSTAKA)
DAFPUS.pdf Restricted to Registered users only Download (98kB) |
|
|
Text (LAMPIRAN)
Lampiran.pdf Restricted to Registered users only Download (258kB) |
Abstract
Heart disease remains one of the leading causes of death worldwide, highlighting the need for early detection to support faster and more objective risk identification. This study aims to develop a web-based Decision Support System for predicting heart disease risk using the Naïve Bayes algorithm with specifically using Bernoulli Naïve Bayes algorithm optimized with the Tree-Structured Parzen Estimator (TPE) method. The study utilizes the Heart Failure Prediction Dataset published by fedesoriano on the Kaggle platform as the secondary data source. The research process includes data preprocessing, hyperparameter optimization using the TPE method, training the Bernoulli Naïve Bayes model, implementing the trained model into a web-based application using Streamlit, and evaluating the application's functionality through Black Box Testing. The developed system is designed to receive patients' clinical data, automatically perform prediction, and present the prediction results in the form of Presence or Absence, prediction probability, and clinical recommendations as supporting information. The results indicate that the Bernoulli Naïve Bayes model was successfully implemented in the web-based Decision Support System, and all application features functioned properly according to the results of Black Box Testing. Therefore, the developed application is capable of supporting the early identification of heart disease risk in a faster, more objective, and user-friendly manner as a decision support tool, without replacing professional medical diagnosis. Keyword: Bernoulli Naïve Bayes, Heart Failure Prediction, Machine Learning, Kaggle Dataset, Classification. Penyakit jantung merupakan salah satu penyebab kematian tertinggi di dunia sehingga diperlukan upaya deteksi dini untuk membantu proses identifikasi risiko penyakit secara lebih cepat dan objektif. Penelitian ini bertujuan mengembangkan Sistem Pendukung Keputusan berbasis web untuk memprediksi risiko penyakit jantung menggunakan algoritma Naïve Bayes dengan spesifiknya adalah Bernoulli Naïve Bayes yang dioptimasi dengan metode Tree-Structured Parzen Estimator (TPE). Dataset yang digunakan adalah Heart Failure Prediction Dataset yang dipublikasikan oleh fedesoriano melalui platform Kaggle sebagai sumber data sekunder. Tahapan penelitian meliputi preprocessing data, proses optimasi hyperparameter menggunakan metode TPE, pelatihan model Bernoulli Naïve Bayes, implementasi model ke dalam aplikasi berbasis web menggunakan Streamlit, serta pengujian fungsional aplikasi menggunakan metode Black Box Testing. Sistem dirancang agar mampu menerima data klinis pasien, melakukan proses prediksi secara otomatis, kemudian menampilkan hasil prediksi berupa kategori Presence atau Absence, nilai probabilitas prediksi, serta rekomendasi klinis sebagai informasi pendukung. Hasil penelitian menunjukkan bahwa model Bernoulli Naïve Bayes berhasil diimplementasikan ke dalam Sistem Pendukung Keputusan berbasis web dan seluruh fitur aplikasi dapat berjalan sesuai dengan kebutuhan fungsional berdasarkan hasil Black Box Testing. Dengan demikian, aplikasi yang dikembangkan mampu mendukung proses identifikasi awal risiko penyakit jantung secara lebih cepat, objektif, dan mudah digunakan sebagai media pendukung pengambilan keputusan, tanpa menggantikan diagnosis yang dilakukan oleh tenaga medis. Kata kunci:Bernoulli Naïve Bayes, Prediksi Gagal Jantung, Machine Learning, Heart Failure Dataset, Klasifikasi
Actions (login required)
 |
View Item |
