Penerapan algoritma naive bayes untuk memprediksi keselamatan pasien gagal jantung

Lauwren, Kevin (2022) Penerapan algoritma naive bayes untuk memprediksi keselamatan pasien gagal jantung. Bachelor thesis, Universitas Pelita Harapan.

Preview	Text (Title) Title.pdf Available under License Creative Commons Attribution Non-commercial Share Alike. Download (31kB) | Preview
	Text (Abstract) Abstract.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (325kB)
	Text (ToC) ToC.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (697kB)
	Text (Chapter1) Chapter1.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (650kB)
	Text (Chapter2) Chapter2.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (1MB)
	Text (Chapter3) Chapter3.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (1MB)
	Text (Chapter4) Chapter4.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (2MB)
	Text (Chapter5) Chapter5.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (374kB)
	Text (Bibliography) Bibliography.pdf Restricted to Registered users only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (605kB)
	Text (Appendices) Appendices.pdf Restricted to Repository staff only Available under License Creative Commons Attribution Non-commercial Share Alike. Download (1MB)

Abstract

One of the biggest causes of death, based on data released by WHO (World Health Organization), is heart disease. It is estimated that around 17.9 million people died from cardiovascular disease in 2019; this represents 32% of all global deaths. Of these deaths, 85% are caused by heart disease and stroke. Heart failure conditions are all deriratives from any kind of heart disease that a person is curently having, whether or not they are fully aware of the disease. So those people who have the potential to experience heart failure continue to lead an unhealthy lifestyle. The solution to overcome this is to conduct research in the field of machine learning to find an ideal method for classifying heart failure patients. The method used in this research is Naive Bayes. The Naive Bayes algorithm has been widely implemented in the health sector, such as hepatitis classification, stroke classification, respiratory infection classification, and so on. And the classification results of the Naive Bayes algorithm are proven to provide high accuracy, precision, sensitivity, and a good classification results. In this study, the accuracy for the classification of heart failure patients was 74.58%, the level of precision was 97.67%, for sensitivity was 75%, and AUC (Area Under ROC Curve) of 0,857 which stands for a good classification within 0,80 to 0,90 range. The results of this study can be served as an early warning for patients with the chances of experiencing heart failure. / Salah satu penyebab kematian terbesar, berdasarkan data yang dikeluarkan oleh WHO (World Health Organization), adalah penyakit jantung. Diperkirakan sekitar 17,9 juta orang meninggal akibat penyakit kardiovaskular pada tahun 2019; angka tersebut mewakili 32% dari semua kematian global. Dari kematian tersebut, 85% disebabkan oleh penyakit jantung dan stroke. Kondisi gagal jantung semuanya merupakan turunan dari segala jenis penyakit jantung yang dialami seseorang, terlepas dari apakah mereka sepenuhnya menyadari penyakit tersebut atau tidak. Sehingga orang-orang yang berpotensi mengalami gagal jantung terus menjalani gaya hidup yang tidak sehat. Solusi untuk mengatasi hal tersebut adalah dengan melakukan penelitian di bidang machine learning untuk menemukan metode yang ideal untuk mengklasifikasikan pasien gagal jantung. Metode yang digunakan dalam penelitian ini adalah Naive Bayes. Algoritma Naive Bayes telah banyak diimplementasikan pada bidang kesehatan, seperti klasifikasi hepatitis, klasifikasi stroke, klasifikasi infeksi pernafasan, dan sebagainya. Dan hasil klasifikasi algoritma Naive Bayes terbukti memberikan akurasi, presisi, sensitivitas, dan hasil klasifikasi yang baik. Pada penelitian ini akurasi klasifikasi pasien gagal jantung sebesar 74,58%, tingkat presisi sebesar 97,67%, untuk sensitivitas sebesar 75%, dan AUC (Area Under ROC Curve) sebesar 0,857 yang merupakan klasifikasi baik pada kisaran 0,80 hingga 0,90. Hasil penelitian ini dapat memberikan peringatan awal bagi pasien yang memiliki kemungkinan mengalami gagal jantung.

Actions (login required)

View Item