ANALISIS PERBANDINGAN PREDIKSI PENYAKIT JANTUNG MENGGUNAKAN ALGORITMA LOGISTIC REGRESSION DAN K-NEAREST NEIGHBOR

ABYAN OZAGA, . (2024) ANALISIS PERBANDINGAN PREDIKSI PENYAKIT JANTUNG MENGGUNAKAN ALGORITMA LOGISTIC REGRESSION DAN K-NEAREST NEIGHBOR. Sarjana thesis, UNIVERSITAS NEGERI JAKARTA.

	Text File Cover.pdf Download (1MB)
	Text File BAB 1 Pendahuluan.pdf Download (255kB)
	Text File BAB 2 Tinjauan Pustaka.pdf Restricted to Registered users only Download (362kB) | Request a copy
	Text File BAB 3 Metodologi Penelitian.pdf Restricted to Registered users only Download (420kB) | Request a copy
	Text File BAB 4 Hasil Dan Pembahasan.pdf Restricted to Registered users only Download (1MB) | Request a copy
	Text File BAB 5 Kesimpulan Dan Saran.pdf Restricted to Registered users only Download (169kB) | Request a copy
	Text File Daftar Pustaka.pdf Download (247kB)
	Text File Lampiran & Daftar Riwayat Hidup.pdf Restricted to Registered users only Download (895kB) | Request a copy

Abstract

Penyakit jantung merupakan salah satu penyebab utama kematian di dunia, sehingga deteksi dini sangat krusial dalam upaya pencegahan dan pengobatan. Penelitian ini bertujuan membandingkan performa algoritma K-Nearest Neighbors (KNN) dan Logistic Regression dalam memprediksi risiko penyakit jantung berdasarkan data medis pasien yang diperoleh dari UCI Heart Disease Dataset. Dataset ini mencakup berbagai parameter klinis seperti tekanan darah (trestbps), kadar kolesterol (chol), detak jantung maksimum (thalach), serta indikator lainnya yang berhubungan dengan kondisi jantung. Metode K-Fold Cross Validation (5 fold) digunakan untuk membagi data guna memastikan hasil yang lebih akurat dan menghindari bias, sementara confusion matrix digunakan sebagai metrik evaluasi untuk menilai efektivitas model dalam mengklasifikasikan pasien dengan dan tanpa penyakit jantung. Hasil pengujian menunjukkan bahwa Logistic Regression memperoleh akurasi 89%, sedangkan K-Nearest Neighbors (KNN) menghasilkan akurasi 80%, yang menunjukkan bahwa Logistic Regression lebih unggul dalam mengenali pola data yang terkait dengan penyakit jantung. Dengan demikian, penelitian ini memberikan kontribusi dalam pengembangan sistem prediksi berbasis machine learning yang lebih akurat dan dapat membantu tenaga medis dalam mendeteksi potensi penyakit jantung secara lebih dini dan efisien. *****Comparative Analysis of Heart Disease Prediction Using Logistic Regression and K-Nearest Neighbor Algorithms. Thesis. Information Systems And Technology Study Program, Faculty of Engineering, State University of Jakarta 2025. Supervisor : Murien Nungraheni S.T.,M.Cs and Dr. Widodo, S.Kom,. M.Kom. Heart disease is one of the leading causes of death worldwide, making early detection crucial for prevention and treatment. This study aims to compare the performance of the K-Nearest Neighbors (KNN) and Logistic Regression (LogReg) algorithms in predicting heart disease risk based on medical patient data obtained from the UCI Heart Disease Dataset. The dataset includes various clinical parameters such as blood pressure (trestbps), cholesterol levels (chol), maximum heart rate (thalach), and other indicators related to heart conditions. The K-Fold Cross Validation (5-fold) method was applied to partition the data, ensuring more accurate results and reducing bias, while the confusion matrix was used as an evaluation metric to assess the effectiveness of the models in classifying patients with and without heart disease. The results show that Logistic Regression achieved an accuracy of 89%, while K-Nearest Neighbors (KNN) obtained 80%, indicating that Logistic Regression outperforms KNN in recognizing data patterns associated with heart disease. Thus, this study contributes to the development of a more accurate machine learning-based prediction system that can assist healthcare professionals in detecting potential heart disease cases earlier and more efficiently.

Item Type:	Thesis (Sarjana)
Additional Information:	1). Murien Nugraheni, S.T., M.Cs ; 2). Dr. Widodo, S.Kom,. M.Kom
Subjects:	Sains > Matematika > Ilmu Komputer Sains > Matematika > Software, Sistem Informasi Komputer
Divisions:	FT > S1 Sistem dan Teknologi Informasi
Depositing User:	Abyan Ozaga .
Date Deposited:	12 Feb 2025 06:32
Last Modified:	12 Feb 2025 06:32
URI:	http://repository.unj.ac.id/id/eprint/52732

Actions (login required)

View Item