Skripsi/Tugas Akhir
Komparasi Algoritma Naive Bayes dan Support Vector Machine dalam Memprediksi Kasus Hipertensi di Puskesmas Tawanga
ABSTRAK
Kasus hipertensi di Puskesmas Tawanga meningkat, menghadirkan ancaman serius terhadap kesehatan penduduk. Deteksi dini dan prediksi yang tepat menjadi penting. Penelitian ini membandingkan algoritma Naive Bayes dan Support Vector Machine (SVM) dalam memprediksi kasus hipertensi. Data rekam medis dari 490 pasien digunakan, dan evaluasi kinerja menggunakan Confusion Matrix. Naive Bayes memiliki presisi 96%, akurasi 97%, recall 94%, dan F1- Score 95%. SVM memiliki presisi 100%, akurasi 96%, recall 88%, dan F1-Score 93%. Dari hasil penelitian ini menyatakan bahwan Naive Bayes lebih unggul dalam memprediksi kasus hipertensi dibandingkan dengan SVM. Ini memiliki kinerja yang lebih tinggi dan seimbang dalam mengklasifikasikan kedua kelas.
Kata Kunci: Hipertensi, Prediksi, Naive Bayes, Support Vector Machine, Algoritma Klasifikasi
ABSTRACT
The cases of hypertension in the Tawanga Community Health Center have been on the rise, posing a serious threat to the population's health. Early detection and accurate prediction have become crucial. This research compares the Naive Bayes and Support Vector Machine (SVM) algorithms in predicting hypertension cases. Medical records data from 490 patients were utilized, and performance evaluation was done using the Confusion Matrix. Naive Bayes exhibited a precision of 96%, accuracy of 97%, recall of 94%, and an F1-Score of 95%. SVM demonstrated a precision of 100%, accuracy of 96%, recall of 88%, and an F1-Score of 93%. The findings from this study suggest that Naive Bayes outperforms SVM in predicting hypertension cases. It exhibits higher and well-balanced performance in classifying both classes.
Keywords: Hypertension, Prediction, Naive Bayes, Support Vector Machine, Classification Algorithms
Tidak ada salinan data
Universitas DIPA Makassar
NPP 7371142D1000002
Jln. Perintis Kemerdekaan KM.9
Telp. (0411)587194
Hotline: +6281228221994
WhatsApp Admin: +6281342092072
e-Mail: perpustakaan@undipa.ac.id
© 2024 — Perpustakaan UNDIPA Makassar - SLiMS