JOURNAL OF SCIENCE AND SOCIAL RESEARCH
Vol 8, No 3 (2025): August 2025

PENERAPAN ALGORITMA NAIVE BAYES UNTUK KLASIFIKASI PENYAKIT BERDASARKAN GEJALA DAN PROFIL PASIEN

Sitorus, Indi Ramadhani (Unknown)
Apdilah, Dicky (Unknown)



Article Info

Publish Date
28 Aug 2025

Abstract

Abstract: This study aims to implement the Naive Bayes algorithm to develop a web-based disease classification system utilizing patient symptoms and profile data. The dataset, obtained from Kaggle, consists of 349 entries with five primary attributes: fever, cough, fatigue, difficulty breathing, and age group. Classification is performed by manually calculating the posterior probability of each disease class using the Naive Bayes approach. The model is integrated into a PHP-MySQL-based system and evaluated using 20 randomly selected test data. Performance evaluation resulted in an accuracy of 45%, with a precision of 0.45, recall of 0.45, and F1-score of 0.45. These results indicate that the Naive Bayes algorithm is applicable as an initial method in developing a symptom- and profile-based disease classification system, although further improvement is needed through feature enrichment and model optimization. Keyword: naive bayes; disease classification; symptoms; patient profile; system evaluation Abstrak: Penelitian ini bertujuan menerapkan algoritma Naive Bayes untuk membangun sistem klasifikasi penyakit berbasis web dengan memanfaatkan data gejala dan profil pasien. Dataset yang digunakan diperoleh dari Kaggle, terdiri atas 349 entri dengan lima atribut utama: demam, batuk, kelelahan, kesulitan bernapas, dan kelompok umur. Proses klasifikasi dilakukan dengan menghitung probabilitas posterior setiap kelas penyakit secara manual menggunakan pendekatan Naive Bayes. Model diterapkan ke dalam sistem berbasis PHP dan MySQL, kemudian diuji menggunakan 20 data acak sebagai data uji. Evaluasi performa menghasilkan akurasi sebesar 45%, precision 0,45, recall 0,45, dan F1-score 0,45. Hasil ini menunjukkan bahwa algoritma Naive Bayes dapat diterapkan sebagai metode awal dalam pengembangan sistem klasifikasi penyakit berbasis data gejala dan karakteristik pasien, meskipun performanya masih perlu ditingkatkan melalui pengayaan fitur dan optimasi algoritma. Kata Kunci: naive bayes; klasifikasi penyakit; gejala; profil pasien; evaluasi sistem

Copyrights © 2025






Journal Info

Abbrev

JSSR

Publisher

Subject

Computer Science & IT Economics, Econometrics & Finance Education Social Sciences

Description

Journal of Science and Social Research is accepts research works from academicians in their respective expertise of studies. Journal of Science and Social Research is platform to disclose the research abilities and promote quality and excellence of young researchers and experienced thoughts towards ...