PUTRI CHAIRUNNISA, NPM 2109100061 (2025) IMPLEMENTASI GEJALA PENYAKIT LAMBUNG MENGGUNAKAN METODE NAIVE BAYES (KASUS STUDI : PUSKESMAS SEI BEROMBANG KAB. LABUHANBATU). Skripsi thesis, Universitas Labuhanbatu.
![[img]](http://repository.ulb.ac.id/style/images/fileicons/text.png) |
Text
COVER.pdf Download (1MB) |
|
Text
BAB I.pdf Download (482kB) |
|
Text
BAB II.pdf Download (600kB) |
|
Text
BAB III.pdf Download (550kB) |
|
Text
BAB IV.pdf Download (897kB) |
|
Text
BAB V.pdf Download (191kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (318kB) |
|
Text
LAMPIRAN.pdf Download (1MB) |
Abstract
Kesehatan lambung merupakan salah satu aspek penting yang sering terganggu akibat pola makan tidak teratur, stres, serta infeksi bakteri. Gejala penyakit lambung seperti gastritis, tukak lambung, gastroesophageal reflux disease (GERD), dispepsia, hingga kanker lambung membutuhkan diagnosis yang cepat dan akurat agar penanganan medis lebih efektif. Penelitian ini bertujuan untuk mengimplementasikan algoritma Naïve Bayes dalam mengklasifikasikan gejala penyakit lambung berdasarkan data pasien Puskesmas Sei Berombang, Kabupaten Labuhanbatu. Metode penelitian menggunakan pendekatan campuran kualitatif dan kuantitatif dengan sampel sebanyak 90 data rekam medis pasien. Data dibagi menjadi data training dan data testing, kemudian dilakukan perhitungan probabilitas prior, likelihood, serta pengujian akurasi menggunakan Microsoft Excel dan RapidMiner. Hasil penelitian menunjukkan bahwa algoritma Naïve Bayes mampu mengklasifikasikan gejala penyakit lambung dengan tingkat akurasi sangat tinggi, yaitu mencapai 100% pada data uji. Temuan ini membuktikan bahwa metode Naïve Bayes efektif diterapkan sebagai sistem pendukung keputusan untuk membantu tenaga medis dalam diagnosis awal penyakit lambung serta meningkatkan kualitas pelayanan kesehatan di Puskesmas Sei Berombang. Kata Kunci : Naïve Bayes, klasifikasi, gejala penyakit lambung, sistem pendukung keputusan, Puskesmas Sei Berombang =================================================================================================== Gastric health is an essential aspect that is often disrupted due to irregular eating patterns, stress, and bacterial infections. Gastric diseases such as gastritis, peptic ulcer, gastroesophageal reflux disease (GERD), dyspepsia, and gastric cancer require fast and accurate diagnosis to ensure effective medical treatment. This study aims to implement the Naïve Bayes algorithm to classify gastric disease symptoms based on patient data from Puskesmas Sei Berombang, Labuhanbatu Regency. The research method applies a mixed qualitative and quantitative approach with a sample of 90 patient medical records. The data were divided into training and testing sets, followed by the calculation of prior probabilities, likelihood, and accuracy testing using Microsoft Excel and RapidMiner. The results show that the Naïve Bayes algorithm can classify gastric disease symptoms with a very high accuracy rate, reaching 100% on the test data. These findings prove that the Naïve Bayes method is effective as a decision support system to assist medical personnel in the early diagnosis of gastric diseases and to improve the quality of healthcare services at Puskesmas Sei Berombang. Keywords : Naïve Bayes, classification, gastric disease symptoms, decision support system, Puskesmas Sei Berombang
| Item Type: | Thesis (Skripsi) |
|---|---|
| Uncontrolled Keywords: | Naïve Bayes, klasifikasi, gejala penyakit lambung, sistem pendukung keputusan, Puskesmas Sei Berombang===============Naïve Bayes, classification, gastric disease symptoms, decision support system, Puskesmas Sei Berombang |
| Subjects: | Z Bibliography. Library Science. Information Resources > Z665 Library Science. Information Science Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4050 Electronic information resources |
| Divisions: | Fakultas Sains Dan Teknologi > Sistem Informasi |
| Depositing User: | Unnamed user with email repository@ulb.ac.id |
| Date Deposited: | 02 Oct 2025 03:44 |
| Last Modified: | 02 Oct 2025 03:44 |
| URI: | http://repository.ulb.ac.id/id/eprint/1749 |
Actions (login required)
 |
View Item |
