Klasifikasi Penyakit Pneumonia Menggunakan Algoritma Naive Bayes Di Unit Rawat Inap RSUD Blambangan Banyuwangi

Hewuni, Putri Meilisa (2026) Klasifikasi Penyakit Pneumonia Menggunakan Algoritma Naive Bayes Di Unit Rawat Inap RSUD Blambangan Banyuwangi. Undergraduate thesis, Politeknik Negeri Jember.

	Text (Abstract) Abstract.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (204kB)
	Text (Bab 1 Pendahuluan) Bab 1 Pendahuluan.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (351kB)
	Text (Daftar Pustaka) Daftar Pustaka.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (202kB)
	Text (Laporan Lengkap) Laporan Lengkap.pdf - Submitted Version Restricted to Registered users only Download (3MB) | Request a copy

Abstract

Pneumonia is an acute infection of the lung tissue that remains a health problem with high morbidity and mortality rates. Based on the top 10 inpatient diseases at Blambangan Regional General Hospital, Banyuwangi, in 2025, there were 483 cases of pneumonia, including 40 deaths. The symptoms of pneumonia are similar to those of other pulmonary diseases, particularly pulmonary tuberculosis, which accounted for 268 cases. Both diseases are treated in the same unit, namely the Pulmonary Center, which may create difficulties in achieving rapid and accurate diagnosis and increase the risk of misdiagnosis. Therefore, an approach that can support disease classification is needed. The utilization of medical record data through data mining techniques can be used as an alternative to support disease classification. This study aimed to classify Pneumonia and Pulmonary Tuberculosis using the Naive Bayes algorithm in the Inpatient Unit of Blambangan Regional General Hospital, Banyuwangi. This quantitative study used RapidMiner as the data processing tool. The sample consisted of 262 medical records, comprising 131 Pneumonia patients and 131 Pulmonary Tuberculosis patients. The study variables included age, sex, comorbidities, cough, sputum production, fever, shortness of breath, signs of pulmonary consolidation, leukocyte count, fatigue, nausea, and vomiting. The results showed that the 80%:20% training and testing ratio achieved an accuracy of 90.38%, precision of 86.21%, and recall of 96.15%. This study also developed a classification system based on Microsoft Excel using VBA to automatically determine the Pneumonia and Non-Pneumonia classes. Keywords:Naive Bayes,Pneumonia, Pulmonary Tuberculosis, RapidMiner.Penelitian ini bertujuan untuk menganalisis klasifikasi penyakit Pneumonia dan Tuberkulosis Paru menggunakan algoritma Naive Bayes di Unit Rawat Inap RSUD Blambangan Banyuwangi. Jenis penelitian yang digunakan adalah penelitian kuantitatif dengan bantuan tools RapidMiner menggunakan algoritma Naive Bayes. Sampel penelitian berjumlah 262 rekam medis pasien rawat inap yang terdiri dari 131 pasien Pneumonia dan 131 pasien Non Pneumonia yaitu Tuberkulosis Paru. Variabel yang diteliti meliputi usia, jenis kelamin, penyakit penyerta, batuk, produksi sputum, demam, sesak napas, tanda konsolidasi paru, leukosit, lemas, mual, dan muntah. Teknik pengumpulan data dilakukan melalui observasi dokumen rekam medis menggunakan lembar observasi dan checklist. Hasil penelitian menunjukkan bahwa rasio pembagian data training dan testing sebesar 80%:20% memberikan performa klasifikasi dengan nilai accuracy 90,38%, precision 86,21%, dan recall 96,15%. Penelitian ini juga menghasilkan sistem klasifikasi berbasis Microsoft Excel yang dibantu dengan Visual Basic for Applications (VBA) untuk menentukan kelas Pneumonia dan Non Pneumonia yaitu Tuberkulosis Paru secara otomatis. Saran untuk penelitian selanjutnya adalah menambah jumlah dataset agar model klasifikasi menjadi lebih representatif dan akurat, membandingkan algoritma Naive Bayes dengan metode klasifikasi lain untuk memperoleh performa yang lebih optimal, serta mengembangkan aplikasi yang telah dibuat menjadi sistem deteksi dini Pneumonia berbasis web atau mobile yang dapat dimanfaatkan di RSUD Blambangan Banyuwangi.

Actions (login required)

View Item