CD Skripsi

Prediksi Penyakit Gagal Ginjal Kronis (Ckd) Menggunakan Metode Duo Output Neural Network Ensemble (Donne) Berbasis Website

---

Chronic Kidney Disease (CKD) is one of the degenerative diseases that has seen a significant increase and has a major impact on the quality of life of those affected. Early detection of CKD is crucial for reducing the risk of complications and improving patient prognosis. This study aims to develop a CKD prediction system using the Duo Output Neural Network Ensemble (DONNE) method. The research data were collected from outpatient medical records at Arifin Achmad General Hospital in Riau Province, with a total of 397 samples. The DONNE method combines multiple artificial neural network models to produce more accurate and robust predictions. Three experiments were conducted to evaluate the model's performance, with the first experiment using a configuration of 10 Models, 50 Epoch s, and a Batch Size of 32 yielding the best results. This experiment achieved an accuracy of 97.79%, Recall of 89.83%, Precision of 98.15%, and an F1-score of 93.81%. These results indicate that the DONNE method is capable of providing better predictions than traditional methods. The developed system is expected to become an effective and easily accessible diagnostic tool to assist medical personnel in early decision-making.
Keywords: Artificial Neural Network, Chronic Kidney Failure, DONNE, Early Detection, Ensemble Learning.

---

Ketersediaan

Informasi Detail

Judul Seri

-

No. Panggil

2103110497

Penerbit

Pekanbaru : Universitas Riau FMIPA Sistem Informasi., 2025

Deskripsi Fisik

-

Bahasa

Indonesia

ISBN/ISSN

-

Klasifikasi

2103110497

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

-

Subjek

SISTEM INFORMASI

Info Detail Spesifik

-

Pernyataan Tanggungjawab

Mutia

Versi lain/terkait

Lampiran Berkas

Komentar

---

Anda harus masuk sebelum memberikan komentar