Claim Missing Document
Check
Articles

Found 1 Documents
Search

Prediksi Risiko Penyakit Parkinson Menggunakan Seleksi Fitur Algoritma Genetika dan SMOTE-XGBoost Nabila, Verina Tita; Jayadi, Rewan
Jurnal Riset Informatika dan Inovasi Vol 3 No 11 (2026): JRIIN : Jurnal Riset Informatika dan Inovasi (INPRESS)
Publisher : shofanah Media Berkah

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Parkinson’s disease is a progressive neurodegenerative disorder that affects the central nervous system and is characterized by reduced motor control and changes in voice quality due to impaired motor function. To date, the diagnosis of Parkinson’s disease largely depends on the expertise and clinical experience of specialists. The uneven distribution of clinicians across regions remains a major challenge in providing accurate diagnosis and appropriate treatment. Therefore, this study aims to develop a machine learning–based model for predicting the risk of Parkinson’s disease by incorporating feature selection using a genetic algorithm, handling data imbalance through the SMOTE approach, and performing prediction using the XGBoost method. The results indicate that the proposed method achieves excellent performance, with an accuracy of 95%, sensitivity of 93%, specificity of 100%, precision of 100%, an F1-score of 97%, and an AUC value of 97%. Several selected features include fundamental voice frequency, pitch stability, amplitude perturbation across voice cycles averaged over five periods, harmonic-to-noise ratio, and spectral spread measure 2.