Deteksi Alzheimer Berbasis Random Forest dengan Feature Selection dan Analisis SHAP pada Data Klinis
Abstract
Penyakit Alzheimer merupakan gangguan neurodegeneratif progresif yang menjadi penyebab utama demensia, namun deteksi dininya di Indonesia masih terkendala oleh mahalnya metode pencitraan otak seperti MRI dan PET Scan. Machine learning menawarkan alternatif deteksi dini berbasis data klinis rutin yang lebih terjangkau dan mudah diakses. Penelitian ini bertujuan mengembangkan model deteksi dini Alzheimer menggunakan algoritma Random Forest yang dioptimalkan melalui seleksi fitur dan disertai analisis interpretabilitas SHAP (SHapley Additive exPlanations) pada data klinis non-pencitraan. Dataset yang digunakan bersumber dari Kaggle, terdiri dari 2.149 data pasien dengan 32 fitur prediktor setelah pra-pemrosesan, mencakup aspek demografis, medis, kognitif, dan fungsional. Ketidakseimbangan kelas pada data latih (1.111 pasien sehat berbanding 608 pasien Alzheimer) ditangani menggunakan SMOTE. Seleksi fitur dilakukan melalui kombinasi Random Forest Feature Importance dan RFECV (Recursive Feature Elimination with Cross-Validation) dengan skema 5-fold Stratified Cross-Validation, sementara optimasi hyperparameter dilakukan menggunakan GridSearchCV terhadap 72 kombinasi parameter. Hasil penelitian menunjukkan bahwa model Random Forest menghasilkan performa yang sangat baik dengan accuracy 94,19%, precision 94,41%, recall 88,82%, F1-Score 91,53%, dan ROC-AUC 0,938. Hasil RFECV secara objektif memvalidasi bahwa seluruh 32 fitur tetap relevan bagi model, berbeda dari pendekatan pemangkasan fitur sepihak pada penelitian acuan. Analisis SHAP mengungkap bahwa Functional Assessment, ADL, MMSE, Memory Complaints, dan Behavioral Problems merupakan lima fitur paling dominan, dengan pola hubungan berbentuk ambang batas pada Functional Assessment dan ADL, serta interpretasi transparan pada level individu pasien melalui waterfall plot. Penelitian ini diharapkan dapat memberikan kontribusi pada pengembangan sistem pendukung keputusan medis untuk deteksi dini Alzheimer yang akurat sekaligus interpretatif.
References
“Dementia.” Accessed: Aug. 31, 2026. [Online]. Available: https://www.who.int/news-room/fact-sheets/detail/dementia
“Direktorat Jenderal Kesehatan Lanjutan.” Accessed: Aug. 31, 2026. [Online]. Available: https://keslan.kemkes.go.id/view_artikel/2819/mengenal-demensia-alzheimer
S. P. Yuni, M. Oktavianingrum, and F. Aksa, “Analisis Feature Importance pada Penyakit Alzheimer Menggunakan Random Forest,” vol. 02, no. 01, 2026.
M. Rohini and D. Surendran, “Toward Alzheimer’s disease classification through machine learning,” Soft Computing, vol. 25, no. 4, pp. 2589–2597, Feb. 2021, doi: 10.1007/s00500-020-05292-x.
R. N. Fadhila, N. Ulinnuha, and D. Yuliati, “Implementation of Random Forest Method with Information Gain Selection and Hyperparameter Tuning for Alzheimer’s Disease Classification,” LKJITI, vol. 16, no. 1, pp. 1–13, Oct. 2025, doi: 10.24843/LKJITI.2025.v16.i01.p01.
Firman Akbar and Rahmaddeni, “Komparasi Algoritma Machine Learning Untuk Memprediksi Penyakit Alzheimer,” JKT, vol. 8, no. 2, pp. 236–245, Nov. 2022, doi: 10.35143/jkt.v8i2.5713.
Y. Sari and Z. Fatah, “Klasifikasi Penyakit Alzheimer Menggunakan Data Mining Decision Tree”.
A. M. Priyatno and T. Widiyaningtyas, “A SYSTEMATIC LITERATURE REVIEW: RECURSIVE FEATURE ELIMINATION ALGORITHMS,” jitk, vol. 9, no. 2, pp. 196–207, Feb. 2024, doi: 10.33480/jitk.v9i2.5015.
M. Awad and S. Fraihat, “Recursive Feature Elimination with Cross-Validation with Decision Tree: Feature Selection Method for Machine Learning-Based Intrusion Detection Systems,” JSAN, vol. 12, no. 5, p. 67, Sep. 2023, doi: 10.3390/jsan12050067.
A. Ghasemi, S. Hashtarkhani, D. L. Schwartz, and A. Shaban‐Nejad, “Explainable artificial intelligence in breast cancer detection and risk prediction: A systematic scoping review,” Cancer Innovation, vol. 3, no. 5, p. e136, Oct. 2024, doi: 10.1002/cai2.136.
C. Hidayat, A. Nugroho, and A. Suprianto, “Prediksi Risiko Stroke Berdasarkan Faktor Klinis Menggunakan Random Forest Dengan Optimasi Threshold dan SHAP,” jacis, vol. 6, no. 1, pp. 127–137, Apr. 2026, doi: 10.47134/jacis.v6i1.178.
S. Gholampour, “Impact of Nature of Medical Data on Machine and Deep Learning for Imbalanced Datasets: Clinical Validity of SMOTE Is Questionable,” MAKE, vol. 6, no. 2, pp. 827–841, Apr. 2024, doi: 10.3390/make6020039.
N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, “SMOTE: Synthetic Minority Over-sampling Technique,” jair, vol. 16, pp. 321–357, Jun. 2002, doi: 10.1613/jair.953.
A. Yaqoob et al., “SGA-Driven feature selection and random forest classification for enhanced breast cancer diagnosis: A comparative study,” Sci Rep, vol. 15, no. 1, p. 10944, Mar. 2025, doi: 10.1038/s41598-025-95786-1.
L. Breiman, “Random Forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, Oct. 2001, doi: 10.1023/A:1010933404324.
A. A. Soladoye, N. Aderinto, D. Osho, and D. B. Olawade, “Explainable machine learning models for early Alzheimer’s disease detection using multimodal clinical data,” International Journal of Medical Informatics, vol. 204, p. 106093, Dec. 2025, doi: 10.1016/j.ijmedinf.2025.106093.
S. Jahan et al., “Explainable AI-based Alzheimer’s prediction and management using multimodal data,” PLoS ONE, vol. 18, no. 11, p. e0294253, Nov. 2023, doi: 10.1371/journal.pone.0294253.
I. Guyon and A. Elisseeff, “An Introduction to Variable and Feature Selection”.
S. M. Lundberg and S.-I. Lee, “A Unified Approach to Interpreting Model Predictions”.
S. M. Lundberg et al., “From local explanations to global understanding with explainable AI for trees,” Nat Mach Intell, vol. 2, no. 1, pp. 56–67, Jan. 2020, doi: 10.1038/s42256-019-0138-9.
J. N. Mandrekar, “Receiver Operating Characteristic Curve in Diagnostic Test Assessment,” Journal of Thoracic Oncology, vol. 5, no. 9, pp. 1315–1316, Sep. 2010, doi: 10.1097/JTO.0b013e3181ec173d.
T. Saito and M. Rehmsmeier, “The Precision-Recall Plot Is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced Datasets,” PLoS ONE, vol. 10, no. 3, p. e0118432, Mar. 2015, doi: 10.1371/journal.pone.0118432.
M. Rohini and D. Surendran, “Weighted Hybrid Random Forest Model for Significant Feature prediction in Alzheimer’s Disease Stages,” Int J Comput Intell Syst, vol. 18, no. 1, p. 53, Mar. 2025, doi: 10.1007/s44196-025-00780-0.
P. A. Ong, F. R. Annisafitrie, N. Purnamasari, C. Calista, N. Sagita, Y. Sofiatin, and Y. Dikot, "Dementia Prevalence, Comorbidities, and Lifestyle Among Jatinangor Elders," Front. Neurol., vol. 12, p. 643480, Jul. 2021, doi: 10.3389/fneur.2021.643480.
Copyright (c) 2026 Nirwana Hendrastuty, Marta Santra Wijaya, Debby Alita
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
