Prediksi Demensia Alzheimer Menggunakan Pembelajaran Ensemble Soft Voting dengan ROS dan Grid Search Hyper Parameter Tuning

• Edwin Rudini
• 14220004

---

ABSTRAK

Alzheimer's dementia (AD) adalah penyakit otak degeneratif yang ditandai dengan penurunan fungsi kognitif dan memori. Memprediksi AD sangat penting untuk mencegah perkembangan penyakit ini menjadi semakin berbahaya. Algoritma pembelajaran mesin dapat membantu dalam prediksi dini AD. Tujuan utama penelitian ini adalah mengembangkan model prediktif dengan akurasi yang lebih baik menggunakan metode ensemble learning dan algoritma pembelajaran mesin (ML). Dataset Oasis Longitudinal dari Oasis Brains, yang mengumpulkan rincian pasien dengan dan tanpa AD, dipertimbangkan untuk eksperimen ini. Klasifikasi biner difasilitasi oleh classifier ensemble learning menggunakan teknik soft voting dengan empat algoritma ensemble learning: Extreme Gradient Boosting Classifier (XGBC), Random Forest (RF), AdaBoost Classifier (ADC), dan Gradient Boosting Classifier (GBC) untuk tugas klasifikasi. Evaluasi empiris dari metodologi yang diusulkan dilakukan dengan kriteria evaluasi akurasi, presisi, recall, dan f1-score. Dalam konteks prediksi AD, kinerja algoritma menggunakan metode resampling Random Over Sampling (ROS) dan tuning hyperparameter grid search untuk algoritma GBC terbukti menjadi yang terbaik dengan akurasi 97 %. Pendekatan ensemble learning yang diusulkan dengan teknik soft voting menghasilkan nilai akurasi, presisi, sensitivitas, f1-score, dan kurva ROC AUC tertinggi masing-masing sebesar 97%, 98%, 97%, 97%, dan 98% pada dataset pengujian.

Kata Kunci: Dementia Alzheimer, Klasifikasi, Ensemble Learning, ROS and Grid Search hyper tuning Algoritma GBC

KATA KUNCI

Ensemble,Algoritma,Metode Klasifikasi

---

DAFTAR PUSTAKA

[1] M. Ali Mohammed, “Alzheimer Disease Detection and Prognosis from Clinical Data using Machine Learning Techniques Research Project MSc in Data Analytics (MSCDA-B).” [Online]. Available: https://www.who.int/news- room/fact-sheets/detail/the-top-10-causes-of-death

[2] P. Iso-Markku, U. M. Kujala, K. Knittle, J. Polet, E. Vuoksimaa, and K. Waller, “Physical activity as a protective factor for dementia and Alzheimer’s disease: systematic review, meta-analysis and quality assessment of cohort and case- control studies,” Jun. 01, 2022, BMJ Publishing Group. doi: 10.1136/bjsports- 2021-104981.

[3] S. Grueso and R.Viejo-Sobera, “Machine learning methods for predicting progression from mild cognitive impairment to Alzheimer’s disease dementia: a systematic review,” Alzheimers Res Ther, vol. 13, no. 1, Dec. 2021, doi: 10.1186/s13195-021-00900

[4] M. Bari Antor et al., “A Comparative Analysis of Machine Learning Algorithms to Predict Alzheimer’s Disease,” J Healthc Eng, vol. 2021, 2021, doi: 10.1155/2021/9917919.

[5] S. Khotimatul Wildah, S. Agustiani, M. S. Rangga Ramadhan, W. Gata, H. Mahmud Nawawi, and S. Nusa Mandiri, “Deteksi Penyakit Alzheimer Menggunakan Algoritma Naïve Bayes dan Correlation Based Feature Selection,” JURNAL INFORMATIKA, vol. 7, no. 2, pp. 166–173, 2020, [Online]. Available: http://ejournal.bsi.ac.id/ejurnal/index.php/ji

[6] A. Javeed, A. L. Dallora, J. S. Berglund, and P. Anderberg, “An Intelligent Learning System for Unbiased Prediction of Dementia Based on Autoencoder and Adaboost Ensemble Learning,” Life, vol. 12, no. 7, Jul. 2022, doi: 10.3390/life12071097.

[7] Q. Cao et al., “The Prevalence of Dementia: A Systematic Review and Meta- Analysis,” J Alzheimers Dis, vol.73, no.3, pp.1157–1166, 2020, doi: 10.3233/JAD-191092. 66 Program Studi Ilmu Komputer (S2) FTI Universitas Nusa Mandiri

[8] R. Ren et al., “The China Alzheimer Report 2022,” Mar. 11, 2022, BMJ Publishing Group. doi: 10.1136/gpsych-2022-100751.

[9] B. Mahesh, “Machine Learning Algorithms - A Review,” International Journal of Science and Research (IJSR), vol. 9, no.1, pp. 381–386, Jan. 2020, doi: 10.21275/ART20203995.

[10] S. Kailasam and P. J. Basilio, “Alzheimer’s disease can be diagnosed from healthcare information using machine learning MSc Research Project Data Analytics.”

[11] S. Badillo et al., “An Introduction to Machine Learning,” CLINICAL PHARMACOLOGY & THERAPEUTICS | VOLUME, vol. 107, no. 4, 2020, doi: 10.1002/cpt.1796.

[12] S. Diantika et al., “Perbandingan Algoritma Klasifikasi K-Nearest Neighbor, Random Forest dan Gradient Boosting untuk Memprediksi Ketertarikan Nasabah pada Polis Asuransi Kendaraan,” vol.6, no.3, pp. 463–469, 2021, doi: 10.32493/informatika.v6i3.9419.

[13] P. Mahajan, S. Uddin, F. Hajati, and M. A. Moni, “Ensemble Learning for DiseasePrediction:AReview,”Jun.01,2023,MDPI.doi:10.3390/healthcare11121 808.

[14] F. Titiani and D. Riana, “Ensemble Learning for the Prediction of Marketing Campaign Acceptance,” International Journal of Software Engineering and ComputerSystems,vol.8,no.2,pp.67–76,Jul.2022,doi: 10.15282/ijsecs.8.2.2022.7.0104.

[15] A. Mahajan et al., “A Novel Stacking-Based Deterministic Ensemble Model for Infectious Disease Prediction,” Mathematics,vol. 10, no. 10, May 2022, doi: 10.3390/math10101714.

[16] S. Dong, A. Khattak, I. Ullah, J. Zhou, and A. Hussain, “Predicting and Analyzing Road Traffic Injury Severity Using Boosting-Based Ensemble Learning Models with SHAPley Additive exPlanations,” Int J Environ Res Public Health, vol. 19, no. 5, Mar. 2022, doi: 10.3390/ijerph19052925.

[17] S. Chatterjee and Y. C. Byun, “Voting Ensemble Approach for Enhancing 67 Program Studi Ilmu Komputer (S2) FTI Universitas Nusa Mandiri Alzheimer’s Disease Classification,” Sensors, vol. 22, no. 19, Oct. 2022, doi: 10.3390/s22197661.

[18] A. Manconi, G. Armano, M. Gnocchi, and L. Milanesi, “A Soft-Voting Ensemble Classifier for Detecting Patients Affected by COVID-19,” Applied Sciences (Switzerland), vol. 12, no. 15, Aug. 2022, doi: 10.3390/app12157554.

[19] A. H. Syed, T. Khan, A. Hassan, N. A. Alromema, M. Binsawad, and A. O. Alsayed, “An Ensemble- Learning Based Application to Predict the Earlier Stages of Alzheimer’s Disease (AD),” IEEE Access, vol. 8, pp. 222126–222143, 2020, doi: 10.1109/ACCESS.2020.3043715.

[20] S. Kumari, D. Kumar, and M. Mittal, “An ensemble approach for classification and prediction of diabetes mellitus using soft voting classifier,” International Journal of Cognitive Computing in Engineering, vol. 2, pp. 40–46, Jun. 2021, doi: 10.1016/j.ijcce.2021.01.001.

[21] S. Parvez, S. Zubair, and A. Khan, “A Hybrid Approach for Weak Learners Utilizing Ensemble Technique for Alzheimer’s Disease Prognosis,” Indian J Sci Technol,vol.16,no.32,pp.2518–2533,Aug.2023,doi: 10.17485/IJST/v16i32.1007.

[22] C. Kavitha, V. Mani, S. R. Srividhya, O. I. Khalaf, and C. A. Tavera Romero, “Early-Stage Alzheimer’s Disease Prediction Using Machine Learning Models,”FrontPublicHealth,vol.10,Mar.2022, doi: 10.3389/fpubh.2022.853294.

[23] G. Battineni et al., “Improved alzheimer’s disease detection by MRI using multimodal machine learningalgorithms,” Diagnostics,vol.11,no. 11, Nov. 2021, doi: 10.3390/diagnostics11112103.

[24] R. Dahlia, S. Hadianti, R. Dahlia, N. Wuryani, W. Gata, and A. Selawati, “PENERAPAN DATA MINING TERHADAP DATA COVID-19 MENGGUNAKAN ALGORITMA KLASIFIKASI,” 1045.

[25] V. Çetin and O. Y?ld?z, “A comprehensive review on data preprocessing techniques in data analysis,” Pamukkale University Journal of Engineering Sciences, vol. 28, no. 2, pp. 299–312, 2022, doi: 10.5505/pajes.2021.62687.

[26] G. Kabir, S. Tesfamariam, J. Hemsing, and R. Sadiq, “Handling incomplete and 68 Program Studi Ilmu Komputer (S2) FTI Universitas Nusa Mandiri missing data in water network database using imputation methods,” Sustain Resilient Infrastruct, vol. 5, no. 6, pp. 365–377, Nov. 2020, doi: 10.1080/23789689.2019.1600960.

[27] R. Zebari, A. Abdulazeez, D. Zeebaree, D. Zebari, and J. Saeed, “A Comprehensive Review of Dimensionality Reduction Techniques for Feature Selection and Feature Extraction,” Journal of Applied Science and Technology Trends, vol.1, no. 1, pp. 56–70, May 2020, doi: 10.38094/jastt1224.

[28] M. V. Polyakova and V. N. Krylov, “Data normalization methods to improve the quality of classification in the breast cancer diagnostic system,” Applied Aspects of Information Technology, vol. 5, no. 1, pp. 55– 63, Apr. 2022, doi: 10.15276/aait.05.2022.5.

[29] R. A. Nugraha, H. F. Pardede, and A. Subekti, “Oversampling based on generative adversarial networks to overcome imbalance data in predicting fraud insurance claim.”

[30] M. Khushi et al., “A Comparative Performance Analysis of Data Resampling Methods on Imbalance Medical Data,” IEEE Access, vol. 9, pp.109960– 109975,2021,doi: 10.1109/ACCESS.2021.3102399.

[31] A. Salim, W. Gata, M. Hilman Fakhriza, C. Sri Rhayu, A. Budiarto, and P. Studi Magister Ilmu Komputer STMIK Nusa Mandiri Jakarta, “Analisis Sentiment Instagram Menggunakan Metode Support Vector Machine (SVM) Berbasis Grid Search Algorithm (GSA).”

[32] X. Jiang and C. Xu, “Deep Learning and Machine Learning with Grid Search to Predict Later Occurrence of Breast Cancer Metastasis Using Clinical Data,” J Clin Med, vol. 11, no. 19, Oct. 2022, doi: 10.3390/jcm11195772.

[33] T. Herwanto, “Logistic Regression with Hyper Parameter Tuning Optimization for Heart Failure Prediction,” Journal Medical Informatics Technology, pp. 13– 18, Mar. 2023, doi: 10.37034/medinftech.v1i1.3.

[34] T. F. Thien and W. S. Yeo, “A comparative study between PCR, PLSR, and LW- PLS on the predictive performance at different data splitting ratios,” Chem Eng Commun,vol.209,no.11,pp.1439–1456,2022,doi: 69 Program Studi Ilmu Komputer (S2) FTI Universitas Nusa Mandiri 10.1080/00986445.2021.1957853.

[35] S. E. Ryu, D. H. Shin, and K. Chung, “Prediction model of dementia risk based on XGBoost using derived variable extraction and hyper parameter optimization,” IEEE Access, vol. 8, pp. 177708–177719, 2020, doi: 10.1109/ACCESS.2020.3025553.

[36] U. Khultsum and A. Subekti, “Penerapan Algoritma Random Forest dengan Kombinasi Ekstraksi Fitur Untuk Klasifikasi Penyakit Daun Tomat,” JURNAL MEDIA INFORMATIKA BUDIDARMA, vol. 5, no. 1,p. 186, Jan. 2021, doi: 10.30865/mib.v5i1.2624.

[37] H. Nalatissifa, W. Gata, S. Diantika, and K. Nisa, “Perbandingan Kinerja Algoritma Klasifikasi Naive Bayes, Support Vector Machine (SVM), dan Random Forest untuk Prediksi Ketidakhadiran di Tempat Kerja,” Jurnal Informatika Universitas Pamulang, vol. 5, no. 4, p. 578, Dec. 2021, doi: 10.32493/informatika.v5i4.7575.

[38] A. Subekti, “Analisis Sentiment pada Ulasan Film Dengan Optimasi Ensemble Learning,” JURNAL INFORMATIKA, vol. 7, no. 1, 2020, [Online]. Available: http://reviews.imdb.com/Reviews.

[39] F. Ernawan, U. Malaysia Pahang Pekan, M. Kartika Handayani, M. Fakhreldin, and Y. Abbker, “Light Gradient Boosting with Hyper Parameter Tuning Optimization for COVID-19 Prediction,”2022.[Online].Available: www.ijacsa.thesai.org

[40] K. Yongcharoenchaiyasit, S. Arwatchananukul, P. Temdee, and R. Prasad, “Gradient Boosting Based Model for Elderly Heart Failure, Aortic Stenosis, and DementiaClassification,”IEEEAccess,vol.11,pp.48677–48696,2023,doi: 10.1109/ACCESS.2023.3276468.

[41] D. Chicco and G. Jurman, “The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation,” BMC Genomics, vol. 21, no. 1, Jan. 2020, doi: 10.1186/s12864-019- 6413-7.

[42] Z. Mushtaq, M. F. Ramzan, S. Ali, S. Baseer, A. Samad, and M. Husnain, 70 Program Studi Ilmu Komputer (S2) FTI Universitas Nusa Mandiri “Voting Classification-Based Diabetes Mellitus Prediction Using Hypertuned Machine-Learning Techniques,” Mobile Information Systems, vol. 2022, 2022, doi: 10.1155/2022/6521532.

[43] A. Rahmawati, Y. Rianto, D. Riana, P. Studi Ilmu Komputer, and S. Tinggi Manajemen Informatika dan Komputer Nusa Mandiri, “Deteksi Defect Coffee Pada Citra Tunggal Green Beans Menggunakan Metode Ensamble Decision Tree Detection of Defect Coffee in Green Beans Single Image Using the Ensemble Decision Tree Method,” 2021.

[44] D.Riana et al., “Identifikasi Citra Pap Smear RepoMedUNM dengan Menggunakan K-Means Clustering dan GLCM,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol.6, no.1, pp.1–8, Jan.2022, doi: 10.29207/resti.v6i1.3495.

[45] K. Gajowniczek and T. Z?bkowski, “ImbTreeAUC: An R package for building classification trees using the area under the ROC curve (AUC) on imbalanced datasets,” SoftwareX, vol. 15, Jul. 2021, doi: 10.1016/j.softx.2021.100755.

[46] G. Wei, J. Zhao, Y. Feng, A. He, and J. Yu, “A novel hybrid feature selection method based on dynamic feature importance,” Applied Soft Computing Journal, vol. 93, Aug. 2020, doi: 10.1016/j.asoc.2020.106337.

[47] O. Oleghe, “A predictive noise correction methodology for manufacturing process datasets,” J Big Data, vol. 7, no. 1, Dec. 2020, doi: 10.1186/s40537- 020-00367-w.