Optimasi Prediksi Hipertensi Menggunakan Logistic Regression Berbasis Borderline SMOTE dan Penjelasan Model dengan SHAP

Risky Radison Nasution ; Kurniabudi Kurniabudi ; Dodo Zaenal Abidin
Prosiding Seminar Nasional Ilmu Teknik 📅 2025 Vol 2, No 2 🔗 DOI: 10.61132/prosemnasproit.v2i2.139
Abstract
Hypertension is a major global health risk that requires accurate early detection, yet conventional methods struggle with complex and imbalanced health datasets. This study aims to optimize hypertension prediction using a Logistic Regression model integrated with Borderline-SMOTE to enhance recall and provide model transparency through SHAP (Shapley Additive Explanations). The method utilizes the BRFSS dataset, applying Borderline-SMOTE to address class imbalance at the decision boundary and XAI techniques for global and local interpretation. The findings show that the model achieved an accuracy of 0.719, an AUC of 0.800, and a significantly improved recall of 0.756. SHAP analysis identified age, high cholesterol, and BMI as the most influential risk factors, while waterfall plots successfully clarified individual risk extremes, ranging from 1.72% to 99.43% probability. These results imply that the proposed approach provides a sensitive and transparent screening tool for public health practitioners, effectively balancing statistical efficiency with clinical accountability.
Keywords
Borderline-SMOTE; Explainable Artificial Intelligence; Hipertensi; Logistic Regression; SHAP
How to Cite

Risky Radison Nasution, et al. (2025). Optimasi Prediksi Hipertensi Menggunakan Logistic Regression Berbasis Borderline SMOTE dan Penjelasan Model dengan SHAP. Prosiding Seminar Nasional Ilmu Teknik, 2(2). https://doi.org/10.61132/prosemnasproit.v2i2.139

Risky Radison Nasution; Kurniabudi Kurniabudi; Dodo Zaenal Abidin, "Optimasi Prediksi Hipertensi Menggunakan Logistic Regression Berbasis Borderline SMOTE dan Penjelasan Model dengan SHAP," Prosiding Seminar Nasional Ilmu Teknik, vol. 2, no. 2, 2025.

Risky Radison Nasution; Kurniabudi Kurniabudi; Dodo Zaenal Abidin. "Optimasi Prediksi Hipertensi Menggunakan Logistic Regression Berbasis Borderline SMOTE dan Penjelasan Model dengan SHAP." Prosiding Seminar Nasional Ilmu Teknik, vol. 2, no. 2, 2025.

Risky Radison Nasution; Kurniabudi Kurniabudi; Dodo Zaenal Abidin. "Optimasi Prediksi Hipertensi Menggunakan Logistic Regression Berbasis Borderline SMOTE dan Penjelasan Model dengan SHAP." Prosiding Seminar Nasional Ilmu Teknik 2, no. 2 (2025).

Risky Radison Nasution, et al. (2025) 'Optimasi Prediksi Hipertensi Menggunakan Logistic Regression Berbasis Borderline SMOTE dan Penjelasan Model dengan SHAP', Prosiding Seminar Nasional Ilmu Teknik, 2(2). doi: 10.61132/prosemnasproit.v2i2.139.

Risky Radison Nasution; Kurniabudi Kurniabudi; Dodo Zaenal Abidin. Optimasi Prediksi Hipertensi Menggunakan Logistic Regression Berbasis Borderline SMOTE dan Penjelasan Model dengan SHAP. Prosiding Seminar Nasional Ilmu Teknik. 2025;2(2).

Artikel Terkait

Pengolahan Citra Digital Kamera Multispektral Berbasis Drone dengan Artificial Neural Network (ANN) untuk Identifikasi Cekaman Air pada Tanaman Padi

Shahiban Muzaki

Analisis Tingkat Kepuasan Pengguna Pada Website Smp Negeri 5 Kota Jambi Menggunakan Model Webqual 4.0 Dan Importance Performance Analisis (Ipa)

Usi Nofriana; Nurhadi Nurhadi; Joni Devitra

Implementasi Simple Additive Weighting Untuk Rekomendasi Karir Mahasiswa Berdasarkan Hasil Tes Psikologi

Moh Nur Iman Siyus Setyowati; Dihin Muriyatmoko; Eko Prasetio Widhi

Analisis Performa Convolutional Neural Network untuk Klasifikasi Aktivitas Pengemudi Terganggu

Zufar Abdullah Rabbani; Wahyu Syaifullah J S; Alfan Rizaldy Pratama

Analisis Korelasi Faktor Gaya Hidup Terhadap Indikator Kesehatan Menggunakan Metode Shapiro-Wilk dan Spearman

Mohd Fadli Ariansyah; Eka Pandu Cynthia

Pengukuran Tingkat Kesiapan Pasien RSUD Abdul Manap Terhadap Mobile JKN Menggunakan Metode HOT-Fit

Titania Arida Nandini; Setiawan Assegaff; Nurhadi Nurhadi
Tren Sitasi Jurnal