Identifikasi Faktor Dominan Risiko Depresi Remaja Menggunakan XGBoost dengan Interpretasi SHAP

Hartati Tammamah Lubis; Randy Brilliant Chandra; Muhammad Nasri Gea; Erica Rian Safitri

doi:10.30865/json.v7i4.9864

Authors

Hartati Tammamah Lubis Universitas Prima Indonesia
Randy Brilliant Chandra Institut Bisnis IT&B
Muhammad Nasri Gea Akademi Manajemen Informatika dan Komputer ITMI
Erica Rian Safitri Universitas Muhammadiyah OKU Timur

DOI:

https://doi.org/10.30865/json.v7i4.9864

Keywords:

Depresi Remaja, XGBoost, Explainable Artificial Intelligence, SHAP, Klasifikasi

Abstract

Depresi pada remaja merupakan salah satu masalah kesehatan mental yang dapat memengaruhi kesejahteraan psikologis, prestasi akademik, dan interaksi sosial. Identifikasi faktor-faktor yang berkontribusi terhadap risiko depresi diperlukan untuk mendukung upaya deteksi dini dan pencegahan yang lebih efektif. Penelitian ini bertujuan mengidentifikasi faktor dominan yang berkontribusi terhadap prediksi risiko depresi remaja menggunakan Extreme Gradient Boosting (XGBoost) dengan interpretasi SHapley Additive exPlanations (SHAP). Penelitian memanfaatkan dataset publik yang terdiri atas 1.200 sampel remaja dengan atribut karakteristik individu, kondisi psikologis, penggunaan media sosial, dan aspek gaya hidup. Untuk mengatasi ketidakseimbangan kelas digunakan pendekatan scale_pos_weight, sedangkan evaluasi model dilakukan menggunakan Repeated Stratified Cross Validation. Hasil pengujian menunjukkan rata-rata F1-score sebesar 96,11% dengan standar deviasi 5,66%, yang mengindikasikan performa klasifikasi yang baik dan konsisten. Analisis SHAP menunjukkan bahwa sleep_hours, stress_level, daily_social_media_hours, dan anxiety_level merupakan variabel yang memberikan kontribusi terbesar terhadap prediksi model. Temuan ini menunjukkan bahwa pada dataset yang digunakan, berkurangnya durasi tidur, tingginya tingkat stres dan kecemasan, serta penggunaan media sosial yang lebih intens berkontribusi terhadap peningkatan prediksi risiko depresi. Selain menghasilkan performa klasifikasi yang baik, pendekatan XGBoost dengan SHAP juga meningkatkan transparansi model dalam menjelaskan kontribusi masing-masing variabel terhadap hasil prediksi. Hasil penelitian ini bersifat prediktif berdasarkan dataset yang digunakan dan tidak dimaksudkan sebagai dasar diagnosis klinis depresi.

References

[1] A. Maerlender and P. G. Bray, Adolescent Mental Health in the Twenty-First Century.pdf, 1st Editio. Cham, Switzerland: Springer Nature, 2024. doi: 10.1007/978-3-031-68294-0_2.

[2] A. Yoo et al., “Prediction of adolescent depression from prenatal and childhood data from ALSPAC using machine learning,” Sci. Rep., pp. 1–13, 2024, doi: 10.1038/s41598-024-72158-9.

[3] C. Mimikou et al., “Explainable Machine Learning in the Prediction of Depression,” Diagnostics, vol. 15, no. 11, pp. 1–18, 2025, doi: 10.3390/diagnostics15111412.

[4] Amirah Ellyza Wahdi; Althaf Setyawan; Yufan Astrini Putri; Siswanto Agus Wilopo; Holly E. Erskine; Krystina Wallis; Cartiah McGrath; Sarah J. Blondell; Harvey A. Whiteford; James G. Scott; Robert Blum; Shoshanna Fine; Mengmeng Li; Astha Ramaiya, “Indonesia – National Adolescent Mental Health Survey (I-NAMHS) Report,” Center for Reproductive Health, Yogyakarta, Indonesia, 2022.

[5] H. Do et al., “Apply Machine Learning to Predict Risk for Adolescent Depression in a Cohort of Kenyan Adolescents,” Healthcare, vol. 13, no. 20, pp. 1–19, 2025, doi: 10.3390/healthcare13202620.

[6] X. Chen et al., “BMC Med Inform Decis Mak Article in Press Predicting adolescent depression : an interpretable machine learning model IN AR IN,” BMC Med. Inform. Decis. Mak., 2026, doi: 10.1186/s12911-026-03482-5.

[7] N. Agyapong-opoku, F. Agyapong-opoku, and A. J. Greenshaw, “Effects of Social Media Use on Youth and Adolescent Mental Health : A Scoping Review of Reviews,” Behav. Sci. (Basel)., vol. 15, no. 5, pp. 1–22, 2025, doi: 10.3390/bs15050574.

[8] M. Syahruzzidan, A. Syauqi, and P. Nahariani, “The Impact of Social Media Use on Adolescent Mental Health,” J. Ilm. Keperawatan, vol. 20, pp. 40–47, 2025, doi: 10.30643/jiksht.v20i2.427.

[9] M. Gao and C. Lee, “Sleep duration and depression among adolescents : Mediation effect of collective integration,” no. November, pp. 1–14, 2022, doi: 10.3389/fpsyg.2022.1015089.

[10] S. O. Mensah et al., “Evaluation and treatment of sleep disorders in adolescents with depression ; a scoping review,” BMC Psychiatry, vol. 25, no. 2025, 2026, doi: 10.1186/s12888-025-07652-z.

[11] A. Putri and A. Ispriantari, “Sleep Quality And Mental Health Among Junior High School Students,” Prof. Heal. J., vol. 8, no. 1, pp. 125–132, 2026, doi: 10.54832/phj.v8i1.1347.

[12] M. T. Mardini, G. E. Khalil, C. Bai, A. M. Divakaran, and J. M. Ray, “Identifying Adolescent Depression and Anxiety Through Real-World Data and Social Determinants of Health : Machine Learning Model Development and Validation,” vol. 12, pp. 1–11, 2025, doi: 10.2196/66665.

[13] Y. Xin et al., “Machine learning-based analysis and prediction of factors influencing mental health among children and adolescents in Jiangsu Province,” Child Adolesc. Psychiatry Ment. Health, vol. 5, pp. 1–8, 2025, doi: 10.1186/s13034-025-00959-5.

[14] G. Sharma, M. J. Yaffe, P. Ghadiri, R. Gandhi, and L. Pinkham, “Use of Artificial Intelligence in Adolescents ’ Mental Health Care : Systematic Scoping Review of Current Applications and Future Directions,” vol. 12, pp. 1–14, doi: 10.2196/70438.

[15] J. Ilmiah et al., “EARLY DETECTION OF ACADEMIC DEPRESSION USING SMARTPHONE-,” J. Ilm. Ilmu Terap. Univ. Jambi, vol. 9, no. 3, pp. 1104–1116, 2025, doi: 10.22437/jiituj.v9i3.46375.

[16] I. Ahmed, A. Brahmacharimayum, R. H. Ali, T. A. Khan, M. O. Ahmad, and M. O. Ahmad, “Explainable AI for Depression Detection and Severity Classification From Activity Data : Development and Evaluation Study of an Interpretable Framework,” JMIR Ment. Heal., vol. 12, no. 1, 2025, doi: 10.2196/72038.

[17] K. Lamba, S. Rani, and M. Shabaz, “Explainable machine learning for mental health prediction from social media behavior : a nested cross-validation study with SHAP and LIME interpretability,” Discov. Ment. Heal., vol. 6, 2026, doi: 10.1007/s44192-026-00373-z.

[18] C. Molnar, Interpretable Machine Learning A Guide for Making Black Box Models Explainable. Munich, Germany: Leanpub, 2022.

[19] M. Shahzad, “Social Media Impact on Teen Mental Health,” Kaggle. Accessed: Jun. 02, 2026. [Online]. Available: https://www.kaggle.com/datasets/algozee/teenager-menthal-healy

[20] E. Junianto and S. Nurkhodijah, “Explainable Ensemble Learning for Depression Risk Classification Using Multidomain Behavioral Features,” J. Tek. Inform., vol. 7, no. 2, pp. 778–792, 2026, doi: 10.52436/1.jutif.2026.7.2.5009.