Analisis Komparatif Algoritma Machine Learning untuk Prediksi Depresi Mahasiswa Berbasis PHQ-9

Asep Setiyono; Yulia Wardani; Margaretha Kurniastuti

doi:10.30865/json.v7i4.9768

Authors

Asep Setiyono STIKes Panti Rapih Yogyakarta
Yulia Wardani STIKes Panti Rapih Yogyakarta
Margaretha Kurniastuti STIKes Panti Rapih Yogyakarta

DOI:

https://doi.org/10.30865/json.v7i4.9768

Keywords:

machine learning, prediksi, depresi, PHQ-9, Komparatif

Abstract

Depresi adalah suatu kondisi gangguan mental yang perlu mendapatkan perhatian serius, terutama di kalangan mahasiswa yang menghadapi tekanan akademik dan sosial. Prevalensi depresi pada mahasiswa mencapai angka yang mengkhawatirkan, dengan deteksi dini dan intervensi yang akurat menjadi krusial. Penelitian ini bertujuan untuk menganalisis dan membandingkan kinerja empat algoritma machine learning (Random Forest, Logistic Regression, Support Vector Machine, dan Extreme Gradient Boosting) dalam memprediksi depresi mahasiswa di Sekolah Tinggi Ilmu Kesehatan Panti Rapih Yogyakarta. Menggunakan dataset kuesioner PHQ-9 dari 679 mahasiswa, data dipra-proses termasuk penanganan ketidakseimbangan kelas menggunakan SMOTE pada data pelatihan. Evaluasi model dilakukan dengan Stratified K-Fold Cross Validation dan metrik seperti akurasi, presisi, recall, F1-Score serta ROC AUC. Hasil menunjukkan bahwa semua model memiliki kinerja prediktif yang sangat tinggi (akurasi > 92%). Support Vector Machine menunjukkan kinerja terbaik secara keseluruhan dengan akurasi 94,30%, F1-Score 94,40% dan ROC AUC 98,57%. Random Forest unggul dalam recall sebesar 96,12% sementara Extreme Gradient Boosting mencapai presisi tertinggi (93,51%). Penelitian ini mengidentifikasi Support Vector Machine sebagai algoritma paling seimbang untuk prediksi depresi mahasiswa, menawarkan potensi sebagai alat skrining awal yang objektif dan efisien.

References

[1] H. Jin et al., “Predicting depression using serum perfluoroalkyl and polyfluoroalkyl substances levels via interpretable machine learning,” J. Affect. Disord., vol. 391,pp.119976 Dec. 2025, doi: 10.1016/j.jad.2025.119976.

[2] P. W. Simarmata and P. T. Prasetyaningrum, “Development of a Student Depression Prediction Model Based on Machine Learning with Algorithm Performance Evaluation,” J.Inf.Syst.Inform, vol. 7, no. 2, pp. 1283–1305, Jun. 2025, doi: 10.51519/journalisi.v7i2.1087.

[3] J. J. Mann, C. A. Michel, and R. P. Auerbach, “Improving Suicide Prevention Through Evidence-Based Strategies: A Systematic Review,” Am.J.Psychiatry,vol.178,no 7,pp.605-608, Jul.2021, doi: 10.1176/appi.ajp.2020.20060864.

[4] D. Arini Izzah, S. Yitnamurti, and N. M. Rehatta, “Prevalence Of Depression In First-Year Medical Students At Universitas Airlangga, Surabaya, Indonesia,” Maj. Biomorfologi, vol. 31, no. 2, p. 39-42, Jun. 2021, doi: 10.20473/mbiom.v31i2.2021.39-43.

[5] A. S. Ramadianto, I. Kusumadewi, F. Agiananda, and N. W. Raharjanti, “Symptoms of depression and anxiety in Indonesian medical students: association with coping strategy and resilience,” BMC Psychiatry, vol. 22, no. 1, Dec. 2022, doi: 10.1186/s12888-022-03745-1.

[6] N. Arif Ismail, M. Farid Adnan, and I. Fidianingsih, “Psychological Status among the Young Muslim Community in Yogyakarta Province, Indonesia, during the COVID-19 Pandemic,” IMJM, vol. 22, no. 3, 2023, doi: 10.31436/imjm.v22i3.

[7] D. Kurniawan, Pengenalan Machine Learning dengan Python. Jakarta: Gramedia, 2022.

[8] G. H. Al Masud, R. I. Shanto, I. Sakin, and M. R. Kabir, “Effective depression detection and interpretation: Integrating machine learning, deep learning, language models, and explainable AI,” Array, vol. 25,pp. 100375, Mar. 2025, doi: 10.1016/j.array.2025.100375.

[9] M. Nayan et al., “Comparison of the performance of machine learning-based algorithms for predicting depression and anxiety among University Students in Bangladesh: A result of the first wave of the COVID-19 pandemic,” Asian J.Soc. Health and Behav, vol. 5, no. 2, pp. 75–84, Apr. 2022, doi: 10.4103/shb.shb_38_22.

[10] S. M. Pahlevi, Kecerdasan Buatan dengan Deep Learning. Jakarta: Elex Media Komputindo, 2023.

[11] K. Mao, Y. Wu, and J. Chen, “A systematic review on automated clinical depression diagnosis,” Nature Digit.Med, vol.6,no 1,pp 251,Dec.2023, doi: 10.1038/s44184-023-00040-z.

[12] Y. Luo, Y. Chen, A. Salekin, and T. Rahman, “Toward Foundation Model for Multivariate Wearable Sensing of Physiological Signals,” arXiv preprint arXiv: 2412.09758, May 2025.

[13] T. Vu et al., “Prediction of depressive disorder using machine learning approaches: findings from the NHANES,” BMC Med. Inform. Decis. Mak., vol. 25, no. 1, p.27, Dec. 2025, doi: 10.1186/s12911-025-02903-1.

[14] Y. L. Q. Song, L. Chen, H. Liu, and Y. Liu, “Machine learning algorithms to predict depression in older adults in China: a cross-sectional study,” Front. Public Health, vol. 12, p. 1462387, 2024, doi: 10.3389/fpubh.2024.1462387.

[15] C. Mimikou et al., “Explainable Machine Learning in the Prediction of Depression,” Diagnostics, vol. 15, no. 11,pp.1412, Jun. 2025, doi: 10.3390/diagnostics15111412.

[16] U. M. Haque, E. Kabir, and R. Khanam, “Detection of child depression using machine learning methods,” PLoS One, vol. 16, no. 12,pp..e0261131,Dec 2021, doi: 10.1371/journal.pone.0261131.

[17] T. Zhu, “Analysis on the applicability of the random forest,” in Journal of Physics: Conference Series, Institute of Physics Publishing, Aug. 2020, doi: 10.1088/1742-6596/1607/1/012123.

[18] L. Luo et al., “Predictors of depression among Chinese college students: a machine learning approach,” BMC Public Health, vol. 25, no. 1,pp.106, Dec. 2025, doi: 10.1186/s12889-025-21632-8.

[19] P. Schober and T. R. Vetter, “Logistic Regression in Medical Research,” Anesthesia&Analgesia, vol. 132, no. 2, pp.365, Feb 2021.

[20] A. Zaidi and A. S. M. Al Luhayb, “Two Statistical Approaches to Justify the Use of the Logistic Function in Binary Logistic Regression,” Math. Probl. Eng., vol. 2023, no. 1,pp. 5525675, Jan. 2023, doi: 10.1155/2023/5525675.

[21] A. O. Hassan, I. M. Jamal, S. D. Ahmed, and A. U. Abdullahi, “Predicting Student Depression using Machine Learning: A Comparative Analysis of Machine Learning Algorithms for Early Depression Detection in Students,” Am.Int.Theism Univ.Sci.Res.J, vol. 5, no. 1, 2025, doi: 10.63094/AITUSRJ.25.4.1.4.

[22] V. Piccialli and M. Sciandrone, “Nonlinear optimization and support vector machines,” Ann. Oper. Res., vol. 314, no. 1, pp. 15–47, Jul. 2022, doi: 10.1007/s10479-022-04655-x.

[23] N. Huda Ovirianti, M. Zarlis, and H. Mawengkang, “Support Vector Machine Using A Classification Algorithm,” J.Penelit.Tek.Inform, vol. 6, no. 3, 2022, doi: 10.33395/sinkron.v7i3.

[24] Q. Qiang et al., “Identifying risk factors for depression and positive/negative mood changes in college students using machine learning,” Front. Public Health, vol. 13,p. 1606947, 2025, doi: 10.3389/fpubh.2025.1606947.

[25] P. Zhang, Y. Jia, and Y. Shang, “Research and application of XGBoost in imbalanced data,” ,” Int. J. Distrib. Sens. Netw., vol. 18, no. 6, p. 1106935, Jun. 2022, doi: 10.1177/15501329221106935.

[26] C. Yu, X. Kong, W. Yu, X. Ni, J. Chen, and X. Liao, “Machine learning models for predicting the risk of depressive symptoms in Chinese college students,” Front. Psychiatry, vol. 16, p. 1648585,2025, doi: 10.3389/fpsyt.2025.1648585.

[27] S. K. Hashemi, S. L. Mirtaheri, and S. Greco, “Fraud Detection in Banking Data by Machine Learning Techniques,” IEEE Access, vol. 11, pp. 3034–3043, 2023, doi: 10.1109/ACCESS.2022.3232287.

[28] I. Emmanuel, Y. Sun, and Z. Wang, “A machine learning-based credit risk prediction engine system using a stacked classifier and a filter-based feature selection method,” J. Big Data, vol. 11, no. 1, Dec. 2024, doi: 10.1186/s40537-024-00882-0.

[29] A. Hade and M. Elhia, “Predicting mortgage credit defaults in morocco using machine learning approaches,” Discover Artif. Intell, vol. 5, no. 1, Dec. 2025, doi: 10.1007/s44163-025-00303-y.