Interpretative Decision Tree Modeling for Identifying Depression Risk Factors in College Students Using PHQ-9 Data
Isi Artikel Utama
Abstrak
: Penelitian ini bertujuan mengembangkan model Decision Tree yang interpretatif untuk mengidentifikasi tingkat depresi mahasiswa menggunakan data Patient Health Questionnaire-9 (PHQ-9). Depresi pada mahasiswa menjadi isu kesehatan mental yang semakin meningkat, sementara sebagian besar model machine learning masih sulit diinterpretasikan. Oleh karena itu, penelitian ini menggunakan Decision Tree sebagai pendekatan explainable artificial intelligence (XAI) yang mampu menghasilkan aturan keputusan yang transparan dan mudah dipahami. Metode penelitian menggunakan pendekatan supervised learning dengan data PHQ-9 yang direpresentasikan dalam bentuk teks dan dikonversi menjadi numerik menggunakan Label Encoding. Variabel target dibentuk berdasarkan kategori tingkat depresi dari skor total PHQ-9. Model dievaluasi menggunakan teknik 5-fold cross-validation dengan metrik accuracy, precision, recall, dan F1-score. Hasil penelitian menunjukkan bahwa model memperoleh accuracy sebesar 54.4% pada cross-validation dan 68% pada data pelatihan, dengan macro F1-score sebesar 0.67. Analisis feature importance menunjukkan bahwa variabel PHQ2 menjadi faktor paling dominan dalam klasifikasi depresi. Selain itu, struktur Decision Tree mampu memberikan interpretasi yang jelas terhadap pola gejala depresi mahasiswa. Penelitian ini menunjukkan bahwa Decision Tree berpotensi mendukung deteksi dini depresi mahasiswa secara lebih transparan dan interpretable.
Rincian Artikel
Referensi
[2] R. Beiter, et al., The prevalence and correlates of depression, anxiety, and stress in a sample of college students, Journal of Affective Disorders (2015). doi:10.1016/j.jad.2014.10.054
[3] T. M. Evans, et al., Evidence for a mental health crisis in graduate education, Nature Biotechnology (2018). doi:10.1038/nbt.4089.
URL https://doi.org/10.1038/nbt.4089
[4] K. Kroenke, R. L. Spitzer, J. B. Williams, The phq-9: validity of a brief depression severity measure, Journal of General Internal Medicine (2001). doi:10.1046/j.1525-1497.2001.016009606.x.
[5] R. L. Spitzer, K. Kroenke, J. B. W. Williams, Validation and utility of a self-report version of prime-md, JAMA (1999). doi:10.1001/jama. 282.18.1737.
[6] B. Levis, et al., Accuracy of patient health questionnaire-9 (phq-9) for screening to detect major depression, BMJ (2019). doi:10.1136/bmj.I146. URL https://doi.org/10.1136/bmj.l1476
[7] American Psychiatric Association, Diagnostic and statistical manual of mental disorders (dsm-5)Official manual, often via APA or library (2013). doi:10.1176/appi.books.9780890425596.
[8] A. Rajkomar, J. Dean, I. Kohane, Machine learning in medicine, New England Journal of Medicine (2019). doi:10.1056/NEJMra1814259.
URL https://doi.org/10.1056/NEJMra1814259
[9] A. B. R. Shatte, et al., Understanding the effect of adding auto-mated and human coaching to a mobile health physical activity app for afghanistan and iraq veterans: Protocol for a randomized con-trolled trial of the stay strong intervention, JMIR Mental Health (2019). doi:10.2196/12526.
URL https://doi.org/10.2196/12526
[10] E. J. Topol, High-performance medicine: the convergence of human and artificial intelligence, Nature Medicine (2019). doi:10.1038/ s41591-018-0300-7.
URL https://doi.org/10.1038/s41591-018-0300-7
[11] F. Doshi-Velez, B. Kim, Towards a rigorous science of interpretable ml, arXiv (2017). doi:10.48550/arXiv.1702.08608.
URL https://arxiv.org/abs/1702.08608
[12] C. Molnar, Interpretable machine learningOnline book (free) (2020).
URL https://christophm.github.io/interpretable-ml-book/
[13] L. Breiman, J. Friedman, R. A. Olshen, C. J. Stone, Classification and Regression Trees, 1984, classic book, often available via library or archive. doi:10.1201/9781315139470.
URL https://doi.org/10.1201/9781315139470
[14] R. H. Salk, J. S. Hyde, L. Y. Abramson, Gender differences in de-pression in representative national samples: Meta-analyses of diag-noses and symptoms, Psychological Bulletin 143 (8) (2017) 783–822. doi:10.1037/bul0000102. URL https://doi.org/10.1037/bul0000102
[15] J. Dinis, M. Bragança, Quality of sleep and depression in college students: A systematic review, Sleep Science (2018). doi:10.5935/ 1984-0063.20180045. URL https://doi.org/10.5935/1984-0063.20180045
[16] D. Bzdok, A. Meyer-Lindenberg, Machine learning for precision psychia-try, Biological Psychiatry (2018). doi:10.1016/j.bpsc.2017.11.007.
URL https://doi.org/10.1016/j.bpsc.2017.11.007
[17] I. Goodfellow, Y. Bengio, A. Courville, Deep learningMIT Press book (2016). URL https://www.deeplearningbook.org/
[18] S. M. Lundberg, S.-I. Lee, A unified approach to interpreting model predictions, Advances in Neural Information Processing Systems (NeurIPS) (2017). URL https://papers.nips.cc/paper/ 7062-a-unified-approach-to-interpreting-model-predictions
[19] S. M. Lundberg, G. Erion, H. Chen, A. DeGrave, J. M. Prutkin, B. Nair,
R. Katz, J. Himmelfarb, N. Bansal, S.-I. Lee, From local explanations to global understanding with explainable ai for trees, Nature Machine Intelligence 2 (1) (2020) 56–67. doi:10.1038/s42256-019-0138-9.
URL https://doi.org/10.1038/s42256-019-0138-9
[20] T. Hastie, R. Tibshirani, J. Friedman, The elements of statistical learn-ingSecond edition 2009 (most cited) (2001). URL https://hastie.su.domains/ElemStatLearn/