Studi Eksploratif Pipeline Multilayer Perceptron pada Dataset Sintetik Berlabel Deterministik: Implikasi Metodologis untuk Klasifikasi Hipertensi

Ivónia Fátima Ruas da Silva; Bambang Purnomosidi Dwi Putranto; Widyastuti Andriyani

doi:10.56427/jcbd.v5i2.991

Authors

Ivónia Fátima Ruas da Silva Universitas Teknologi Digital Indonesia
Bambang Purnomosidi Dwi Putranto Universitas Teknologi Digital Indonesia
Widyastuti Andriyani Universitas Teknologi Digital Indonesia

DOI:

https://doi.org/10.56427/jcbd.v5i2.991

Keywords:

Hipertensi, Multilayer Perceptron, Deep Learning, Dataset Sintetik, Skrining Klinis

Abstract

Hipertensi merupakan penyakit kardiovaskular dengan prevalensi tinggi dan menjadi penyebab utama mortalitas global, sehingga deteksi dini menjadi kebutuhan klinis yang krusial. Namun, pengembangan model deep learning pada konteks sumber daya terbatas sering terkendala ketersediaan dataset berskala besar. Gap penelitian yang diidentifikasi adalah belum tersedianya studi eksploratif yang secara eksplisit menguji kelayakan pipeline Multilayer Perceptron (MLP) sederhana pada dataset berukuran sangat kecil dengan dokumentasi reproducible. Penelitian ini bertujuan mendemonstrasikan pipeline MLP end-to-end pada dataset sintetik 150 sampel dengan sembilan fitur biometrik dan gaya hidup. Setelah one-hot encoding dan normalisasi Min-Max, dimensi input menjadi 15 neuron. Arsitektur MLP terdiri atas tiga hidden layer (64-32-16, ReLU) dan output sigmoid, dilatih 100 epoch menggunakan optimizer Adam (learning rate 0,001; batch size 16) dengan early stopping. Evaluasi pada test set (n = 30) memperoleh akurasi 90,00%, presisi 85,00%, recall 100%, F1-score 91,90%, dan AUC-ROC 0,91, dengan tiga false positive teridentifikasi sebagai kasus borderline pre-hypertension. Kontribusi penelitian terletak pada penyajian artefak reproducible—dataset sintetik, kode preprocessing, dan visualisasi diagnostik—sebagai baseline pedagogis untuk institusi berketerbatasan data. Keterbatasan utama, yaitu sifat deterministik label yang berpotensi menimbulkan circular reasoning pada fitur tekanan darah, didokumentasikan eksplisit sebagai catatan validitas internal.

Downloads

Download data is not yet available.

Author Biography

Bambang Purnomosidi Dwi Putranto, Universitas Teknologi Digital Indonesia

References

[1] World Health Organization, Global report on hypertension: The race against a silent killer. Geneva: WHO Press, 2023. [Online]. Available: https://www.who.int/publications/i/item/9789240081062

[2] K. T. Mills, A. Stefanescu, and J. He, “The global epidemiology of hypertension,” Nature Reviews Nephrology, vol. 16, no. 4, pp. 223–237, 2020, doi: 10.1038/s41581-019-0244-2.

[3] B. Williams et al., “2018 ESC/ESH Guidelines for the management of arterial hypertension,” European Heart Journal, vol. 39, no. 33, pp. 3021–3104, 2018, doi: 10.1093/eurheartj/ehy339.

[4] P. K. Whelton et al., “2017 ACC/AHA/AAPA/ABC/ACPM/AGS/APhA/ASH/ASPC/NMA/PCNA Guideline for the Prevention, Detection, Evaluation, and Management of High Blood Pressure in Adults,” Hypertension, vol. 71, no. 6, pp. e13–e115, 2018, doi: 10.1161/HYP.0000000000000065.

[5] D. Dey, P. J. Slomka, P. Leeson, D. Comaniciu, S. Shrestha, P. P. Sengupta, and T. H. Marwick, “Artificial Intelligence in Cardiovascular Imaging: JACC State-of-the-Art Review,” Journal of the American College of Cardiology, vol. 73, no. 11, pp. 1317–1335, 2019, doi: 10.1016/j.jacc.2018.12.054.

[6] A. Esteva et al., “A guide to deep learning in healthcare,” Nature Medicine, vol. 25, no. 1, pp. 24–29, 2019, doi: 10.1038/s41591-018-0316-z.

[7] M. Baharoon et al., “HyMNet: A Multimodal Deep Learning System for Hypertension Prediction Using Fundus Images and Cardiometabolic Risk Factors,” Bioengineering, vol. 11, no. 11, art. 1080, 2024, doi: 10.3390/bioengineering11111080.

[8] H. Kim, S. Hwang, S. Lee, and Y. Kim, “Classification and Prediction on Hypertension with Blood Pressure Determinants in a Deep Learning Algorithm,” International Journal of Environmental Research and Public Health, vol. 19, no. 22, art. 15301, 2022, doi: 10.3390/ijerph192215301.

[9] I. Skalidis et al., “Artificial Intelligence and Advanced Digital Health for Hypertension: Evolving Tools for Precision Cardiovascular Care,” Medicina, vol. 61, no. 9, art. 1597, 2025, doi: 10.3390/medicina61091597.

[10] M. Asadullah et al., “Evaluation of machine learning techniques for hypertension risk prediction based on medical data in Bangladesh,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 31, no. 3, pp. 1794–1802, 2023, doi: 10.11591/ijeecs.v31.i3.pp1794-1802.

[11] E. Bisong, N. Jibril, P. Premnath, E. Buligwa, G. Oboh, and A. Chukwuma, “Predicting high blood pressure using machine learning models in low- and middle-income countries,” BMC Medical Informatics and Decision Making, vol. 24, no. 1, art. 234, 2024, doi: 10.1186/s12911-024-02634-9.

[12] M. M. Islam et al., “Predicting the risk of hypertension using machine learning algorithms: A cross sectional study in Ethiopia,” PLOS ONE, vol. 18, no. 8, art. e0289613, 2023, doi: 10.1371/journal.pone.0289613.

[13] J. S. Cho and J. H. Park, “Application of artificial intelligence in hypertension,” Clinical Hypertension, vol. 30, no. 1, pp. 1–9, 2024, doi: 10.1186/s40885-024-00266-9.

[14] T. Chaikijurajai, L. J. Laffin, and W. H. W. Tang, “Artificial intelligence and hypertension: Recent advances and future outlook,” American Journal of Hypertension, vol. 33, no. 11, pp. 967–974, 2020, doi: 10.1093/ajh/hpaa102.

[15] A. Ostovar, D. D. Davari, and M. Dzikuć, “Determinants of Design with Multilayer Perceptron Neural Networks: A Comparison with Logistic Regression,” Sustainability, vol. 17, no. 6, art. 2611, 2025, doi: 10.3390/su17062611.

[16] Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, 2015, doi: 10.1038/nature14539.

[17] K. He, X. Zhang, S. Ren, and J. Sun, “Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification,” in Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2015, pp. 1026–1034, doi: 10.1109/ICCV.2015.123.

[18] D. P. Kingma and J. Ba, “Adam: A Method for Stochastic Optimization,” in Proceedings of the 3rd International Conference on Learning Representations (ICLR), San Diego, CA, USA, 2015, arXiv:1412.6980.

[19] N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, “Dropout: A Simple Way to Prevent Neural Networks from Overfitting,” Journal of Machine Learning Research, vol. 15, no. 1, pp. 1929–1958, 2014.