Publisher

IDID

Journal Jurnal Ilmu Komputer dan InformatikaJurnal Ilmu Komputer dan Informatika Abstract

Heart failure remains one of the leading causes of mortality worldwide, highlighting the need for reliable early‑detection models to support clinical decision‑making. This study investigates the effect of Random Search–based hyperparameter optimization on a Decision Tree model for heart failure risk prediction using a clinical dataset comprising 918 samples and 11 demographic and cardiovascular features. Rather than introducing a novel optimization algorithm, this work focuses on analyzing model performance sensitivity to hyperparameter tuning in a real‑world medical dataset. The baseline Decision Tree achieved an accuracy of 0.80; after Random Search optimization, accuracy improved to 0.84, while recall for the positive class increased from 0.83 to 0.90, indicating a notable reduction in false‑negative predictions. The optimized configuration, characterized by a shallow tree depth and increased minimum samples per leaf, suggests improved generalization and reduced overfitting. Compared with related studies employing ensemble‑based models and genetic optimization, the proposed approach achieves competitive performance using a simpler and more interpretable classifier. These findings demonstrate that systematic hyperparameter tuning can substantially enhance the clinical utility of conventional machine learning models. Practically, the improved recall supports the use of the optimized Decision Tree as a screening‑oriented decision support tool, enabling earlier identification of high‑risk patients while maintaining model transparency. This study highlights the importance of dataset‑specific optimization and provides a foundation for future work involving ensemble methods and advanced optimization strategies to develop robust and clinically applicable heart failure prediction systems.

Conclusion

Penggunaan Random Search untuk mengoptimalkan hyperparameter Decision Tree meningkatkan akurasi dan sensitivitas prediksi risiko gagal jantung, khususnya dengan menurunkan jumlah kesalahan negatif palsu.Meskipun mencapai performa yang kompetitif dengan model ensemble yang lebih kompleks, model tunggal ini tetap mempertahankan kejelasan dan interpretabilitas.Penelitian ini menegaskan bahwa pemilihan hyperparameter yang tepat dapat membuat model sederhana menjadi alat bantu keputusan klinis yang andal dan efisien.

Future Research

Penelitian lanjutan dapat memanfaatkan metode pencarian bayesian atau perbaikan evolusioner untuk mengidentifikasi konfigurasi hyperparameter yang lebih optimal pada data gagal jantung, dengan tujuan meningkatkan akurasi lebih tinggi tanpa mengorbankan interpretabilitas. Selain itu, studi dapat memperluas validasi eksternal dengan mengaplikasikan model yang dioptimalkan pada dataset multi‑pusat, sehingga dapat menilai generalisasi dan ketahanan model di berbagai populasi klinis. Akhirnya, pengembangan hybrid antara Decision Tree dan metode ensemble ringan seperti Gradient Boosting dapat dieksplorasi untuk mengeksploitasi keunggulan interpretasi sekaligus menambah kekuatan prediksi, dengan fokus pada minimalisasi overhead komputasi agar cocok untuk aplikasi di perangkat mobile atau rumah sakit dengan sumber daya terbatas.

References

1. Application of Machine Learning for Cardiovascular Disease Risk Prediction - Dalal - 2023 - Computational... doi.org/10.1155/2023/9418666Application of Machine Learning for Cardiovascular Disease Risk Prediction Dalal 2023 Computational doi 10 1155 2023 9418666

Metadata

File size	551.65 KB
Pages	12
DMCA	Report