COMPARATIVE ANALYSIS OF HYPERPARAMETER OPTIMIZATION TECHNIQUES ON LIGHTGBM FOR ASTHMA PREDICTION
DOI:
https://doi.org/10.33480/jitk.v11i2.7369Keywords:
asthma prediction , bayesian optimization , hyperparameter optimization , ightgbm , machine learningAbstract
This study presents a comparative study of hyperparameter optimization methods applied to the Light Gradient Boosting Machine (LightGBM) algorithm for asthma prediction. Traditional machine learning models often face limitations in accuracy and generalization capabilities due to suboptimal hyperparameter configurations. To address these challenges, this study evaluates and compares four approaches: Default LightGBM, RandomizedSearchCV, Optuna Optimization, and Bayesian Optimization. Experimental results show that Bayesian Optimization provides the best performance with an accuracy of 78%, a precision of 0.7778, a recall of 0.7778, an F1-score of 0.7778, and an ROC-AUC of 0.975. These findings emphasize the importance of selecting an appropriate optimization strategy to improve model performance in clinical prediction tasks. Overall, this study confirms the effectiveness of Bayesian Optimization in improving the predictive capabilities of LightGBM and provides an important contribution to the development of decision support systems in healthcare, particularly in the diagnosis and management of asthma
Downloads
References
S. Maleki Varnosfaderani and M. Forouzanfar, “The Role of AI in Hospitals and Clinics: Transforming Healthcare in the 21st Century,” Bioengineering, vol. 11, no. 4, pp. 1–38, 2024, doi: 10.3390/bioengineering11040337.
A. Husnain, S. Rasool, A. Saeed, A. Yousaf Gill, and H. Khawar Hussain, “AI’S Healing Touch: Examining Machine Learning’s Transformative Effects On Healthcare,” J. World Sci., vol. 2, no. 10, pp. 1681–1695, 2023, doi: 10.58344/jws.v2i10.448.
S. Balakrishna and V. Kumar Solanki, “A Comprehensive Review on AI-Driven Healthcare Transformation,” Ing. Solidar., vol. 20, no. 2, pp. 1–30, 2024, doi: 10.16925/2357-6014.2024.02.07.
N. N. Khanna et al., “Economics of Artificial Intelligence in Healthcare: Diagnosis vs. Treatment,” Healthc., vol. 10, no. 12, 2022, doi: 10.3390/healthcare10122493.
D. C. Das and M. S. Akter, “AI-Powered Multimodal Diagnostics in Modern Healthcare : A Shift Toward Integrative Intelligence,” Asia Pacific J. Med. Innov., vol. 2, no. 3, 2025, doi: https://doi.org/10.70818/apjmi.v02i03.027.
Z. Ahmad, S. Rahim, M. Zubair, and J. Abdul-Ghafar, “Artificial intelligence (AI) in medicine, current applications and future role with special emphasis on its potential and promise in pathology: present and future impact, obstacles including costs and acceptance among pathologists, practical and philosoph,” Diagn. Pathol., vol. 16, no. 1, pp. 1–16, 2021, doi: 10.1186/s13000-021-01085-4.
M. Caminati et al., “Biologics and global burden of asthma: A worldwide portrait and a call for action,” World Allergy Organ. J., vol. 14, no. 2, p. 100502, 2021, doi: 10.1016/j.waojou.2020.100502.
P. M. Pitrez, “The challenges of asthma care in low-and middle-income countries: what’s next?,” J. Bras. Pneumol., vol. 49, no. 3, pp. 2–3, 2023, doi: 10.36416/1806-3756/e20230215.
A. S. Listyoko, R. Okazaki, T. Harada, G. Inui, and A. Yamasaki, “Exploring the association between asthma and chronic comorbidities: impact on clinical outcomes,” Front. Med., vol. 11, no. January, 2024, doi: 10.3389/fmed.2024.1305638.
A. A. Faniyi et al., “Addressing the asthma crisis in Africa: challenges, strategies, and recommendations for improved management,” Egypt. J. Intern. Med., vol. 36, no. 1, 2024, doi: 10.1186/s43162-024-00340-6.
R. Hurtado-Ruzza et al., “Asthma, much more than a respiratory disease: Influence of depression and anxiety,” Rev. Assoc. Med. Bras., vol. 67, no. 4, pp. 571–576, 2021, doi: 10.1590/1806-9282.20201066.
S. Sharma, N. Tasnim, K. Agadi, U. Asfeen, and J. Kanda, “Vulnerability for Respiratory Infections in Asthma Patients: A Systematic Review,” Cureus, vol. 14, no. 9, pp. 6–11, 2022, doi: 10.7759/cureus.28839.
R. D. Wagh, P. Khade, and Hingane, “Asthma: A Comprehensive Outlook,” Int. J. Res. Appl. Sci. Eng. Technol., vol. 10, no. 1, pp. 691–698, 2022, doi: 10.22214/ijraset.2022.39893.
D. Toumpanakis and O. S. Usmani, “Small airways in asthma: Pathophysiology, identification and management,” Chinese Med. J. Pulm. Crit. Care Med., vol. 1, no. 3, pp. 171–180, 2023, doi: 10.1016/j.pccm.2023.07.002.
E. Y. A. Qaid and I. Long, “Asthma unravelled: a comprehensive review of epidemiology, phenotypes, pathophysiology, and emerging therapies,” Egypt. J. Bronchol., vol. 19, no. 1, 2025, doi: 10.1186/s43168-025-00443-w.
V. E. Georgakopoulou, D. A. Spandidos, and A. Corlateanu, “Diagnostic tools in respiratory medicine (Review),” Biomed. Reports, vol. 23, no. 1, pp. 1–13, 2025, doi: 10.3892/br.2025.1990.
R. Nooreldeen and H. Bach, “Current and future development in lung cancer diagnosis,” Int. J. Mol. Sci., vol. 22, no. 16, 2021, doi: 10.3390/ijms22168661.
S. Sarkar, U. Jadhav, B. Ghewade, S. Sarkar, and P. Wagh, “Oscillometry in Lung Function Assessment: A Comprehensive Review of Current Insights and Challenges,” Cureus, vol. 15, no. 10, 2023, doi: 10.7759/cureus.47935.
M. A. Almeshari, J. Stockley, and E. Sapey, “The diagnosis of asthma. Can physiological tests of small airways function help?,” Chron. Respir. Dis., vol. 18, pp. 1–12, 2021, doi: 10.1177/14799731211053332.
M. Xia et al., “Expert consensus on difficult airway assessment,” Hepatobiliary Surg. Nutr., vol. 12, no. 4, pp. 545–566, 2023, doi: 10.21037/hbsn-23-46.
Y. Lyu et al., “Non-invasive acoustic classification of adult asthma using an XGBoost model with vocal biomarkers,” Sci. Rep., vol. 15, no. 1, pp. 1–28, 2025, doi: 10.1038/s41598-025-14645-1.
Q. Qian, J. Wu, J. Wang, H. Sun, and L. Yang, “Prediction models for aki in icu: A comparative study,” Int. J. Gen. Med., vol. 14, pp. 623–632, 2021, doi: 10.2147/IJGM.S289671.
X. Qi, S. Wang, C. Fang, J. Jia, L. Lin, and T. Yuan, “Machine learning and SHAP value interpretation for predicting comorbidity of cardiovascular disease and cancer with dietary antioxidants,” Redox Biol., vol. 79, no. 12, p. 103470, 2025, doi: 10.1016/j.redox.2024.103470.
L. H. Lai et al., “The Use of Machine Learning Models with Optuna in Disease Prediction,” Electron., vol. 13, no. 23, pp. 1–20, 2024, doi: 10.3390/electronics13234775.
X. Wang et al., “A Joint Ensemble Framework for the Detection of Acute Exacerbations in Chronic Obstructive Pulmonary Disease,” Res. Sq., pp. 1–19, 2023, doi: 10.21203/rs.3.rs-3712629/v1.
A. K. Muthevi and V. M. Mutyam, “Using an Enhanced LightGBM Model to Predict Coronary Heart Disease: Performance Evaluation and Comparison,” Nanotechnol. Perceptions, vol. 20, no. S14, pp. 2446–2457, 2024, doi: 10.62441/nano-ntp.v20is14.164.
K.-T. Nguyen, T.-N. Tran, and H.-T. Nguyen, “Research on the Influence of Genetic Algorithm Parameters on XGBoost in Load Forecasting,” Eng. Technol. Appl. Sci. Res., vol. 14, no. 6, pp. 18849–18854, 2024, doi: 10.48084/etasr.8863.
R. Sibindi, R. W. Mwangi, and A. G. Waititu, “A boosting ensemble learning based hybrid light gradient boosting machine and extreme gradient boosting model for predicting house prices,” Eng. Reports, vol. 5, no. 4, pp. 1–19, 2023, doi: 10.1002/eng2.12599.
H. Yang, Z. Chen, H. Yang, and M. Tian, “Predicting Coronary Heart Disease Using an Improved LightGBM Model: Performance Analysis and Comparison,” IEEE Access, vol. 11, no. February, pp. 23366–23380, 2023, doi: 10.1109/ACCESS.2023.3253885.
P. K. Sahu and T. Fatma, “Optimized Breast Cancer Classification Using PCA-LASSO Feature Selection and Ensemble Learning Strategies with Optuna Optimization,” IEEE Access, vol. 13, no. February, pp. 35645–35661, 2025, doi: 10.1109/ACCESS.2025.3539746.
M. Khaldi, Z. Alilat, H. Bendoubba, and N. Mahammed, “Hyperparameter Optimization for Malicious URL Detection: Leveraging Optuna and Random Search in Machine Learning and Deep Learning Models,” Informatica, vol. 49, no. 27, pp. 57–68, 2025, doi: 10.31449/inf.v49i27.9106.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Zulfian Azmi, Rina Julita, Novica Irawati, Sofyan Pariyasto, Ellanda Purwawijaya
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
-a.jpg)
-b.jpg)
