EUVIMEDEUVIMED entdecken
Open Access · CC BY-SA 4.0

Prediction of Bronchitis Disease Indications Using CatBoost Algorithm

Lukman Hakim, Yisti Vita Via, Eva Yulia Puspaningrum

bit-Tech · 10.08.2026 · 9 (1) · 722-732

DOI: 10.32877/bt.v9i1.3970 ↗

Kurz gefasst

Fachartikel in der Zeitschrift bit-Tech, online erschienen am 10.08.2026. Verfasst von Lukman Hakim und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Bronchitis represents a highly significant respiratory tract condition categorized under Acute Respiratory Infections (ARIs), clinically characterized by persistent cough, shortness of breath, and high fever. Although a definitive clinical diagnosis strictly necessitates comprehensive medical examinations, automated secondary screening mechanisms can play a vital role in early risk stratification by proactively identifying potential high-risk individuals. This study applies the CatBoost (Categorical Boosting) gradient boosting framework to predict potential bronchitis indications, leveraging a localized pharmacy dataset consisting of comprehensive patient symptom records. The experimental methodology systematically encompasses data collection, data cleaning, target variable labeling derived from cough duration thresholds, label encoding for categorical feature engineering, dataset splitting, hyperparameter optimization executed through GridSearchCV, model training, and performance evaluation. To rigorously evaluate model stability across varying training data volumes, the dataset was evaluated under three distinct partitioning ratios, namely 60:40, 70:30, and 80:20. Empirical evaluation demonstrated that the 60:40 data split scenario achieved the most optimal and balanced overall performance, yielding an accuracy of 84%, precision of 75%, recall of 79%, and an F1-Score of 79%. Ultimately, these findings prove that the CatBoost algorithm can effectively capture underlying structural patterns within symptom data, highlighting its practical utility as a non-invasive secondary decision-support tool to prioritize high-risk patients for formal clinical evaluation.

Zitieren

APA

Hakim, L., Via, Y. V., & Puspaningrum, E. Y. (2026). Prediction of Bronchitis Disease Indications Using CatBoost Algorithm. bit-Tech, 9(1), 722-732. https://doi.org/10.32877/bt.v9i1.3970

Vancouver

Hakim L, Via YV, Puspaningrum EY. Prediction of Bronchitis Disease Indications Using CatBoost Algorithm. bit-Tech. 2026;9(1):722-732. doi:10.32877/bt.v9i1.3970

BibTeX
@article{Hakim2026,
  author = {Hakim, Lukman and Via, Yisti Vita and Puspaningrum, Eva Yulia},
  title = {Prediction of Bronchitis Disease Indications Using CatBoost Algorithm},
  journal = {bit-Tech},
  year = {2026},
  volume = {9},
  number = {1},
  pages = {722--732},
  doi = {10.32877/bt.v9i1.3970}
}
Kostenlos starten →