EUVIMEDEUVIMED entdecken
Open Access · CC BY-SA 4.0

Development of a Web-Based Expert System for Early Tuberculosis Diagnosis Using K-Nearest Neighbors

Lukas Valentino, Vivi Nur Wijayaningrum, Candra Bella Vista

Journal of Applied Informatics and Computing · 16.04.2026 · 10 (2) · 1276-1281

DOI: 10.30871/jaic.v10i2.11747 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Applied Informatics and Computing, online erschienen am 16.04.2026. Verfasst von Lukas Valentino und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Tuberculosis (TB) remains a major infectious disease that continues to challenge global public health, particularly in regions with limited access to early diagnostic services. Early and accurate detection of TB is essential to prevent further transmission and ensure effective treatment. This study aims to develop an intelligent expert system for early TB diagnosis based on the K-Nearest Neighbors (KNN) algorithm. To achieve this, the proposed system classifies patient conditions as TB or Non-TB based on clinical symptoms obtained from anonymized medical record data from a regional hospital in East Java, Indonesia. The dataset comprises eight symptom-based attributes, and several experiments were conducted to optimize parameters, including test-size ratio, number of neighbors (K), and K-Fold cross-validation. Results showed that the best model performance was achieved at K = 5 with a 10% test size, yielding an F1-score of 0.8571, precision of 1.00, and recall of 0.75. In addition, functional and non-functional testing confirmed that the developed web-based system operates reliably and securely. Overall, the proposed system provides an accurate and accessible diagnostic solution for early TB detection, especially in communities with limited healthcare infrastructure.

Zitieren

APA

Valentino, L., Wijayaningrum, V. N., & Vista, C. B. (2026). Development of a Web-Based Expert System for Early Tuberculosis Diagnosis Using K-Nearest Neighbors. Journal of Applied Informatics and Computing, 10(2), 1276-1281. https://doi.org/10.30871/jaic.v10i2.11747

Vancouver

Valentino L, Wijayaningrum VN, Vista CB. Development of a Web-Based Expert System for Early Tuberculosis Diagnosis Using K-Nearest Neighbors. Journal of Applied Informatics and Computing. 2026;10(2):1276-1281. doi:10.30871/jaic.v10i2.11747

BibTeX
@article{Valentino2026,
  author = {Valentino, Lukas and Wijayaningrum, Vivi Nur and Vista, Candra Bella},
  title = {Development of a Web-Based Expert System for Early Tuberculosis Diagnosis Using K-Nearest Neighbors},
  journal = {Journal of Applied Informatics and Computing},
  year = {2026},
  volume = {10},
  number = {2},
  pages = {1276--1281},
  doi = {10.30871/jaic.v10i2.11747}
}
Kostenlos starten →