EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A new extended belief rule base method based on neighborhood covering reduction for diabetes diagnosis

Shucheng Feng, Wei He iD, Li Jiang, Manlin Chen

PLOS One · 05.05.2026 · 21 (5) · e0347303

DOI: 10.1371/journal.pone.0347303 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 05.05.2026. Verfasst von Shucheng Feng und 3 weiteren Autor:innen. Beteiligte Einrichtung: Harbin Normal University, Harbin, China. Hauptthemen laut MEDLINE: Diabetes Mellitus. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Laboratory of the Ministry of Education on Application of Artificial Intelligence in Equipment, Natural Science Foundation of Heilongjiang Province, Basic Research Support Program for Outstanding Young Teachers in Provincial Undergraduate Universities of Heilongjiang Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The precise diagnosis and scientific management of diabetes are highly important for improving patients’ quality of life and reducing the risk of complications. However, in actual clinical settings, diagnostic processes often face challenges, including significant individual differences among patients, complex and diverse parameters, and heterogeneity in disease progression. These challenges not only impose greater requirements on the adaptability and precision of diagnostic and therapeutic models but also highlight the need for explainable disease mechanisms and rational treatment strategies. To address these issues, this study proposes an Extended Belief Rule Base (EBRB) model based on neighborhood covering reduction, abbreviated as NCR-EBRB, for diabetes prediction and diagnosis. During the model construction phase, the Extreme Gradient Boosting (XGBoost) method is first employed for feature importance evaluation to reasonably screen key features and effectively reduce model dimensionality. In the model inference phase, the Neighborhood Covering Reduction (NCR) method is adopted to implement rule reduction in the rule base, combined with a threshold-based rule activation strategy to filter out inefficient rules, ensuring efficient reasoning processes and effective result output. During the model optimization phase, the Projection Covariance Matrix Adaptive Evolution Strategy (P-CMA-ES) is applied to optimize the parameters of the streamlined rule base, aiming to identify optimal parameter configurations for further improving model performance. Through this meticulous parameter tuning, the diagnostic accuracy is enhanced, and the robustness of the model is improved.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Diabetes MellitusHumansBoosting Machine Learning Algorithms

Autor:innen und Institutionen

  • Harbin Normal University, Harbin, China.
  • Harbin Medical University Cancer Hospital, Harbin, China.
  • ChangChun University of Technology, Changchun, China.

ORCID-Profile: Wei He

Förderung

  • Key Laboratory of the Ministry of Education on Application of Artificial Intelligence in Equipment
  • Natural Science Foundation of Heilongjiang Province
  • Basic Research Support Program for Outstanding Young Teachers in Provincial Undergraduate Universities of Heilongjiang Province

Zitieren

APA

Feng, S., He, W., Jiang, L., & Chen, M. (2026). A new extended belief rule base method based on neighborhood covering reduction for diabetes diagnosis. PLOS One, 21(5), e0347303. https://doi.org/10.1371/journal.pone.0347303

Vancouver

Feng S, He W, Jiang L, Chen M. A new extended belief rule base method based on neighborhood covering reduction for diabetes diagnosis. PLOS One. 2026;21(5):e0347303. doi:10.1371/journal.pone.0347303

BibTeX
@article{Feng2026,
  author = {Feng, Shucheng and He, Wei and Jiang, Li and Chen, Manlin},
  title = {A new extended belief rule base method based on neighborhood covering reduction for diabetes diagnosis},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {5},
  pages = {e0347303},
  doi = {10.1371/journal.pone.0347303}
}
Kostenlos starten →