EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Bayesian-optimized convex neural networks with embedded feature selection for high-dimensional anthropometric health prediction

Faten S. Alamri, Sunusi Bala Abdullahi, Noor Ayesha, Fatima Alshannaq, Tanzila Saba

PeerJ Computer Science · 09.04.2026 · 12 · e3752

DOI: 10.7717/peerj-cs.3752 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PeerJ Computer Science, online erschienen am 09.04.2026. Verfasst von Faten S. Alamri und 4 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia, Prince Sultan University, Riyadh, Saudi Arabia.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background and Objectives Anthropometric prediction and metabolic disorder screening require cost-effective solutions in resource-limited settings. We develop a convex-optimized neural network with embedded feature selection to establish quantitative relationships between body morphology and metabolic health.

Methods

Our framework combines Bayesian hyperparameter tuning with $\ell$1–$\ell$2 regularized feature selection (λ1 = 0.020, λ2 = 0.002), processing 4,464 3D body scans, 1,000 Iraqi clinical records, and 768 Pima Indian diabetes cases. Spatial fully connected networks preserve anatomical relationships during feature selection.

Results

The model achieved 99.000% accuracy (95% CI [98.750–99.250]) for anthropometric gender classification, 94.700% accuracy (95% CI [93.200–96.200]) for Iraqi diabetes triage, and 90.040% accuracy (95% CI [86.800–91.280], Area Under the Receiver Operating Characteristic Curve (AUC) = 0.941) for Pima diabetes prediction, outperforming conventional methods (paired t = 27.340, p < 0.001). Key findings include identification of spine-to-scye length (weight = 0.990, Pearson r = 0.920) and Very Low-Density Lipoprotein (VLDL) (weight = 0.990, r = 0.982) as previously unreported predictors requiring further investigation, alongside traditional indicators.

Conclusion

The framework demonstrates anthropometry’s viability for security and diagnostic screening, with 57% parameter reduction vs . ensemble baselines while maintaining application-grade performance.

Förderung

  • Princess Nourah bint Abdulrahman University, Riyadh, Saudi Arabia
  • Prince Sultan University, Riyadh, Saudi Arabia

Zitieren

APA

Alamri, F. S., Abdullahi, S. B., Ayesha, N., Alshannaq, F., & Saba, T. (2026). Bayesian-optimized convex neural networks with embedded feature selection for high-dimensional anthropometric health prediction. PeerJ Computer Science, 12, e3752. https://doi.org/10.7717/peerj-cs.3752

Vancouver

Alamri FS, Abdullahi SB, Ayesha N, Alshannaq F, Saba T. Bayesian-optimized convex neural networks with embedded feature selection for high-dimensional anthropometric health prediction. PeerJ Computer Science. 2026;12:e3752. doi:10.7717/peerj-cs.3752

BibTeX
@article{Alamri2026,
  author = {Alamri, Faten S. and Abdullahi, Sunusi Bala and Ayesha, Noor and Alshannaq, Fatima and Saba, Tanzila},
  title = {Bayesian-optimized convex neural networks with embedded feature selection for high-dimensional anthropometric health prediction},
  journal = {PeerJ Computer Science},
  year = {2026},
  volume = {12},
  pages = {e3752},
  doi = {10.7717/peerj-cs.3752}
}
Kostenlos starten →