EUVIMEDEUVIMED entdecken
Open Access

Temporal Reproducibility of a Genetic Algorithm–Derived Health Risk Score: Standardized Out-of-Fold Validation Framework (2021-2023)

Yoichiro Aoki, Hiroki Takeda, Kinichi Yokota, Ryoko Yoshida

JMIR Bioinformatics and Biotechnology · 21.04.2026 · 7 · e85659-e85659

DOI: 10.2196/85659 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JMIR Bioinformatics and Biotechnology, online erschienen am 21.04.2026. Verfasst von Yoichiro Aoki und 3 weiteren Autor:innen. Beteiligte Einrichtung: Yoshida Hospital-Keiyukai Medical Corporation, 1-2, Nishi 4-chome, 4-jyo, Asahikawa, Hokkaido, 070-0054, Japan, 81 166-23-0685. Die Arbeit nennt 5 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Genetic algorithm (GA)–based scoring has been proposed as a data-driven approach for health risk stratification . However, performance estimates may be inflated when preprocessing, optimization, and evaluation are not strictly separated within a prespecified validation framework. Demonstrating temporal reproducibility under a standardized out-of-fold (OOF) evaluation framework with transparent uncertainty quantification is therefore essential for ensuring translational reliability in preventive health screening.

Objective

This study aimed to evaluate the temporal reproducibility of a GA-derived composite health risk score across three consecutive annual cohorts (2021‐2023) under a standardized OOF validation pipeline and to assess robustness to policy-driven structural HbA 1c missingness through a prespecified ON/OFF sensitivity analysis.

Methods

Annual health examination datasets from 2021 (n=3744), 2022 (n=5153), and 2023 (n=5352) were analyzed using an identical preprocessing and modeling pipeline. Thirteen clinical indicators and eight lifestyle questionnaire variables were included as predictors. The outcome was based on an A–D grading framework and binarized using an OR rule across domains (grade ≥B in any domain). Continuous variables were median-imputed and standardized within each training fold to prevent information leakage. GA optimization was performed using fixed random seeds, and fitness estimation employed stratified K-fold cross-validation. Predicted probabilities were obtained by fitting logistic regression models to GA-derived composite scores within the OOF framework. Discrimination and overall predictive performance were quantified using the area under the receiver operating characteristic curve (AUC) and the Brier score calculated from OOF predicted probabilities. Uncertainty was estimated using 2,000-replicate percentile bootstrap resampling. A prespecified sensitivity analysis excluded HbA 1c while maintaining an identical evaluation framework.

Results

OOF AUC values were stable across cohorts (2021: 0.810; 2022: 0.814; 2023: 0.812), with overlapping 95% percentile bootstrap confidence intervals. Brier scores ranged from 0.172 to 0.176. Exclusion of HbA 1c resulted in small changes in discrimination (median ΔAUC was ≤0.007), consistent with the prespecified ON/OFF sensitivity analysis.

Conclusions

Under a harmonized OOF validation framework, the GA-derived composite risk score showed stable temporal discrimination and consistent overall predictive performance across three consecutive annual cohorts. These findings underscore the methodological importance of prespecified, standardized evaluation procedures and transparent uncertainty quantification when assessing reproducibility of risk stratification models in routine health screening data.

Schlagwörter

Stichwörter der Autor:innen

AUCROCarea under the receiver operating characteristic curvecross-validationgenetic algorithmhealth risk scoringpreventive medicinereproducibility

Autor:innen und Institutionen

  • Yoshida Hospital-Keiyukai Medical Corporation, 1-2, Nishi 4-chome, 4-jyo, Asahikawa, Hokkaido, 070-0054, Japan, 81 166-23-0685.
  • Department of Cardiovascular Medicine, Yoshida Hospital- Keiyukai Medical Corporation, Asahikawa, Hokkaido, Japan.
  • Department of Gastroenterology, Yoshida Hospital-Keiyukai Medical Corporation, Asahikawa, Hokkaido, Japan.

Zitieren

APA

Aoki, Y., Takeda, H., Yokota, K., & Yoshida, R. (2026). Temporal Reproducibility of a Genetic Algorithm–Derived Health Risk Score: Standardized Out-of-Fold Validation Framework (2021-2023). JMIR Bioinformatics and Biotechnology, 7, e85659-e85659. https://doi.org/10.2196/85659

Vancouver

Aoki Y, Takeda H, Yokota K, Yoshida R. Temporal Reproducibility of a Genetic Algorithm–Derived Health Risk Score: Standardized Out-of-Fold Validation Framework (2021-2023). JMIR Bioinformatics and Biotechnology. 2026;7:e85659-e85659. doi:10.2196/85659

BibTeX
@article{Aoki2026,
  author = {Aoki, Yoichiro and Takeda, Hiroki and Yokota, Kinichi and Yoshida, Ryoko},
  title = {Temporal Reproducibility of a Genetic Algorithm–Derived Health Risk Score: Standardized Out-of-Fold Validation Framework (2021-2023)},
  journal = {JMIR Bioinformatics and Biotechnology},
  year = {2026},
  volume = {7},
  pages = {e85659--e85659},
  doi = {10.2196/85659}
}
Kostenlos starten →