Interpretable Lifestyle-Only Diabetes Screening: A Clinically Grounded XAI Pipeline
International Journal of Intelligent Systems and Data Science · 31.10.2026 · 1 (6)
DOI: 10.67231/e62wm710 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Intelligent Systems and Data Science, online erschienen am 31.10.2026. Verfasst von Mafaz Mohammed Nadherssa. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Themen: Diabetes mellitus
Abstract (Originalsprache)
This paper presents an explainable AI pipeline for diabetes screening that learns from non-laboratory, self-reported health indicators and then provides patient-specific, actionable risk rationales clinicians can audit and communicate. A deep neural classifier, gradient boosting, and a regularized logistic baseline are trained on a large BRFSS-derived tabular cohort with severe class imbalance; the logistic baseline provides stable feature attributions for lifestyle factors while the black-box models optimize discrimination, reflecting best practices in XAI for healthcare tabular data. The system attains verified discrimination between diabetes-free and diabetes cases on the held-out test set, with macro-averaged F1-scores of 0.432 (DNN), 0.423 (XGBoost), and 0.389 (logistic regression), computed with macro averaging over the three classes; these values are consistent with the class-level F1-scores reported and with the underlying held-out test predictions. Explanations are based on regularized logistic regression coefficients aligned with established XAI methods, and the system is positioned as preliminary risk stratification rather than clinically validated screening. The pre-diabetes class remains poorly identified (F1 ≤ 0.050 for all models), and claims of equitable early intervention in resource-limited settings require further prospective validation.
Zitieren
APA
Nadherssa, M. M. (2026). Interpretable Lifestyle-Only Diabetes Screening: A Clinically Grounded XAI Pipeline. International Journal of Intelligent Systems and Data Science, 1(6). https://doi.org/10.67231/e62wm710
Vancouver
Nadherssa MM. Interpretable Lifestyle-Only Diabetes Screening: A Clinically Grounded XAI Pipeline. International Journal of Intelligent Systems and Data Science. 2026;1(6). doi:10.67231/e62wm710
BibTeX
@article{Nadherssa2026,
author = {Nadherssa, Mafaz Mohammed},
title = {Interpretable Lifestyle-Only Diabetes Screening: A Clinically Grounded XAI Pipeline},
journal = {International Journal of Intelligent Systems and Data Science},
year = {2026},
volume = {1},
number = {6},
doi = {10.67231/e62wm710}
}
EUVIMED