EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Trustworthy AI for radar vital signs: detecting and mitigating gender bias in healthcare

Nour Ghadban iD, Jonathan Cooper, Julien Le Kernec

Complex & Intelligent Systems · 2026-07 · 12 (7)

DOI: 10.1007/s40747-026-02296-2 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Complex & Intelligent Systems, online erschienen am 25.04.2026. Verfasst von Nour Ghadban und 2 weiteren Autor:innen. Beteiligte Einrichtung: James Watt School of Engineering, University of Glasgow, Glasgow, Scotland UK. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Engineering and Physical Sciences Research Council and Women in Science Chair.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Artificial intelligence (AI) has emerged as a fundamental component in modern healthcare, particularly in noninvasive monitoring of vital signs using radar-based systems. However, algorithmic fairness concerns, such as gender bias, can undermine trust in these systems. This study investigates the impact of gender representation in training data on the accuracy and fairness of radar-based vital sign estimation. We trained machine-learning models on 60 dataset configurations–male-only, female-only, balanced, male-dominant and female-dominant–each containing 640 radar-derived samples (3200 total). Models trained on female-dominant data achieved the highest classification accuracy (94.5%) and lowest regression error (RMSE = 0.70), whereas male-only datasets performed worst (accuracy = 78.2%, RMSE = 1.80). Disparate impact analysis revealed up to a 16.5% performance advantage for female-skewed training data, and multiple fairness metrics, including disparate impact ratio and statistical parity difference, were employed to quantify bias across subgroups. To address these disparities, we implemented a multilevel mitigation framework integrating TimeGAN-based data augmentation, fairness-aware learning constraints, and threshold adjustment. This approach reduced the bias score from 0.0261 to 0.00005 ( $$\textit{p} < 0.001$$ p < 0.001 ) while maintaining a high F1 score ( $$> 0.98$$ > 0.98 ). Our results underscore the necessity of balanced and diverse datasets and demonstrate that incorporating fairness-aware strategies can yield equitable and trustworthy AI systems for clinical vital sign monitoring.

Schlagwörter

Stichwörter der Autor:innen

Algorithmic fairnessAlgorithmic gender biasBias detection and mitigationHealthcare artificial intelligenceRadar-based vital sign monitoringTrustworthy AI

Autor:innen und Institutionen

  • James Watt School of Engineering, University of Glasgow, Glasgow, Scotland UK.

ORCID-Profile: Nour Ghadban

Förderung

  • Engineering and Physical Sciences Research Council and Women in Science Chair

Zitieren

APA

Ghadban, N., Cooper, J., & Le Kernec, J. (2026). Trustworthy AI for radar vital signs: detecting and mitigating gender bias in healthcare. Complex & Intelligent Systems, 12(7). https://doi.org/10.1007/s40747-026-02296-2

Vancouver

Ghadban N, Cooper J, Le Kernec J. Trustworthy AI for radar vital signs: detecting and mitigating gender bias in healthcare. Complex & Intelligent Systems. 2026;12(7). doi:10.1007/s40747-026-02296-2

BibTeX
@article{Ghadban2026,
  author = {Ghadban, Nour and Cooper, Jonathan and Le Kernec, Julien},
  title = {Trustworthy AI for radar vital signs: detecting and mitigating gender bias in healthcare},
  journal = {Complex & Intelligent Systems},
  year = {2026},
  volume = {12},
  number = {7},
  doi = {10.1007/s40747-026-02296-2}
}
Kostenlos starten →