EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

HIV-PrivFed: Privacy–Utility–Fairness-Aware Federated Learning for HIV Risk Stratification and Testing Prioritization Under Non-IID Clinical Heterogeneity

Md Wahidur Rahman iD, Haitham Y Adarbah iD, Atena Pasha iD, Afzel Noore iD

Diagnostics · 30.10.2026 · 16 (21) · 3590

DOI: 10.3390/diagnostics16213590 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Diagnostics, online erschienen am 30.10.2026. Verfasst von Md Wahidur Rahman und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical Engineering and Computer Science, Texas A&M University-Kingsville (TAMUK), Kingsville, TX 78363, USA. Die Arbeit nennt 70 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background/Objectives: HIV screening from routinely collected behavioral data could help to prioritize testing across clinics that cannot centralize sensitive records; however, the utility, privacy, and client-level fairness of federated models on real non-IID data are poorly characterized.

Methods

Using Sialon-II, a cohort of men who have sex with men in 13 European cities (13 natural clients; horizontal federated learning), we benchmarked ten conventional classifiers and a centralized residual MLP, compared local-only, FedAvg, and FedProx baselines, and evaluated HIV-PrivFed, a differentially private FedProx-based algorithm with client-by-client Rényi accounting and client-level fairness auditing (fairness is audited, not enforced); secure aggregation overhead was benchmarked in simulation.

Results

The best conventional model reached an AUROC of 0.696 (AUPRC 0.235), statistically indistinguishable from logistic regression on the original partition. Federated learning exceeded local-only learning (AUROC 0.607 versus 0.565). Achieved worst-client privacy budgets (ε = 22.1–224.1) were far looser than the nominal targets and give no meaningful guarantee; accuracy was retained at these budgets (AUROC 0.629–0.650) but fell to 0.553 and 0.524 at ε=8 and 4. Client-level estimates were highly uncertain.

Conclusions

Useful accuracy and a meaningful privacy guarantee did not coexist in this small-cohort setting; larger cohorts and external validation are needed before deployment.

Schlagwörter

Stichwörter der Autor:innen

HIV screeningdifferential privacyfairness-aware learningfederated learninghealthcare machine learningnon-IID clinical heterogeneityprivacy–utility tradeoff

Autor:innen und Institutionen

  • Department of Electrical Engineering and Computer Science, Texas A&M University-Kingsville (TAMUK), Kingsville, TX 78363, USA.
  • Department of Psychology and Sociology, Texas A&M University-Kingsville (TAMUK), Kingsville, TX 78363, USA.

ORCID-Profile: Md Wahidur Rahman, Haitham Y Adarbah, Atena Pasha, Afzel Noore

Zitieren

APA

Rahman, M. W., Adarbah, H. Y., Pasha, A., & Noore, A. (2026). HIV-PrivFed: Privacy–Utility–Fairness-Aware Federated Learning for HIV Risk Stratification and Testing Prioritization Under Non-IID Clinical Heterogeneity. Diagnostics, 16(21), 3590. https://doi.org/10.3390/diagnostics16213590

Vancouver

Rahman MW, Adarbah HY, Pasha A, Noore A. HIV-PrivFed: Privacy–Utility–Fairness-Aware Federated Learning for HIV Risk Stratification and Testing Prioritization Under Non-IID Clinical Heterogeneity. Diagnostics. 2026;16(21):3590. doi:10.3390/diagnostics16213590

BibTeX
@article{Rahman2026,
  author = {Rahman, Md Wahidur and Adarbah, Haitham Y and Pasha, Atena and Noore, Afzel},
  title = {HIV-PrivFed: Privacy–Utility–Fairness-Aware Federated Learning for HIV Risk Stratification and Testing Prioritization Under Non-IID Clinical Heterogeneity},
  journal = {Diagnostics},
  year = {2026},
  volume = {16},
  number = {21},
  pages = {3590},
  doi = {10.3390/diagnostics16213590}
}
Kostenlos starten →