Adversarial debiasing for age-equitable diabetes prediction: performance-fairness trade-offs and partition…

AI / informaticsFrontiers in digital health· 2026

Adversarial debiasing for age-equitable diabetes prediction: performance-fairness trade-offs and partition dependency in machine learning.

Vinod Kumar Yata, Sravanthi Jena, Meera Indracanti … Narasaiah Kolliputi

AI Evaluation & GovernanceAI / informaticsQ1IF 5.4

Adversarial debiasing improved diabetes-detection sensitivity for patients over age 50

Adversarial debiasing for age-equitable diabetes prediction: performance-fairness trade-offs and partition dependency in machine learning.

Vinod Kumar Yata … Narasaiah Kolliputi

Frontiers in digital health · 2026 · Q1 in Health Informatics

Background

Machine learning models used for diabetes risk prediction may encode age-related biases that reduce diagnostic accuracy for specific demographic groups.

Methods

Adversarial debiasing was evaluated for age-bias mitigation in diabetes prediction using the publicly available Pima Indians Diabetes Database ( n = 768).

n = 768

Results

detected 3 in 4 diabetes cases in over-50s, up from about half

More results

However, the recall parity gap increased from 0.0996 to 0.2153 (+11.57 pp), reflecting a concurrent decline in recall for the <30-year group (-6.25 pp).

Across five random seeds, the mean recall parity gap showed a modest mean reduction (0.3282 → 0.3033, -2.49 pp), but with high variability (SD > 0.27) exceeding the mean difference.

More results

The adversarial model reduced the fairness gap in three of five seeds, increased it in one, and produced no change in one.

“

Conclusion · 1 of 2

Adversarial debiasing can improve predictive recall for underrepresented demographic subgroups but does not guarantee consistent fairness improvements across data partitions, particularly when subgroup sample sizes are small.

Conclusion · 2 of 2

Multi-seed evaluation is essential for reliable fairness assessment; single train-test splits are insufficient.

Adversarial debiasing for age-equitable diabetes prediction: performance-fairness trade-offs and partition dependency in machine learning.

Adversarial debiasing for age-equitable diabetes prediction: performance-fairness trade-offs and partition dependency in machine learning.

Related papers