Trustworthy AI for radar vital signs: detecting and mitigating gender bias in healthcare.
Female-dominant training data yielded highest accuracy for radar vital-sign artificial intelligence models
Trustworthy AI for radar vital signs: detecting and mitigating gender bias in healthcare.
Artificial intelligence (artificial intelligence) has emerged as a fundamental component in modern healthcare, particularly in noninvasive monitoring of vital signs using radar-based systems.
This study investigates the impact of gender representation in training data on the accuracy and fairness of radar-based vital sign estimation.
female-dominant training data produced the most accurate radar readings
However, algorithmic fairness concerns, such as gender bias, can undermine trust in these systems.
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).
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.
Our results underscore the necessity of balanced and diverse datasets and demonstrate that incorporating fairness-aware strategies can yield equitable and trustworthy artificial intelligence systems for clinical vital sign monitoring.