Algorithm Fairness in AI for Medicine and Healthcare
This perspective article highlights fairness challenges in healthcare AI, which is crucial for equitable patient care but is incremental as it reviews existing issues and solutions.
The paper addresses algorithm fairness in AI for healthcare, summarizing how biases arise in clinical workflows and reviewing emerging technologies like federated learning and model explainability to mitigate these biases.
In the current development and deployment of many artificial intelligence (AI) systems in healthcare, algorithm fairness is a challenging problem in delivering equitable care. Recent evaluation of AI models stratified across race sub-populations have revealed inequalities in how patients are diagnosed, given treatments, and billed for healthcare costs. In this perspective article, we summarize the intersectional field of fairness in machine learning through the context of current issues in healthcare, outline how algorithmic biases (e.g. - image acquisition, genetic variation, intra-observer labeling variability) arise in current clinical workflows and their resulting healthcare disparities. Lastly, we also review emerging technology for mitigating bias via federated learning, disentanglement, and model explainability, and their role in AI-SaMD development.