Abstract
The lack of attention to sex and gender biases in biomedicine and healthcare hinders the advancement toward Precision Medicine. This chapter introduces a unified framework that captures the main steps that AI stakeholders need to go through in order to deal with desired and undesired sex and gender biases in AI models used for biomedical research and clinical practice. The framework consists of three main steps around biases: identification, explanation, and mitigation or exploitation for the health benefit of the patient. For each of these steps, we describe a number of methods and techniques that can be implemented to manage biases, and we illustrate them with practical examples.