Sex and Gender Bias in Technology and Artificial Intelligence: Chapter 3 - Bias and fairness in machine learning and artificial intelligence

Sex and gender biases can be entrenched in the life cycle of Artificial Intelligence (AI) development, from data acquisition to technological design and deployment. AI systems that fail to account for the contribution of sex and gender to health generate suboptimal results and discriminatory outcomes. Assessing sex and gender biases in these resources enables to acquire insights and awareness on the pressing need of an ethically informed science, paving the way to robust, trustworthy, and intelligible applications of AI accounting for sex and gender equity. Nevertheless, sex and gender biases are not the only types of biases that can manifest in AI systems. In this chapter, we provide an overview on the pervasiveness of several types of biases in AI development and a categorization of the main types of biases as well as bias metrics and available implementations for AI fairness evaluation, with special emphasis on sex and gender categories.