Raising awareness of sex and gender bias in artificial intelligence and health

Abstract

Historically, biomedical research has been led by and focused on men. The recent introduction of Artificial Intelligence (AI) in this area has further proven this practice to be discriminatory for other sexes and genders, more noticeably for women. To move towards a fair AI development, it is essential to include sex and gender diversity both in research practices and in the workplace. In this context, the Bioinfo4women (B4W) program of the Barcelona Supercomputing Center (i) promotes the participation of women scientists by improving their visibility, (ii) fosters international collaborations between institutions and programs and (iii) advances research on sex and gender bias in AI and health. In this article, we discuss methodology and results of a series of conferences, titled “Sex and Gender Bias in Artificial Intelligence and Health, organized by B4W and La Caixa Foundation from March to June 2021 in Barcelona, Spain. The series consisted of nine hybrid events, composed of keynote sessions and seminars open to the general audience, and two working groups with invited experts from different professional backgrounds (academic fields such as biology, engineering, and sociology, as well as NGOs, journalists, lawyers, policymakers, industry). Based on this awareness-raising action, we distilled key recommendations to facilitate the inclusion of sex and gender perspective into public policies, educational programs, industry, and biomedical research, among other sectors, and help overcome sex and gender biases in AI and health.

Keywords: AI; bias in science; gender bias; gender policies; health.

Figure 1

Infographic representing structure, timeline and outcomes of the B4W series of conferences “Sex and Gender Biases in Artificial Intelligence and Health” (Barcelona, March-June 2021). The series of conferences consisted of an opening conference, two blocks of activities focused on two themes (Personalized Medicine and Artificial Intelligence), and a closing conference. The main outcomes were distilled into recommendations generated after the end of the event. The detailed calendar of the series of conferences and participating domain experts are provided as Supplementary Table S1.