Patents with all-female inventor teams are more likely than all-male teams to address problems that specifically or disproportionately affect women, according to a new study. The findings, derived from an analysis of more than 440,000 U.S. biomedical patents filed from 1976 to 2010, suggest that who benefits most from innovation largely depends on who gets to invent. While the gender gap in research and innovation is well known, its broader impact on what gets invented - and for whom - isn't well understood. To address this question, Rembrand Koning and colleagues used machine learning text analysis to evaluate all U.S. biomedical patents filed from 1976 to 2010. They found that patents filed from all-female inventor teams were more than 35% more likely to focus on women's health than all-male teams, while teams that were majority female were 18% more likely to make products with women in mind. The data show that women were represented in only 25% of patents. In another part of their analysis, Koning and colleagues uncovered that female researchers are more likely to make female-focused discoveries that could ultimately lead to women's health patents. If patents were invented between men and women equally during their study period, Koning et al. estimate that there would have been roughly 6,500 more female-focused inventions. According to the authors, the findings underscore the many promising female-focused discoveries that have yet to be made and/or commercialized because women are less likely to obtain patents. "Beyond recognizing the loss of human talent that arises when women are under-represented in innovation, this finding highlights the types of problems (and solutions) that are overlooked in the current system with its support of a homogeneous group of inventors," writes Fiona Murray in a related Perspective. On June 21, Murray will participate in a related National Academies of Science, Engineering, and Medicine workshop, "Overcoming Structural Barriers for Women in Entrepreneurship."