Yoon Ha Young, Lee Heisook, Yee Jeong, Gwak Hye Sun
College of Pharmacy and Graduate School of Pharmaceutical Sciences, Ewha Womans University, Seoul, South Korea.
Korea Center for Gendered Innovations for Science and Technology Research, Seoul, South Korea.
Front Med (Lausanne). 2022 May 17;9:868040. doi: 10.3389/fmed.2022.868040. eCollection 2022.
This study aimed to assess the research on medical Artificial intelligence (AI) related to sex/gender and explore global research trends over the past 20 years. We searched the Web of Science (WoS) for gender-related medical AI publications from 2001 to 2020. We extracted the bibliometric data and calculated the annual growth of publications, Specialization Index, and Category Normalized Citation Impact. We also analyzed the publication distributions by institution, author, WoS subject category, and journal. A total of 3,110 papers were included in the bibliometric analysis. The number of publications continuously increased over time, with a steep increase between 2016 and 2020. The United States of America and Harvard University were the country and institution that had the largest number of publications. Surgery and urology nephrology were the most common subject categories of WoS. The most occurred keywords were machine learning, classification, risk, outcomes, diagnosis, and surgery. Despite increased interest, gender-related research is still low in medical AI field and further research is needed.
本研究旨在评估与性别相关的医学人工智能（AI）研究，并探索过去20年的全球研究趋势。我们在科学网（WoS）中搜索了2001年至2020年与性别相关的医学人工智能出版物。我们提取了文献计量数据，并计算了出版物的年增长率、专业化指数和类别归一化引文影响力。我们还分析了按机构、作者、WoS学科类别和期刊划分的出版物分布情况。文献计量分析共纳入3110篇论文。出版物数量随时间持续增加，在2016年至2020年间急剧增加。美国和哈佛大学是出版物数量最多的国家和机构。外科学和泌尿外科学肾脏病学是WoS中最常见的学科类别。出现最多的关键词是机器学习、分类、风险、结果、诊断和外科手术。尽管关注度有所提高，但医学人工智能领域中与性别相关的研究仍然较少，需要进一步开展研究。
