Over 100 000 research articles and 9000 patents have been published on tissue engineering (TE) in the past 20 years. Yet, very few TE products have made their way to the market during the same period. Experts have proposed a variety of strategies to address the lack of translation of TE products. However, since these proposals are guided by qualitative insights, they are limited in scope and impact. Machine learning is utilized in the current study to analyze the entire body of patents that have been published over the past twenty years and understand patenting trends, topics, areas of application, and exemplifications. This analysis yields surprising and little-known insights about the differences in research priorities and perceptions of innovativeness of tissue engineers in academia and industry, as well as aids to chart true advances in the field during the past twenty years. It is hoped that this analysis and subsequent proposal to improve translational rates of TE products will spur much needed dialogue about this important pursuit.
Keywords: biopharmaceutical industry; innovation; machine learning; tissue engineering; translation.
© 2019 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.