Regulatory-approved deep learning/machine learning-based medical devices in Japan as of 2020: A systematic review
Nao Aisu, Masahiro Miyake, Kohei Takeshita, Masato Akiyama, Ryo Kawasaki, Kenji Kashiwagi, Taiji Sakamoto, Tetsuro Oshika, Akitaka Tsujikawa
Abstract
Machine learning (ML) and deep learning (DL) are changing the world and reshaping the medical field. Thus, we conducted a systematic review to determine the status of regulatory-approved ML/DL-based medical devices in Japan, a leading stakeholder in international regulatory harmonization. Information about the medical devices were obtained from the Japan Association for the Advancement of Medical Equipment search service. The usage of ML/DL methodology in the medical devices was confirmed using public announcements or by contacting the marketing authorization holders via e-mail when the public announcements were insufficient for confirmation. Among the 114,150 medical devices found, 11 were regulatory-approved ML/DL-based Software as a Medical Device, with 6 products (54.5%) related to radiology and 5 products (45.5%) related to gastroenterology. The domestic ML/DL-based Software as a Medical Device were mostly related to health check-ups, which are common in Japan. Our review can help understanding the global overview that can foster international competitiveness and further tailored advancements.