Study on Horizon Scanning with a Focus on the Development of AI-Based Medical Products: Citation Network Analysis

Abstract

Horizon scanning for innovative technologies that might be applied to medical products and requires new assessment approaches to prepare regulators, allowing earlier access to the product for patients and an improved benefit/risk ratio. The purpose of this study is to confirm that citation network analysis and text mining for bibliographic information analysis can be used for horizon scanning of the rapidly developing field of AI-based medical technologies and extract the latest research trend information from the field. We classified 119,553 publications obtained from SCI constructed with the keywords “conventional,” “machine-learning,” or “deep-learning" and grouped them into 36 clusters, which demonstrated the academic landscape of AI applications. We also confirmed that one or two close clusters included the key articles on AI-based medical image analysis, suggesting that clusters specific to the technology were appropriately formed. Significant research progress could be detected as a quick increase in constituent papers and the number of citations of hub papers in the cluster. Then we tracked recent research trends by re-analyzing “young” clusters based on the average publication year of the constituent papers of each cluster. The latest topics in AI-based medical technologies include electrocardiograms and electroencephalograms (ECG/EEG), human activity recognition, natural language processing of clinical records, and drug discovery. We could detect rapid increase in research activity of AI-based ECG/EEG a few years prior to the issuance of the draft guidance by US-FDA. Our study showed that a citation network analysis and text mining of scientific papers can be a useful objective tool for horizon scanning of rapidly developing AI-based medical technologies.

Application of Internet of Medical/Health Things to Decentralized Clinical Trials: Development Status and Regulatory Considerations

“…Figure 1 gives an outline of the citation network analysis process which has been published in references ( 16 , 17 , 20 ). We converted the citation network into an unweighted network, with papers as nodes and citation relationships as links.…”

“…However, it is highly sensitive to certain terms; when text mining is used with other methods, the problem of terminological distortion will be unignorable. Therefore, we propose an objective methodology for horizon scanning that identifies cutting edge technology to be applied to medical products, which are AI-based medical devices, drugs related to T cell immune responses, and extracellular vesicle-based products from all research papers in the target field using both citation network analysis methods and text mining ( 16 – 19 ).…”

Horizon Scanning in Tissue Engineering Using Citation Network Analysis

“…This study revealed that the analysis of the interdisciplinary fields is characterized by the distribution of articles in clusters of their basic technologies, which differs from AI-based medical products and immunology fields [ 12 , 13 ]. When applying horizon scanning based on the citation network analysis to an interdisciplinary research field confirming the development of the product or medical technology under consideration and evaluating not only the research trends in nonclinical studies toward clinical application but also trends in basic technologies that constitute the product or medical technology is necessary.…”

“…This index is calculated for each cluster by applying term frequency inverse document frequency (TFIDF), which is an index used for each document. This method has been used in past analyses [ 12 – 15 , 30 ].…”

“…Furthermore, we recommended that the results of this method should be interpreted according to the development history of each research field. Research activities in the field of immunology have focused on various reactions and molecules for an extended period, whereas the research and development of artificial intelligence (AI)-equipped medical devices have progressed rapidly [ 12 – 15 ]. The Leiden Manifesto issued by the Centre for Science and Technology Studies at Leiden University in 2015 also indicated that bibliometric analysis should be performed with due consideration for differences between research fields [ 16 ].…”