JMIR Publications

ABSTRACT

Background:

Advances in biomedical research utilizing deep learning techniques have generated a large volume of related literature. However, there is a lack of scientometric studies that provide a bird’s eye view of them. This absence leads to a partial and fragmented understanding of the field and its progress.

Objective:

The present study aimed to gain a quantitative and qualitative understanding of the scientific domain, through analyzing the diverse bibliographic entities that represent the research landscape from multiple perspectives and granularity.

Methods:

We searched and retrieved 978 deep learning studies in biomedicine from the PubMed database. A scientometric analysis was performed by analyzing metadata, content of the influential works, and cited references.

Results:

In the process, we identified the current leading fields, major research topics and techniques, knowledge diffusion, and research collaboration. There was a predominant focus on applying deep learning, especially convolutional neural networks (CNNs), to radiology and medical imaging, while a few studies focused on protein or genome analysis. Radiology and medical imaging also appeared as the most significant knowledge source and an important field in knowledge diffusion, followed by computer science and electrical engineering. Co-authorship analysis revealed various collaborations among engineering-oriented and biomedicine-oriented clusters of disciplines.

Conclusions:

The present study investigated the landscape of deep learning research in biomedicine and confirmed its interdisciplinary nature. Though it has been successful, we believe that there is a need for diverse applications in certain areas to further boost the contribution of deep learning in addressing biomedical research problems. We expect the results of this study to help researchers and communities better align their present and future works.