CoChat
Sign Up
PreprintCited by 11scientometrics and bibliometrics researchArtificial Intelligence in Healthcare and EducationDiverse Approaches in Healthcare and Education Studies

The DOI matches its Crossref record; 1 of the 1 references it cites were found in a registry or an index.

Study on horizon-scanning with a focus on the development of AI-based medical products: citation network analysis

Open access
Takata, Takuya, Sasaki, Hajime, Yamano, Hiroko, Honma, Masashi, Shikano, Mayumi·2021·Therapeutic Innovation & Regulatory Science
DOI 10.1101/2021.02.25.21252496PMC PMC8854249

Preprint — published as 10.1007/s43441-021-00355-z

Open this paper in CoChat — free accountOpen PDF

Abstract

Objectives: Horizon-scanning for innovative technologies that might be applied to medical products and require new assessment approaches/regulations will help to prepare regulators, allowing earlier access to the product for patients and an improved benefit/risk ratio. In this study, we focused on the field of AI-based medical image analysis as a retrospective example of medical devices, where many products have recently been developed and applied. We proposed and validated horizon-scanning using citation network analysis and text mining for bibliographic information analysis. Methods and analysis: Research papers for citation network analysis which contain “convolutional*” OR “machine-learning” OR “deep-learning” were obtained from Science Citation Index Expanded (SCI-expanded) in the Web of Science (WoS). The citation network among those papers was converted into an unweighted network with papers as nodes and citation relationships as links. The network was then divided into clusters using the topological clustering method and the characteristics of each cluster were confirmed by extracting a summary of frequently cited academic papers, and the characteristic keywords, in the cluster. Results: We classified 119,553 publications obtained from SCI and grouped them into 36 clusters. Hence, it was possible to understand the academic landscape of AI applications. The key articles on AI-based medical image analysis were included in one or two clusters, suggesting that clusters specific to the technology were appropriately formed. Based on the average publication year of the constituent papers of each cluster, we tracked recent research trends. It was also suggested that significant research progress would be detected as a quick increase in constituent papers and the number of citations of hub papers in the cluster. Conclusion: We validated that citation network analysis applies to the horizon-scanning of innovative medical devices and demonstrated that AI-based electrocardiograms and electroencephalograms can lead to the development of innovative products. Article Summary: Strengths and limitations of this study: Citation network analysis can provide an academic landscape in the investigated research field, based on the citation relationship of research papers and objective information, such as characteristic keywords and publication year. It might be possible to detect possible significant research progress and the emergence of new research areas through analysis every several months. It is important to confirm the opinions of experts in this area when evaluating the results of the analysis. Information on patents and clinical trials for this analysis is currently unavailable.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1101/2021.02.25.21252496

Cites

1 of 1 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig. 1 Steps of clustering and making Academic Landscape based on citation network. This figure has been published in reference [10]. The procedure of the citation network is as follows: (1) Extract the dataset of academic papers for analysis. (2) To extract the data, convert the citation network into an unweighted network with papers as nodes and citation relationships as links. (3) Divide the network into several clusters by using the topological clustering method. (4) Use a large graph layout (LGL), based on a force-direct layout algorithm, to display the largest connected component of the network to generate coordinates for the nodes in two dimensions and to visualize the citation network by expressing inter-cluster links with the same color.
Fig. 1 Steps of clustering and making Academic Landscape based on citation network. This figure has been published in reference [10]. The procedure of the citation network is as follows: (1) Extract the dataset of academic papers for analysis. (2) To extract the data, convert the citation network into an unweighted network with papers as nodes and citation relationships as links. (3) Divide the network into several clusters by using the topological clustering method. (4) Use a large graph layout (LGL), based on a force-direct layout algorithm, to display the largest connected component of the network to generate coordinates for the nodes in two dimensions and to visualize the citation network by expressing inter-cluster links with the same color.CC BY · PubMed Central
Fig. 2 Tracking clusters containing key articles. We analyzed papers obtained from WoS published up to the indicated years. We plotted the cluster numbers that contained the eight key articles shown in Table 1, with the circle sizes representing the approximate number of citations in the cluster for each paper
Fig. 2 Tracking clusters containing key articles. We analyzed papers obtained from WoS published up to the indicated years. We plotted the cluster numbers that contained the eight key articles shown in Table 1, with the circle sizes representing the approximate number of citations in the cluster for each paperCC BY · PubMed Central
Fig. 3 Tracking clusters related to ECG and EEG. We analyzed papers obtained from WoS published up to the indicated years. A cluster number indicates the cluster on ECG and EEG. The circle sizes indicate the approximate citation frequency of the key article, [73] and the number in each circle represents the number of citations in the cluster. Clusters on ECG and EGG were first detected in 2015 as cluster number 10 and were classified into cluster numbers 11, 21, 1, 15, and 15 for 2016, 2017, 2018, 2019, and 2020, respectively
Fig. 3 Tracking clusters related to ECG and EEG. We analyzed papers obtained from WoS published up to the indicated years. A cluster number indicates the cluster on ECG and EEG. The circle sizes indicate the approximate citation frequency of the key article, [73] and the number in each circle represents the number of citations in the cluster. Clusters on ECG and EGG were first detected in 2015 as cluster number 10 and were classified into cluster numbers 11, 21, 1, 15, and 15 for 2016, 2017, 2018, 2019, and 2020, respectivelyCC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 62

  1. 10.1136/bmjopen-2018-026764 · DOI
  2. 10.1016/S0306-4573(98)00068-5 · DOI
  3. 2002, Visualizing and tracking the growth of competing paradigms: Two case studies, Journal of the American Society for information Science and Technology, 53, 678, 10.1002/asi.10075 · DOI
  4. 10.1002/(SICI)1097-4571(1999)50:9<799::AID-ASI9>3.3.CO;2-7 · DOI
  5. 2007, Creating an academic landscape of sustainability science: an analysis of the citation network, Sustainability Science, 2, 221, 10.1007/s11625-007-0027-8 · DOI
  6. 2008, Tracking emerging technologies in energy research: Toward a roadmap for sustainable energy, Technological forecasting and social change, 75, 771, 10.1016/j.techfore.2007.05.005 · DOI
  7. Detecting emerging research fronts in regenerative medicine by citation network analysis of scientific publications. PICMET’09-2009 Portland International Conference on Management of Engineering & Technology; 2009. IEEE.
  8. 2014, Finding linkage between technology and social issue: A Literature Based Discovery approach, Journal of Engineering and Technology Management, 32, 160, 10.1016/j.jengtecman.2013.05.006 · DOI
  9. 2012, Identifying knowledge structure of patent and innovation research, Journal of Intellectual Property Association of Japan, 8, 56
  10. 10.13044/j.sdewes.2016.04.0032 · DOI
  11. 2020, Emerging Scientific Field Detection Using Citation Networks and Topic Models—A Case Study of the Nanocarbon Field, Applied System Innovation, 3, 40, 10.3390/asi3030040 · DOI
  12. 10.1109/5.726791 · DOI · Paper page
  13. 10.1109/TPAMI.2012.231 · DOI · Paper page
  14. 10.1145/3065386 · DOI · Paper page
  15. 10.1001/jamaophthalmol.2013.1743 · DOI
  16. Deep feature learning for knee cartilage segmentation using a triplanar convolutional neural network. International conference on medical image computing and computer-assisted intervention; 2013. Springer.
  17. U-net: Convolutional networks for biomedical image segmentation. International Conference on Medical image computing and computer-assisted intervention; 2015. Springer.
  18. 10.1038/nature14539 · DOI · Paper page
  19. Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition; 2016.
  20. 10.1109/TMI.2016.2536809.69 · DOI
  21. 10.1167/iovs.16-19964 · DOI · Paper page
  22. 10.1038/nature21056 · DOI · Paper page
  23. 10.1016/j.media.2017.07.005 · DOI · Paper page
  24. 10.1111/aos.13613 · DOI · Paper page
  25. 10.1088/1742-5468/2008/10/p10008 · DOI · Paper page
  26. 10.1016/j.jmb.2004.04.047 · DOI
  27. 2016, Academic landscape of hydropower: citation-analysis-based method and its application, International Journal of Energy Technology and Policy, 12, 84, 10.1504/IJETP.2016.074493 · DOI
  28. 10.1001/jama.2016.17216 · DOI · Paper page
  29. 10.1016/j.media.2016.10.004 · DOI · Paper page
  30. 10.1001/jama.2017.14585 · DOI · Paper page
  31. 10.1148/radiol.2017162326 · DOI · Paper page
  32. 10.1038/srep13087 · DOI
  33. 10.1109/tbme.2015.2468589 · DOI
  34. 2016, A novel deep learning approach for classification of EEG motor imagery signals, Journal of neural engineering, 14, 016003
  35. 10.1016/j.compbiomed.2017.09.017 · DOI
  36. 10.1109/TBME.2010.2048568 · DOI
  37. 10.1038/sdata.2014.53 · DOI
  38. 10.1109/TPAMI.2012.59 · DOI
  39. 10.1016/j.imavis.2008.08.005 · DOI · Paper page
  40. 10.1016/j.jbiomech.2004.05.002 · DOI
  41. 10.1145/2629500 · DOI
  42. 10.1056/NEJMp1606181 · DOI · Paper page
  43. 10.1136/amiajnl-2011-000203 · DOI
  44. 10.1257/jep.31.2.87 · DOI · Paper page
  45. 10.1038/s41746-018-0029-1 · DOI · Paper page
  46. 10.1097/CCM.0000000000002936 · DOI · Paper page
  47. 2016, A combined deep-learning and deformable-model approach to fully automatic segmentation of the left ventricle in cardiac MRI, Medical image analysis, 30, 108, 10.1016/j.media.2016.01.005 · DOI
  48. 10.1016/j.neuroimage.2016.02.079 · DOI · Paper page
  49. 10.1016/j.neubiorev.2012.01.004 · DOI · Paper page
  50. 10.1016/j.neuroimage.2014.06.077 · DOI · Paper page
  51. 10.1016/j.neuroimage.2017.03.057 · DOI · Paper page
  52. 10.1177/2167702617691560 · DOI
  53. 10.1016/j.nicl.2017.08.017 · DOI · Paper page
  54. 10.1023/a:1010933404324 · DOI · Paper page
  55. 10.1021/ci500747n · DOI · Paper page
  56. 10.1038/nbt.3300 · DOI · Paper page
  57. 10.1524/auto.2011.0951 · DOI
  58. 10.1016/j.knosys.2018.10.007 · DOI
  59. 2010, Convolutional neural networks for P300 detection with application to brain-computer interfaces, IEEE transactions on pattern analysis and machine intelligence, 33, 433
  60. 10.7748/nr.3.4.79.s8 · DOI
  61. 10.1038/nbt0818-673a · DOI · Paper page
  62. 2017, Trends and typology of emerging antenna propagation technologies: Citation network analysis, International Journal of Innovation and Technology Management, 14, 1740005, 10.1142/S0219877017400053 · DOI

Metadata

Authors
Takata, T., Sasaki, H., Yamano, H., Honma, M., & Shikano, M.
Affiliations
  • Tokyo University of Science (JP)
  • Institute for Future Initiatives, The University of Tokyo (JP)
  • University of Tokyo Hospital (JP)
Corresponding author
Shikano, Mayumi
ORCID
Venue
Therapeutic Innovation & Regulatory Science
Publisher
openRxiv
Published
2021-03-01
Volume
56
Issue
2
Pages
263-275
ISSN
2168-4790 (ISSN-L)
DOI
10.1101/2021.02.25.21252496
PMC
PMC8854249
OpenAlex
W4220993218
Cited by
11
References
1
Citations by year
2025: 3 · 2024: 2 · 2023: 3 · 2022: 1 · 2021: 2
FWCI
1.16
Type
journal article
Language
en
Open access
Licence
cc-by
Locations
  • Therapeutic Innovation & Regulatory Science (publishedVersion, cc-by)
  • medRxiv (acceptedVersion, cc-by-nc)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
Funders
Japan Agency for Medical Research and Development (JP20mk0101155)
Topics
  • Social Sciences › Library and Information Sciences › scientometrics and bibliometrics research
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Health Sciences › Medicine › Public Health, Environmental and Occupational Health › Diverse Approaches in Healthcare and Education Studies
Keywords
horizon scanning, citation network analysis, text mining, research trends, machine learning, deep learning, medical image analysis, human activity recognition, clinical natural language processing, drug discovery, FDA draft guidance, regulatory science
MeSH terms
Artificial Intelligence, Humans, Technology, Data Mining

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review