ORIGINAL RESEARCH


https://doi.org/10.5005/jp-journals-10024-3386
The Journal of Contemporary Dental Practice
Volume 23 | Issue 8 | Year 2022

Characteristics, Impact, and Visibility of Scientific Publications on Artificial Intelligence in Dentistry: A Scientometric Analysis


Ricardo Velasquez1, John Barja-Ore2, Emma Salazar-Salvatierra3, Margot Gutiérrez-Ilave4, Cesar Mauricio-Vilchez5, Roman Mendoza6, Frank Mayta-Tovalino7

1,5,6Postgraduate Department, Faculty of Dentistry, Universidad Nacional Federico Villarreal, Lima, Peru

2Research Direction, Universidad Privada del Norte, Lima, Peru

3School of Obstetrics, Universidad Nacional Mayor de San Marcos, Lima, Peru

4Academic Department of Preventive and Social Stomatology, Faculty of Dentistry, Universidad Nacional Mayor de San Marcos, Lima, Peru

7Vicerrectorado de Investigación, Unidad de Revisiones Sistemáticas y Metaanálisis, Universidad San Ignacio de Loyola, Lima, Peru

Corresponding Author: Frank Mayta-Tovalino, Vicerrectorado de Investigación, Universidad San Ignacio de Loyola, Av. la Fontana, La Molina, Lima, Peru, Phone: +013171000, e-mail: fmayta@usil.edu.pe

How to cite this article: Velasquez R, Barja-Ore J, Salazar-Salvatierra E, et al. Characteristics, Impact, and Visibility of Scientific Publications on Artificial Intelligence in Dentistry: A Scientometric Analysis. J Contemp Dent Pract 2022;23(8):761–767.

Source of support: Nil

Conflict of interest: None

ABSTRACT

Aim: To analyze the bibliometric characteristics, impact, and visibility of scientific publications on artificial intelligence (AI) in dentistry in Scopus.

Materials and methods: Descriptive and cross-sectional bibliometric study, based on the systematic search of information in Scopus between 2017 and July 10, 2022. The search strategy was elaborated with Medical Subject Headings (MeSH) and Boolean operators. The analysis of bibliometric indicators was performed with Elsevier’s SciVal program.

Results: From 2017 to 2022, the number of publications in indexed scientific journals increased, especially in the Q1 (56.1%) and Q2 (30.6%) quartile. Among the journals with the highest production, the majority was from the United States and the United Kingdom, and the Journal of Dental Research has the highest impact (14.9 citations per publication) and the most publications (31). In addition, the Charité – Universitätsmedizin Berlin (FWCI: 8.24) and Krois Joachim (FWCI: 10.09) from Germany were the institution and author with the highest expected performance relative to the world average, respectively. The United States is the country with the highest number of published papers.

Clinical significance: There is an increasing tendency to increase the scientific production on artificial intelligence in the field of dentistry, with a preference for publication in prestigious scientific journals of high impact. Most of the productive authors and institutions were from Japan. There is a need to promote and consolidate strategies to develop collaborative research both nationally and internationally.

Keywords: Artificial intelligence, Bibliometric analysis, Deep learning, Dentistry, Machine learning.

INTRODUCTION

Recently with the technological progress of recent years, computational power and data analysis capacity has increased. In addition, new learning models have enabled rapid progress in many fields of knowledge.1 The strengthening of informatics competence has favored the development of artificial intelligence, which involves complex automated algorithms dependent on statistics that can predict patterns with a certain level of accuracy.2,3

Artificial intelligence has been having a real impact on various aspects of society and the area of health is no stranger to this. It has been demonstrated that the implementation of this technology can generate significant improvements during the delivery of healthcare services.4 In fact, current evidence shows that artificial intelligence can work optimally to identify the diagnosis and treatment of some diseases.5 Intelligence artificial (IA) has different applications in the dental field. For example, it is used for the diagnosis of caries, periodontal disease, and jaw lesions. They are especially useful for an accurate diagnosis of certain oral pathologies using Big Data. Besides, it is expected that, over time, artificial intelligence technologies will continue to develop innovation for future healthcare.6

In the field of dentistry, artificial intelligence is currently used for various purposes, such as periodontics, endodontics, orthodontics, radiology, and detection of oral pathologies. Likewise, its use has been extended to the educational field and especially in the use of dental laboratories.7 Its rapid development in recent years would allow it to be considered a fundamental tool of routine use for modern dentistry, but it is necessary to continue developing instigations and deepening the ethical challenges so that it can become part of the dentist’s professional work.8,9

For the implementation of artificial intelligence, a proactive attitude is required to achieve a change in dental practice that will improve care and reduce costs for the benefit of users and society.10,11 In this sense, dental research should favor the development of these technologies based on an understanding of the different techniques, tools, and concepts that exist today.12

The exploration of the available scientific evidence is necessary, given the accelerated development of science in the field of dentistry. Evaluating the bibliometric indicators of scientific production makes it possible to recognize its impact and relevance in the different collaborative networks. Due to the scarcity of evidence published in a specific dental specialty, this scientometric study covered manuscripts on the use and application of IA in general dentistry. For this reason, the aim of this study is to analyze the bibliometric characteristics, impact, and visibility of scientific publications on artificial intelligence in dentistry in Scopus.

MATERIALS AND METHODS

Study Design

A descriptive, cross-sectional, bibliometric study was conducted based on the analysis of documents published in scientific journals indexed in Scopus between 2017 and July 10, 2022.

Search Strategy

The advanced search for information was carried out with a search strategy that was elaborated with the terms Medical Subject Headings (MeSH), which were grouped with the Boolean operator “OR”; in addition, the sub-area of dentistry was included by means of the operative “AND”. With these precisions, the search strategy was defined as follows: TITLE-ABS (“Machine Learning” OR “Deep Learning” OR “Artificial Intelligence” OR “Learning Deep” OR “Intelligence Artificial” OR “Computational Intelligence” OR “Intelligence Computational” OR “Machine Intelligence” OR “Intelligence Machine” OR “Computer Reasoning” OR “Reasoning Computer” OR “Computer Vision Systems” OR “Computer Vision System” OR “System Computer Vision” OR “Systems Computer Vision” OR “Vision System Computer” OR “Vision Systems Computer” OR “Knowledge Acquisition” OR “Acquisition Knowledge” OR “Knowledge Representation” OR “Knowledge Representations” OR “Representation Knowledge”) AND SUBJAREA (dent). The result of the search was 522 publications of any language made between the year 2017 and 2022; and pertaining to the area of dentistry. As of September 28, 2022, we found Original Article (433), Review (70), Editorial (17), Letter (15), and Conference Paper (12) among other types of published research.

Data Collection

The export of the metadata of the publications was performed on July 10, 2022. Of the total number of publications identified with the search strategy, only 508 were exported with the SciVal software of the Elsevier Corporation and 459 were finally analyzed. This tool allows the analysis of a given topic in a field of knowledge through the exploration of different bibliometric indicators of production, impact, and collaboration. The export was done in a .csv file. In addition, percentages were estimated with the Microsoft Excel program. Finally, all the information was presented in tables.

Selection Criteria

Manuscripts on AI indexed in Scopus.

Manuscripts on AI in all languages.

Manuscripts published during 2017–2022.

Scientometric Analysis

As part of the analysis of this research, the following metrics of the bibliometric methodology were studied: authorship and h-index of each author, country, collaboration, number of publications, number of citations, citations per publication, field-weighted citation impact (FWCI), journal quartile, SCImago Journal Rank (SJR), Source-Normalized Impact per Paper (SNIP), and CiteScore 2020.

RESULTS

Top 10 Countries with the Highest Scientific Production

Among the countries with the highest scientific production, the United States (109) has the highest productivity, with approximately twice as many publications as Japan (54). Although Germany has 32 publications, it is the country with the best performance given that it has a higher number of expected citations with respect to the world average (FWCI: 7.31) (Table 1).

Table 1: Top 10 countries with the highest scientific production
Country/Region Scholarly output Views count FWCI Citation count

United States
109 2341 2.71 772

Japan
54 1082 2.92 564

China
46 716 3.1 184

South Korea
45 916 3.92 811

India
34 832 3.78 225

Turkey
33 786 2.91 236

Germany
32 952 7.31 506

Brazil
31 714 2.9 222

United Kingdom
30 576 2.01 159

Saudi Arabia
21 530 3.21 185
FWCI, field-weighted citation impact

Top 10 Institutions with the Highest Scientific Production

Japan is the country with the most institutions among those with the highest scientific production. In fact, Aichi Gakuin University is the most productive, with 21 publications and 19.5 citations per publication. However, the institution with the highest impact was Yonsei University in South Korea, with 39.5 citations per publication. In addition, the Charité – Universitätsmedizin Berlin of Germany had the highest expected return relative to the world average (FWCI: 8.24) (Table 2).

Table 2: Top 10 institutions with the highest scientific production
Institution Country Scholarly output Citations Authors Citations per publication FWCI
Aichi Gakuin University 21 409 35 19.5 4.24
Charité – Universitätsmedizin Berlin 18 338 30 18.8 8.24
Asahi University 16 389 7 24.3 4.62
KU Leuven 14 69 34 4.9 5.11
Ankara University 14 124 3 8.9 3.64
The University of Hong Kong 13 130 21 10 3.88
Seoul National University 13 241 23 18.5 4.16
Karolinska Institutet 13 117 2 9 5.58
Yonsei University 12 471 31 39.3 4.8
Gifu University 11 367 4 33.4 6.26
FWCI, field-weighted citation impact

Top 10 Scientific Journals with the Highest Number of Scientific Production

The 10 journals with the highest production on artificial intelligence in dentistry are of high impact, located in the Q1 and Q2 quartile, moreover, most of them are from the United States (n = 3) and United Kingdom (n = 3). The Journal of Dental Research has the most publications (n = 31) and the highest impact (14.9 citations per publication) (Table 3).

Table 3: Top 10 scientific journals with the highest number of scientific productions
Scopus source Quartile Country Publications Citations Authors Citations per publication SNIP CiteScore 2020 SJR
Journal of Dental Research Q1 31 461 229 14.9 2.519 12.1 1.78
Dentomaxillofacial Radiology Q1 27 273 132 10.1 1.539 4.4 0.79
Orthodontics and Craniofacial Research Q1 21 46 147 2.2 1.373 3.2 0.82
Journal of Dentistry Q1 20 360 99 18 1.917 6.8 1.11
Oral Surgery, Oral Medicine, Oral Pathology and Oral Radiology Q2 19 226 92 11.9 1.343 3.9 0.57
Oral Oncology Q1 16 214 116 13.4 1.85 7.9 1.42
Clinical Oral Investigations Q1 15 51 90 3.4 1.779 5.8 0.92
Oral Radiology Q2 15 159 78 10.6 1.311 2.7 0.45
Journal of Dental Education Q2 14 31 59 2.2 1.572 2.1 0.46
BMC Oral Health Q1 13 59 69 4.5 1.785 3.6 0.79
SJR, SCImago Journal Rank; SNIP, source-normalized impact per paper

Trend of Scientific Production by Quartile of Indexed Journals

The scientific production increased from 10 publications in 2017 to 169 in 2021. Approximately 90% of the production is in high-impact scientific journals, corresponding to the Q1 (56.1%) and Q2 (30.6%) quartile (Table 4) (Fig. 1).

Table 4: Trend of scientific production by quartile of indexed journals
CiteScore quartile 2017 2018 2019 2020 2021 2022 Overall
n %
Q1 1 4 23 38 99 79 244 56.1
Q2 4 6 13 26 54 30 133 30.6
Q3 4 1 9 15 10 5 44 10.1
Q4 1 0 0 3 6 4 14 3.2
Total 10 11 45 82 169 118 435 100

Fig. 1: Scientific publications by quartile of the indexed journals. Scientific production increased from 10 publications in 2017 to 169 in 2021. The number of publications in scientific journals of the third and fourth quartile maintain a homogeneous trend in all years. Approximately 90% of the production is in high-impact scientific journals, corresponding to quartile Q1 (56.1%) and Q2 (30.6%)

Top 10 Authors with the Highest Production

Among the 10 authors with the highest production, the majority were Japanese (6 publications), and, in fact, the authors with the highest production were Ariji Yoshiko (19 publications) and Katsumata Akitoshi (16 publications). Likewise, Fujita Hiroshi has the highest impact, presenting 33.4 citations per publication. The German author, Krois Joachim, is the one who had the most expected citations, taking as a reference the world average (FWCI: 10.09) (Table 5). The general dentistry category contains the most publications (253) and citations (2084), followed by oral surgery with 124 publications and 999 citations. Dental hygiene is the field least used for publications on artificial intelligence (Fig. 2).

Table 5: Top 10 authors with the highest production
Name Country Scholarly output Most recent publication Citations Citations per publication FWCI h-index
Ariji, Yoshiko 19 2022 408 21.5 4.66 28
Katsumata, Akitoshi 16 2022 370 23.1 4.39 24
Schwendicke, Falk 16 2022 338 21.1 9.27 53
Fukuda, Motoki 16 2022 398 24.9 5.38 11
Ariji, Eiichiro 15 2022 404 26.9 5.7 11
Krois, Joachim 14 2022 335 23.9 10.09 16
Orhan, Kaan 13 2022 102 7.8 3.61 27
Kise, Yoshitaka 12 2022 355 29.6 5.95 14
Fujita, Hiroshi 11 2021 367 33.4 6.26 38
Jacobs, Reinhilde 11 2022 65 5.9 6.16 71
FWCI, field-weighted citation impact

Fig. 2: Scientific publications and citations by specialty. The general dentistry category contains the most publications (253) and citations (2084), and dental hygiene is the field least used for publications on artificial intelligence

Collaboration between Countries

It was found that collaboration between countries was clustered in 7 major clusters. The United States was the country with the highest concentration of collaboration, especially with the United Kingdom, China, and South Korea (Fig. 3).

Fig. 3: Collaboration by country. Bibliometric map showing collaborative networks on IA by countries

DISCUSSION

Advances in various fields of science have led to the development of different technologies, such as artificial intelligence, which has many implications for society. In the field of health, specifically in dentistry, it has been implemented to improve the process of user care, from diagnosis to treatment of dental diseases. Its study is increasingly relevant to strengthen professional dental practice.

The findings show that there is a tendency to increase scientific production on artificial intelligence in the field of dentistry; furthermore, the United States is the country that contributes the most evidence in this field of knowledge; in fact, up to the date of execution of our study, it has almost twice as many publications as Japan. This highlights the need to strengthen the development of collaborative research between authors and institutions of different nationalities, which requires the standardization of processes, conditions, and tangible products of the different types of collaboration to realize collaborative and interdisciplinary research initiatives.13,14

The new research topics that arise with the development of science are of great interest to researchers. The purpose of the development of studies is the dissemination in scientific journals, especially in those with high impact and greater prestige in the scientific community.15 In this regard, the production on artificial intelligence in the field of dentistry is carried out in Q1 and Q2 quartile journals, the main ones being the Journal of Dental Research, Dentomaxillofacial Radiology, and Orthodontics and Craniofacial Research.

Dental research related to artificial intelligence is gaining more currency in recent years. In fact, our research shows that the authors with the highest output made their last publication in the last 2 years (2021 and 2022) and that most of them are from Japan. To date, the documented publications are focused on models based on artificial neural networks and convolutional neural networks,16 which demonstrate that artificial intelligence can handle the whole process of attention.17,18

The evaluation of the impact or performance of authors is based on the analysis of citations, although this widely used indicator is still a frequent source of debate among the scientific community.19 In this regard, the author Fujita Hiroshi has the highest impact, with 33.4 citations per publication; however, Krois Joachim was the one who had the most expected citations in relation to the world average (FWCI: 10.09). Although his production has been oriented to the treatment and diagnosis of diseases,2022 Krois Joachim has also shown that users of dental services are convinced that artificial intelligence would be useful,23 which is why its use should be oriented to organizing the patient’s own data for individualized treatment.24

The main limitation of this bibliometric research was that the search for published documents was only carried out in one database, Scopus,25 however, since it is one of the most important and with the widest coverage worldwide, it can express in a good way the scientific production in the subject studied. In addition, it should be considered that during the export of information with the SciVal program, metadata of the publications may have been lost, due to a bad registration or because some journals are no longer indexed in the database, these limitations are typical of this methodology, but they do not significantly affect the results presented in this research. This type of study makes it possible to identify the type of studies that are published in dentistry26,27 to be able to make decisions on strategic alliances for scientific collaboration.

The main dental specialties that can be developed with IA are those involving diagnostic imaging (radiology) and surgery (periodontics, oral implantology, and oral maxillofacial surgery). However, the main limitation is that IA could not be implemented in technologically underdeveloped countries because it is difficult to find resources such as specialized software and state-of-the-art equipment. Another limitation was that according to the data found, there is little original research on the application of IA in dentistry, therefore, it is important to focus our attention on this field of knowledge for the benefit of dentistry.

CONCLUSION

In conclusion, scientific production on artificial intelligence in dentistry has increased in recent years, especially in high-impact journals located in the Q1 and Q2 quartile. In addition, the authors with the highest contribution are Japanese, and the journals with the highest preference for publication are from the United Kingdom and the United States, the latter being the country with the most published papers.

ACKNOWLEDGMENTS

The authors wish to thank the Universidad Científica del Sur for its constant support in the preparation of this scientific paper.

REFERENCES

1. Badillo S, Banfai B, Birzele F, et al. An introduction to machine learning. Clin Pharmacol Ther 2020;107(4):871–885. DOI: 10.1002/cpt.1796.

2. Olczak J, Pavlopoulos J, Prijs J, et al. Presenting artificial intelligence, deep learning, and machine learning studies to clinicians and healthcare stakeholders: An introductory reference with a guideline and a Clinical AI Research (CAIR) checklist proposal. Acta Orthop 2021;92(5):513–525. DOI: 10.1080/17453674.2021.1918389.

3. Nichols JA, Herbert Chan HW, Baker MAB. Machine learning: Applications of artificial intelligence to imaging and diagnosis. Biophys Rev 2019;11(1):111–118. DOI: 10.1007/s12551-018-0449-9.

4. Bohr A, Memarzadeh K. The rise of artificial intelligence in healthcare applications. Artificial Intelligence Healthcare 2020:25–60. DOI: 10.1016/B978-0-12-818438-7.00002-2.

5. Davenport T, Kalakota R. The potential for artificial intelligence in healthcare. Future Healthc J 2019;6(2):94–98. DOI: 10.7861/futurehosp.6-2-94.

6. Park CW, Seo SW, Kang N, et al. Artificial intelligence in health care: Current applications and issues. J Korean Med Sci 2020;35(42):e379. DOI: 10.3346/jkms.2020.35.e379.

7. Nguyen TT, Larrivée N, Lee A, et al. Use of artificial intelligence in dentistry: Current clinical trends and research advances. J Can Dent Assoc 2021;87:l7. PMID: 34343070.

8. Ossowska A, Kusiak A, Świetlik D. Artificial intelligence in dentistry-narrative review. Int J Environ Res Public Health 2022;19(6):3449. DOI: 10.3390/ijerph19063449.

9. Mörch CM, Atsu S, Cai W, et al. Artificial intelligence and ethics in dentistry: A scoping review. J Dent Res 2021;100(13):1452–1460. DOI: 10.1177/00220345211013808.

10. Shan T, Tay FR, Gu L. Application of artificial intelligence in dentistry. J Dent Res 2021;100(3):232–244. DOI: 10.1177/0022034520969115.

11. Schwendicke F, Samek W, Krois J. Artificial intelligence in dentistry: Chances and challenges. J Dent Res 2020;99(7):769–774. DOI: 10.1177/0022034520915714.

12. Tandon D, Rajawat J. Present and future of artificial intelligence in dentistry. J Oral Biol Craniofac Res 2020;10(4):391–396. DOI: 10.1016/j.jobcr.2020.07.015.

13. Nyström ME, Karltun J, Keller C, et al. Collaborative and partnership research for improvement of health and social services: Researcher’s experiences from 20 projects. Health Res Policy Syst 2018;16(1):46. DOI: 10.1186/s12961-018-0322-0.

14. Rycroft-Malone J, Burton CR, Wilkinson J, et al. Collective action for implementation: A realist evaluation of organisational collaboration in healthcare. Implement Sci 2016;11:17. DOI: 10.1186/s13012-016-0380-z.

15. Jirge PR. Preparing and publishing a scientific manuscript. J Hum Reprod Sci 2017;10(1):3–9. DOI: 10.4103/jhrs.JHRS_36_17.

16. Khanagar SB, Al-Ehaideb A, Maganur PC, et al. Developments, application, and performance of artificial intelligence in dentistry – A systematic review. J Dent Sci 2021;16(1):508–522. DOI: 10.1016/j.jds.2020.06.019.

17. Chen YW, Stanley K, Att W. Artificial intelligence in dentistry: Current applications and future perspectives. Quintessence Int 2020;51(3):248–257. DOI: 10.3290/j.qi.a43952.

18. Ahmed N, Abbasi MS, Zuberi F, et al. Artificial intelligence techniques: Analysis, application, and outcome in dentistry: A systematic review. Biomed Res Int 2021;2021:9751564. DOI: 10.1155/2021/9751564.

19. Belter CW. Bibliometric indicators: Opportunities and limits. J Med Libr Assoc 2015;103(4):219–221. DOI: 10.3163/1536-5050.103.4.014.

20. Nishiyama M, Ishibashi K, Ariji Y, et al. Performance of deep learning models constructed using panoramic radiographs from two hospitals to diagnose fractures of the mandibular condyle. Dentomaxillofac Radiol 2021;50(7):20200611. DOI: 10.1259/dmfr.20200611.

21. Schwendicke F, Mertens S, Cantu AG, et al. Cost-effectiveness of AI for caries detection: randomized trial. J Dent 2022;119:104080. DOI: 10.1016/j.jdent.2022.104080.

22. Krois J, Garcia Cantu A, Chaurasia A, et al. Generalizability of deep learning models for dental image analysis. Sci Rep 2021;11(1):6102. DOI: 10.1038/s41598-021-85454-5.

23. Kosan E, Krois J, Wingenfeld K, et al. Patients’ perspectives on artificial intelligence in dentistry: A controlled study. J Clin Med 2022;11(8):2143. DOI: 10.3390/jcm11082143.

24. Bernauer SA, Zitzmann NU, Joda T. The use and performance of artificial intelligence in prosthodontics: A systematic review. Sensors (Basel) 2021;21(19):6628. DOI: 10.3390/s21196628.

25. Mayta-Tovalino F, Pacheco-Mendoza J, Diaz-Soriano A, et al. Bibliometric study of the National Scientific Production of All Peruvian Schools of Dentistry in Scopus. Int J Dent 2021;2021:5510209. DOI: 10.1155/2021/5510209.

26. Poma-Castillo L, Espinoza-Poma M, Mauricio F, et al. Antifungal activity of ethanol-extracted Bixa orellana (L) (Achiote) on Candida albicans, at six different concentrations. J Contemp Dent Pract 2019;20(10):1159–1163. DOI: 10.5005/jp-journals-10024-2672.

27. Arce J, Palacios A, Alvítez-Temoche D, et al. Tensile strength of novel nonabsorbable PTFE (Teflon®) versus other suture materials: An in vitro study. Int J Dent 2019;2019:7419708. DOI: 10.1155/2019/7419708.

________________________
© The Author(s). 2022 Open Access This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (https://creativecommons.org/licenses/by-nc/4.0/), which permits unrestricted use, distribution, and non-commercial reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available in this article, unless otherwise stated.