Thematic analysis of articles on artificial intelligence with spine trauma, vertebral metastasis, and osteoporosis using chord diagrams: A systematic review and meta-analysis

Abstract

Background: Spine trauma, vertebral metastases, and osteoporosis (SVO) can result in serious health problems. If the diagnosis of SVO is delayed, the prognosis may be deteriorated. The use of artificial intelligence (AI) is an essential method for minimizing the diagnostic errors associated with SVO. research achievements (RAs) of SVO on AI are required as a result of the greatest number of studies on AI solutions reported. The study aimed to: classify article themes using visualizations, illustrate the characteristics of SVO on AI recently, compare RAs of SVO on AI between entities (e.g., countries, institutes, departments, and authors), and determine whether the mean citations of keywords can be used to predict article citations. Methods: A total of 31 articles from SVO on AI (denoted by T31SVOAI) have been found in Web of Science since 2018. The dominant entities were analyzed using the CJAL score and the Y-index. Five visualizations were applied to report: the themes of T31SVOAI and their RAs in comparison for article entities and verification of the hypothesis that the mean citations of keywords can predict article citations, including: network diagrams, chord diagrams, dot plots, a Kano diagram, and radar plots. Results: There were five themes classified (osteoporosis, personalized medicine, fracture, deformity, and cervical spine) by a chord diagram. The dominant entities with the highest CJAL scores were the United States (22.05), the University of Pennsylvania (5.72), Radiology (6.12), and Nithin Kolanu (Australia) (9.88). The majority of articles were published in Bone, J. Bone Miner. Res., and Arch. Osteoporos., with an equal count (=3). There was a significant correlation between the number of article citations and the number of weighted keywords ( F = 392.05; P < .0001). Conclusion: A breakthrough was achieved by displaying the characteristics of T31SVOAI using the CJAL score, the Y-index, and the chord diagram. Weighted keywords can be used to predict article citations. The five visualizations employed in this study may be used in future bibliographical studies.

The model of descriptive, diagnostic, predictive, and prescriptive analytics on 100 top-cited articles of nasopharyngeal carcinoma from 2013 to 2022: Bibliometric analysis

“…In T100NPC, 6 themes were identified using coword analysis, as shown in Figure 3 , including Epstein–Barr virus (EBV), gene expression, whole genome, RNA-guided endonuclease, serum, and chronic lymphocytic leukemia as chief keywords in each cluster. Figure 4 shows a chord diagram [ 39 , 40 ] to present the relationship between themes and articles (in top panel) and counties (in bottom panel). The chord diagram enables us to understand the relationship between themes (or countries) through color-coded curves.…”

“…There are, however, no such methods for assigning themes to articles using Equations 4 and 5. [ 40 , 43 ] Human classification of themes assigned to articles [ 77 ] is a laborious and time-consuming process.…”

“…Three visual representations were used to display the relationship between variables using diagnostic analytics, including a network chart, [ 37 , 38 ] a chord diagram, [ 39 , 40 ] and a Sankey diagram. [ 14 , 41 , 42 ]…”

A leading bibliometric author does not have a dominant contribution to research based on the CJAL score: Bibliometric analysis

“…A chord diagram [ 29 , 51 ] was used to visualize dynamics related to contraceptive use and to bring data into practice. The dashboards (e.g., in Fig.…”

“…Supplemental Digital Content2, http://links.lww.com/MD/I278 provides the R code for reproducing the chord diagram. In addition, chord diagrams [29,51] could be used by network diagrams to clearly illustrate their network relationships, with more effective representations than the traditional displays using the network chart, as illustrated at the top of Figure 2.…”