Can co-authorship networks be used to predict author research impact? A machine-learning based analysis within the field of degenerative cervical myelopathy research

Abstract

Introduction Degenerative Cervical Myelopathy (DCM) is a common and disabling condition, with a relatively modest research capacity. In order to accelerate knowledge discovery, the AO Spine RECODE-DCM project has recently established the top priorities for DCM research. Uptake of these priorities within the research community will require their effective dissemination, which can be supported by identifying key opinion leaders (KOLs). In this paper, we aim to identify KOLs using artificial intelligence. We produce and explore a DCM co-authorship network, to characterise researchers’ impact within the research field. Methods Through a bibliometric analysis of 1674 scientific papers in the DCM field, a co-authorship network was created. For each author, statistics about their connections to the co-authorship network (and so the nature of their collaboration) were generated. Using these connectedness statistics, a neural network was used to predict H-Index for each author (as a proxy for research impact). The neural network was retrospectively validated on an unseen author set. Results DCM research is regionally clustered, with strong collaboration across some international borders (e.g., North America) but not others (e.g., Western Europe). In retrospective validation, the neural network achieves a correlation coefficient of 0.86 (p<0.0001) between the true and predicted H-Index of each author. Thus, author impact can be accurately predicted using only the nature of an author’s collaborations. Discussion Analysis of the neural network shows that the nature of collaboration strongly impacts an author’s research visibility, and therefore suitability as a KOL. This also suggests greater collaboration within the DCM field could help to improve both individual research visibility and global synergy.

We Choose to Call it ‘Degenerative Cervical Myelopathy’: Findings of AO Spine RECODE-DCM, an International and Multi-Stakeholder Partnership to Agree a Standard Unifying Term and Definition for a Disease

“…This appears consistent with definitions used for existing conditions and based on the process, suitable for inclusion within ICD. 30 Whilst there were significant strengths to the process, including its global 31 multistakeholder perspective and iterative approach, an important limitation to acknowledge is that the term 'DCM' was used from the outset, for example within the supporting and explanatory information, as well as the project title AO Spine RECODE-DCM, as having a term to identify the condition was unavoidable. The inclusion of contrasting terms, alongside their prominence within voting and discussion, is a reassuring suggestion at least, that this did not confer an unconscious bias.…”

Secondary analysis of a James Lind Alliance priority setting partnership to facilitate knowledge translation in degenerative cervical myelopathy (DCM): insights from AO Spine RECODE-DCM

“…Countries were further categorised as higher-income countries or not, using the World Bank (worldbank.org) classification (22 October 2020). In addition, we and others have identified that DCM research is largely derived from two geographical clusters: North America (Canada and the USA) and East Asia (Japan, Korea and China) 17 18. To explore a relationship between research activity and KT, participants were also defined by whether they reside or practice within a research cluster or not.…”

Analysis of the Evolution of User Emotion and Opinion Leaders’ Information Dissemination Behavior in the Knowledge Q&A Community during COVID-19

“…We identified network opinion leaders through the mutual influence and interaction between users. The H-index, proposed in 2005, was chosen as the most suitable surrogate impact metric [70], which can also be used to describe and assess the magnitude of users' influence in the network and the amount of output [71]. The degree of attention, interaction, and conversation content obtained through user's posting of posts were used as the basis for measuring the influence of the poster [72], which was specifically reflected in the number of likes and comments on the post.…”