Forty years of emergency medicine research: Uncovering research themes and trends through topic modeling

Exploratory mapping of tumor associated macrophage nanoparticle article abstracts using an eLDA topic modeling machine learning approach

The role of macrophages in regulating the tumor microenvironment has spurned the exponential generation of nanoparticle targeting technologies. With the large amount of literature and the speed at which it is generated it is difficult to remain current with the most up-to-date literature. In this study we performed a topic modeling analysis of 854 abstracts of peer-reviewed literature for the most common usages of nanoparticle targeting of tumor associated macrophages (TAMs) in solid tumors. The data spans 20 years of literature, providing a broad perspective of the nanoparticle strategies. Our topic model found 6 distinct topics: Immune and TAMs, Nanoparticles, Imaging, Gene Delivery and Exosomes, Vaccines, and Multi-modal Therapies. We also found distinct nanoparticle usage, tumor types, and therapeutic trends across these topics. Moreover, we established that the topic model could be used to assign new papers into the existing topics, thereby creating a Living Review. This type of "birds-eye-view" analysis provides a useful assessment tool for exploring new and emerging themes within a large field.

Virtual education strategies in the context of sustainable health care and medical education: A topic modelling analysis of four decades of research

BACKGROUND

The growing importance of sustainability has led to the current literature being saturated with studies on the necessity of, and suggested topics for, education for sustainable health care (ESH). Even so, ESH implementation has been hindered by educator unpreparedness and resource scarcity. A potential resolution lies in virtual education. However, research on the strategies needed for successfully implementing virtual education in the context of sustainable health care and medical education is sparse; this study aims to fill the gap.

METHODS

Topic modelling, a computational text-mining method for analysing recurring patterns of co-occurring word clusters to reveal key topics prevalent across the texts, was used to examine how sustainability was addressed in research in medicine, medical education, and virtual education. A total of 17 631 studies, retrieved from Web of Science, Scopus and PubMed, were analysed.

RESULTS

Sustainability-related topics within health care, medical education and virtual education provided systematic implications for Sustainable Virtual Medical Education (SVME)-ESH via virtual platforms in a sustainable way. Analyses of keywords, phrases, topics and their associated networks indicate that SVME should address the three pillars of environmental, social and economic sustainability and medical practices to uphold them; employ different technologies and methods including simulations, virtual reality (VR), artificial intelligence (AI), cloud computing, distance learning; and implement strategies for collaborative development, persuasive diffusion and quality assurance.

CONCLUSIONS

This research suggests that sustainable strategies in virtual education for ESH require a systems approach, encompassing components such as learning content and objectives, evaluation, targeted learners, media, methods and strategies. The advancement of SVME necessitates that medical educators and researchers play a central and bridging role, guiding both the fields of sustainable health care and medical education in the development and implementation of SVME. In this way, they can prepare future physicians to address sustainability issues that impact patient care.

Artificial intelligence in emergency medicine. A systematic literature review

Motivation and objective: Emergency medicine is becoming a popular application area for artificial intelligence methods but remains less investigated than other healthcare branches. The need for time-sensitive decision-making on the basis of high data volumes makes the use of quantitative technologies inevitable. However, the specifics of healthcare regulations impose strict requirements for such applications. Published contributions cover separate parts of emergency medicine and use disparate data and algorithms. This study aims to systematize the relevant contributions, investigate the main obstacles to artificial intelligence applications in emergency medicine, and propose directions for further studies.

METHODS

The contributions selection process was conducted with systematic electronic databases querying and filtering with respect to established exclusion criteria. Among the 380 papers gathered from IEEE Xplore, ACM Digital Library, Springer Library, ScienceDirect, and Nature databases 116 were considered to be a part of the survey. The main features of the selected papers are the focus on emergency medicine and the use of machine learning or deep learning algorithms.

FINDINGS AND DISCUSSION

The selected papers were classified into two branches: diagnostics-specific and triage-specific. The former ones are focused on either diagnosis prediction or decision support. The latter covers such applications as mortality, outcome, admission prediction, condition severity estimation, and urgent care prediction. The observed contributions are highly specialized within a single disease or medical operation and often use privately collected retrospective data, making them incomparable. These and other issues can be addressed by creating an end-to-end solution based on human-machine interaction.

CONCLUSION

Artificial intelligence applications are finding their place in emergency medicine, while most of the corresponding studies remain isolated and lack higher generalization and more sophisticated methodology, which can be a matter of forthcoming improvements.

Meta-analysis of macrophage nanoparticle targeting across blood and solid tumors using an eLDA Topic modeling Machine Learning approach

The role of macrophages in regulating the tumor microenvironment has spurned the exponential generation of nanoparticle targeting technologies. With the large amount of literature and the speed at which it is generated it is difficult to remain current with the most up-to-date literature. In this study we performed a topic modeling analysis of the most common usages of nanoparticle targeting of macrophages in solid tumors. The data spans 20 years of literature, providing an extensive meta-analysis of the nanoparticle strategies. Our topic model found 6 distinct topics: Immune and TAMs, Nanoparticles, Imaging, Gene Delivery and Exosomes, Vaccines, and Multi-modal Therapies. We also found distinct nanoparticle usage, tumor types, and therapeutic trends across these topics. Moreover, we established that the topic model could be used to assign new papers into the existing topics, thereby creating a Living Review. This type of meta-analysis provides a useful assessment tool for aggregating data about a large field.

Eliciting Insights From Chat Logs of the 25X5 Symposium to Reduce Documentation Burden: Novel Application of Topic Modeling

BACKGROUND

Addressing clinician documentation burden through "targeted solutions" is a growing priority for many organizations ranging from government and academia to industry. Between January and February 2021, the 25 by 5: Symposium to Reduce Documentation Burden on US Clinicians by 75% (25X5 Symposium) convened across 2 weekly 2-hour sessions among experts and stakeholders to generate actionable goals for reducing clinician documentation over the next 5 years. Throughout this web-based symposium, we passively collected attendees' contributions to a chat functionality-with their knowledge that the content would be deidentified and made publicly available. This presented a novel opportunity to synthesize and understand participants' perceptions and interests from chat messages. We performed a content analysis of 25X5 Symposium chat logs to identify themes about reducing clinician documentation burden.

OBJECTIVE

The objective of this study was to explore unstructured chat log content from the web-based 25X5 Symposium to elicit latent insights on clinician documentation burden among clinicians, health care leaders, and other stakeholders using topic modeling.

METHODS

Across the 6 sessions, we captured 1787 messages among 167 unique chat participants cumulatively; 14 were private messages not included in the analysis. We implemented a latent Dirichlet allocation (LDA) topic model on the aggregated dataset to identify clinician documentation burden topics mentioned in the chat logs. Coherence scores and manual examination informed optimal model selection. Next, 5 domain experts independently and qualitatively assigned descriptive labels to model-identified topics and classified them into higher-level categories, which were finalized through a panel consensus.

RESULTS

We uncovered ten topics using the LDA model: (1) determining data and documentation needs (422/1773, 23.8%); (2) collectively reassessing documentation requirements in electronic health records (EHRs) (252/1773, 14.2%); (3) focusing documentation on patient narrative (162/1773, 9.1%); (4) documentation that adds value (147/1773, 8.3%); (5) regulatory impact on clinician burden (142/1773, 8%); (6) improved EHR user interface and design (128/1773, 7.2%); (7) addressing poor usability (122/1773, 6.9%); (8) sharing 25X5 Symposium resources (122/1773, 6.9%); (9) capturing data related to clinician practice (113/1773, 6.4%); and (10) the role of quality measures and technology in burnout (110/1773, 6.2%). Among these 10 topics, 5 high-level categories emerged: consensus building (821/1773, 46.3%), burden sources (365/1773, 20.6%), EHR design (250/1773, 14.1%), patient-centered care (162/1773, 9.1%), and symposium comments (122/1773, 6.9%).

CONCLUSIONS

We conducted a topic modeling analysis on 25X5 Symposium multiparticipant chat logs to explore the feasibility of this novel application and elicit additional insights on clinician documentation burden among attendees. Based on the results of our LDA analysis, consensus building, burden sources, EHR design, and patient-centered care may be important themes to consider when addressing clinician documentation burden. Our findings demonstrate the value of topic modeling in discovering topics associated with clinician documentation burden using unstructured textual content. Topic modeling may be a suitable approach to examine latent themes presented in web-based symposium chat logs.

Research trends of sustainability and marketing research, 2010-2020: Topic modeling analysis

In recent decades, rapid growth has been observed in the incorporation of sustainability into marketing. Accordingly, the contrasting relationships between them have been carefully studied to assess the relevance of one idea to the other and vice versa. In response to this change, scholars and practitioners have been tasked with exploring the trends in sustainability and marketing. Therefore, the purpose of this study is to investigate existing literatures on both sustainability and all levels of marketing, determine the research trends and provide implications of applying the trends for future research and practices. This research has investigated only the title, abstract, and keywords of 2147 articles that were published between 2010 and 2020 in SSCI or SCIE indexed journals by applying the topic modeling based on the Latent Dirichlet Allocation (LDA) model. The results show that the research trend has shifted from general sustainable concept to more environmental and industrial technology based on the empirical evidence of 14 latent topics of sustainability and marketing. This article aids in understanding the recent research trend in sustainability and marketing, and the findings will be a valuable resource for future scholars and practitioners. It contributes to both existing and future literatures by providing valuable insights from recent research trend in sustainability and marketing and by providing recommendations for future research avenue. Among other bibliometric review articles, this is the most up-to-date comprehensive and empirical article, providing overview of the research trend.

Trends in major intensive care medicine journals: A machine learning approach

PURPOSE

Intensive care medicine (ICM) has the particularity of being a multidisciplinary specialty and its literature reflects this multidisciplinarity. However, the proportion of each field in this literature and its trend dynamics are not known. The objective of this study was to analyze the ICM literature, extract latent topics and search for the presence of research trends.

MATERIAL AND METHODS

Abstracts of original articles from the top ICM journals, from their inception until December 31st, 2019, were included. This corpus was fed into a structural topic modeling algorithm to extract latent semantic topics. The temporal distribution was then analyzed and the presence of trends was searched by Mann-Kendall trends tests.

RESULTS

Finally, 49,276 articles from 10 journals were included. After topic modeling analysis and experts' feedback, 124 research topics were selected and labeled. Topics were categorized into 19 categories, the most represented being respiratory, fundamental and neurological research. Increasing trends were observed for research on mechanical ventilation and decreasing trends for cardiopulmonary resuscitation.

CONCLUSIONS

This study reviewed all articles from major ICM journals in a comprehensive way. It provides a better understanding of ICM research landscape by analyzing the temporal evolution of latent research topics in the ICM literature.

Changes in scientific characteristics of abstracts accepted to the Society for Academic Emergency Medicine Annual Meeting, 1990-2020

OBJECTIVES

Since its founding in 1989, the Society for Academic Emergency Medicine (SAEM) has accepted thousands of abstracts for presentation at its annual meeting. We reviewed abstracts to characterize temporal changes in study design, abstract topics, quality scores, and proportion of abstracts published as manuscripts.

METHODS

In this serial cross-sectional study, we compiled accepted SAEM abstracts at 5-year intervals (1990, 1995, 2000, 2005, 2010, 2015, 2020) and then randomly selected 100 abstracts from each year for review by two investigators. We documented each abstract's study design, sample size, and whether it was a single-center or multicenter study. We assigned each abstract to the most appropriate topic category. Applying SAEM's abstract scoring system from 2020, we calculated the mean overall quality score per year. Finally, we searched PubMed to determine if abstracts from 1990-2015 meetings were published as manuscripts.

RESULTS

The number of accepted abstracts increased from 180 in 1990 to 879 in 2020 (+388%). The most common study design changed from laboratory study in 1990 (22%) to cohort study in 2020 (44%; p < 0.001). The median study sample size increased over time, from 105 (interquartile range [IQR] 25-389) in 1990 to 544 (IQR 102-2067) in 2020 (p < 0.001). Multicenter studies have become more common (19% in 1990 vs. 40% in 2020; p = 0.001). The most common topic categories also changed from cardiology/pulmonary/airway (40%) and orthopedic/trauma/burn (17%) in 1990 to health services research/health policy/operations (25%) and cardiology/pulmonary/airway (22%) in 2020. There was a 20% increase in overall quality scores (p < 0.001). Between 37% and 49% of the abstracts reviewed from each year were later published as manuscripts, with no significant change over time (p = 0.33).

CONCLUSIONS

Over the past 30 years, there have been significant changes to the study designs, topics, and quality scores of SAEM meeting abstracts. However, conversion of abstracts to published manuscripts remains a challenge.

Scopus 1900–2020: Growth in articles, abstracts, countries, fields, and journals

Scientometric research often relies on large-scale bibliometric databases of academic journal articles. Long term and longitudinal research can be affected if the composition of a database varies over time, and text processing research can be affected if the percentage of articles with abstracts changes. This article therefore assesses changes in the magnitude of the coverage of a major citation index, Scopus, over 121 years from 1900. The results show sustained exponential growth from 1900, except for dips during both world wars, and with increased growth after 2004. Over the same period, the percentage of articles with 500+ character abstracts increased from 1% to 95%. The number of different journals in Scopus also increased exponentially, but slowing down from 2010, with the number of articles per journal being approximately constant until 1980, then tripling due to megajournals and online-only publishing. The breadth of Scopus, in terms of the number of narrow fields with substantial numbers of articles, simultaneously increased from one field having 1000 articles in 1945 to 308 in 2020. Scopus’s international character also radically changed from 68% of first authors from Germany and the USA in 1900 to just 17% in 2020, with China dominating (25%).

Peer Review

https://publons.com/publon/10.1162/qss_a_00177