Dataset Information

Systematic Evaluation of Research Progress on Natural Language Processing in Medicine Over the Past 20 Years: Bibliometric Study on PubMed.

ABSTRACT: BACKGROUND:Natural language processing (NLP) is an important traditional field in computer science, but its application in medical research has faced many challenges. With the extensive digitalization of medical information globally and increasing importance of understanding and mining big data in the medical field, NLP is becoming more crucial. OBJECTIVE:The goal of the research was to perform a systematic review on the use of NLP in medical research with the aim of understanding the global progress on NLP research outcomes, content, methods, and study groups involved. METHODS:A systematic review was conducted using the PubMed database as a search platform. All published studies on the application of NLP in medicine (except biomedicine) during the 20 years between 1999 and 2018 were retrieved. The data obtained from these published studies were cleaned and structured. Excel (Microsoft Corp) and VOSviewer (Nees Jan van Eck and Ludo Waltman) were used to perform bibliometric analysis of publication trends, author orders, countries, institutions, collaboration relationships, research hot spots, diseases studied, and research methods. RESULTS:A total of 3498 articles were obtained during initial screening, and 2336 articles were found to meet the study criteria after manual screening. The number of publications increased every year, with a significant growth after 2012 (number of publications ranged from 148 to a maximum of 302 annually). The United States has occupied the leading position since the inception of the field, with the largest number of articles published. The United States contributed to 63.01% (1472/2336) of all publications, followed by France (5.44%, 127/2336) and the United Kingdom (3.51%, 82/2336). The author with the largest number of articles published was Hongfang Liu (70), while Stéphane Meystre (17) and Hua Xu (33) published the largest number of articles as the first and corresponding authors. Among the first author's affiliation institution, Columbia University published the largest number of articles, accounting for 4.54% (106/2336) of the total. Specifically, approximately one-fifth (17.68%, 413/2336) of the articles involved research on specific diseases, and the subject areas primarily focused on mental illness (16.46%, 68/413), breast cancer (5.81%, 24/413), and pneumonia (4.12%, 17/413). CONCLUSIONS:NLP is in a period of robust development in the medical field, with an average of approximately 100 publications annually. Electronic medical records were the most used research materials, but social media such as Twitter have become important research materials since 2015. Cancer (24.94%, 103/413) was the most common subject area in NLP-assisted medical research on diseases, with breast cancers (23.30%, 24/103) and lung cancers (14.56%, 15/103) accounting for the highest proportions of studies. Columbia University and the talents trained therein were the most active and prolific research forces on NLP in the medical field.

SUBMITTER: Wang J

PROVIDER: S-EPMC7005695 | biostudies-literature | 2020 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Systematic Evaluation of Research Progress on Natural Language Processing in Medicine Over the Past 20 Years: Bibliometric Study on PubMed.

Wang Jing J Deng Huan H Liu Bangtao B Hu Anbin A Liang Jun J Fan Lingye L Zheng Xu X Wang Tong T Lei Jianbo J

Journal of medical Internet research 20200123 1

<h4>Background</h4>Natural language processing (NLP) is an important traditional field in computer science, but its application in medical research has faced many challenges. With the extensive digitalization of medical information globally and increasing importance of understanding and mining big data in the medical field, NLP is becoming more crucial.<h4>Objective</h4>The goal of the research was to perform a systematic review on the use of NLP in medical research with the aim of understanding ...[more]

PMID: 32012074

Similar Datasets

Project description:Introduction Research on hepatocellular carcinoma (HCC) has grown significantly, and researchers cannot access the vast amount of literature. This study aimed to explore the research progress in studying HCC over the past 30 years using a machine learning-based bibliometric analysis and to suggest future research directions. Methods Comprehensive research was conducted between 1991 and 2020 in the public version of the PubMed database using the MeSH term “hepatocellular carcinoma.” The complete records of the collected results were downloaded in Extensible Markup Language format, and the metadata of each publication, such as the publication year, the type of research, the corresponding author’s country, the title, the abstract, and the MeSH terms, were analyzed. We adopted a latent Dirichlet allocation topic modeling method on the Python platform to analyze the research topics of the scientific publications. Results In the last 30 years, there has been significant and constant growth in the annual publications about HCC (annual percentage growth rate: 7.34%). Overall, 62,856 articles related to HCC from the past 30 years were searched and finally included in this study. Among the diagnosis-related terms, “Liver Cirrhosis” was the most studied. However, in the 2010s, “Biomarkers, Tumor” began to outpace “Liver Cirrhosis.” Regarding the treatment-related MeSH terms, “Hepatectomy” was the most studied; however, recent studies related to “Antineoplastic Agents” showed a tendency to supersede hepatectomy. Regarding basic research, the study of “Cell Lines, Tumors,’’ appeared after 2000 and has been the most studied among these terms. Conclusion This was the first machine learning-based bibliometric study to analyze more than 60,000 publications about HCC over the past 30 years. Despite significant efforts in analyzing the literature on basic research, its connection with the clinical field is still lacking. Therefore, more efforts are needed to convert and apply basic research results to clinical treatment. Additionally, it was found that microRNAs have potential as diagnostic and therapeutic targets for HCC.

Project description:BackgroundEthiopia has set the ambitious national targets of eliminating soil-transmitted helminths (STH) and schistosomiasis (SCH) as public health problems by 2020, and breaking their transmission by 2025. This systematic review was performed to provide insight into the progress made by the national STH and SCH control programme purposed with reaching these targets.MethodsStudies published on STH and SCH in Ethiopia were searched for using Web of Science, PubMed, Scopus, and the resulting references of selected studies. Prevalence and intensity were analysed, stratified by region, age, and diagnostics.ResultsA total of 231 papers published between 2000 and 2020 were included. Over the past two decades, Trichuris trichiura (TT) infection has shown the most statistically significant decrease (93%, p < 0.0001), followed by Schistosoma mansoni (SM) (69%, p < 0.0001), Ascaris lumbricoides (AL) (67%, p < 0.0001) and Schistosoma haematobium (83%, p = 0.038) infections. Geographically, parasite burden has only consistently shown a significant reduction in the Southern Nations, Nationalities and Peoples' Region of Ethiopia, where AL, TT, hookworm and SM significantly decreased by 80% (p = 0.006), 95% (p = 0.005), 98% (p = 0.009) and 87% (p = 0.031), respectively. Prevalence of STH was highest among adults across all species, contrary to typical age-infection profiles for TT and AL that peak among school-aged children. Expanding treatment to the whole community would target reservoirs of adult and preschool-aged infection within the community, assisting Ethiopia in reaching their national transmission break targets. There was substantial heterogeneity in diagnostic methods used across studies, the majority of which predominantly used single-slide Kato-Katz. This low slide frequency provides poor diagnostic sensitivity, particularly in low endemic settings.ConclusionThe prevalence of STH and SCH in Ethiopia has decreased over time due to the strategic use of anthelmintics. Both standardising and increasing the sensitivity of the diagnostics used, alongside the ubiquitous use of parasite intensity with prevalence, would enable a more accurate and comparable understanding of Ethiopia's epidemiological progress. Further work is needed on community-wide surveillance in order to understand the burden and subsequent need for treatment among those outside of the standard school-based control program.

Project description:Background: Despite a 2010 Kenyan constitutional amendment limiting members of elected public bodies to < two-thirds of the same gender, only 22 percent of the 12th Parliament members inaugurated in 2017 were women. Investigating gender bias in the media is a useful tool for understanding socio-cultural barriers to implementing legislation for gender equality. Natural language processing (NLP) methods, such as word embedding and sentiment analysis, can efficiently quantify media biases at a scope previously unavailable in the social sciences. Methods: We trained GloVe and word2vec word embeddings on text from 1998 to 2019 from Kenya's Daily Nation newspaper. We measured gender bias in these embeddings and used sentiment analysis to predict quantitative sentiment scores for sentences surrounding female leader names compared to male leader names. Results: Bias in leadership words for men and women measured from Daily Nation word embeddings corresponded to temporal trends in men and women's participation in political leadership (i.e., parliamentary seats) using GloVe (correlation 0.8936, p = 0.0067, r 2 = 0.799) and word2vec (correlation 0.844, p = 0.0169, r 2 = 0.712) algorithms. Women continue to be associated with domestic terms while men continue to be associated with influence terms, for both regular gender words and female and male political leaders' names. Male words (e.g., he, him, man) were mentioned 1.84 million more times than female words from 1998 to 2019. Sentiment analysis showed an increase in relative negative sentiment associated with female leaders (p = 0.0152) and an increase in positive sentiment associated with male leaders over time (p = 0.0216). Conclusion: Natural language processing is a powerful method for gaining insights into and quantifying trends in gender biases and sentiment in news media. We found evidence of improvement in gender equality but also a backlash from increased female representation in high-level governmental leadership.

Project description:BackgroundHypothalamic hamartoma (HH) is a rare intracranial disease whose manifestations include gelastic seizures and precocious puberty. The diagnosis and treatment of HH have changed substantially over the past three decades as medical care has improved. Bibliometrics can reveal the evolution and development of a scientific field.MethodsDocuments on HH were retrieved from the Web of Science Core Collection (WoSCC) database on September 8, 2022. The search terms were as follows: "hypothalamic hamartoma" or "hamartoma of the hypothalamus" or "hypothalamic hamartomas." The types of documents were restricted to articles, case reports, and reviews. VOSviewer, CiteSpace, and the R package "bibliometrix" were used for a bibliometric analysis.ResultsA total of 667 independent documents on HH were obtained from the WoSCC database. The most common types of documents were articles (n = 498, 75%) and reviews (n = 103, 15%). The number of annual publications fluctuated but showed an upward trend overall, and the annual growth rate was 6.85%. The cumulative publication data indicated that the most influential journals in the HH field include Epilepsia, Epileptic Disorders, Child's Nervous System, Neurosurgery, and the Journal of Neurosurgery. Kerrigan JF, Ng YT, Rekate HL, Regis J, and Kameyama S were among the most prominent authors in the field of HH, with numerous publications and citations. American research institutions, especially the Barrow Neurological Institute, occupied a pivotal position in HH research. Other countries and institutions were catching up and producing considerable research results. Research on HH has steadily switched its emphasis from Pallister-Hall syndrome (PHS) and precocious puberty to epilepsy and new diagnostic and therapeutic techniques, including Gamma Knife, laser ablation, and interstitial thermal therapy.ConclusionHH remains a special neurological disease with significant research prospects. The development of novel technologies, including MRI-guided laser-induced thermal therapy (MRg-LiTT) and stereotactic radiofrequency thermocoagulation (RF-TC), has enabled the efficient treatment of gelastic seizures in HH while minimizing the risks associated with craniotomies. Through bibliometric analysis, this study points out the direction for future HH research.

Project description:ObjectiveAcupuncture has become popular and widely practiced in many countries around the world. Despite the large amount of acupuncture-related literature that has been published, broader trends in the prevalence and scope of acupuncture research remain underexplored. The current study quantitatively analyzes trends in acupuncture research publications in the past 20 years.MethodsA bibliometric approach was used to search PubMed for all acupuncture-related research articles including clinical and animal studies. Inclusion criteria were articles published between 1995 and 2014 with sufficient information for bibliometric analyses. Rates and patterns of acupuncture publication within the 20 year observational period were estimated, and compared with broader publication rates in biomedicine. Identified eligible publications were further analyzed with respect to study type/design, clinical condition addressed, country of origin, and journal impact factor.ResultsA total of 13,320 acupuncture-related publications were identified using our search strategy and eligibility criteria. Regression analyses indicated an exponential growth in publications over the past two decades, with a mean annual growth rate of 10.7%. This compares to a mean annual growth rate of 4.5% in biomedicine. A striking trend was an observed increase in the proportion of randomized clinical trials (RCTs), from 7.4% in 1995 to 20.3% in 2014, exceeding the 4.5% proportional growth of RCTs in biomedicine. Over the 20 year period, pain was consistently the most common focus of acupuncture research (37.9% of publications). Other top rankings with respect to medical focus were arthritis, neoplasms/cancer, pregnancy or labor, mood disorders, stroke, nausea/vomiting, sleep, and paralysis/palsy. Acupuncture research was conducted in 60 countries, with the top 3 contributors being China (47.4%), United States (17.5%), and United Kingdom (8.2%). Retrieved articles were published mostly in complementary and alternative medicine (CAM) journals with impact factors ranging between 0.7 and 2.8 in the top 20 journals, followed by journals specializing in neuroscience, pain, anesthesia/analgesia, internal medicine and comprehensive fields.ConclusionAcupuncture research has grown markedly in the past two decades, with a 2-fold higher growth rate than for biomedical research overall. Both the increases in the proportion of RCTs and the impact factor of journals support that the quality of published research has improved. While pain was a consistently dominant research focus, other topics gained more attention during this time period. These findings provide a context for analyzing strengths and gaps in the current state of acupuncture research, and for informing a comprehensive strategy for further advancing the field.

Dataset Information

Systematic Evaluation of Research Progress on Natural Language Processing in Medicine Over the Past 20 Years: Bibliometric Study on PubMed.

Publications

Systematic Evaluation of Research Progress on Natural Language Processing in Medicine Over the Past 20 Years: Bibliometric Study on PubMed.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets