Natural language processing (NLP) to facilitate abstract review in medical research: the application of BioBERT to exploring the 20-year use of NLP in medical research.

BACKGROUND: Abstract review is a time and labor-consuming step in the systematic and scoping literature review in medicine. Text mining methods, typically natural language processing (NLP), may efficiently replace manual abstract screening. This study applies NLP to a deliberately selected literature review problem, the trend of using NLP in medical research, to demonstrate the performance of this automated abstract review model. METHODS: Scanning PubMed, Embase, PsycINFO, and CINAHL databases, we identified 22,294 with a final selection of 12,817 English abstracts published between 2000 and 2021. We invented a manual classification of medical fields, three variables, i.e., the context of use (COU), text source (TS), and primary research field (PRF). A training dataset was developed after reviewing 485 abstracts. We used a language model called Bidirectional Encoder Representations from Transformers to classify the abstracts. To evaluate the performance of the trained models, we report a micro f1-score and accuracy. RESULTS: The trained models' micro f1-score for classifying abstracts, into three variables were 77.35% for COU, 76.24% for TS, and 85.64% for PRF. The average annual growth rate (AAGR) of the publications was 20.99% between 2000 and 2020 (72.01 articles (95% CI: 56.80-78.30) yearly increase), with 81.76% of the abstracts published between 2010 and 2020. Studies on neoplasms constituted 27.66% of the entire corpus with an AAGR of 42.41%, followed by studies on mental conditions (AAGR = 39.28%). While electronic health or medical records comprised the highest proportion of text sources (57.12%), omics databases had the highest growth among all text sources with an AAGR of 65.08%. The most common NLP application was clinical decision support (25.45%). CONCLUSIONS: BioBERT showed an acceptable performance in the abstract review. If future research shows the high performance of this language model, it can reliably replace manual abstract reviews.

Exposure to Low Levels of Radiofrequency Electromagnetic Fields Emitted from Cell-phones as a Promising Treatment of Alzheimer's Disease: A Scoping Review Study.

Background: Alzheimer's disease (AD) is one of the most significant public health concerns and tremendous economic challenges. Studies conducted over the past decades show that exposure to radiofrequency electromagnetic fields (RF-EMFs) may relieve AD symptoms. Objective: To determine if exposure to RF-EMFs emitted by cellphones affect the risk of AD. Material and Methods: In this review, all relevant published articles reporting an association of cell phone use with AD were studied. We systematically searched international datasets to identify relevant studies. Finally, 33 studies were included in the review. Our review discusses the effects of RF-EMFs on the amyloid ß (Aß), oxidative stress, apoptosis, reactive oxygen species (ROS), neuronal death, and astrocyte responses. Moreover, the role of exposure parameters, including the type of exposure, its duration, and specific absorption rate (SAR), are discussed. Results: Progressive factors of AD such as Aß, myelin basic protein (MBP), nicotinamide adenine dinucleotide phosphate (NADPH) oxidase, and neurofilament light polypeptide (NFL) were decreased. While tau protein showed no change, factors affecting brain activity such as glial fibrillary acidic protein (GFAP), mitogen-activated protein kinases (MAPKs), cerebral blood flow (CBF), brain temperature, and neuronal activity were increased. Conclusion: Exposure to low levels of RF-EMFs can reduce the risk of AD by increasing MAPK and GFAP and decreasing MBP. Considering the role of apoptosis in AD and the effect of RF-EMF on the progression of the process, this review indicates the positive effect of these exposures.

Is There Any Relationship between Trichomonas vaginalis Infection and Male Urethritis Risk? A Systematic Review and Meta-Analysis.

Background: Male urethritis is one of the most common genital tract syndromes. Though the number of patients with urethritis is increasing worldwide, the cause of many cases of non-gonococcal urethritis (NGU) is still unknown. Objectives: This study aimed to delineate the association between Trichomonas vaginalis (T. vaginalis) infection and male urethritis. Methods: The literature was searched in PubMed, Scopus, and Web of Science databases using the search terms "urethritis," "Trichomonas vaginalis," "trichomoniasis," and "male urethritis" up to February 2020. Overall risk difference(RD) was applied to assess the relationship between T. vaginalis infection and male urethritis. Results: In total, seven articles were included in this systematic review and meta-analysis study. Our meta-analysis involved the review of case-control studies, including 2,242 urethritis cases and 929 individuals as controls. Among subjects examined for trichomoniasis, in the case group, 211 males were infected, and in the control group, 32 individuals were infected. The overall risk difference (RD) was 0.06, and the total reported p value was 0.00001. Although the result of our meta-analysis was not significant, it was shown that the risk of urethritis is 0.06 more in trichomoniasis patients than in the non-exposed group. Conclusion: Findings from the included papers showed that trichomoniasis is not a risk factor for male urethritis. Although trichomoniasis alone is not the main cause of urethritis, it can be considered one of the risk factors in male urethritis. Therefore, in the future, it is necessary to perform further studies to clarify the detailed association between T. vaginalis infection and urethritis risk in male patients.