PDF(Pubmed)
Abstract：
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.
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.
摘要：
背景：摘要综述是医学系统和范围界定文献综述中的一个耗时且费力的步骤。文本挖掘方法,通常是自然语言处理(NLP)，可以有效地取代手动抽象筛选。本研究将NLP应用于一个刻意选择的文献综述问题，在医学研究中使用NLP的趋势，来演示这种自动抽象评论模型的性能。
方法：扫描PubMed，Embase,PsycINFO,和CINAHL数据库，我们确定了22,294,最终选择了2000年至2021年之间发表的12,817份英文摘要.我们发明了医学领域的手动分类，三个变量，即，使用上下文(COU)，文本源(TS)，和主要研究领域(PRF)。在审查了485篇摘要后，开发了一个训练数据集。我们使用了一种称为“来自变形金刚的双向编码器表示”的语言模型来对摘要进行分类。要评估训练模型的性能，我们报告微f1评分和准确性。
结果：用于分类摘要的训练模型\'microf1-score，分为三个变量，COU为77.35%，TS为76.24%，PRF为85.64%。在2000年至2020年之间，出版物的平均年增长率（AAGR）为20.99％（每年增加72.01篇（95％CI：56.80-78.30）），81.76%的摘要在2010年至2020年之间发表。对肿瘤的研究占整个语料库的27.66％，AAGR为42.41％，其次是关于精神状况的研究(AAGR=39.28%)。虽然电子健康或医疗记录占文本来源的比例最高(57.12%)，在所有文本来源中,组学数据库的增长率最高,AAGR为65.08%.最常见的NLP应用是临床决策支持（25.45%）。
结论：BioBERT在摘要综述中显示出可接受的表现。如果未来的研究表明这种语言模型的高性能，它可以可靠地替代手动摘要评论。
方法：扫描PubMed，Embase,PsycINFO,和CINAHL数据库，我们确定了22,294,最终选择了2000年至2021年之间发表的12,817份英文摘要.我们发明了医学领域的手动分类，三个变量，即，使用上下文(COU)，文本源(TS)，和主要研究领域(PRF)。在审查了485篇摘要后，开发了一个训练数据集。我们使用了一种称为“来自变形金刚的双向编码器表示”的语言模型来对摘要进行分类。要评估训练模型的性能，我们报告微f1评分和准确性。
结果：用于分类摘要的训练模型\'microf1-score，分为三个变量，COU为77.35%，TS为76.24%，PRF为85.64%。在2000年至2020年之间，出版物的平均年增长率（AAGR）为20.99％（每年增加72.01篇（95％CI：56.80-78.30）），81.76%的摘要在2010年至2020年之间发表。对肿瘤的研究占整个语料库的27.66％，AAGR为42.41％，其次是关于精神状况的研究(AAGR=39.28%)。虽然电子健康或医疗记录占文本来源的比例最高(57.12%)，在所有文本来源中,组学数据库的增长率最高,AAGR为65.08%.最常见的NLP应用是临床决策支持（25.45%）。
结论：BioBERT在摘要综述中显示出可接受的表现。如果未来的研究表明这种语言模型的高性能，它可以可靠地替代手动摘要评论。
