☆ 4.7 Article

A Deep Learning Method to Automatically Identify Reports of Scientifically Rigorous Clinical Research from the Biomedical Literature: Comparative Analytic Study

JOURNAL OF MEDICAL INTERNET RESEARCH (2018)

期刊

JOURNAL OF MEDICAL INTERNET RESEARCH

卷 20, 期 6, 页码 -

出版社

JMIR PUBLICATIONS, INC

DOI: 10.2196/10281

关键词

information retrieval; evidence-based medicine; deep learning; machine learning; literature databases

类别

Health Care Sciences & Services Medical Informatics

资金

National Library of Medicine grant [1R01LM011416]
National Cancer Institute [1U24CA204800]
Defense Advanced Research Projects Agency (DARPA) Program Office [W31P4Q-17-C-0103]
InferLink Corporation
US National Library of Medicine
Canadian Institutes of Health Research
NATIONAL CANCER INSTITUTE [U24CA204800] Funding Source: NIH RePORTER
NATIONAL LIBRARY OF MEDICINE [R01LM011416] Funding Source: NIH RePORTER

向作者/读者索取更多资源

Protocol

社区支持

Reagent

社区支持

摘要

Background: A major barrier to the practice of evidence-based medicine is efficiently finding scientifically sound studies on a given clinical topic. Objective: To investigate a deep learning approach to retrieve scientifically sound treatment studies from the biomedical literature. Methods: We trained a Convolutional Neural Network using a noisy dataset of 403,216 PubMed citations with title and abstract as features. The deep learning model was compared with state-of-the-art search filters, such as PubMed's Clinical Query Broad treatment filter, McMaster's textword search strategy (no Medical Subject Heading, MeSH, terms), and Clinical Query Balanced treatment filter. A previously annotated dataset (Clinical Hedges) was used as the gold standard Results: The deep learning model obtained significantly lower recall than the Clinical Queries Broad treatment filter (96.9% vs 98.4%; P<.001); and equivalent recall to McMaster's textword search (96.9% vs 97.1%; P=.57) and Clinical Queries Balanced filter (96.9% vs 97.0%; P=.63). Deep learning obtained significantly higher precision than the Clinical Queries Broad filter (34.6% vs 22.4%; P<.001) and McMaster's textword search (34.6% vs 11.8%; P<.001), but was significantly lower than the Clinical Queries Balanced filter (34.6% vs 40.9%; P<.001). Conclusions: Deep learning performed well compared to state-of-the-art search filters, especially when citations were not indexed. Unlike previous machine learning approaches, the proposed deep learning model does not require feature engineering, or time-sensitive or proprietary features, such as MeSH terms and bibliometrics. Deep learning is a promising approach to identifying reports of scientifically rigorous clinical research. Further work is needed to optimize the deep learning model and to assess generalizability to other areas, such as diagnosis, etiology, and prognosis.

作者

我是这篇论文的作者

点击您的名字以认领此论文并将其添加到您的个人资料中。

主要评分

4.7

评分不足

次要评分

新颖性

重要性

科学严谨性

评价这篇论文

Machine Learning Approaches to Retrieve High-Quality, Clinically Relevant Evidence From the Biomedical Literature: Systematic Review

Wael Abdelkader, Tamara Navarro, Rick Parrish, Chris Cotoi, Federico Germini, Alfonso Iorio, R. Brian Haynes, Cynthia Lokker

Summary: Machine learning approaches demonstrate good performance in retrieving high-quality clinical studies, achieving high sensitivity and precision levels. The study shows that supervised machine learning methods have been applied with high-quality standards during model training.

JMIR MEDICAL INFORMATICS (2021)