PDF(Pubmed)
Abstract：
BACKGROUND: Despite the significance and prevalence of acute respiratory distress syndrome (ARDS), its detection remains highly variable and inconsistent. In this work, we aim to develop an algorithm (ARDSFlag) to automate the diagnosis of ARDS based on the Berlin definition. We also aim to develop a visualization tool that helps clinicians efficiently assess ARDS criteria.
METHODS: ARDSFlag applies machine learning (ML) and natural language processing (NLP) techniques to evaluate Berlin criteria by incorporating structured and unstructured data in an electronic health record (EHR) system. The study cohort includes 19,534 ICU admissions in the Medical Information Mart for Intensive Care III (MIMIC-III) database. The output is the ARDS diagnosis, onset time, and severity.
RESULTS: ARDSFlag includes separate text classifiers trained using large training sets to find evidence of bilateral infiltrates in radiology reports (accuracy of 91.9%±0.5%) and heart failure/fluid overload in radiology reports (accuracy 86.1%±0.5%) and echocardiogram notes (accuracy 98.4%±0.3%). A test set of 300 cases, which was blindly and independently labeled for ARDS by two groups of clinicians, shows that ARDSFlag generates an overall accuracy of 89.0% (specificity = 91.7%, recall = 80.3%, and precision = 75.0%) in detecting ARDS cases.
CONCLUSIONS: To our best knowledge, this is the first study to focus on developing a method to automate the detection of ARDS. Some studies have developed and used other methods to answer other research questions. Expectedly, ARDSFlag generates a significantly higher performance in all accuracy measures compared to those methods.
METHODS: ARDSFlag applies machine learning (ML) and natural language processing (NLP) techniques to evaluate Berlin criteria by incorporating structured and unstructured data in an electronic health record (EHR) system. The study cohort includes 19,534 ICU admissions in the Medical Information Mart for Intensive Care III (MIMIC-III) database. The output is the ARDS diagnosis, onset time, and severity.
RESULTS: ARDSFlag includes separate text classifiers trained using large training sets to find evidence of bilateral infiltrates in radiology reports (accuracy of 91.9%±0.5%) and heart failure/fluid overload in radiology reports (accuracy 86.1%±0.5%) and echocardiogram notes (accuracy 98.4%±0.3%). A test set of 300 cases, which was blindly and independently labeled for ARDS by two groups of clinicians, shows that ARDSFlag generates an overall accuracy of 89.0% (specificity = 91.7%, recall = 80.3%, and precision = 75.0%) in detecting ARDS cases.
CONCLUSIONS: To our best knowledge, this is the first study to focus on developing a method to automate the detection of ARDS. Some studies have developed and used other methods to answer other research questions. Expectedly, ARDSFlag generates a significantly higher performance in all accuracy measures compared to those methods.
摘要：
背景：尽管急性呼吸窘迫综合征（ARDS）的重要性和患病率，它的检测仍然是高度可变和不一致的。在这项工作中,我们的目标是开发一种算法（ARDSFlag），以根据柏林定义自动诊断ARDS。我们还旨在开发一种可视化工具，帮助临床医生有效评估ARDS标准。
方法：ARDSFlag应用机器学习（ML）和自然语言处理（NLP）技术通过在电子健康记录（EHR）系统中整合结构化和非结构化数据来评估柏林标准。该研究队列包括重症监护医学信息集市III（MIMIC-III）数据库中的19,534名ICU入院。输出是ARDS诊断，发病时间,和严重性。
结果：ARDSFlag包括使用大型训练集训练的单独文本分类器，以发现放射学报告中的双侧浸润（准确度为91.9％±0.5％）和放射学报告中的心力衰竭/液体超负荷（准确度为86.1％±0.5％）和超声心动图注释（准确度为98.4％±0.3％）。一套300例的测试，两组临床医生盲目独立标记ARDS，显示ARDSFlag产生的总体准确度为89.0%(特异性=91.7%，召回率=80.3%，检测ARDS病例的准确率为75.0%)。
结论：据我们所知，这是第一项专注于开发自动化ARDS检测方法的研究。一些研究已经开发并使用其他方法来回答其他研究问题。期望,与这些方法相比，ARDSFlag在所有精度度量方面都能产生明显更高的性能。
方法：ARDSFlag应用机器学习（ML）和自然语言处理（NLP）技术通过在电子健康记录（EHR）系统中整合结构化和非结构化数据来评估柏林标准。该研究队列包括重症监护医学信息集市III（MIMIC-III）数据库中的19,534名ICU入院。输出是ARDS诊断，发病时间,和严重性。
结果：ARDSFlag包括使用大型训练集训练的单独文本分类器，以发现放射学报告中的双侧浸润（准确度为91.9％±0.5％）和放射学报告中的心力衰竭/液体超负荷（准确度为86.1％±0.5％）和超声心动图注释（准确度为98.4％±0.3％）。一套300例的测试，两组临床医生盲目独立标记ARDS，显示ARDSFlag产生的总体准确度为89.0%(特异性=91.7%，召回率=80.3%，检测ARDS病例的准确率为75.0%)。
结论：据我们所知，这是第一项专注于开发自动化ARDS检测方法的研究。一些研究已经开发并使用其他方法来回答其他研究问题。期望,与这些方法相比，ARDSFlag在所有精度度量方面都能产生明显更高的性能。
