使用自然语言处理技术准确识别结肠镜检查质量和息肉发现。
Accurate Identification of Colonoscopy Quality and Polyp Findings Using Natural Language Processing.
机构信息
Department of Medicine, Division of Gastroenterology, University of California San Francisco, San Francisco.
Division of Research, Kaiser Permanente Northern California, Oakland, CA.
出版信息
J Clin Gastroenterol. 2019 Jan;53(1):e25-e30. doi: 10.1097/MCG.0000000000000929.
OBJECTIVES
The aim of this study was to test the ability of a commercially available natural language processing (NLP) tool to accurately extract examination quality-related and large polyp information from colonoscopy reports with varying report formats.
BACKGROUND
Colonoscopy quality reporting often requires manual data abstraction. NLP is another option for extracting information; however, limited data exist on its ability to accurately extract examination quality and polyp findings from unstructured text in colonoscopy reports with different reporting formats.
STUDY DESIGN
NLP strategies were developed using 500 colonoscopy reports from Kaiser Permanente Northern California and then tested using 300 separate colonoscopy reports that underwent manual chart review. Using findings from manual review as the reference standard, we evaluated the NLP tool's sensitivity, specificity, positive predictive value (PPV), and accuracy for identifying colonoscopy examination indication, cecal intubation, bowel preparation adequacy, and polyps ≥10 mm.
RESULTS
The NLP tool was highly accurate in identifying examination quality-related variables from colonoscopy reports. Compared with manual review, sensitivity for screening indication was 100% (95% confidence interval: 95.3%-100%), PPV was 90.6% (82.3%-95.8%), and accuracy was 98.2% (97.0%-99.4%). For cecal intubation, sensitivity was 99.6% (98.0%-100%), PPV was 100% (98.5%-100%), and accuracy was 99.8% (99.5%-100%). For bowel preparation adequacy, sensitivity was 100% (98.5%-100%), PPV was 100% (98.5%-100%), and accuracy was 100% (100%-100%). For polyp(s) ≥10 mm, sensitivity was 90.5% (69.6%-98.8%), PPV was 100% (82.4%-100%), and accuracy was 95.2% (88.8%-100%).
CONCLUSION
NLP yielded a high degree of accuracy for identifying examination quality-related and large polyp information from diverse types of colonoscopy reports.
目的
本研究旨在测试一款商用自然语言处理（NLP）工具从不同报告格式的结肠镜检查报告中准确提取与检查质量相关和大息肉信息的能力。
背景
结肠镜检查质量报告通常需要手动数据提取。NLP 是提取信息的另一种选择；然而，关于其从不同报告格式的结肠镜检查报告中的非结构化文本中准确提取检查质量和息肉发现的能力的数据有限。
研究设计
使用 Kaiser Permanente Northern California 的 500 份结肠镜检查报告开发 NLP 策略，然后使用 300 份单独的接受手动图表审查的结肠镜检查报告进行测试。使用手动审查的结果作为参考标准，我们评估了 NLP 工具识别结肠镜检查适应证、盲肠插管、肠道准备充分性和 ≥10mm 息肉的灵敏度、特异性、阳性预测值（PPV）和准确性。
结果
NLP 工具在从结肠镜检查报告中识别与检查质量相关的变量方面具有高度准确性。与手动审查相比，筛查适应证的灵敏度为 100%（95%置信区间：95.3%-100%），PPV 为 90.6%（82.3%-95.8%），准确性为 98.2%（97.0%-99.4%）。对于盲肠插管，灵敏度为 99.6%（98.0%-100%），PPV 为 100%（98.5%-100%），准确性为 99.8%（99.5%-100%）。对于肠道准备充分性，灵敏度为 100%（98.5%-100%），PPV 为 100%（98.5%-100%），准确性为 100%（100%-100%）。对于 ≥10mm 的息肉，灵敏度为 90.5%（69.6%-98.8%），PPV 为 100%（82.4%-100%），准确性为 95.2%（88.8%-100%）。
结论
NLP 工具从各种类型的结肠镜检查报告中识别与检查质量相关和大息肉信息具有高度准确性。
Zotero 插件