Department of Radiology, Massachusetts General Hospital, Boston, MA, United States of America; Harvard Medical School, Boston, MA, United States of America.
Department of Radiology, Massachusetts General Hospital, Boston, MA, United States of America; Harvard Medical School, Boston, MA, United States of America.
Am J Emerg Med. 2021 Nov;49:52-57. doi: 10.1016/j.ajem.2021.05.057. Epub 2021 May 27.
During the COVID-19 pandemic, emergency department (ED) volumes have fluctuated. We hypothesized that natural language processing (NLP) models could quantify changes in detection of acute abdominal pathology (acute appendicitis (AA), acute diverticulitis (AD), or bowel obstruction (BO)) on CT reports.
This retrospective study included 22,182 radiology reports from CT abdomen/pelvis studies performed at an urban ED between January 1, 2018 to August 14, 2020. Using a subset of 2448 manually annotated reports, we trained random forest NLP models to classify the presence of AA, AD, and BO in report impressions. Performance was assessed using 5-fold cross validation. The NLP classifiers were then applied to all reports.
The NLP classifiers for AA, AD, and BO demonstrated cross-validation classification accuracies between 0.97 and 0.99 and F1-scores between 0.86 and 0.91. When applied to all CT reports, the estimated numbers of AA, AD, and BO cases decreased 43-57% in April 2020 (first regional peak of COVID-19 cases) compared to 2018-2019. However, the number of abdominal pathologies detected rebounded in May-July 2020, with increases above historical averages for AD. The proportions of CT studies with these pathologies did not significantly increase during the pandemic period.
Dramatic decreases in numbers of acute abdominal pathologies detected by ED CT studies were observed early on during the COVID-19 pandemic, though these numbers rapidly rebounded. The proportions of CT cases with these pathologies did not increase, which suggests patients deferred care during the first pandemic peak. NLP can help automatically track findings in ED radiology reporting.
在 COVID-19 大流行期间，急诊科（ED）的就诊量波动较大。我们假设自然语言处理（NLP）模型可以量化 CT 报告中急性腹部病理（急性阑尾炎（AA）、急性憩室炎（AD）或肠梗阻（BO））检测的变化。
这项回顾性研究纳入了 2018 年 1 月 1 日至 2020 年 8 月 14 日在城市急诊科进行的腹部/骨盆 CT 检查的 22182 份放射学报告。使用 2448 份手动标注报告的子集，我们训练随机森林 NLP 模型来对报告印象中 AA、AD 和 BO 的存在进行分类。使用 5 折交叉验证评估性能。然后将 NLP 分类器应用于所有报告。
AA、AD 和 BO 的 NLP 分类器在交叉验证中的分类准确率在 0.97 到 0.99 之间，F1 得分在 0.86 到 0.91 之间。当应用于所有 CT 报告时，与 2018-2019 年相比，2020 年 4 月（COVID-19 病例的第一个区域高峰）AA、AD 和 BO 的估计病例数减少了 43-57%。然而，2020 年 5 月至 7 月，腹部病理的检测数量迅速反弹，AD 的数量超过了历史平均值。在大流行期间，这些病理的 CT 研究比例并没有显著增加。
在 COVID-19 大流行早期，急诊科 CT 研究中检测到的急性腹部病理数量急剧下降，但这些数量迅速反弹。这些病理的 CT 病例比例没有增加，这表明患者在第一波大流行高峰期间推迟了治疗。NLP 可以帮助自动跟踪急诊科放射学报告中的发现。
