Background

Many studies emphasize the role of structured reports (SRs) because they are readily accessible for further automated analyses. However, using SR data obtained in clinical routine for research purposes is not yet well represented in literature.

Purpose

To compare the performance of the Qanadli scoring system with a clot burden score mined from structured pulmonary embolism (PE) reports from CT angiography.

Materials and Methods

In this retrospective study, a rule-based text mining pipeline was developed to extract descriptors of PE and right heart strain from SR of patients with suspected PE between March 2017 and February 2020. From standardized PE reporting, a pulmonary artery obstruction index (PAOI) clot burden score (PAOI_CBS) was derived and compared with the Qanadli score (PAOI_Q). Scoring time and confidence from two independent readings were compared. Interobserver and interscore agreement was tested by using the intraclass correlation coefficient (ICC) and Bland-Altman analysis. To assess conformity and diagnostic performance of both scores, areas under the receiver operating characteristic curve (AUCs) were calculated to predict right heart strain incidence, as were optimal cutoff values for maximum sensitivity and specificity.

Results

SR content authored by 67 residents and signed off by 32 consultants from 1248 patients (mean age, 63 years ± 17 [standard deviation]; 639 men) was extracted accurately and allowed for PAOI_CBS calculation in 304 of 357 (85.2%) PE-positive reports. The PAOI_CBS strongly correlated with the PAOI_Q (r = 0.94; P < .001). Use of PAOI_CBS yielded overall time savings (1.3 minutes ± 0.5 vs 3.0 minutes ± 1.7), higher confidence levels (4.2 ± 0.6 vs 3.6 ± 1.0), and a higher ICC (ICC, 0.99 vs 0.95), respectively, compared with PAOI_Q (each, P < .001). AUCs were similar for PAOI_CBS (AUC, 0.75; 95% CI: 0.70, 0.81) and PAOI_Q (AUC, 0.77; 95% CI: 0.72, 0.83; P = .68), with cutoff values of 27.5% for both scores.

Conclusion

Data mining of structured reports enabled the development of a CT angiography scoring system that simplified the Qanadli score as a semiquantitative estimate of thrombus burden in patients with pulmonary embolism.

© RSNA, 2021

Online supplemental material is available for this article.

See also the editorial by Hunsaker in this issue.

中文翻译：

---

肺栓塞结构化报告数据挖掘的 CT 血管造影血块负荷评分

背景

许多研究强调结构化报告 (SR) 的作用，因为它们很容易用于进一步的自动化分析。然而，将临床常规中获得的 SR 数据用于研究目的尚未在文献中得到很好的体现。

目的

将 Qanadli 评分系统的性能与从 CT 血管造影的结构化肺栓塞 (PE) 报告中提取的凝块负荷评分进行比较。

材料和方法

在这项回顾性研究中，开发了一个基于规则的文本挖掘管道，用于从 2017 年 3 月至 2020 年 2 月期间疑似 PE 患者的 SR 中提取 PE 和右心应变的描述符。根据标准化的 PE 报告，肺动脉阻塞指数 (PAOI)得出凝块负荷评分 (PAOI _CBS ) 并与 Qanadli 评分 (PAOI _Q）。比较了两个独立读数的评分时间和置信度。使用组内相关系数 (ICC) 和 Bland-Altman 分析测试观察者间和评分间一致性。为了评估两种评分的一致性和诊断性能，计算受试者工作特征曲线下面积 (AUC) 以预测右心应变发生率，以及最大灵敏度和特异性的最佳截止值。

结果

SR 内容由来自 1248 名患者（平均年龄，63 岁 ± 17 [标准差]；639 名男性）的 67 名居民撰写并由 32 名顾问签署，并在 357 名（85.2%）PE-中的 304 名（85.2%）PE-中进行了 PAOI _CBS计算。正面报道。PAOI _CBS与 PAOI _Q强相关( r = 0.94; P < .001)。与 PAOI 相比，使用 PAOI _{CBS 分别}节省了总体时间（1.3 分钟 ± 0.5 对 3.0 分钟 ± 1.7）、更高的置信水平（4.2 ± 0.6 对 3.6 ± 1.0）和更高的 ICC（ICC，0.99 对 0.95）_Q（每个，P < .001）。PAOI _{CBS 的}AUC 相似(AUC, 0.75; 95% CI: 0.70, 0.81) 和 PAOI _Q (AUC, 0.77; 95% CI: 0.72, 0.83; P = .68)，两个分数的截止值为 27.5%。

结论

结构化报告的数据挖掘促成了 CT 血管造影评分系统的开发，该系统将 Qanadli 评分简化为肺栓塞患者血栓负荷的半定量估计。

© 北美放射学会，2021

本文提供在线补充材料。

另请参阅本期 Hunsaker 的社论。