Department of Computer Science, University of Pittsburgh, PA.
Department of Surgery, University of Pittsburgh Medical Center, PA.
Surgery. 2021 Sep;170(3):797-805. doi: 10.1016/j.surg.2021.03.049. Epub 2021 Apr 27.
The radiographic finding of pneumatosis intestinalis can indicate a spectrum of underlying processes ranging from a benign finding to a life-threatening condition. Although radiographic pneumatosis intestinalis is relatively common, there is no validated clinical tool to guide surgical management.
Using a retrospective cohort of 300 pneumatosis intestinalis cases from a single institution, we developed 3 machine learning models for 2 clinical tasks: (1) the distinction of benign from pathologic pneumatosis intestinalis cases and (2) the determination of patients who would benefit from an operation. The 3 models are (1) an imaging model based on radiomic features extracted from computed tomography scans, (2) a clinical model based on clinical variables, and (3) a combination model using both the imaging and clinical variables.
The combination model achieves an area under the curve of 0.91 (confidence interval: 0.87-0.94) for task I and an area under the curve of 0.84 (confidence interval: 0.79-0.88) for task II. The combination model significantly (P < .05) outperforms the imaging model and the clinical model for both tasks. The imaging model achieves an area under the curve of 0.72 (confidence interval: 0.57-0.87) for task I and 0.68 (confidence interval: 0.61-0.74) for task II. The clinical model achieves an area under the curve of 0.87 (confidence interval: 0.83-0.91) for task I and 0.76 (confidence interval: 0.70-0.81) for task II.
This study suggests that combined radiographic and clinical features can identify pathologic pneumatosis intestinalis and aid in patient selection for surgery. This tool may better inform the surgical decision-making process for patients with pneumatosis intestinalis.
影像学上的肠气肿表现可以提示一系列潜在的过程，范围从良性发现到危及生命的情况。尽管影像学上的肠气肿相对常见，但目前还没有经过验证的临床工具来指导手术管理。
我们使用来自单个机构的 300 例肠气肿病例的回顾性队列，为 2 项临床任务开发了 3 种机器学习模型：（1）良性与病理性肠气肿病例的区分，（2）确定哪些患者将从手术中受益。这 3 种模型是（1）基于从计算机断层扫描中提取的放射组学特征的成像模型，（2）基于临床变量的临床模型，（3）使用成像和临床变量的组合模型。
组合模型在任务 1 中达到了 0.91 的曲线下面积（置信区间：0.87-0.94），在任务 2 中达到了 0.84 的曲线下面积（置信区间：0.79-0.88）。组合模型在两个任务中均显著（P<0.05）优于成像模型和临床模型。成像模型在任务 1 中达到了 0.72 的曲线下面积（置信区间：0.57-0.87），在任务 2 中达到了 0.68 的曲线下面积（置信区间：0.61-0.74）。临床模型在任务 1 中达到了 0.87 的曲线下面积（置信区间：0.83-0.91），在任务 2 中达到了 0.76 的曲线下面积（置信区间：0.70-0.81）。
本研究表明，联合放射学和临床特征可以识别病理性肠气肿，并有助于为手术选择患者。该工具可以更好地为肠气肿患者的手术决策过程提供信息。
