Model and expert performance compared to reports.

This paper presents an artificial intelligence-based classification model for the detection of pulmonary embolism in computed tomography angiography. The proposed model, developed from public data and validated on a large dataset from a tertiary hospital, uses a two-dimensional approach that integrates temporal series to classify each slice of the examination and make predictions at both slice and examination levels. The training process consists of two stages: first using a convolutional neural network InceptionResNet V2 and then a recurrent neural network long short-term memory model. This approach achieved an accuracy of 93% at the slice level and 77% at the examination level. External validation using a hospital dataset resulted in a precision of 86% for positive pulmonary embolism cases and 69% for negative pulmonary embolism cases. Notably, the model excels in excluding pulmonary embolism, achieving a precision of 73% and a recall of 82%, emphasizing its clinical value in reducing unnecessary interventions. In addition, the diverse demographic distribution in the validation dataset strengthens the model’s generalizability. Overall, this model offers promising potential for accurate detection and exclusion of pulmonary embolism, potentially streamlining diagnosis and improving patient outcomes.

本研究提出了一种基于人工智能（artificial intelligence, AI）的分类模型，用于计算机断层血管造影（computed tomography angiography）中的肺栓塞（pulmonary embolism）检测。该模型基于公开数据开发，并在某三级医院的大型数据集上完成验证，采用融合时序信息的二维处理方法，对检查的每一层影像进行分类，并同时在影像层面与检查整体层面作出预测。
模型的训练分为两个阶段：首先采用卷积神经网络InceptionResNet V2，随后使用循环神经网络长短期记忆（long short-term memory, LSTM）模型。该方法在影像层面的准确率达93%，在检查整体层面的准确率达77%。
使用某医院数据集开展的外部验证结果显示，肺栓塞阳性病例的精确率为86%，肺栓塞阴性病例的精确率为69%。值得注意的是，该模型在肺栓塞排除任务中表现优异，精确率达73%、召回率（recall）达82%，凸显了其在减少不必要临床干预方面的临床价值。此外，验证数据集覆盖了多样的人口统计学特征分布，进一步提升了模型的泛化能力。
综上，该模型在肺栓塞的精准检测与排除方面展现出良好应用潜力，有望优化诊断流程并改善患者预后。