Division of Cardiology, Department of Clinical Medicine, Fluminense Federal University, Rua Marquês do Paraná 303, Niterói, Rio de Janeiro CEP 24033-900, Brazil.
Emergency Department, Christchurch Hospital, Riccarton Avenue, Christchurch 8011, New Zealand.
Eur Heart J Acute Cardiovasc Care. 2022 Jan 12;11(1):13-19. doi: 10.1093/ehjacc/zuab089.
To develop a machine learning model to predict the diagnosis of pulmonary embolism (PE).
We undertook a derivation and internal validation study to develop a risk prediction model for use in patients being investigated for possible PE. The machine learning technique, generalized logistic regression using elastic net, was chosen following an assessment of seven machine learning techniques and on the basis that it optimized the area under the receiver operator characteristic curve (AUC) and Brier score. Models were developed both with and without the addition of D-dimer. A total of 3347 patients were included in the study of whom, 219 (6.5%) had PE. Four clinical variables (O2 saturation, previous deep venous thrombosis or PE, immobilization or surgery, and alternative diagnosis equal or more likely than PE) plus D-dimer contributed to the machine learning models. The addition of D-dimer improved the AUC by 0.16 (95% confidence interval 0.13-0.19), from 0.73 to 0.89 (0.87-0.91) and decreased the Brier score by 14% (10-18%). More could be ruled out with a higher positive likelihood ratio than by the Wells score combined with D-dimer, revised Geneva score combined with D-dimer, or the Pulmonary Embolism Rule-out Criteria score. Machine learning with D-dimer maintained a low-false-negative rate at a true-negative rate of nearly 53%, which was better performance than any of the other alternatives.
A machine learning model outperformed traditional risk scores for the risk stratification of PE in the emergency department. However, external validation is needed.
开发一种机器学习模型以预测肺栓塞（PE）的诊断。
我们进行了一项推导和内部验证研究，以开发一种用于疑似 PE 患者的风险预测模型。机器学习技术，广义逻辑回归使用弹性网，是在评估了七种机器学习技术之后选择的，并且基于它优化了接收者操作特征曲线（AUC）和 Brier 评分的面积。在没有添加 D-二聚体的情况下和添加 D-二聚体的情况下分别开发了模型。共有 3347 名患者纳入研究，其中 219 名（6.5%）患有 PE。四个临床变量（O2 饱和度、先前的深静脉血栓形成或 PE、固定或手术、替代诊断与 PE 同等或更有可能）加 D-二聚体有助于机器学习模型的建立。添加 D-二聚体使 AUC 提高了 0.16（95%置信区间 0.13-0.19），从 0.73 提高到 0.89（0.87-0.91），Brier 评分降低了 14%（10-18%）。与 Wells 评分加 D-二聚体、修订版 Geneva 评分加 D-二聚体或肺栓塞排除标准评分相比，通过更高的阳性似然比可以排除更多的患者。
机器学习模型在急诊科对 PE 的风险分层表现优于传统风险评分。然而，需要进行外部验证。
