Reproductive Medicine Center, Quzhou People's Hospital, The Quzhou Affiliated Hospital of Wenzhou Medical University, No. 100, Minjiang Avenue, Quzhou, 324000, Zhejiang, China.
Department of Orthopedics, Quzhou People's Hospital, The Quzhou Affiliated Hospital of Wenzhou Medical University, No. 100, Minjiang Avenue, Quzhou, 324000, Zhejiang, China.
J Transl Med. 2023 Sep 25;21(1):664. doi: 10.1186/s12967-023-04487-8.
Rapid identification of high-risk polytrauma patients is crucial for early intervention and improved outcomes. This study aimed to develop and validate machine learning models for predicting 72 h mortality in adult polytrauma patients using readily available clinical parameters.
A retrospective analysis was conducted on polytrauma patients from the Dryad database and our institution. Missing values pertinent to eligible individuals within the Dryad database were compensated for through the k-nearest neighbor algorithm, subsequently randomizing them into training and internal validation factions on a 7:3 ratio. The patients of our institution functioned as external validation cohorts. The predictive efficacy of random forest (RF), neural network, and XGBoost models was assessed through an exhaustive suite of performance indicators. The SHapley Additive exPlanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) methods were engaged to explain the supreme-performing model. Conclusively, restricted cubic spline analysis and multivariate logistic regression were employed as sensitivity analyses to verify the robustness of the findings.
Parameters including age, body mass index, Glasgow Coma Scale, Injury Severity Score, pH, base excess, and lactate emerged as pivotal predictors of 72 h mortality. The RF model exhibited unparalleled performance, boasting an area under the receiver operating characteristic curve (AUROC) of 0.87 (95% confidence interval [CI] 0.84-0.89), an area under the precision-recall curve (AUPRC) of 0.67 (95% CI 0.61-0.73), and an accuracy of 0.83 (95% CI 0.81-0.86) in the internal validation cohort, paralleled by an AUROC of 0.98 (95% CI 0.97-0.99), an AUPRC of 0.88 (95% CI 0.83-0.93), and an accuracy of 0.97 (95% CI 0.96-0.98) in the external validation cohort. It provided the highest net benefit in the decision curve analysis in relation to the other models. The outcomes of the sensitivity examinations were congruent with those inferred from SHAP and LIME.
The RF model exhibited the best performance in predicting 72 h mortality in adult polytrauma patients and has the potential to aid clinicians in identifying high-risk patients and guiding clinical decision-making.
快速识别高危多发伤患者对于早期干预和改善预后至关重要。本研究旨在开发和验证使用易于获得的临床参数预测成年多发伤患者 72 小时死亡率的机器学习模型。
对 Dryad 数据库和我们机构的多发伤患者进行回顾性分析。通过 K-最近邻算法补偿与 Dryad 数据库中合格个体相关的缺失值，随后将其随机分为 7:3 的训练和内部验证组。我们机构的患者作为外部验证队列。通过一整套性能指标评估随机森林 (RF)、神经网络和 XGBoost 模型的预测效果。采用 SHapley Additive exPlanations (SHAP) 和 Local Interpretable Model-Agnostic Explanations (LIME) 方法解释表现最佳的模型。最后，进行限制性立方样条分析和多变量逻辑回归作为敏感性分析，以验证结果的稳健性。
包括年龄、体重指数、格拉斯哥昏迷评分、损伤严重程度评分、pH 值、碱剩余和乳酸在内的参数被确定为 72 小时死亡率的关键预测因素。RF 模型表现卓越，在内部验证队列中的受试者工作特征曲线下面积 (AUROC) 为 0.87(95%置信区间[CI]0.84-0.89)，精度-召回曲线下面积 (AUPRC) 为 0.67(95%CI0.61-0.73)，准确率为 0.83(95%CI0.81-0.86)，外部验证队列中的 AUROC 为 0.98(95%CI0.97-0.99)，AUPRC 为 0.88(95%CI0.83-0.93)，准确率为 0.97(95%CI0.96-0.98)。在决策曲线分析中，它与其他模型相比提供了最高的净收益。敏感性检查的结果与 SHAP 和 LIME 推断的结果一致。
RF 模型在预测成年多发伤患者 72 小时死亡率方面表现最佳，具有帮助临床医生识别高危患者和指导临床决策的潜力。
