创伤性脑损伤患者脑灌注压的潜在轨迹与风险预测模型:基于可解释人工神经网络
本研究基于MIMIC-IV 2.1和eICU-CRD 2.0数据库纳入331例有脑灌注压(CPP)记录的创伤性脑损伤(TBI)患者,用基于组的轨迹模型识别CPP轨迹,并用人工神经网络预测不良轨迹;另用HiRID数据库310例患者进行外部验证。识别出5个CPP轨迹组,其中第1组和第5组因院内死亡率不利合并为class 1;最佳6个预测因子包括有创收缩压变异系数、静脉血氯离子浓度、PaCO2、凝血酶原时间、CPP变异系数和平均CPP;Scaled Conjugate Gradient算法在识别class 1上表现相对较好。
要点
- 基于组的轨迹模型识别出5个CPP轨迹组,其中2组与风险升高相关、3组与风险降低相关。
- 第1组和第5组因院内死亡率不利合并为class 1。
- PaCO2可能是预测不良CPP分类的强预测因子。
核心结论
- 本研究识别出2个与风险升高相关的CPP轨迹组和3个与风险降低相关的CPP轨迹组,PaCO2可能是预测不良CPP分类的强预测因子。
- 人工神经网络模型实现了风险分层的主要目标,有助于早期干预和个体化治疗。
研究设计与样本
- 从MIMIC-IV 2.1和eICU-CRD 2.0数据库识别有CPP记录的TBI患者,共331例记录用于轨迹分析和模型开发。
- 另从HiRID数据库1.1.1纳入310例患者数据进行外部验证。
- 研究分两阶段:先用基于组的轨迹模型(GBTM)识别CPP轨迹,再用不同人工神经网络算法预测CPP轨迹。
主要发现
- GBTM识别出5个CPP轨迹组,第1组和第5组基于院内死亡率不利合并为class 1。
- 最佳6个预测因子为有创收缩压变异系数、静脉血氯离子浓度、PaCO2、凝血酶原时间、CPP变异系数和平均CPP。
- 与其他算法相比,Scaled Conjugate Gradient在识别class 1上表现相对更好。
关键数值与推荐
- 共331例来自MIMIC-IV 2.1和eICU-CRD 2.0的患者记录用于轨迹分析和模型开发。
- 310例来自HiRID的患者数据用于外部验证。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
OBJECTIVE: This study aimed to characterize long-term cerebral perfusion pressure (CPP) trajectory in traumatic brain injury (TBI) patients and construct an interpretable prediction model to assess the risk of unfavorable CPP evolution patterns. METHODS: TBI patients with CPP records were identified from the Medical Information Mart for Intensive Care (MIMIC)-IV 2.1, eICU Collaborative Research Database (eICU-CRD) 2.0, and HiRID dataset 1.1.1. The research process consisted of 2 stages. First, group-based trajectory modeling (GBTM) was used to identify different CPP trajectories. Second, different artificial neural network (ANN) algorithms were used to predict the trajectories of CPP. RESULTS: A total of 331 eligible patients' records from MIMIC-IV 2.1 and eICU-CRD 2.0 were used for trajectory analysis and model development. Additionally, 310 patients' data from HiRID were used for external validation. The GBTM identified 5 CPP trajectory groups, group 1 and group 5 were merged into class 1 based on unfavorable in-hospital mortality. The best 6 predictors were invasive systolic blood pressure coefficient of variation, venous blood chloride ion concentration, PaCO2, prothrombin time, CPP coefficient of variation, and mean CPP. Compared with other algorithms, Scaled Conjugate Gradient performed relatively better in identifying class 1. CONCLUSIONS: This study identified 2 CPP trajectory groups associated with elevated risk and 3 with reduced risk. PaCO2 might be a strong predictor for the unfavorable CPP class. The ANN model achieved the primary goal of risk stratification, which is conducive to early intervention and individualized treatment.
引用
- Zhou H, Zhao Y, Zheng H, et al. Latent Trajectories of Cerebral Perfusion Pressure and Risk Prediction Models Among Patients with Traumatic Brain Injury: Based on an Interpretable Artificial Neural Network. World Neurosurg. 2024. PMID: 39278542. doi:10.1016/j.wneu.2024.09.045
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。