应用人工智能工具预测单心室生理婴儿的不良事件
本研究为回顾性队列,纳入158例单心室生理患儿(共324次入院),在三级心脏ICU中利用连续生理数据训练多种机器学习分类器,预测心脏骤停、ECMO插管和气管插管等不良事件。共分析256次不良事件,随机森林模型在事件前8、4、2、1小时观察窗的AUROC分别为0.998、0.996、0.996、0.997。在合并ECMO-心脏骤停类别的多分类模型中,1小时观察窗的测试集AUROC为:插管0.819、ECMO-心脏骤停0.804、无事件0.840。结论认为机器学习模型可预测并区分单心室婴儿双向Glenn术前的不良事件类型,准确预测可能有助于及时干预。
要点
- 在单心室生理婴儿中,随机森林模型对不良事件检测的AUROC在8小时窗为0.998、4小时窗0.996、2小时窗0.996、1小时窗0.997。
- 合并ECMO-心脏骤停类别的多分类随机森林模型在1小时窗的测试集AUROC:插管0.819、ECMO-心脏骤停0.804、无事件0.840。
- 共分析256次不良事件:插管157次(61.328%)、ECMO事件42次(16.406%)、心脏骤停44次(17.187%)、体外心肺复苏13次(5.078%)。
- 模型使用15个生理和实验室变量提取,其中6个高质量变量纳入机器学习模型。
- 预测目标为单心室婴儿在双向Glenn术前发生的心脏骤停、ECMO插管和气管插管。
适用人群与场景
- 单心室生理婴儿,入住三级心脏ICU,在双向Glenn术前阶段。
研究设计与关键结果
- 研究类型:回顾性队列,推导队列158例单心室患者(324次入院),内部验证采用总数据集10%的留出测试组。
- 共分析256次不良事件:插管157次(61.328%)、ECMO事件42次(16.406%)、心脏骤停44次(17.187%)、体外心肺复苏13次(5.078%)。
- 随机森林模型在留出测试集对所有时间窗的不良事件检测AUROC:8小时0.998、4小时0.996、2小时0.996、1小时0.997。
- 合并ECMO-心脏骤停类别的多分类随机森林模型在1小时观察窗的留出测试集AUROC:插管0.819、ECMO-心脏骤停0.804、无事件0.840。
证据类型、等级与局限
- 证据类型:回顾性队列研究,内部验证。
- 局限:原文未报告局限性。
对床旁实践的改变
- 作者认为准确的预测可能有助于及时干预,可能降低发病率、死亡率和医疗费用。
提炼说明
- 本条依据论文摘要整理;摘要未涉及「诊断标准与关键阈值」「处置流程与药物剂量」「红旗征与不能漏的情况」「指南或共识出处」,故未列出这些栏目;全文请点「阅读原文」。
英文原文(摘要)· 点击展开
BACKGROUND: Adverse events (AEs) within the cardiac ICU (CICU) are associated with high mortality and comorbidity. Patients with single ventricle (SV) physiology are particularly vulnerable to experiencing such events before second stage surgery (bidirectional Glenn). Timely identification and management of AEs are critical for improving patient outcomes and enabling earlier, more targeted medical interventions in this vulnerable population.
OBJECTIVES: To develop and evaluate machine learning (ML) models using continuous physiologic data to predict and identify AEs including cardiac arrest (CA), extracorporeal membrane oxygenation (ECMO) cannulation, and endotracheal intubation, up to 8 hours before occurrence in SV infants.
DERIVATION COHORT: Retrospective cohort of 158 SV patients (324 admissions) admitted to the tertiary care CICU at Children's National Hospital.
VALIDATION COHORT: Internal validation occurred in the held-out testing group of the data (10% of the total dataset).
PREDICTION MODEL: Supervised ML classifiers were (e.g., decision tree, logistic regression, support vector machine, extreme gradient boosting, random forest [RF]) trained and compared across four observation windows (8, 4, 2, and 1 hr) preceding each event. Model Performance was evaluated using the area under the receiver operating characteristic curve (AUROC). Fifteen physiologic and laboratory variables were extracted, of which six high-quality variables were included in the ML model. AEs were categorized into four categories (e.g., intubation, CA, ECMO, no event) for multiclass classification and ECMO-CA were also combined into a single class (ECMO-CA) to improve stability for rare events.
RESULTS: A total of 256 AEs were analyzed: 157 intubations (61.328%), 42 ECMO events (16.406%), 44 CAs (17.187%), and 13 extracorporeal cardiopulmonary resuscitation events (5.078%). Across all time windows, the RF model achieved the best performance on the held-out test set for AE detection (AUROCs 0.998 at 8 hr, 0.996 at 4 hr, 0.996 at 2 hr, and 0.997 at 1 hr). For the combined-class multiclass classification RF model at 1-hour observation window, the held-out test set results showed AUROCs of 0.819 for intubation, 0.804 for ECMO-CA, and 0.840 for no-event prediction.
CONCLUSIONS: A ML model can predict and discriminate between several types of AEs in SV infants before bidirectional Glenn. Accurate predictions may help perform timely interventions, potentially reducing morbidity, mortality, and healthcare costs.
参考来源
- Yu M, Saenz Gaitan L, Lopez Magallon A, et al. Prediction of Adverse Events in Single Ventricle Physiology Infants Using Artificial Intelligence Tools. Crit Care Explor. 2026. PMID: 41661165. doi:10.1097/CCE.0000000000001381
供执业医师抢救与诊疗参考,不替代临床判断;剂量请结合体重、肝肾功能和本院药品规格复核,以指南原文为准。