arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2401.00972cs.LGcs.CYstat.AP
收藏

用于预测非创伤性ICU患者输血需求的稳健元模型

Robust Meta-Model for Predicting the Need for Blood Transfusion in Non-traumatic ICU Patients

Emory University(埃默里大学);Emory University School of Medicine(埃默里大学医学院);The Johns Hopkins University School of Medicine(约翰斯·霍普金斯大学医学院);Johns Hopkins All Children’s Hospital(约翰斯·霍普金斯全儿童医院)

Alireza Rafiei, Ronald Moore, Tilendra Choudhary, Curtis Marshall, Geoffrey Smith, John D. Roback, Ravi M. Patel, Cassandra D. Josephson, Rishikesan Kamaleswaran

AI总结:

本研究开发了一个基于元学习的机器学习模型,利用72,072名非创伤性ICU患者数据预测未来24小时输血需求,在最佳场景下达到AUROC 0.97、准确率0.93和F1分数0.89,并识别了关键生物标志物。

摘要:

目的:输血在ICU环境中对于管理贫血和凝血功能障碍至关重要,需要准确预测以有效分配资源和评估患者风险。然而,现有的临床决策支持系统主要针对具有独特医疗条件的特定患者群体,并专注于单一类型的输血。本研究旨在开发一种先进的基于机器学习的模型,以预测未来24小时内各类非创伤性ICU患者输血需求的概率。方法:我们对2016年至2020年间入住美国一家大型城市学术医院的72,072名成年非创伤性ICU患者进行了回顾性队列研究。我们开发了一个元学习器(meta-learner)和多种机器学习模型作为预测器,使用四年数据进行年度训练,并在第五个未见年份上进行评估,如此迭代五年。结果:实验结果显示,元模型在不同开发场景中均优于其他模型。在最佳场景中,它取得了显著的性能指标,包括接收者操作特征曲线下面积(AUROC)为0.97,准确率为0.93,F1分数为0.89。结论:本研究开创了使用机器学习模型预测重症患者群体输血需求的先河。评估结果证实,我们的模型不仅能有效预测输血需求,还能识别用于输血决策的关键生物标志物。

英文摘要:

Objective: Blood transfusions, crucial in managing anemia and coagulopathy in ICU settings, require accurate prediction for effective resource allocation and patient risk assessment. However, existing clinical decision support systems have primarily targeted a particular patient demographic with unique medical conditions and focused on a single type of blood transfusion. This study aims to develop an advanced machine learning-based model to predict the probability of transfusion necessity over the next 24 hours for a diverse range of non-traumatic ICU patients. Methods: We conducted a retrospective cohort study on 72,072 adult non-traumatic ICU patients admitted to a high-volume US metropolitan academic hospital between 2016 and 2020. We developed a meta-learner and various machine learning models to serve as predictors, training them annually with four-year data and evaluating on the fifth, unseen year, iteratively over five years. Results: The experimental results revealed that the meta-model surpasses the other models in different development scenarios. It achieved notable performance metrics, including an Area Under the Receiver Operating Characteristic (AUROC) curve of 0.97, an accuracy rate of 0.93, and an F1-score of 0.89 in the best scenario. Conclusion: This study pioneers the use of machine learning models for predicting blood transfusion needs in a diverse cohort of critically ill patients. The findings of this evaluation confirm that our model not only predicts transfusion requirements effectively but also identifies key biomarkers for making transfusion decisions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑