机器学习在预测早期重症监护需求方面优于加拿大分辨率和敏度度量 (CTAS)
Lars Grant1,2,3, Magueye Diagne4,5, Rafael Aroutiunian4,6
1Department of Emergency Medicine, McGill University, Montreal, QC, Canada. lars.grant@mcgill.ca.
CJEM
|November 19, 2024
概括
机器学习模型在预测急救部门的急症护理需求方面明显优于加拿大分辨率敏度度表 (CTAS). 这些人工智能工具对改善急诊室分拣准确性和患者结果显示出希望.
科学领域:
- 紧急医疗 紧急医疗
- 人工智能的人工智能
- 医疗信息学 医疗信息学
背景情况:
- 紧急部门 (ED) 的分拣对于优先考虑患者护理至关重要.
- 加拿大分辨率敏度度表 (CTAS) 是一个广泛使用的,但潜在的可改进的分辨率系统.
- 早期识别需要重症监护的患者对于改善结果至关重要.
研究的目的:
- 将机器学习 (ML) 模型的预测性能与CTAS进行比较,用于在ED到达12小时内识别需要重症监护的患者.
- 调查ML的潜力,以提高ED分拣准确度.
主要方法:
- 开发和评估了三种ML模型 (LASSO回归,梯度增强树,深度学习),使用670,841次ED访问的回顾性数据.
- 将ML模型的性能与CTAS进行比较,使用接收器-运营商特征曲线 (ROC) 和精度回忆曲线 (PRC) 下的面积.
- 利用Shapley增量解释得分来分析预测者的重要性.
主要成果:
- 机器学习模型表现出卓越的性能:深度学习 (ROC 0.926),梯度增强树木 (ROC 0.912) 和LASSO回归 (ROC 0.892).
- CTAS实现了较低的ROC,为0.804.
- 与CTAS相比,ML模型也显示了更高的精度回忆曲线值.
结论:
- 机器学习模型在识别可能需要在ED分拣时早期关键护理的患者方面显著优于CTAS.
- 机器学习模型具有提高分辨率和分类算法的可靠性的潜力.
- 未来的验证研究建议将ML纳入修订后的CTAS协议中.
相关概念视频
Receiver Operating Characteristic Plot
83
A ROC (Receiver Operating Characteristic) plot is a graphical tool used to assess the performance of a binary classification model by illustrating the trade-off between sensitivity (true positive rate) and specificity (false positive rate). By plotting sensitivity against 1 - specificity across various threshold settings, the ROC curve shows how well the model distinguishes between classes, with a curve closer to the top-left corner indicating a more accurate model. The area under the ROC curve...
83
Methods of Documentation VI: Case Management Model
559
The case management model is a multidisciplinary approach that involves healthcare professionals from diverse disciplines, such as physicians, nurses, therapists, social workers, and pharmacists, working collaboratively to address the various needs of patients. Each healthcare professional brings unique expertise and perspectives, contributing to a more comprehensive understanding of the patient's condition and tailoring treatment plans accordingly.
For example, a patient with a chronic...
For example, a patient with a chronic...
559


