Weakly Supervised Classification of Vital Sign Alerts as Real or Artifact
Weakly Supervised Classification of Vital Sign Alerts as Real or Artifact
复制标题
DOI：
10.48550/arxiv.2206.09074
复制
发表时间：
2022-06
期刊：
影响因子：
--
通讯作者：
Arnab Dey-;Mononito Goswami;J. H. Yoon;G. Clermont;M. Pinsky;M. Hravnak;A. Dubrawski
中科院分区：
文献类型：
--
作者：
Arnab Dey-;Mononito Goswami;J. H. Yoon;G. Clermont;M. Pinsky;M. Hravnak;A. Dubrawski
相当大比例的临床生理监测警报是错误的。这往往会导致临床人员的警觉疲劳，不可避免地危及患者的安全。为了解决这个问题，研究人员试图建立机器学习(ML)模型，能够准确地判断血流动力学监测患者床边发出的生命体征(VS)警报是真实的还是人为的。以前的研究使用了需要大量手工标记数据的有监督的ML技术。然而，手动收集此类数据可能成本高、耗时长且平淡无奇，并且是限制ML在医疗保健(HC)中广泛采用的关键因素。相反，我们探索使用多个单独不完美的启发式方法，在弱监督的情况下自动将概率标签分配给未标记的训练数据。我们的弱监督模型的性能与传统的监督技术相比具有竞争力，并且需要更少的领域专家参与，展示了它们在ML的HC应用中作为监督学习的有效和实用的替代方案的使用。
A significant proportion of clinical physiologic monitoring alarms are false. This often leads to alarm fatigue in clinical personnel, inevitably compromising patient safety. To combat this issue, researchers have attempted to build Machine Learning (ML) models capable of accurately adjudicating Vital Sign (VS) alerts raised at the bedside of hemodynamically monitored patients as real or artifact. Previous studies have utilized supervised ML techniques that require substantial amounts of hand-labeled data. However, manually harvesting such data can be costly, time-consuming, and mundane, and is a key factor limiting the widespread adoption of ML in healthcare (HC). Instead, we explore the use of multiple, individually imperfect heuristics to automatically assign probabilistic labels to unlabeled training data using weak supervision. Our weakly supervised models perform competitively with traditional supervised techniques and require less involvement from domain experts, demonstrating their use as efficient and practical alternatives to supervised learning in HC applications of ML.