Department of Biomedical Informatics, College of Medicine, University of Cincinnati, Cincinnati, OH.
Division of Biomedical Informatics, Cincinnati Children's Hospital Medical Center, Cincinnati, OH.
AMIA Annu Symp Proc. 2022 Feb 21;2021:783-792. eCollection 2021.
Inaccurate body weight measures can cause critical safety events in clinical settings as well as hindering utilization of clinical data for retrospective research. This study focused on developing a machine learning-based automated weight abnormality detector (AWAD) to analyze growth dynamics in pediatric weight charts and detect abnormal weight values. In two reference-standard based evaluation of real-world clinical data, the machine learning models showed good capacity for detecting weight abnormalities and they significantly outperformed the methods proposed in literature (p-value<0.05). A deep learning model with bi-directional long short-term memory networks achieved the best predictive performance, with AUCs ≥0.989 across the two datasets. The positive predictive value and sensitivity achieved by the system suggested more than 98% screening effort reduction potential in weight abnormality detection. Consequently, we hypothesize that the AWAD, when fully deployed, holds great potential to facilitate clinical research and healthcare delivery that rely on accurate and reliable weight measures.
不准确的体重测量可能会导致临床环境中的严重安全事件，并阻碍临床数据的利用进行回顾性研究。本研究旨在开发一种基于机器学习的自动体重异常检测器 (AWAD)，以分析儿科体重图表中的生长动态并检测异常体重值。在对真实临床数据的两种参考标准评估中，机器学习模型在检测体重异常方面表现出良好的能力，并且显著优于文献中提出的方法 (p 值<0.05)。具有双向长短期记忆网络的深度学习模型取得了最佳的预测性能，在两个数据集上的 AUC 值均≥0.989。系统的阳性预测值和敏感性表明，在体重异常检测方面，筛查工作的潜在减少率超过 98%。因此，我们假设，当 AWAD 完全部署时，它具有很大的潜力来促进依赖准确可靠体重测量的临床研究和医疗保健服务。
