桥梁人工智能和临床实践:集成自动睡眠评分算法与不确定性引导的医生审查
Michal Bechny1,2, Giuliana Monachino1,2, Luigi Fiorillo2
1Institute of Computer Science, University of Bern, Bern, Switzerland.
Nature and science of sleep
|June 3, 2024
概括
这项研究引入了一种不确定性估计方法,以改善自动睡眠评分,显著减少临床医生需要的手动审查. 这种方法提高了分析睡眠障碍的多睡眠学数据的准确性和效率.
科学领域:
- 睡眠医学 睡眠医学
- 人工智能的人工智能
- 生物医学数据分析
背景情况:
- 自动睡眠评分算法对于分析多睡眠学 (PSG) 数据至关重要.
- 在手动评分中,得分者之间的差异性需要临床医生对自动预测进行审查.
- 目前的方法由于固有的变性而面临准确性的局限性.
研究的目的:
- 提高自动睡眠评分算法的临床实用性.
- 开发一种不确定性估计方法,以便对催眠仪进行高效的手动审查.
- 减少实现预定义协议水平所需的审查范围.
主要方法:
- 训练U-Sleep,一个最先进的睡眠评分算法,对来自13个数据库的19,578个PSG进行了训练.
- 使用8832名PSG (年龄0-91岁,各种睡眠障碍) 的临床数据库,改进了U-Sleep和评估不确定性量化.
- 利用一种新的信任网络进行不确定性估计,在域内 (ID) 和域外 (OOD) 数据上进行验证.
主要成果:
- 在U-Sleep中,Cohen的 kappa达到76.2% (ID) 和73.8-78.8% (OOD).
- 信任网络在识别不确定的预测方面获得了85.7% (ID) 和82.5-85.6% (OOD) 的AUROC得分.
- 达成90%的协议需要审查<29.0%的不确定时期,大大减少了工作量.
结论:
- 计分器之间的变化限制了自动计分准确度的80%左右.
- 将不确定性估计与U-Sleep整合起来,可以提高催眠仪审查与医生评分的对齐.
- 经过验证的方法改善了在各种睡眠障碍的临床环境中自动评分工具的可用性.
相关概念视频
02:07Blind Procedures
10.6K
Ideally, the people who observe and record the children’s behavior are unaware of who was assigned to the experimental or control group, in order to control for experimenter bias. Experimenter bias refers to the possibility that a researcher’s expectations might skew the results of the study. Remember, conducting an experiment requires a lot of planning, and the people involved in the research project have a vested interest in supporting their hypotheses. If the observers knew which...
10.6K
01:25Errors occurring during blood pressure monitoring
704
Blood pressure monitoring is a crucial clinical procedure in diagnosing and managing various cardiovascular conditions. Despite its significance, the accuracy of blood pressure measurements can be compromised by multiple factors, potentially leading to either falsely high or low readings. These inaccuracies are critical as they can significantly impact patient care. So, it is vital to understand these challenges deeply and adopt strategic approaches to minimize errors.
Several factors...
Several factors...
704