预测单心室生理学婴儿使用人工智能工具的不良事件
Min Yu1, Lucas Saenz Gaitan1,2, Alejandro Lopez Magallon1,2,3
1Telemedicine Program, Children's National Hospital, Washington, DC.
Critical care explorations
|February 9, 2026
概括
机器学习模型可以提前8小时预测单心室婴儿的心脏骤停等不良事件. 这种早期检测有助于及时干预,可能改善弱势婴儿的结果.
科学领域:
- 儿童心脏病学 儿童心脏病学
- 生物医学工程 生物医学工程
- 人工智能在医学中的应用
背景情况:
- 在心脏重症监护室 (CICU) 的不良事件 (AEs) 携带高死亡风险.
- 在双向格伦手术之前,单心室 (SV) 生理学的婴儿特别容易受到AE的影响.
- 早期发现和管理AE对于改善这一群体的结果至关重要.
研究的目的:
- 开发和评估机器学习 (ML) 模型,用于预测患有SV生理学的婴儿的异常现象.
- 为了识别AE,包括心脏骤停 (CA),体外膜氧化 (ECMO) 管道和内内输管,在发生前8小时.
- 利用连续的生理数据,在脆弱的儿科群体中进行预测建模.
主要方法:
- 分析了158名SV婴儿 (324次入院) 的回顾性队列.
- 包括随机森林 (RF) 在内的监督的ML分类器被训练在AEs之前的1,2,4和8小时窗口中的生理数据上.
- 模型性能是使用接收器操作特征曲线 (AUROC) 下的面积来评估的.
主要成果:
- 射频模型在预测AEs方面表现出很高的性能,AUROC在所有时间窗口中从0.996到0.998不等.
- 对于在1小时窗口中的多类分类,射频模型在输管时达到0.819的AUROC,ECMO-CA时为0.804,无事件预测时为0.840.
- 确定了六个高质量的变量,并纳入预测性ML模型.
结论:
- 在双向格伦手术之前,ML模型可以有效地预测和区分SV婴儿的各种AE.
- 准确的AE预测有助于及时干预,可能降低发病率,死亡率和医疗保健成本.
- 连续的生理学数据与ML相结合,为儿科心脏护理中积极的患者管理提供了一个有前途的方法.
相关概念视频
Intelligence
8.7K
The term "intelligence" is complex because it refers to both behavior and individuals, and its interpretation varies across cultures. European Americans tend to link intelligence with reasoning and cognitive skills, while in Kenya, it is tied to responsible participation in family and social life. In Uganda, intelligence is seen as the ability to know the right actions and carry them out effectively, while the Iatmul people of Papua New Guinea associate it with the capacity to remember...
8.7K
Anatomy of the Brain: Ventricles
9.1K
There are hollow fluid-filled cavities known as ventricles deep inside the human brain. There are two lateral ventricles, one in each cerebral hemisphere, and each has three different projections — the anterior, inferior, and posterior horns visible from the lateral side. A thin membrane called the septum pellucidum separates the two lateral ventricles. The slender third ventricle in the diencephalon is connected to each lateral ventricle via a channel called the interventricular foramen.
9.1K
Predicting Molecular Geometry
46.1K
VSEPR Theory for Determination of Electron Pair Geometries
46.1K
Measures of Intelligence
8.5K
Psychologists measure intelligence by using standardized tests that produce a score known as the intelligence quotient or IQ. To understand IQ tests, it's important to recognize the key principles behind their construction: validity, reliability, and standardization.
Validity refers to how well a test measures what it claims to measure. An intelligence test should accurately assess intelligence rather than another characteristic, like anxiety. Criterion validity is one way to evaluate this;...
Validity refers to how well a test measures what it claims to measure. An intelligence test should accurately assess intelligence rather than another characteristic, like anxiety. Criterion validity is one way to evaluate this;...
8.5K
Local Anesthetics: Adverse Effects
815
While local anesthetics are generally safe and well-tolerated, they can occasionally cause adverse effects that vary in severity. Local anesthetics can induce toxicity at two distinct levels. They can either produce local effects through direct contact with the neural elements or be absorbed into the bloodstream from the injection site, leading to systemic effects.
Once absorbed into the systemic circulation, local anesthetics can affect the organs that depend on the functioning of sodium...
Once absorbed into the systemic circulation, local anesthetics can affect the organs that depend on the functioning of sodium...
815
Prediction Intervals
3.4K
The interval estimate of any variable is known as the prediction interval. It helps decide if a point estimate is dependable.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
3.4K


