使用三层神经网络预测早产新生儿与子宫内生长限制的不良神经发育结果
Anca Bivoleanu1, Liliana Gheorghe2, Bogdan Doroftei3
1Head of Neonatal Intensive Care Unit, "Cuza voda" Maternity Hospital, 700038 Iasi, Romania.
Diagnostics (Basel, Switzerland)
|January 11, 2025
概括
这项研究评估了人工神经网络,以预测早产婴儿与子宫内生长限制 (IUGR) 的神经发育结果. 模型显示轻度延迟的准确性中等,但对中度至严重的结果的准确性较低.
科学领域:
- 新生儿神经学 新生儿神经学
- 发育儿科 发育儿科
- 医学中的人工智能
背景情况:
- 预测早产婴儿与子宫内生长限制 (IUGR) 的不良神经发育结果需要改进.
- 早期识别对于及时干预和更好的长期预后至关重要.
研究的目的:
- 评估三层人工神经网络 (ANN) 对神经发育结果的预测性能.
- 用贝利婴儿和幼儿发展尺度,第三版 (贝利-III) 来评估ANN在两岁时预测结果的能力.
主要方法:
- 对早产婴儿进行回顾性观察研究,具有或没有IUGR.
- 从三级新生儿重症监护室收集的数据 (2018年1月 - 2022年12月).
- 使用阿米尔-蒂森和贝利-III尺度,以及临床和准临床数据来训练一个三层的ANN.
主要成果:
- 在轻微的认知,运动和语言延迟方面,ANN表现出适度的预测性能.
- 对于中度和严重的神经发育结果的预测准确度从中度到低.
结论:
- 人工神经网络显示出作为预测高风险婴儿神经发育结果的工具的潜力.
- 纳入更广泛的临床和准临床数据可以提高ANN的预测准确性.
相关概念视频
Neurulation
Neurulation is the embryological process which forms the precursors of the central nervous system and occurs after gastrulation has established the three primary cell layers of the embryo: ectoderm, mesoderm, and endoderm. In humans, the majority of this system is formed via primary neurulation, in which the central portion of the ectoderm—originally appearing as a flat sheet of cells—folds upwards and inwards, sealing off to form a hollow neural tube. As development proceeds, the anterior...
Teratogenicity
The ability of a drug to produce structural deformations and functional abnormalities in the developing embryo or the fetus is called teratogenicity, and the drug producing this effect is known as a teratogen. Teratogenic effects include stillbirth, miscarriage, intrauterine growth restriction, and neurocognitive delay. A teratogen may affect the embryo at different stages of development, which is important in determining the type and extent of the damage. During blastocyst formation, the early...


