Search research articles

关于 JoVE

概览领导团队博客 JoVE 帮助中心

作者

出版流程编辑委员会范围与政策同行评审常见问题投稿

图书馆员

用户评价订阅访问资源图书馆顾问委员会常见问题

研究

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

相关概念视频

Ultrasonography

Ultrasonography

Ultrasonography is an imaging technique that uses high-frequency sound waves to visualize the body's internal structures. It is a non-invasive and safe procedure that does not involve the use of ionizing radiation, making it widely used in various medical fields. Ultrasonography is used to study heart function, blood flow in the neck or extremities, certain conditions such as gallbladder disease, and fetal growth and development.
During an ultrasonography procedure, a handheld device called a...

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序

Same author

Clinicopathological Profile of Conjunctival Melanoma at a Referral Ophthalmology Center in Peru.

Clinical ophthalmology (Auckland, N.Z.)·2026

Same author

Profile of Eye Injuries in Patients Examined at a Tertiary Eye Care Center in Peru.

Clinical ophthalmology (Auckland, N.Z.)·2025

Same author

Factors associated with complications from COVID-19 in hospital workers: A retrospective cohort study.

Medwave·2022

Same author

Maternal-perinatal outcomes in pregnant women with covid-19 in a level III hospital in Peru.

Revista peruana de medicina experimental y salud publica·2021

Same author

Characterization of children infected with HIV due to mother-to-child transmission in hospitals in Lima, Peru.

Revista peruana de medicina experimental y salud publica·2021

Search research articles

相关实验视频

Updated: May 8, 2026

A Novel Use of Three-dimensional High-frequency Ultrasonography for Early Pregnancy Characterization in the Mouse

A Novel Use of Three-dimensional High-frequency Ultrasonography for Early Pregnancy Characterization in the Mouse

Published on: October 24, 2017

基于超声波生物识别的胎儿体重估计的机器学习模型:开发和验证研究研究.

Marcos Espinola-Sánchez^1,2, Antonio Limay-Rios³, Andrés Campaña-Acuña³

¹Facultad de Ciencias de la Salud, Universidad Privada del Norte, Lima, Peru.

|May 19, 2025

概括

机器学习模型可以准确估计胎儿的体重. 与传统公式相比, Tabular Prior-data Fitted Network (TabPFN) 模型显示出更高的预测准确性,为产科护理提供了一个有前途的工具.

关键词:

胎儿的体重胎儿的体重人工智能的人工智能是人工智能.机器学习是机器学习.围产期护理围产期护理怀孕怀孕怀孕怀孕怀孕在产前产前产前.超声波学超声波学超声波学超声波学

更多相关视频

Fetal Mouse Cardiovascular Imaging Using a High-frequency Ultrasound 30/45MHZ System

Fetal Mouse Cardiovascular Imaging Using a High-frequency Ultrasound 30/45MHZ System

Published on: May 5, 2018

High Frequency Ultrasound for the Analysis of Fetal and Placental Development In Vivo

High Frequency Ultrasound for the Analysis of Fetal and Placental Development In Vivo

Published on: November 8, 2018

相关实验视频

Last Updated: May 8, 2026

A Novel Use of Three-dimensional High-frequency Ultrasonography for Early Pregnancy Characterization in the Mouse

A Novel Use of Three-dimensional High-frequency Ultrasonography for Early Pregnancy Characterization in the Mouse

Published on: October 24, 2017

Fetal Mouse Cardiovascular Imaging Using a High-frequency Ultrasound 30/45MHZ System

Fetal Mouse Cardiovascular Imaging Using a High-frequency Ultrasound 30/45MHZ System

Published on: May 5, 2018

High Frequency Ultrasound for the Analysis of Fetal and Placental Development In Vivo

High Frequency Ultrasound for the Analysis of Fetal and Placental Development In Vivo

Published on: November 8, 2018

科学领域:

医学成像和诊断医学成像和诊断
医疗保健中的人工智能
围产儿医学围产儿医学

背景情况:

机器学习 (ML) 提出了一种用于估计胎儿体重的创新方法.
整合多个生物识别和临床变量可以提高准确性.

研究的目的:

开发和验证使用超声波生物识别数据估计胎儿体重的ML模型.
评估ML模型的准确性,并将其与哈德洛克和谢帕德等传统公式进行比较.

主要方法:

一项回顾性观察性研究包括3525例低风险单子妊娠 (2009-2022年).
ML模型 (渐变增强,SVM,随机森林,TabPFN) 经过培训和验证,使用胎儿生物识别 (双侧直径,腹周,头周,大腿长度) 和妊娠年龄.
使用R2和平均平方误差 (MSE) 评估了准确性.

主要成果:

在最初的研究阶段,TabPFN模型获得了最高的准确性 (R2=0.856,MSE=0.146),超过了哈德洛克 (R2=0.807,MSE=0.195) 和谢帕德 (R2=0.801,MSE=0.201) 的公式.
在独立验证样本 (2019-2022) (R2=0.873,MSE=0.144) 中,TabPFN保持了优异的表现.
通过交叉验证和样本随机化证实了模型的一致性.

结论:

TabPFN模型显著优于传统公式和其他ML方法来估计胎儿体重.
它的高预测准确性和稳定性使其成为产科中潜在的临床决策支持工具.
TabPFN与超参数调整的独立性提高了其临床实用性.