Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
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 JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关实验视频

Updated: Jul 17, 2025

Fetal Mouse Cardiovascular Imaging Using a High-frequency Ultrasound 30/45MHZ System
07:34

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

Published on: May 5, 2018

11.7K

一个机器学习模型用于从行政数据中预测先天性心脏缺陷.

Haoming Shi1, Wendy Book2,3, Cheryl Raskind-Hood3

  • 1Department of Biomedical Engineering, Georgia Institute Technology, Atlanta, Georgia, USA.

Birth defects research
|September 8, 2023
PubMed
概括

相关概念视频

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

Classification of the Source of 1D Doppler Ultrasound Activity in Fetal Monitoring.

Computing in cardiology·2026
Same authorSame journal

Fetal and Obstetric Complications Among Pregnant Women With Congenital Heart Disease in a Georgia Medicaid Dataset.

Birth defects research·2026
Same author

A Kalman Filter-Based Framework for Granger Causality Assessment: Application in Tracking Maternal-Fetal Heart Rate Coupling.

IEEE transactions on bio-medical engineering·2026
Same authorSame journal

Preventive Dental Care Utilization and Infective Endocarditis Among Georgia Medicaid Beneficiaries With Congenital Heart Defects, 2008-2019.

Birth defects research·2026
Same author

PCT-Anchored Machine Learning for Pre-Culture Identification of Gram-Negative Sepsis in Children: A Four-Site Study.

Shock (Augusta, Ga.)·2026
Same author

Mortality risk prediction from dense PICU data from patients with suspected infection: data-derived physiological trajectories outperform expert assessments when temporal resolution is high.

International journal of infectious diseases : IJID : official publication of the International Society for Infectious Diseases·2026

机器学习 (ML) 算法显著提高了在行政数据中识别先天性心脏缺陷 (CHD) 的准确性,而不是仅使用国际疾病分类 (ICD) 代码. 这有助于加强对心血管疾病患者的公共卫生监测.

科学领域:

  • 医疗信息学 医疗信息学
  • 公共卫生 公共卫生
  • 机器学习 机器学习

背景情况:

  • 国际疾病分类 (ICD) 代码通常用于在行政数据中识别先天性心脏缺陷 (CHD).
  • 然而,ICD代码可能会不准确地识别患有心脏病的真实阳性 (TP) 个体,从而可能削弱监测工作.

研究的目的:

  • 通过使用机器学习 (ML) 算法在行政记录中准确识别TP CHD病例来加强CHD监测.
  • 在大型行政数据集中确定预测TP CHD个体的关键特征.

主要方法:

  • 应用传统的ML模型 (逻辑回归,高斯天真贝叶斯,随机森林,XGBoost) 对779名患者的验证数据集.
  • 在四个美国地点利用了接触级数据,包括2011-2013年的ICD-9-CM和CPT代码.
  • 采用五倍交叉验证来识别重叠的重要特征,并使用PPV和F1-score等指标比较模型性能.

主要成果:

  • 专家临床医生对ICD-9-CM CHD代码的验证产生了76.5%的基线积极预测值 (PPV).
  • ML特征选择将7138个特征减少到10个,显著改善了TP CHD病例的预测.
  • 极端梯度提升 (XGBoost) 显示出卓越的性能,达到0.94的PPV中位数 (95%CI:0.94,0.95) 和0.84的F1得分 (95%CI:0.76,0.91).
关键词:
遗传性心脏病是一种先天性心脏病.机器学习是机器学习.人口健康 人口健康

更多相关视频

A Pipeline to Characterize Structural Heart Defects in the Fetal Mouse
08:19

A Pipeline to Characterize Structural Heart Defects in the Fetal Mouse

Published on: December 16, 2022

1.9K
Analysis of Congenital Heart Defects in Mouse Embryos Using Qualitative and Quantitative Histological Methods
08:28

Analysis of Congenital Heart Defects in Mouse Embryos Using Qualitative and Quantitative Histological Methods

Published on: March 10, 2020

6.9K

相关实验视频

Last Updated: Jul 17, 2025

Fetal Mouse Cardiovascular Imaging Using a High-frequency Ultrasound 30/45MHZ System
07:34

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

Published on: May 5, 2018

11.7K
A Pipeline to Characterize Structural Heart Defects in the Fetal Mouse
08:19

A Pipeline to Characterize Structural Heart Defects in the Fetal Mouse

Published on: December 16, 2022

1.9K
Analysis of Congenital Heart Defects in Mouse Embryos Using Qualitative and Quantitative Histological Methods
08:28

Analysis of Congenital Heart Defects in Mouse Embryos Using Qualitative and Quantitative Histological Methods

Published on: March 10, 2020

6.9K

结论:

  • 与单独使用ICD代码相比,ML算法大大提高了识别TPCHD病例的准确性.
  • 这种ML方法提高了从大型数据集到心脏病患者群体的发现的概括性.
  • 改进的识别准确性加强了对先天性心脏缺陷的公共卫生监测.