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

相关概念视频

Survival Tree01:19

Survival Tree

86
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
 Building a Survival Tree
Constructing a...
86

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

Perspectives on the definition of 'evidence': a qualitative interview study among interest-holders.

BMJ evidence-based medicine·2026
Same author

Postgraduate Clinical Training Programs and Physician Recruitment in Post-Disaster Fukushima: A 15-Year Overview From the Hamadori Region.

Disaster medicine and public health preparedness·2026
Same author

Prostate and colorectal cancer screening among sexual minority individuals assigned male at birth in Japan: Evidence from a national online survey.

Annals of epidemiology·2026
Same author

Assessing Demand for Welfare Evacuation Shelters After the 2024 Noto Peninsula Earthquake: A Case Study Based on Evacuee Flow.

Disaster medicine and public health preparedness·2026
Same author

Japan essential medicine list and medicine supply issues: a cross-sectional study.

Journal of pharmaceutical policy and practice·2026
Same author

Correction: Disaster-related deaths with alcohol-related diseases after the Fukushima Daiichi nuclear power plant accident: case series.

Frontiers in public health·2026

相关实验视频

Updated: Jul 5, 2025

Author Spotlight: Generating Neuronal Phenotypic Profiles - A Protocol to Culture and Image Human Midbrain Dopaminergic Neurons
09:21

Author Spotlight: Generating Neuronal Phenotypic Profiles - A Protocol to Culture and Image Human Midbrain Dopaminergic Neurons

Published on: July 7, 2023

1.5K

使用时间序列聚类和光梯度增强机器预测CKD进展.

Hirotaka Saito1, Hiroki Yoshimura2, Kenichi Tanaka3,4

  • 1Department of Nephrology and Hypertension, Fukushima Medical University, 1 Hikariga-Oka, Fukushima City, Fukushima, 960-1295, Japan.

Scientific reports
|January 19, 2024
PubMed
概括

预测慢性病的进展是具有挑战性的. 这项研究使用机器学习来识别具有相似功能轨迹的患者群体,发现基线GFR是预测未来功能下降的关键.

更多相关视频

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging
11:38

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

Published on: October 4, 2024

577
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.3K

相关实验视频

Last Updated: Jul 5, 2025

Author Spotlight: Generating Neuronal Phenotypic Profiles - A Protocol to Culture and Image Human Midbrain Dopaminergic Neurons
09:21

Author Spotlight: Generating Neuronal Phenotypic Profiles - A Protocol to Culture and Image Human Midbrain Dopaminergic Neurons

Published on: July 7, 2023

1.5K
Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging
11:38

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

Published on: October 4, 2024

577
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.3K

科学领域:

  • 腎臟病學 (nephrology) 是一種醫學專業.
  • 数据科学数据科学数据科学
  • 生物统计学 生物统计学

背景情况:

  • 慢性病 (CKD) 的进展很难预测,因为细微的症状和复杂因素.
  • 早期识别CKD患者的发展轨迹对于及时干预和管理至关重要.

研究的目的:

  • 用先进的机器学习技术预测非透析CKD患者的功能轨迹.
  • 确定影响估计淋巴膜过率 (GFR) 下降的关键参数.

主要方法:

  • 应用时间序列集群分析,根据5年估计的GFR变化将780名CKD患者分为不同的群体.
  • 利用光梯度增强机器算法和Shapley增量解释用于预测模型开发和参数重要性分析.
  • 定义了五个不同的患者群,基线GFR和观察到的GFR下降率各不相同.

主要成果:

  • 将参与者分为五个集群,GFR下降率在五年内从4.9%到45.1%不等.
  • 对于估计的GFR轨迹,实现了0.675的预测准确度.
  • 确定基线估计GFR (1.61),血红蛋白 (0.12) 和体重指数 (0.11) 是最重要的预测因素.

结论:

  • 基线估计的GFR是CKD患者功能转变的主要决定因素.
  • 估计GFR的约50mL/min/1.73m2的值似乎对轨迹预测至关重要.
  • 机器学习模型为个性化CKD进展预测提供了一个有希望的方法.