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

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

Multi-omics integration reveals that pterostilbene ameliorates cyclophosphamide-induced liver injury <i>via</i> the gut-liver axis by inhibiting inflammation and oxidative stress.

Food & function·2026
Same author

Intramolecular charge transfer endows near-infrared mitochondrial targeted photosensitizers with enhanced photodynamic therapy.

Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy·2026
Same author

Lumican deficiency dysregulates trophoblast function via PI3K/AKT and P53 signaling in preeclampsia.

NPJ Regenerative medicine·2026
Same author

Fibromodulin promotes PDAC progression through multifaceted regulation of tumor growth pathways: Implications for therapeutic targeting.

Pancreatology : official journal of the International Association of Pancreatology (IAP) ... [et al.]·2026
Same author

Advances in the Study of Noncoding RNAs in the Pathogenesis of Pregnancy-related Diseases.

Current protein & peptide science·2026
Same author

Gut dysbiosis and immune dysfunction induced by chronic cola replacement of water in rats: not just a sugar problem.

Frontiers in nutrition·2026

相关实验视频

Updated: May 23, 2025

Author Spotlight: Advancing Early Detection and Treatment of Gastrointestinal Tumors
03:05

Author Spotlight: Advancing Early Detection and Treatment of Gastrointestinal Tumors

Published on: February 16, 2024

950

使用可解释机器学习模型预测胆囊息肉患者的新发性息肉:回顾性队列研究.

Zhaobin He1, Shengbiao Yang1, Jianqiang Cao1

  • 1Department of Hepatobiliary Surgery, General Surgery, Qilu Hospital, Shandong University, Jinan, Shandong, P.R. China.

Cancer medicine
|March 7, 2025
PubMed
概括

机器学习模型准确地预测了瘤胆囊聚体 (GBPs),将其与良性生长区分开来. 息肉大小是关键预测因素,指导潜在恶性瘤的临床监测和干预.

关键词:
这就是 SHAP SHAP 的意思.胆囊聚体是胆囊中的一个.可以解释的机器学习.瘤的多种类型.

更多相关视频

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

8.2K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.6K

相关实验视频

Last Updated: May 23, 2025

Author Spotlight: Advancing Early Detection and Treatment of Gastrointestinal Tumors
03:05

Author Spotlight: Advancing Early Detection and Treatment of Gastrointestinal Tumors

Published on: February 16, 2024

950
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

8.2K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.6K

科学领域:

  • 胃肠病学和肝病学
  • 医疗信息学 医疗信息学
  • 在瘤学瘤学.

背景情况:

  • 胆囊聚体 (GBPs) 是常见的,其中的一个子集具有恶性转变的风险.
  • 准确区分良性和瘤性GBP对于适当的管理至关重要.
  • 新生性GBP需要及时干预,以防止进展为胆囊癌.

研究的目的:

  • 开发和验证可解释的机器学习 (ML) 模型,用于预测瘤GBP.
  • 确定预测GBP瘤转变的关键特征.
  • 为了提高模型的透明度和临床实用性,使用Shapley添加式解释 (SHAP).

主要方法:

  • 对924名经过胆囊切除术的GBP患者的回顾性分析.
  • 使用患者特征,实验室结果,超声波和病理学数据.
  • 开发和比较9个ML算法,评估性能与AUC和SHAP进行解释性.

主要成果:

  • K-最近的邻居,C5.0决策树和梯度增强机器模型表现出优越的预测性能.
  • 通过SHAP方法确定了关键预测因素,其中聚大小是最重要的.
  • 病变≥18mm被强调需要加强临床监测和及时干预.

结论:

  • 可解释的ML模型可以准确预测瘤性GBP.
  • 这些模型有助于 GBP 患者的治疗规划和资源分配.
  • 模型透明度建立了医生信任,促进了患者护理中的自信应用.