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

Cancer Survival Analysis01:21

Cancer Survival Analysis

456
Cancer survival analysis focuses on quantifying and interpreting the time from a key starting point, such as diagnosis or the initiation of treatment, to a specific endpoint, such as remission or death. This analysis provides critical insights into treatment effectiveness and factors that influence patient outcomes, helping to shape clinical decisions and guide prognostic evaluations. A cornerstone of oncology research, survival analysis tackles the challenges of skewed, non-normally...
456

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 journal

Metastatic appendiceal mucinous adenocarcinoma presenting as bilateral ovarian masses mimicking advanced ovarian cancer: a case report.

Ewha medical journal·2026
Same journal

Clinical phenotypes and clustering patterns of human toxocariasis in PubMed-indexed case reports: an Antigravity-assisted systematic scoping review.

Ewha medical journal·2026
Same journal

Effect of ultrasound-guided bilateral rectus sheath block on postoperative pain control after robotic single-site gynecologic surgery: a randomized study.

Ewha medical journal·2026
Same journal

SKYVaricella (a live attenuated varicella vaccine) safety issues revisited.

Ewha medical journal·2026
Same journal

Primary breast leiomyosarcoma-pathological challenges and immunohistochemical insights in diagnosing a rare tumor: a case report.

Ewha medical journal·2026
Same journal

Artificial intelligence as a pragmatic adjunct to molecular classification in endometrial cancer.

Ewha medical journal·2026

相关实验视频

Updated: Sep 14, 2025

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

通过基于SHAP的机器学习模型的特征工程来改善尾癌的预测:一个预测研究.

Ji Yoon Kim1

  • 1Ewha Womans University College of Medicine, Seoul, Korea.

Ewha medical journal
|July 24, 2025
PubMed
概括
此摘要是机器生成的。

沙普利添加式解释 (SHAP) 功能工程提高了尾癌症预测准确性和透明度. 这种可解释的模型增强了对罕见疾病预测的临床相关性.

关键词:
算法算法是一种算法.尾瘤是什么?尾瘤是什么?机器学习是机器学习.随机的森林随机的森林

更多相关视频

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

6.9K
Murine Appendectomy Model of Chronic Colitis Associated Colorectal Cancer by Precise Localization of Caecal Patch
08:51

Murine Appendectomy Model of Chronic Colitis Associated Colorectal Cancer by Precise Localization of Caecal Patch

Published on: August 24, 2019

10.1K

相关实验视频

Last Updated: Sep 14, 2025

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
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

6.9K
Murine Appendectomy Model of Chronic Colitis Associated Colorectal Cancer by Precise Localization of Caecal Patch
08:51

Murine Appendectomy Model of Chronic Colitis Associated Colorectal Cancer by Precise Localization of Caecal Patch

Published on: August 24, 2019

10.1K

科学领域:

  • 在瘤学瘤学.
  • 人工智能的人工智能
  • 机器学习 机器学习

背景情况:

  • 传统的尾癌预测模型往往缺乏透明度,限制了临床采用.
  • 可解释的人工智能对于将预测模型集成到临床实践中至关重要.

研究的目的:

  • 开发和评估基于沙普利增材解释 (SHAP) 的特征工程框架,用于尾癌预测.
  • 通过整合SHAP来增强模型准确性和临床解释性,用于特征选择,构建和权重.

主要方法:

  • 使用了Kaggle附录癌症预测数据集 (26万个样本,21个特征).
  • 应用数据预处理,包括标签编码和SMOTE用于类不平衡.
  • 与基线模型进行比较 (随机森林,XGBoost,LightGBM),选择LightGBM以获得卓越的性能.
  • 实施了SHAP分析,用于特征选择,基于交互的特征构建和特征加权.

主要成果:

  • 基于SHAP的框架改善了LightGBM模型的性能,特征加权实现了最高的F1得分 (0.8877) 和精度 (0.9940).
  • 确定的主要预测特征包括红细胞计数和慢性严重程度.
  • 工程模型保持了可解释性,同时提高了预测准确性.

结论:

  • 基于SHAP的特征工程框架显著提高了尾癌预测的准确性和透明度.
  • 这种方法为罕见疾病预测提供了一个可扩展和可解释的解决方案.
  • 建议对现实数据进行进一步验证,以确保可通用性.