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

Construction of two drug-loaded gold nanoclusters@mesoporous polydopamine nanospheres and the synergistic treatment of abdominal aortic aneurysms.

Journal of materials chemistry. B·2026
Same author

NIR-II Neuromodulation Combined with Metabolite-Mediated Immunoregulation for Accelerated Deeply Located Nerve Repair.

ACS nano·2026
Same author

Vanadium-Doped Bioactive Glass-Modified GelMA/CMCS/HA Injectable Hydrogel for Osteosarcoma Postoperative Therapy and Bone Regeneration.

Materials (Basel, Switzerland)·2026
Same author

Organic-inorganic heterostructure empowers infected wound healing.

Journal of materials chemistry. B·2025
Same author

Integrating graph convolutional networks with large language models for structured biomedical material knowledge representation.

Regenerative biomaterials·2025
Same author

Exosomes from rADSCs Stress-Preconditioned by Pathological Tissue Homogenate for Diabetic Wound Treatment.

ACS biomaterials science & engineering·2025

相关实验视频

Updated: Jun 15, 2025

Biological Compatibility Profile on Biomaterials for Bone Regeneration
10:28

Biological Compatibility Profile on Biomaterials for Bone Regeneration

Published on: November 16, 2018

12.6K

骨感应生物材料:用于预测和解释的机器学习.

Sicong Lin1, Yan Zhuang1, Ke Chen1

  • 1College of Biomedical Engineering, Sichuan University, Chengdu 610065, China; Provincial Engineering Research Center for Biomaterials Genome of Sichuan, Sichuan University, Chengdu 610065, China.

Acta biomaterialia
|August 23, 2024
PubMed
概括
此摘要是机器生成的。

机器学习加速了用于骨修复的骨感应生物材料的设计. 一个新的数据策略提高了模型的准确性,导致了优化材料,增强了骨再生能力.

关键词:
生物材料是一种生物材料.实验验证实验验验证的验证可以解释性 解释性机器学习 机器学习

更多相关视频

A Lab-On-A-Chip Platform for Stimulating Osteocyte Mechanotransduction and Analyzing Functional Outcomes of Bone Remodeling
08:28

A Lab-On-A-Chip Platform for Stimulating Osteocyte Mechanotransduction and Analyzing Functional Outcomes of Bone Remodeling

Published on: May 21, 2020

6.6K
Author Spotlight: Advanced Techniques for Characterizing Tissue Mineralization in Bone Regeneration Research
07:29

Author Spotlight: Advanced Techniques for Characterizing Tissue Mineralization in Bone Regeneration Research

Published on: September 27, 2024

690

相关实验视频

Last Updated: Jun 15, 2025

Biological Compatibility Profile on Biomaterials for Bone Regeneration
10:28

Biological Compatibility Profile on Biomaterials for Bone Regeneration

Published on: November 16, 2018

12.6K
A Lab-On-A-Chip Platform for Stimulating Osteocyte Mechanotransduction and Analyzing Functional Outcomes of Bone Remodeling
08:28

A Lab-On-A-Chip Platform for Stimulating Osteocyte Mechanotransduction and Analyzing Functional Outcomes of Bone Remodeling

Published on: May 21, 2020

6.6K
Author Spotlight: Advanced Techniques for Characterizing Tissue Mineralization in Bone Regeneration Research
07:29

Author Spotlight: Advanced Techniques for Characterizing Tissue Mineralization in Bone Regeneration Research

Published on: September 27, 2024

690

科学领域:

  • 生物材料科学 生物材料科学
  • 再生医学是一种再生医学.
  • 机器学习应用 机器学习应用

背景情况:

  • 骨诱导生物材料对于骨缺陷修复至关重要.
  • 机器学习 (ML) 有助于分析生物材料的骨诱导性和材料设计.
  • 对于骨质感应材料创建全面,高质量的数据库存在挑战.

研究的目的:

  • 通过30年的研究,开发一个强大的骨质诱导生物材料数据库.
  • 使用数据增强策略解决数据限制 (样本大小,缺失数据,稀疏性).
  • 通过ML识别影响骨质诱导性的关键因素,并通过ML优化生物材料设计.

主要方法:

  • 编制并验证了30年的骨质诱导生物材料研究数据库.
  • 实施数据增强战略,以克服数据稀缺性和质量问题.
  • 利用机器学习模型,包括部分依赖图 (PDP) 分析,用于模型解释和优化.

主要成果:

  • 数据增强策略实现了高性能指标:AUC 0.921,精度 0.839,回忆 0.833.
  • 确定了关键的骨质诱导性决定因素包括多孔性,骨形态遗传蛋白-2 (BMP-2) 和酸 (HA) 的比例.
  • 与数据库平均值 (10.97%) 相比,优化的生物材料显示出明显增加的新骨面积比率 (14.7 ± 7%).

结论:

  • 机器学习与数据增强策略相结合,有效地分析和加速骨感应生物材料的设计.
  • 优化毛孔结构和材料成分对于增强骨再生至关重要.
  • 这种方法显示出促进骨修复新生物材料开发的巨大潜力.