对同一个人工智能工具的两个版本的性能进行比较研究,用于对儿科骨成熟度的评估
Grammatina Boitsios1, Thomas Saliba2, Paolo Simoni3
1Department of Radiology, Hôpital Delta, Centre Hospitalier Interrégional Edith Cavell (CHIREC), Brussels, Belgium. gboitsios@gmail.com.
European radiology
|January 7, 2026
概括
最新版本的BoneXpert (版本3) 在估计儿童骨年龄方面显示了与版本2相似的准确性. 然而,版本3提供了更高和更可变的骨年龄标准偏差分数 (SDS),将报告范围扩展到年轻年龄.
科学领域:
- 儿科内分泌学 儿科内分泌学
- 放射学 放射学是一门学科.
- 医学中的人工智能.
背景情况:
- 准确的骨龄评估对于诊断和管理儿童生长障碍至关重要.
- 像BoneXpert这样的人工智能驱动的工具旨在标准化和提高骨年龄估计的准确性.
- 评估AI算法的更新对于临床可靠性至关重要.
研究的目的:
- 为了比较BoneXpert版本3与版本2在健康儿童的骨年龄和骨健康指数 (BHI) 估计中的性能.
- 使用平均绝对误差 (MAE) 和根平均平方误差 (RMSE) 评估准确性.
- 评估骨年龄标准偏差分数 (SDS) 的差异及其可变性.
主要方法:
- 对449名健康儿童 (231名女性,218名男性) 的回顾性分析.
- 使用BoneXpert版本2和3估计的骨龄.
- 计算了与时间年龄 (R2),MAE和RMSE的相关性.
- 按性别和年龄组分层的分析;不同版本的骨龄SDS和BHI的比较.
主要成果:
- 这两种版本都与时间年龄有很强的相关性 (R2 ≈ 0.91-0.93).
- MAE和RMSE在版本之间没有显著差异 (MAE ≈ 0.88-0.89年,RMSE ≈ 1.12-1.15).
- 与版本2 (平均值0.19,SDS1.29) 相比,版本3的SDS值较高且变化更大,并且将SDS报告扩展到更年轻的儿童. BHI和BHI SDS没有显著差异.
结论:
- 这两种BoneXpert版本都对健康儿童的骨年龄评估有效和同样准确.
- 版本3通过提供更高和更可变的骨年龄SDS,并将报告扩展到年轻年龄组,提供了优势.
- 持续验证人工智能算法更新对于可靠的临床应用是必要的.
相关概念视频
Improving Translational Accuracy
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
Improving Translational Accuracy
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
Multiple Comparison Tests
Multiple comparison test, abbreviated as MCT, is a post hoc analysis generally performed after comparing multiple samples with one or more tests. An MCT will help identify a significantly different sample among multiple samples or a factor among multiple factors.
It would be easy to compare two samples using a significance alpha level of 0.05. In other words, there is only one sample pair to be compared. However, it would be difficult to identify a significantly different sample if the number...
It would be easy to compare two samples using a significance alpha level of 0.05. In other words, there is only one sample pair to be compared. However, it would be difficult to identify a significantly different sample if the number...


