构建和验证用于预测宫内皮质新生病II级+的模型:通过机器学习进行横截面人口研究
Juan He1,2, Kang-Jia Chen1,3, Ya-Xing Fang1,2
1Department of Gynecology, Maternal and Child Medical Center of Anhui Medical University, Hefei, Anhui, 230032, People's Republic of China.
将人类乳头瘤病毒 (HPV) 测试与ThinPrep细胞学测试 (TCT) 和临床数据相结合,显著改善了II级或更高 (CINII+) 的宫内皮质瘤的预测. 这种综合方法可以提高早期宫癌查的准确性.
科学领域:
- 妇科 妇科 妇科 妇科
- 在瘤学瘤学.
- 医疗信息学 医疗信息学
背景情况:
- 宫癌是全球女性的主要恶性瘤.
- 早期查至关重要,但缺乏有效的宫病变预测模型.
- 准确预测宫内皮质瘤II级或更高 (CINII+) 是对及时干预至关重要的.
研究的目的:
- 使用机器学习开发CINII+的预测模型.
- 将ThinPrep细胞学测试 (TCT) +人类乳头瘤病毒 (HPV) 测试与临床数据相比TCT +传统临床数据集成模型的疗效进行比较.
- 评估不同机器学习模型在CINII+检测中的预测性能.
主要方法:
- 从接受宫癌查 (2020-2024) 的妇女收集的临床数据.
- 应用了10个机器学习算法来构建两个模型:模型1 (TCT+HPV+临床数据) 和模型2 (TCT+传统临床数据).
- 使用AUC,校准曲线和决策曲线分析评估模型性能.
主要成果:
- 鉴定出HPV阳性,TCT显示HSIL,大肠镜检查结果和早期怀孕年龄是CINII+的预测因素.
- 模型1 (TCT+HPV+临床数据) 的预测效率明显高于模型2 (TCT+临床数据).
- 模型之间的AUC差异是统计学上显著的 (P=0.006在训练中,P=0.035在测试中).
结论:
- 与仅使用TCT的模型相比,TCT+HPV集成模型在预测CINII+方面表现优异.
- 将HPV检测纳入常规查中可以提高宫病变的早期诊断准确度.
- 这项研究支持HPV测试的整合,以改善宫癌查结果.
更多相关视频
03:05Author Spotlight: Advancing Early Detection and Treatment of Gastrointestinal Tumors
Published on: February 16, 2024
07:13Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
Published on: April 18, 2025
相关概念视频
Mouse Models of Cancer Study
The development of transgenic, knockout, and knock-in mice has led to an exponential increase in their use as model organisms in research,...
Mouse Models of Cancer Study
The development of transgenic, knockout, and knock-in mice has led to an exponential increase in their use as model organisms in research,...
Mechanistic Models: Compartment Models in Individual and Population Analysis
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
Steps in Outbreak Investigation
