ChromoCheck:使用支持矢量机器学习模型预测产后染色体三胞胎病例
Nabras Al-Mahrami1, Nuha Al Jabri1, Amal A W Sallam2
1Medical Laboratory Sciences Program, Health Sciences, Oman College of Health Sciences, P.O. Box 3720, Muscat 112, Oman.
Genes
|June 26, 2025
概括
这项研究引入了一种机器学习模型,用于预测产后染色体三症. 支持矢量机实现了高精度,证明了其提高细胞遗传诊断的潜力.
科学领域:
- 遗传学 是一个遗传学.
- 计算生物学 计算生物学
- 医学诊断 医学诊断 医学诊断
背景情况:
- 型定型是一种传统的方法来识别染色体异常,如三症.
- 尽管它具有历史意义,但在实验室程序中,型造型具有局限性.
- 机器学习为医学诊断提供了先进的预测能力.
研究的目的:
- 开发和评估用于预测产后染色体三症的机器学习模型.
- 为此预测任务使用支向量机 (SVM).
- 用关键指标和交叉验证来评估模型的性能.
主要方法:
- 分析了2013-2023年946个新生儿记录的数据集.
- 甲状腺激素和甲状腺刺激激素水平是关键特征.
- 一个具有线性,辐射和多项式内核的SVM模型使用leave-one-out交叉验证进行了测试.
主要成果:
- 线性内核表现出最佳的分类性能,训练准确率为81%,测试准确率为82%.
- 获得了高灵敏度 (97-98%) 和特异性 (79-80%).
- 曲线下的面积在训练数据中达到0.89,在测试数据中达到0.90.
- 该模型被部署为一个Web工具,ChromoCheck.
结论:
- 机器学习模型可以显著增强传统的细胞遗传诊断方法.
- 开发的SVM模型显示了三症预测中临床决策的前景.
- 这种方法为提高遗传疾病诊断的效率和准确性提供了有价值的工具.
更多相关视频
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
8.4K
10:04A Neural Network-Based Identification of Developmentally Competent or Incompetent Mouse Fully-Grown Oocytes
Published on: March 3, 2018
6.8K
相关概念视频
Meiosis vs. Mitosis
58.4K
Cell division is necessary for growth and reproduction in organisms. Mitosis aids cell growth and development by dividing somatic cells. In contrast, meiosis causes the division of germ cells and plays an essential role in sexual reproduction. Due to their unique functional requirements, mitosis and meiosis differ from each other in multiple aspects.
Before the start of mitosis and meiosis I, the cell synthesizes DNA, resulting in two homologous copies of each chromosome. DNA synthesis is...
Before the start of mitosis and meiosis I, the cell synthesizes DNA, resulting in two homologous copies of each chromosome. DNA synthesis is...
58.4K
Karyotyping
62.5K
Overview
62.5K
