迈向机器学习驱动的数字双胞胎,用于实时激素生物传感在个性化的不孕症护理中
IEEE transactions on bio-medical engineering
|March 13, 2026
概括
这项研究开发了一种机器学习生物传感器数字双胞胎,用于个性化不孕症治疗. K-最近邻居模型在预测激素水平方面取得了高准确性,为智能健康监测奠定了基础.
科学领域:
- 生物医学工程 生物医学工程
- 数字健康数字健康
- 精准医学是一门精准的医学.
背景情况:
- 个性化的医疗保健需要先进的解决方案,而不仅仅是适合所有人的方法.
- 数字双胞胎 (DT) 技术通过监控,模拟和预测为个性化医疗提供实时虚拟复制品.
研究的目的:
- 开发一种机器学习驱动的生物传感器数字双胞胎,用于个性化的不孕症治疗.
- 将生物传感器DT与智能健康监测系统集成.
- 使用实验数据复制基于场效应晶体管 (FET) 的生物传感器的行为.
主要方法:
- 训练了一个数字双胞胎使用实验数据从纳米网BioFET原型功能化与17β-雌二醇aptamers.
- 评估了七个监督机器学习算法,从电气参数 (Vg,Isd) 中预测激素度.
- 使用Leave-One-Biosensor-Out验证来评估跨设备的概括性.
主要成果:
- 该K-最近邻居 (KNN) 模型显示了最高的预测准确性 (R2 = 0.99,CV-R2 = 0.98,RMSE = 11.87 pg/mL).
- 该KNN模型显示了强大的跨设备概括 (R2 = 0.59),证实了其捕捉非线性关系的能力.
- 该模型在独立制造的传感器中成功地被通用化.
结论:
- 开发的模型是生物传感器数字双胞胎的验证预测核心.
- 该框架支持数据驱动的生物传感器数字双胞胎,用于在个性化的不孕症护理中进行智能健康监测.
- 未来的工作将重点关注适应性临床应用的实时同步和闭环反.
相关概念视频
01:33Hormonal Regulation
36.7K
The renin-aldosterone system is an endocrine system which guides the renal absorption of water and electrolytes, thus managing blood pressure and osmoregulation. Activation of the system begins in the kidneys with a small cluster of cells adjacent to the afferent and efferent blood vessels of the renal corpuscle. As the nephrons are filtering blood, juxtaglomerular cells monitor blood pressure. If they detect a decrease in pressure, they release the hormone renin into the bloodstream.
36.7K
01:40Hormonal Regulation
49.4K
Hormones regulate a significant portion of digestion through activation of the neuroendocrine system. The neuroendocrine system of digestion contains many different hormones all with multiple functions that are both, directly and indirectly, involved in digestion.
49.4K
01:08Intracellular Hormone Receptors
62.0K
Lipid-soluble hormones diffuse across the plasma and nuclear membrane of target cells to bind to their specific intracellular receptors. These receptors act as transcription factors that regulate gene expression and protein synthesis in the target cell
62.0K