通过机器学习对成年移植患者甘西克洛维尔暴露的估计
Hamza Sayadi1, Yeleen Fromage1, Marc Labriffe1,2
1Department of Pharmacology, Toxicology and Pharmacovigilance, CHU de Limoges, Limoges, France.
The AAPS journal
|February 28, 2025
概括
机器学习模型使用肌素清除和有限的药物度在移植患者中准确估计甘西克洛维尔 (GCV) AUC0-24h. 这种方法优化了对瓦尔甘西克洛维尔的治疗药物监测,有效预防感染.
科学领域:
- 药理动力学和药理动力学
- 机器学习在医学中的应用
- 移植医学 移植医学
背景情况:
- 瓦尔甘西克洛维尔 (GCV) 预防了移植后的细胞巨乳病毒感染.
- 剂量根据肌素清除率 (CrCL) 进行调整,以达到目标GCV AUC0-24h (40-60 mg*h/L).
- 当前的剂量调整可能导致药物暴露低于最佳水平 (过度或不足).
研究的目的:
- 开发和验证用于精确估计GCV AUC0-24h的机器学习 (ML) 算法.
- 改进治疗药物监测策略,用于固体器官移植接受者的瓦尔甘西克洛维尔.
主要方法:
- 来自人口药理动力学模型的模拟患者数据用于培训 (75%) 和测试 (25%).
- 三组ML算法 (XGBoost) 使用CrCL和2或3个GCV度进行训练.
- 验证使用独立的模拟数据集和真实患者数据进行,与MAP-BE相比.
主要成果:
- 使用3种度的XGBoost模型显示了最高的准确性,在测试数据集中相对偏差低 (-0.02%至1.5%) 和RMSE (2.6%至8.5%).
- 验证数据集显示出强大的性能,相对偏差在1.5%至5.8%之间,RMSE在8.5%至19.7%之间.
- ML算法,特别是那些使用2个度对真实患者数据的算法,显示了1.26%的相对偏差和12.68%的RMSE,表现优于或匹配MAP-BE.
结论:
- 机器学习模型,特别是XGBoost,可以在有限的数据 (CrCL和少数度) 中准确估计GCV AUC0-24h.
- 这些ML模型为优化移植患者的瓦尔甘西克洛维尔剂量和治疗药物监测提供了一个有希望的策略.
- 开发的算法显示出良好的概括性和稳定性,支持其临床实用性.
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
8.2K
09:16Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis
Published on: June 18, 2020
6.8K
相关概念视频
Estimation of k and VD of Aminoglycosides
Aminoglycosides are a class of antibiotics used to treat various bacterial infections. Clinicians must determine the elimination rate constant (k) and volume of distribution (VD) to optimize therapeutic efficacy and minimize toxicity. The k value represents the rate at which the drug is removed from the body, and the VD reflects the degree to which the drug distributes into body tissues. Accurately estimating these parameters allows healthcare professionals to tailor drug dosing to individual...
Drug Dosing in Renal Diseases: Estimation of Glomerular Filtration Rate Based on Serum Creatinine Concentration
Glomerular filtration rate (GFR) can be estimated from serum creatinine using the modification of diet in renal disease (MDRD) formula or the chronic kidney disease–epidemiology collaboration (CKD–EPI) equation. Both methods are widely used in clinical practice to assess kidney function and guide treatment decisions.The MDRD equation does not require weight or height measurements and is normalized to the body surface area of 1.73 m², considered the average adult surface area. This equation is...
