他克莫司对中国和印度特发性膜性肾病患者蛋白尿的影响：机器学习研究的结果。
Effects of tacrolimus on proteinuria in Chinese and Indian patients with idiopathic membranous nephropathy: the results of machine learning study.
机构信息
Department of Orthopaedics, The Affiliated Jiangyin Clinical College of Xuzhou Medical University, Jiangyin, 214400, Jiangsu, China.
Department of Pharmacy, Taixing People's Hospital, Taixing, 225400, Jiangsu, China.
出版信息
Int Urol Nephrol. 2024 Sep;56(9):3047-3055. doi: 10.1007/s11255-024-04056-y. Epub 2024 Apr 20.
PURPOSE
The present study aims to explore the effects of tacrolimus on proteinuria in patients with idiopathic membranous nephropathy (IMN) and recommend an appropriate dosage schedule via machine learning method.
METHODS
The E model was constructed to analyze the effects of tacrolimus on proteinuria in patients with IMN. Data were mined from published literature and machine learning was built up with E model, among which the efficacy indicator was proteinuria change rates from baseline. 463 IMN patients were included for modeling, and tacrolimus therapeutic window concentrations were 4-10 ng/ml.
RESULTS
In machine learning model, the E from tacrolimus effecting proteinuria in IMN patients was -72.7%, the ET was 0.43 months, and the time to achieving 25% E, 50% E, 75% E, and 80% (plateau) E of tacrolimus on proteinuria in patients with IMN were 0.15, 0.43, 1.29, and 1.72 months, respectively.
CONCLUSION
For achieving better therapeutic effects from tacrolimus on proteinuria in patients with IMN, tacrolimus concentration range need to be maintained at 4-10 ng/ml for at least 1.72 months.
目的
本研究旨在通过机器学习方法探讨他克莫司对特发性膜性肾病（IMN）患者蛋白尿的影响，并推荐合适的剂量方案。
方法
构建 E 模型分析他克莫司对 IMN 患者蛋白尿的影响。从已发表的文献中挖掘数据，并使用 E 模型建立机器学习，其中疗效指标为蛋白尿从基线的变化率。纳入 463 例 IMN 患者进行建模，他克莫司治疗窗浓度为 4-10ng/ml。
结果
在机器学习模型中，他克莫司对 IMN 患者蛋白尿的 E 值为-72.7%，ET 为 0.43 个月，达到他克莫司对 IMN 患者蛋白尿的 25%、50%、75%和 80%（平台）E 的时间分别为 0.15、0.43、1.29 和 1.72 个月。
结论
为了使他克莫司对 IMN 患者蛋白尿的治疗效果更好，他克莫司浓度范围需要至少维持在 4-10ng/ml 1.72 个月。
Zotero 插件