Use of Japanese big data from electronic medical records to investigate risk factors and identify their high-risk combinations for linezolid-induced thrombocytopenia
Use of Japanese big data from electronic medical records to investigate risk factors and identify their high-risk combinations for linezolid-induced thrombocytopenia
复制标题
DOI：
10.1007/s00228-023-03455-x
复制
发表时间：
2023-01-30
影响因子：
2.9
通讯作者：
Imai, Shungo
中科院分区：
文献类型：
--
作者：
Inoue, Yuki;Takekuma, Yoh;Imai, Shungo
血小板减少症是利奈唑胺（LZD）治疗的主要不良事件。影响LZD诱导的血小板减少症（LIT）的因素已在既往研究中报告。然而，与LIT有关的几个问题尚未澄清。在本研究中，我们使用日本的大数据来调查相关因素及其高风险组合，影响LIT.MethodsPatients服用LZD之间2006年5月和2020年10月被纳入本研究。LIT定义为血小板从基线减少30%或更多或血小板值<100，000/μ L。我们评估了影响LIT的因素和改变LIT风险的因素的组合，根据决策树（DT）分析，一个典型的机器学习method.ResultsWe成功招募了1399例患者和LIT发生在44.7%的患者（n = 626）。我们将肾功能、LZD持续时间、年龄和体重（BW）的实验室数据分类为较小的类别。多因素分析结果显示，LZD治疗时间延长，体重< 45 kg，估计肾小球滤过率（eGFR）< 30 mL/min/1.73 m2，DT分析显示，LZD持续时间>= 14天和eGFR < 30 mL/min/1.73 m（2）的组合风险最高结论本研究提取了四个危险因素，并确定了LIT的高风险组合，应密切监测具有这些危险因素的患者。
PurposeThrombocytopenia is a major event associated with linezolid (LZD) therapy. Factors affecting LZD-induced thrombocytopenia (LIT) have been reported in previous studies. However, several issues pertaining to LIT have not yet been clarified. In the present study, we used Japanese big data to investigate associated factors and their high-risk combinations that influence LIT.MethodsPatients administered LZD between May 2006 and October 2020 were included in this study. LIT was defined as either a 30% or more reduction from the baseline platelets or platelet values of < 100,000/mu L. We evaluated factors affecting LIT and combinations of factors that alter LIT risk according to a decision tree (DT) analysis, a typical machine learning method.ResultsWe successfully enrolled 1399 patients and LIT occurred in 44.7% of the patients (n = 626). We classified the laboratory data on renal function, LZD duration, age, and body weight (BW) into smaller categories. The results of multivariate analysis showed that prolonged LZD therapy, BW < 45 kg, estimated glomerular filtration rate (eGFR) < 30 mL/min/1.73 m(2), and dialysis were risk factors for LIT. The DT analysis revealed that the highest risk was a combination of LZD duration >= 14 days and eGFR < 30 mL/min/1.73 m(2).ConclusionsThe present study extracted four risk factors and identified high-risk combinations for LIT. Patients with these risk factors should be closely monitored.