Pharmacy Department, Sir Run Run Shaw Hospital, School of Medicine, Zhejiang University, Hangzhou, 310020, China.
Zhejiang Cancer Hospital, Hangzhou, Zhejiang, 310022, China.
BMC Med Inform Decis Mak. 2024 Oct 4;24(1):284. doi: 10.1186/s12911-024-02694-x.
In clinical practice, the incidence of hypofibrinogenemia (HF) after tigecycline (TGC) treatment significantly exceeds the probability claimed by drug manufacturers.
We aimed to identify the risk factors for TGC-associated HF and develop prediction and survival models for TGC-associated HF and the timing of TGC-associated HF.
This single-center retrospective cohort study included 222 patients who were prescribed TGC. First, we used binary logistic regression to screen the independent factors influencing TGC-associated HF, which were used as predictors to train the extreme gradient boosting (XGBoost) model. Receiver operating characteristic curve (ROC), calibration curve, decision curve analysis (DCA), and clinical impact curve analysis (CICA) were used to evaluate the performance of the model in the verification cohort. Subsequently, we conducted survival analysis using the random survival forest (RSF) algorithm. A consistency index (C-index) was used to evaluate the accuracy of the RSF model in the verification cohort.
Binary logistic regression identified nine independent factors influencing TGC-associated HF, and the XGBoost model was constructed using these nine predictors. The ROC and calibration curves showed that the model had good discrimination (areas under the ROC curves (AUC) = 0.792 [95% confidence interval (CI), 0.668-0.915]) and calibration ability. In addition, DCA and CICA demonstrated good clinical practicability of this model. Notably, the RSF model showed good accuracy (C-index = 0.746 [95%CI, 0.652-0.820]) in the verification cohort. Stratifying patients treated with TGC based on the RSF model revealed a statistically significant difference in the mean survival time between the low- and high-risk groups.
The XGBoost model effectively predicts the risk of TGC-associated HF, whereas the RSF model has advantages in risk stratification. These two models have significant clinical practical value, with the potential to reduce the risk of TGC therapy.
在临床实践中，替加环素（TGC）治疗后低纤维蛋白原血症（HF）的发生率明显超过了药物制造商声称的概率。
我们旨在确定 TGC 相关 HF 的危险因素，并为 TGC 相关 HF 及 TGC 相关 HF 发生时间开发预测和生存模型。
这项单中心回顾性队列研究纳入了 222 例接受 TGC 治疗的患者。首先，我们使用二项逻辑回归筛选影响 TGC 相关 HF 的独立因素，这些因素被用作训练极端梯度提升（XGBoost）模型的预测因子。我们使用受试者工作特征曲线（ROC）、校准曲线、决策曲线分析（DCA）和临床影响曲线分析（CICA）来评估模型在验证队列中的性能。随后，我们使用随机生存森林（RSF）算法进行生存分析。一致性指数（C-index）用于评估 RSF 模型在验证队列中的准确性。
二项逻辑回归确定了 9 个影响 TGC 相关 HF 的独立因素，我们使用这 9 个预测因子构建了 XGBoost 模型。ROC 和校准曲线显示该模型具有良好的区分度（ROC 曲线下面积（AUC）=0.792[95%置信区间（CI）：0.668-0.915]）和校准能力。此外，DCA 和 CICA 显示了该模型良好的临床实用性。值得注意的是，RSF 模型在验证队列中具有良好的准确性（C-index=0.746[95%CI：0.652-0.820]）。基于 RSF 模型对接受 TGC 治疗的患者进行分层，发现低风险组和高风险组之间的平均生存时间存在统计学显著差异。
XGBoost 模型可有效预测 TGC 相关 HF 的风险，而 RSF 模型在风险分层方面具有优势。这两种模型具有重要的临床实用价值，有可能降低 TGC 治疗的风险。
