Early Warning Models to Estimate the 30-Day Mortality Risk After Stent Placement for Patients with Malignant Biliary Obstruction
Early Warning Models to Estimate the 30-Day Mortality Risk After Stent Placement for Patients with Malignant Biliary Obstruction
复制标题
评估恶性胆道梗阻患者支架置入后 30 天死亡风险的早期预警模型
DOI：
10.1007/s00270-019-02331-5
复制
发表时间：
2019-09
影响因子：
2.9
通讯作者：
Teng Gao-Jun
中科院分区：
文献类型：
--
作者：
Zhou Hai-Feng;Lu Jian;Zhu Hai-Dong;Guo Jin-He;Huang Ming;Ji Jian-Song;Lv Wei-Fu;Li Yu-Liang;Xu Hao;Chen Li;Zhu Guang-Yu;Teng Gao-Jun
PurposeTo开发，验证，并比较早期预警模型的30天死亡率风险的恶性胆道梗阻（MBO）患者接受经皮经鞘胆道支架置入术（PTBS）。材料和方法2013年1月至2018年10月，这项多中心回顾性研究包括299例MBOs谁接受PTBS。训练集由来自4个队列的166例患者组成，另外两个独立队列被分配为外部验证集A和B，分别有75例患者和58例患者。Logistic模型和人工神经网络（ANN）模型被开发来预测PTBS后30天死亡率的风险。这两个模型的预测性能进行了验证内部和externals. ResultsANN模型有较高的值的曲线下面积比Logistic模型在训练集（0.819比0.797），特别是在验证集A（0.802比0.714）和B（0.732比0.568）。两种模型在三组中均具有较高的准确性（75.9-83.1%）。沿着高特异性，ANN模型提高了灵敏度。净重新分类的改善和综合歧视的改善也表明，人工神经网络模型导致预测能力的改善相比，logistic model.ConclusionsEarly预警模型提出了预测的风险与MBO患者PTBS后30天的死亡率。人工神经网络模型比逻辑斯蒂模型具有更高的精度和更好的泛化能力。
PurposeTo develop, validate, and compare early warning models of the 30-day mortality risk for patients with malignant biliary obstruction (MBO) undergoing percutaneous transhepatic biliary stent placement (PTBS).Materials and MethodsBetween January 2013 and October 2018, this multicenter retrospective study included 299 patients with MBOs who underwent PTBS. The training set consisted of 166 patients from four cohorts, and another two independent cohorts were allocated as external validation sets A and B with 75 patients and 58 patients, respectively. A logistic model and an artificial neural network (ANN) model were developed to predict the risk of 30-day mortality after PTBS. The predictive performance of these two models was validated internally and externally.ResultsThe ANN model had higher values of area under the curve than the logistic model in the training set (0.819 vs 0.797), especially in the validation sets A (0.802 vs 0.714) and B (0.732 vs 0.568). Both models had high accuracy in the three sets (75.9–83.1%). Along with a high specificity, the ANN model improved the sensitivity. The net reclassification improvement and integrated discrimination improvement also demonstrated that the ANN model led to improvements in predictive ability compared with the logistic model.ConclusionsEarly warning models were proposed to predict the risk of 30-day mortality after PTBS in patients with MBO. The ANN model has higher accuracy and better generalizability than the logistic model.
登录
查看更多内容
影响因子：
2.4
作者：
Ji, Jun Ho;Song, Haa-Na;Kang, Jung-Hun
通讯作者：
Kang, Jung-Hun
影响因子：
7.7
作者：
Enochsson, Lars;Swahn, Fredrik;Persson, Gunnar
通讯作者：
Persson, Gunnar
影响因子：
2
作者：
Alabiso ME;Iasiello F;Pellino G;Iacomino A;Roberto L;Pinto A;Riegler G;Selvaggi F;Reginelli A
通讯作者：
Reginelli A
影响因子：
5.9
作者：
Tapping, C. R.;Byass, O. R.;Cast, J. E. I.
通讯作者：
Cast, J. E. I.
DOI：
10.1093/med/9780199796816.003.0041
发表时间：
2013-02
期刊：
--
影响因子：
--
作者：
H. Lavretsky;M. Sajatovic;C. Reynolds
通讯作者：
H. Lavretsky;M. Sajatovic;C. Reynolds