From the Hubei Key Laboratory of Agricultural Bioinformatics, College of Informatics, Huazhong Agricultural University, Wuhan.
Departments of Gastroenterology.
Pancreas. 2021 Jul 1;50(6):873-878. doi: 10.1097/MPA.0000000000001839.
The objective of this study was to develop and validate a model, based on the blood biochemical (BBC) indexes, to predict the recurrence of acute pancreatitis patients.
We retrospectively enrolled 923 acute pancreatitis patients (586 in the primary cohort and 337 in the validation cohort) from January 2014 to December 2016. Aiming for an extreme imbalance between recurrent acute pancreatitis (RAP) and non-RAP patients (about 1:4), we designed BBC index selection using least absolute shrinkage and selection operator regression, along with an ensemble-learning strategy to obtain a BBC signature. Multivariable logistic regression was used to build the RAP predictive model.
The BBC signature, consisting of 35 selected BBC indexes, was significantly higher in patients with RAP (P < 0.001). The area under the curve of the receiver operating characteristic curve of BBC signature model was 0.6534 in the primary cohort and 0.7173 in the validation cohort. The RAP predictive nomogram incorporating the BBC signature, age, hypertension, and diabetes showed better discrimination, with an area under the curve of 0.6538 in the primary cohort and 0.7212 in the validation cohort.
Our study developed a RAP predictive nomogram with good performance, which could be conveniently and efficiently used to optimize individualized prediction of RAP.
本研究旨在开发和验证一种基于血液生化（BBC）指标的模型，以预测急性胰腺炎患者的复发情况。
我们回顾性纳入了 2014 年 1 月至 2016 年 12 月期间的 923 例急性胰腺炎患者（首发队列 586 例，验证队列 337 例）。为了使复发急性胰腺炎（RAP）和非 RAP 患者之间的严重失衡（约 1:4），我们采用最小绝对收缩和选择算子回归（LASSO）以及集成学习策略设计 BBC 指数选择，以获得 BBC 特征。多变量逻辑回归用于建立 RAP 预测模型。
RAP 患者的 BBC 特征（由 35 个选定的 BBC 指数组成）显著升高（P < 0.001）。在首发队列和验证队列中，BBC 特征模型的受试者工作特征曲线下面积分别为 0.6534 和 0.7173。纳入 BBC 特征、年龄、高血压和糖尿病的 RAP 预测列线图显示出更好的判别能力，在首发队列和验证队列中的曲线下面积分别为 0.6538 和 0.7212。
本研究开发了一种具有良好性能的 RAP 预测列线图，可方便、有效地用于优化 RAP 的个体化预测。
