Department of Neurosurgery, Cancer Prevention and Treatment Institute of Chengdu, Chengdu Fifth People's Hospital (The Second Clinical Medical College, Affiliated Fifth People's Hospital of Chengdu University of Traditional Chinese Medicine), Chengdu, China.
West China Fourth Hospital/West China School of Public Health, Sichuan University, Chengdu, China.
Front Public Health. 2022 Jun 28;10:910479. doi: 10.3389/fpubh.2022.910479. eCollection 2022.
Lumbar drainage is widely used in the clinic; however, forecasting lumbar drainage-related meningitis (LDRM) is limited. We aimed to establish prediction models using supervised machine learning (ML) algorithms.
We utilized a cohort of 273 eligible lumbar drainage cases. Data were preprocessed and split into training and testing sets. Optimal hyper-parameters were archived by 10-fold cross-validation and grid search. The support vector machine (SVM), random forest (RF), and artificial neural network (ANN) were adopted for model training. The area under the operating characteristic curve (AUROC) and precision-recall curve (AUPRC), true positive ratio (TPR), true negative ratio (TNR), specificity, sensitivity, accuracy, and kappa coefficient were used for model evaluation. All trained models were internally validated. The importance of features was also analyzed.
In the training set, all the models had AUROC exceeding 0.8. SVM and the RF models had an AUPRC of more than 0.6, but the ANN model had an unexpectedly low AUPRC (0.380). The RF and ANN models revealed similar TPR, whereas the ANN model had a higher TNR and demonstrated better specificity, sensitivity, accuracy, and kappa efficiency. In the testing set, most performance indicators of established models decreased. However, the RF and AVM models maintained adequate AUROC (0.828 vs. 0.719) and AUPRC (0.413 vs. 0.520), and the RF model also had better TPR, specificity, sensitivity, accuracy, and kappa efficiency. Site leakage showed the most considerable mean decrease in accuracy.
The RF and SVM models could predict LDRM, in which the RF model owned the best performance, and site leakage was the most meaningful predictor.
腰椎引流在临床上广泛应用，但对腰椎引流相关脑膜炎（LDRM）的预测有限。我们旨在使用有监督机器学习（ML）算法建立预测模型。
我们使用了 273 例符合条件的腰椎引流病例的队列。数据经过预处理并分为训练集和测试集。通过 10 折交叉验证和网格搜索来确定最佳超参数。采用支持向量机（SVM）、随机森林（RF）和人工神经网络（ANN）进行模型训练。使用受试者工作特征曲线下面积（AUROC）和精确召回曲线下面积（AUPRC）、真阳性率（TPR）、真阴性率（TNR）、特异性、敏感性、准确性和kappa 系数来评估模型。所有训练模型均进行内部验证。还分析了特征的重要性。
在训练集中，所有模型的 AUROC 均超过 0.8。SVM 和 RF 模型的 AUPRC 均超过 0.6，但 ANN 模型的 AUPRC 出人意料地低（0.380）。RF 和 ANN 模型的 TPR 相似，而 ANN 模型的 TNR 较高，特异性、敏感性、准确性和 kappa 效率较好。在测试集中，所建立模型的大多数性能指标均有所下降。然而，RF 和 AVM 模型仍保持了足够的 AUROC（0.828 对 0.719）和 AUPRC（0.413 对 0.520），RF 模型的 TPR、特异性、敏感性、准确性和 kappa 效率也更好。部位渗漏显示出最显著的平均准确性降低。
RF 和 SVM 模型可预测 LDRM，其中 RF 模型性能最佳，部位渗漏是最有意义的预测指标。
