Bray David P, Saad Hassan, Douglas James Miller, Grogan Dayton, Dawoud Reem A, Chow Jocelyn, Deibert Christopher, Pradilla Gustavo, Nduom Edjah K, Olson Jeffrey J, Alawieh Ali M, Hoang Kimberly B
Department of Neurosurgery, Emory University School of Medicine, Atlanta, Georgia, USA.
Emory School of Medicine, Atlanta, Georgia, USA.
Neurooncol Adv. 2022 Sep 13;4(1):vdac145. doi: 10.1093/noajnl/vdac145. eCollection 2022 Jan-Dec.
Resection of posterior fossa tumors (PFTs) can result in hydrocephalus that requires permanent cerebrospinal fluid (CSF) diversion. Our goal was to prospectively validate a machine-learning model to predict postoperative hydrocephalus after PFT surgery requiring permanent CSF diversion.
We collected preoperative and postoperative variables on 518 patients that underwent PFT surgery at our center in a retrospective fashion to train several statistical classifiers to predict the need for permanent CSF diversion as a binary class. A total of 62 classifiers relevant to our data structure were surveyed, including regression models, decision trees, Bayesian models, and multilayer perceptron artificial neural networks (ANN). Models were trained using the ( = 518) retrospective data using 10-fold cross-validation to obtain accuracy metrics. Given the low incidence of our positive outcome (12%), we used the positive predictive value along with the area under the receiver operating characteristic curve (AUC) to compare models. The best performing model was then prospectively validated on a set of 90 patients.
Twelve percent of patients required permanent CSF diversion after PFT surgery. Of the trained models, 8 classifiers had an AUC greater than 0.5 on prospective testing. ANNs demonstrated the highest AUC of 0.902 with a positive predictive value of 83.3%. Despite comparable AUC, the remaining classifiers had a true positive rate below 35% (compared to ANN, < .0001). The negative predictive value of the ANN model was 98.8%.
ANN-based models can reliably predict the need for ventriculoperitoneal shunt after PFT surgery.
后颅窝肿瘤（PFTs）切除可导致脑积水，这需要永久性脑脊液（CSF）分流。我们的目标是前瞻性验证一个机器学习模型，以预测PFT手术需要永久性CSF分流后的术后脑积水。
我们以回顾性方式收集了在我们中心接受PFT手术的518例患者的术前和术后变量，以训练几个统计分类器，将永久性CSF分流的需求预测为二元分类。共调查了62个与我们的数据结构相关的分类器，包括回归模型、决策树、贝叶斯模型和多层感知器人工神经网络（ANN）。使用（ = 518）回顾性数据，通过10倍交叉验证对模型进行训练，以获得准确性指标。鉴于我们的阳性结果发生率较低（12%），我们使用阳性预测值以及受试者操作特征曲线下面积（AUC）来比较模型。然后在一组90例患者中对表现最佳的模型进行前瞻性验证。
12%的患者在PFT手术后需要永久性CSF分流。在训练的模型中，8个分类器在前瞻性测试中的AUC大于0.5。人工神经网络的AUC最高，为0.902，阳性预测值为83.3%。尽管AUC相当，但其余分类器的真阳性率低于35%（与人工神经网络相比， <.0001）。人工神经网络模型的阴性预测值为98.8%。
基于人工神经网络的模型可以可靠地预测PFT手术后脑室腹腔分流的需求。
