Abouzari Mehdi, Goshtasbi Khodayar, Sarna Brooke, Khosravi Pooya, Reutershan Trevor, Mostaghni Navid, Lin Harrison W, Djalilian Hamid R
Division of Neurotology and Skull Base Surgery, Department of Otolaryngology-Head and Neck Surgery University of California Irvine California.
Division of Pediatric Otolaryngology Children's Hospital of Orange County Orange California.
Laryngoscope Investig Otolaryngol. 2020 Feb 17;5(2):278-285. doi: 10.1002/lio2.362. eCollection 2020 Apr.
To compare two statistical models, namely logistic regression and artificial neural network (ANN), in prediction of vestibular schwannoma (VS) recurrence.
Seven hundred eighty-nine patients with VS diagnosis completed an online survey. Potential predictors for recurrence were derived from univariate analysis by reaching the cut off value of .05. Those nine potential predictors were years since treatment, surgeon's specialty, resection amount, and having incomplete eye closure, dry eye, double vision, facial pain, seizure, and voice/swallowing problem as a complication following treatment. Multivariate binary logistic regression model was compared with a four-layer 9-5-10-1 feedforward backpropagation ANN for prediction of recurrence.
The overall recurrence rate was 14.5%. Significant predictors of recurrence in the regression model were years since treatment and resection amount (both < .001). The regression model did not show an acceptable performance (area under the curve [AUC] = 0.64; = .27). The regression model's sensitivity and specificity were 44% and 69%, respectively and correctly classified 56% of cases. The ANN showed a superior performance compared to the regression model (AUC = 0.79; = .001) with higher sensitivity (61%) and specificity (81%), and correctly classified 70% of cases.
The constructed ANN model was superior to logistic regression in predicting patient-answered VS recurrence in an anonymous survey with higher sensitivity and specificity. Since artificial intelligence tools such as neural networks can have higher predictive abilities compared to logistic regression models, continuous investigation into their utility as complementary clinical tools in predicting certain surgical outcomes is warranted.
比较逻辑回归和人工神经网络（ANN）这两种统计模型在预测前庭神经鞘瘤（VS）复发方面的效果。
789例确诊为VS的患者完成了一项在线调查。通过单因素分析得出P值截止为0.05时的复发潜在预测因素。这九个潜在预测因素包括治疗后的年份、外科医生的专业、切除量，以及治疗后出现的不完全眼睑闭合、干眼、复视、面部疼痛、癫痫发作和声音/吞咽问题等并发症。将多变量二元逻辑回归模型与一个四层9-5-10-1前馈反向传播人工神经网络进行比较，以预测复发情况。
总体复发率为14.5%。回归模型中复发的显著预测因素是治疗后的年份和切除量（均P<0.001）。回归模型的表现不尽人意（曲线下面积[AUC]=0.64；P=0.27）。回归模型的敏感性和特异性分别为44%和69%，正确分类了56%的病例。与回归模型相比，人工神经网络表现更优（AUC=0.79；P=0.001），敏感性（61%）和特异性（81%）更高，正确分类了70%的病例。
在一项匿名调查中，构建的人工神经网络模型在预测患者回答的VS复发方面优于逻辑回归，具有更高的敏感性和特异性。由于神经网络等人工智能工具相比逻辑回归模型可能具有更高的预测能力，因此有必要持续研究它们作为预测某些手术结果的辅助临床工具的效用。
