Prediction of vestibular schwannoma recurrence using artificial neural network

Abstract

Objectives: To compare two statistical models, namely logistic regression and artificial neural network (ANN), in prediction of vestibular schwannoma (VS) recurrence.Methods: 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 P 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.Results: The overall recurrence rate was 14.5%. Significant predictors of recurrence in the regression model were years since treatment and resection amount (both P < .001). The regression model did not show an acceptable performance (area under the curve [AUC] = 0.64; P = .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; P = .001) with higher sensitivity (61%) and specificity (81%), and correctly classified 70% of cases.Conclusion: 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.Mehdi Abouzari and Khodayar Goshtasbi contributed equally to this manuscript.

Deep Learning for Classification of Pediatric Otitis Media

“…As the most widespread algorithm of deep learning, CNNs have shown human‐level performance in automated analysis of medical images 11 . In otolaryngology, AI using neural networks has been applied to clinical data, such as gene expression profiles, audiological data, endoscopic and radiological images to improve detection and complete extirpation of head and neck malignancies, predict auditory and speech perception outcomes, and develop expert systems in classification and evaluation 12–14 . One of the important challenges of AI in otolaryngology is high‐quality and large quantities of patient data collection 13 .…”

Convolutional Neural Networks for Classifying Laterality of Vestibular Schwannomas on Single MRI Slices—A Feasibility Study

“…Four of those results were unrelated to radiology [19][20][21][22]. One publication used an NN to predict vs. recurrence following surgery from clinical parameters in tabular format [23]. The remaining four publications used NNs to segment VS for either radiotherapy planning or response assessment [24][25][26][27].…”

Artificial Neural Network as a Tool to Predict Facial Nerve Palsy in Parotid Gland Surgery for Benign Tumors

“…Previous articles have investigated the application of ANN in otolaryngology—head and neck surgery. Abouzari et al compare an ANN model with a logistic regression model to predict the risk of vestibular schwannoma recurrence, obtaining a higher sensitivity and specificity with the use of the ANN [ 13 ]. Alabi et al published a study in which they summarize data from Finland and Brazil to estimate the risk of locoregional recurrence in early stage SCC of the oral tongue.…”

“…Recently, different studies have been published about the use of ANNs related to the medical and the otolaryngological field and to estimate prognosis in some tumors [ 8 , 9 , 10 , 11 , 12 , 13 , 14 ]. However, the use of ANNs specifically to evaluate the risk of FNI after parotid gland surgery for benign tumors has not been previously studied.…”