Telemedicine for Neurosurgery Consultations at a Pituitary Center of Excellence: Patient Preference and Willingness to Proceed with Surgery.

Objective The purpose of this study was to evaluate pituitary tumor patient satisfaction with telemedicine, patient preference for telemedicine, potential socioeconomic benefit of telemedicine, and patients' willingness to proceed with surgery based on a telemedicine visit alone. Method In total, 134 patients who had pituitary surgery and a telemedicine visit during the coronavirus disease 2019 (COVID-19) pandemic (April 23, 2020-March 4, 2021) were called to participate in a 13-part questionnaire. Chi-square, ANOVA, and Wilcoxon Rank Sum tests were used to determine significance. Result Of 134 patients contacted, 90 responded (67%). Ninety-five percent were "satisfied" or "very satisfied" with their telemedicine visit, with 62% stating their visit was "the same" or "better" than previous in-person appointments. Eighty-two percent of the patients rated their telemedicine visit as "easy" or "very easy." On average, patients saved 150 minutes by using telemedicine compared with patient reported in-person visit times. Seventy-seven percent of patients reported the need to take off from work for in-person visits, compared with just 12% when using telemedicine. Forty-nine percent of patients preferred in-person visits, 34% preferred telemedicine, and 17% had no preference. Fifty percent of patients said they would feel comfortable proceeding with surgery based on a telemedicine visit alone. Patients with both initial evaluation and follow-up conducted via telemedicine were more likely to feel comfortable proceeding with surgery based on a telemedicine visit alone compared with patients who had only follow-up telemedicine visits ( p = 0.051). Conclusion Many patients are satisfied with telemedicine visits and feel comfortable proceeding with surgery based on a telemedicine visit alone. Telemedicine is an important adjunct to increase access to care at a Pituitary Center of Excellence.

Artificial neural networks predict the need for permanent cerebrospinal fluid diversion following posterior fossa tumor resection.

Background: 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. Methods: 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 (N = 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. Results: 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, P < .0001). The negative predictive value of the ANN model was 98.8%. Conclusions: ANN-based models can reliably predict the need for ventriculoperitoneal shunt after PFT surgery.