Computer-assisted EEG diagnostic review for idiopathic generalized epilepsy.

Epilepsy diagnosis can be costly, time-consuming, and not uncommonly inaccurate. The reference standard diagnostic monitoring is continuous video-electroencephalography (EEG) monitoring, ideally capturing all events or concordant interictal discharges. Automating EEG data review would save time and resources, thus enabling more people to receive reference standard monitoring and also potentially heralding a more quantitative approach to therapeutic outcomes. There is substantial research into the automated detection of seizures and epileptic activity from EEG. However, automated detection software is not widely used in the clinic, and despite numerous published algorithms, few methods have regulatory approval for detecting epileptic activity from EEG. This study reports on a deep learning algorithm for computer-assisted EEG review. Deep convolutional neural networks were trained to detect epileptic discharges using a preexisting dataset of over 6000 labelled events in a cohort of 103 patients with idiopathic generalized epilepsy (IGE). Patients underwent 24-hour ambulatory outpatient EEG, and all data were curated and confirmed independently by two epilepsy specialists (Seneviratne et al., 2016). The resulting automated detection algorithm was then used to review diagnostic scalp EEG for seven patients (four with IGE and three with events mimicking seizures) to validate performance in a clinical setting. The automated detection algorithm showed state-of-the-art performance for detecting epileptic activity from clinical EEG, with mean sensitivity of >95% and corresponding mean false positive rate of 1 detection per minute. Importantly, diagnostic case studies showed that the automated detection algorithm reduced human review time by 80%-99%, without compromising event detection or diagnostic accuracy. The presented results demonstrate that computer-assisted review can increase the speed and accuracy of EEG assessment and has the potential to greatly improve therapeutic outcomes. This article is part of the Special Issue "NEWroscience 2018".

Impact of podiatry resident experience level in hallux valgus surgery on postoperative outcomes.

BACKGROUND: Despite modern advancements in transosseous fixation and operative technique, hallux valgus (i.e., bunion) surgery is still associated with a higher than usual amount of patient dissatisfaction and is generally recognized as a complex and nuanced procedure requiring precise osseous and capsulotendon balancing. It stands to reason then that familiarity and skill level of trainee surgeons might impact surgical outcomes in this surgery. The aim of this study was to determine whether podiatry resident experience level influences midterm outcomes in hallux valgus surgery (HVS). METHODS: Consecutive adults who underwent isolated HVS via distal metatarsal osteotomy at a single US metropolitan teaching hospital from January 2004 to January 2009 were contacted and asked to complete a validated outcome measure of foot health (Manchester-Oxford Foot Questionnaire) regarding their operated foot. Resident experience level was quantified using the surgical logs for the primary resident of record at the time of each case. Associations were assessed using linear and logistic regression analyses. RESULTS: A total of 102 adult patients (n = 102 feet) agreed to participate with a mean age of 46.8 years (standard deviation 13.1, range 18-71) and average length of follow-up 6.2 y (standard deviation 1.4, range 3.6-8.6). Level of trainee experience was not associated with postoperative outcomes in either the univariate (odds ratio 0.99 [95% confidence interval, 0.98-1.01], P = 0.827) or multivariate analyses (odds ratio 1.00 [95% confidence interval, 0.97-1.02], P = 0.907). CONCLUSIONS: We conclude that podiatry resident level of experience in HVS does not contribute appreciably to postoperative clinical outcomes.