Accurate automatic spike detection is highly beneficial to clinical assessment of epileptic electroencephalogram (EEG) data. In this paper, a new two-stage approach is proposed for epileptic spike detection. First, the k-point nonlinear energy operator (k-NEO) is adopted to detect all possible spike candidates, then a newly proposed spike model with slow wave features is applied to these candidates for spike classification. Experimental results show that the proposed system, using the AdaBoost classifier, outperforms the conventional method in both two- and three-class EEG pattern classification problems. The proposed system not only achieves better accuracy for spike detection, but also provides new ability to differentiate between spikes and spikes with slow waves. Though spikes with slow waves occur frequently in epileptic EEGs, they are not used in conventional spike detection. Identifying spikes with slow waves allows the proposed system to have better capability for assisting clinical neurologists in routine EEG examinations and epileptic diagnosis.

Phenytoin is a commonly prescribed antiepileptic drug. Due to its saturation (zero‐order) pharmacokinetics, phenytoin carries a special risk of dose‐related toxicity that is an important issue in emergency medicine. The purpose of this cross‐sectional case‐series study was to investigate the causes, symptoms, misdiagnoses, and outcomes of acute phenytoin intoxication. It was based on a retrospective chart review of 30 inpatients (mean age, 41.6 ± 22.8 years) with 36 episodes of acute phenytoin intoxication at our university hospital in the past 13 years. The average initial serum phenytoin level was 47.3 ± 9.7 μg/mL (range, 27.9‐70.4 μg/mL). Excessive self‐medication, misunderstanding of the prescription order, and probable drug interaction were the three leading causes of acute phenytoin intoxication. Unsteady gait, dizziness/vertigo, nausea/vomiting, general weakness, and drowsiness were the most common presenting symptoms. The tentative diagnostic accuracy was 67%. The most common initial misdiagnosis was brainstem or cerebellum stroke (14%). The clinical course in all patients was uneventful under temporary withdrawal of phenytoin and supportive care. We concluded that acute phenytoin intoxication was relatively under‐diagnosed in the emergency service. Although acute phenytoin intoxication causes no mortality and has a good outcome, the unsteady gait increases the risk of injuries caused by falls. The management of acute phenytoin intoxication includes temporary withdrawal of phenytoin and supportive care.