Application of Machine Learning in Epileptic Seizure Detection.

Epileptic seizure is a neurological condition caused by short and unexpectedly occurring electrical disruptions in the brain. It is estimated that roughly 60 million individuals worldwide have had an epileptic seizure. Experiencing an epileptic seizure can have serious consequences for the patient. Automatic seizure detection on electroencephalogram (EEG) recordings is essential due to the irregular and unpredictable nature of seizures. By thoroughly analyzing EEG records, neurophysiologists can discover important information and patterns, and proper and timely treatments can be provided for the patients. This research presents a novel machine learning-based approach for detecting epileptic seizures in EEG signals. A public EEG dataset from the University of Bonn was used to validate the approach. Meaningful statistical features were extracted from the original data using discrete wavelet transform analysis, then the relevant features were selected using feature selection based on the binary particle swarm optimizer. This facilitated the reduction of 75% data dimensionality and 47% computational time, which eventually sped up the classification process. After having been selected, relevant features were used to train different machine learning models, then hyperparameter optimization was utilized to further enhance the models' performance. The results achieved up to 98.4% accuracy and showed that the proposed method was very effective and practical in detecting seizure presence in EEG signals. In clinical applications, this method could help relieve the suffering of epilepsy patients and alleviate the workload of neurologists.

Successful Treatment of a Paroxysmal Kinesigenic Dyskinesia Patient with Carbamazepine-Induced Stevens-Johnson Syndrome Using Oxcarbazepine Monotherapy: A Case Report.

Paroxysmal kinesigenic dyskinesia (PKD) is a rare condition characterized by abnormal involuntary movements that are precipitated by a sudden movement. PKD is often misdiagnosed with psychogenic movement disorders. Carbamazepine is usually the first choice of medication due to its well-established evidence but could induce Stevens-Johnson syndrome. We report a 21-year-old male patient with PKD referred to our movement disorders clinic after being misdiagnosed with conversion syndrome. PRRT2 gene testing using next-generation sequencing revealed a mutation in c.649dupC p. (Arg217fs). The patient responded well to carbamazepine but had to withdraw the treatment due to carbamazepine-induced Stevens-Johnson syndrome after 3 weeks of medication. Our patient did not respond to trials of levetiracetam and phenytoin but finally responded well to oxcarbazepine. The patient was followed up for 4 years, during which he had no attacks and no side effects. Here, we present a PKD case with carbamazepine-induced Stevens-Johnson syndrome successfully treated with oxcarbazepine despite the risk of cross-reactive skin eruption between these antiepileptics. Careful history taking and examining patient's attacks are crucial to accurate diagnosis and treatment in PKD patients.

Structure and dynamics of Au+ ion in aqueous solution: ab initio QM/MM MD simulations.

Structure and dynamics of hydrated Au(+) have been investigated by means of molecular dynamics simulations based on ab initio quantum mechanical molecular mechanical forces at Hartree-Fock level for the treatment of the first hydration shell. The outer region of the system was described using a newly constructed classical three-body corrected potential. The structure was evaluated in terms of radial and angular distribution functions and coordination number distributions. Water exchange processes between coordination shells and bulk indicate a very labile structure of the first hydration shell whose average coordination number of 4.7 is a mixture of 3-, 4-, 5-, 6-, and 7-coordinated species. Fast water exchange reactions between first and second hydration shell occur, and the second hydration shell is exceptionally large. Therefore, the mean residence time of water molecules in the first hydration shell (5.6 ps/7.5 ps for t*= 0.5 ps/2.0 ps) is shorter than that in the second shell (9.4 ps/21.2 ps for t*= 0.5 ps/2.0 ps), leading to a quite specific picture of a "structure-breaking" effect.

Characterization of dynamics and reactivities of solvated ions by ab initio simulations.

Based on a systematic investigation of trajectories of ab initio quantum mechanical/molecular mechanical simulations of numerous cations in water a standardized procedure for the evaluation of mean ligand residence times is proposed. For the characterization of reactivity and structure-breaking/structure-forming properties of the ions a measure is derived from the mean residence times calculated with different time limits. It is shown that ab initio simulations can provide much insight into ultrafast dynamics that are presently not easily accessible by experiment.