Utilizing machine learning algorithms to predict subject genetic mutation class from in silico models of neuronal networks.

BACKGROUND: Epilepsy is the fourth-most common neurological disorder, affecting an estimated 50 million patients globally. Nearly 40% of patients have uncontrolled seizures yet incur 80% of the cost. Anti-epileptic drugs commonly result in resistance and reversion to uncontrolled drug-resistant epilepsy and are often associated with significant adverse effects. This has led to a trial-and-error system in which physicians spend months to years attempting to identify the optimal therapeutic approach. OBJECTIVE: To investigate the potential clinical utility from the context of optimal therapeutic prediction of characterizing cellular electrophysiology. It is well-established that genomic data alone can sometimes be predictive of effective therapeutic approach. Thus, to assess the predictive power of electrophysiological data, machine learning strategies are implemented to predict a subject's genetically defined class in an in silico model using brief electrophysiological recordings obtained from simulated neuronal networks. METHODS: A dynamic network of isogenic neurons is modeled in silico for 1-s for 228 dynamically modeled patients falling into one of three categories: healthy, general sodium channel gain of function, or inhibitory sodium channel loss of function. Data from previous studies investigating the electrophysiological and cellular properties of neurons in vitro are used to define the parameters governing said models. Ninety-two electrophysiological features defining the nature and consistency of network connectivity, activity, waveform shape, and complexity are extracted for each patient network and t-tests are used for feature selection for the following machine learning algorithms: Neural Network, Support Vector Machine, Gaussian Naïve Bayes Classifier, Decision Tree, and Gradient Boosting Decision Tree. Finally, their performance in accurately predicting which genetic category the subjects fall under is assessed. RESULTS: Several machine learning algorithms excel in using electrophysiological data from isogenic neurons to accurately predict genetic class with a Gaussian Naïve Bayes Classifier predicting healthy, gain of function, and overall, with the best accuracy, area under the curve, and F1. The Gradient Boosting Decision Tree performs the best for loss of function models indicated by the same metrics. CONCLUSIONS: It is possible for machine learning algorithms to use electrophysiological data to predict clinically valuable metrics such as optimal therapeutic approach, especially when combining several models.

Statistical parameters of epileptiform brain activity differentiate frontal and temporal lobe patients.

Statistical properties of electromagnetic brain activity may increase the understanding of the human brain by providing precise numerical vales associated with neuronal activity. A statistical analysis was performed on frontal and temporal lobe patients to investigate possible differences between the two populations. Results were then compared to clinical results to confirm findings. Frontal lobe patients had a larger spatial distribution of interictal spikes when compared to temporal lobe patients. Statistical properties from interictal spike data may differentiate patients with frontal and temporal lobe epilepsy.

Hemispheric language dominance in magnetoencephalography: sensitivity, specificity, and data reduction techniques.

Understanding the areas involved in language functions not only enables investigators to understand neuroanatomical structures, but may be a promising technique in the presurgical evaluation of epilepsy. The predictive power of various data reduction techniques was tested on language data obtained by magnetoencephalography (MEG) of 16 patients and 12 control subjects. Words were presented aurally in two phases: the study phase and the recognition phase. Subjects were asked to remember words from the study phase and indicate if they remembered those words during the recognition phase. Single equivalent-current dipoles were calculated to determine laterality indices and the neuroanatomical correlates of language function. For all patients, results indicated a concordance, sensitivity, and specificity of 0.75. After consideration of IQ scores and exclusion from the analysis of those patients with scores below the average range, the results indicated a concordance of 0.90, sensitivity of 0.86, and specificity of 1.00. These findings are consistent with previous MEG investigations of language function in comparison with the Wada technique and support the use of MEG language mapping in most patients with an IQ within or above the average range.