BIOMARKER FUSION CLASSIFICATION The complexity of assessing all possible combinations of qEEG & ERP biomarker features scales up with the addition of each potential feature. Neuronetrix has implemented a flexible architecture to facilitate automated classification of aEEG/ERP data using artificial neural networks. The COGNISION™ Classifier module enables rapid testing and validation of meaningful combinations of qEEG/ERP biomarkers. Features of the COGNISION™ Classifier module include: • Database: Entire classification system is built on the COGNISION™ Patient Manager database so all clinical biomarker information can be used in the classification model • Meta Modeling: Easy and intuitive definition of classification model architecture (Class-Set, Feature Set, Training Set, Experts, Validation, etc.) • Data Fusion: Can combine data from qEEG and ERP tests (spectral properties, amplitude vs time, areas under the curve, wavelets, etc.) • Feature Fusion: Automatically extracts and combines groups of features using optimized experts (Support Vector Machine, Multi-Layer Perceptron, • Decision Fusion: Combines decisions from multiple experts for final classification (Weighted Majority Voting, Stacked Generalization, etc.) • Model Validation: Implements automatic k-fold validation Feature Fusion Decision Fusion COGNISION™ APPLICATIONS * Cognitive Research * Large-scale Therapeutic Trials * Clinical Investigations of Cognitive Disorders REMOTE USER Datient Records CLIENT APPLICATION SCIENTIFIC & CLINICAL REFERENCES Luck S. J., Mathalon D. H., O'Donnell B. F., Hamalainen M. S., Spencer K. M., Javitt D. C, Uhlhaas P. J., A Roadmap for the Development and Validation of Event-Related Potential Biomarkers in Schizophrenia Research, Biological Psychiatry, 70(1), 28-34 (2011) Polikar R., Topalis A., Green D., Kounios J., Clark CM. Comparative multiresolution analysis and ensemble of classifiers approach for early diagnosis of Alzheimer's disease. Computers in LeiserS. C, Dunlop J., Bowlby M., Devilbliss D. M., Aligning strategies for using EEG as a surrogate biomarker: A review of preclinical and clinical research, Biochem Pharmacol (2010) Bewernitz, M., Derendorf, H. Electroencephalogram-based pharmacodynamic measures: a review. International Journal of Clinical Pharmacology and Therapeutics, 50(3), 162-184 (2012) Javitt D. C, Spencer K. M., Thaker G. K., Winterer G., Hajos M., Neurophysiological biomarkers of drug development in schizophrenia, Nat Rev Drug Discov. January;7(l):68-83 (2008) PolichJ. & Herbst,K.L P300 as a clinical assay: rationale, evaluation, and findings. Int. J. Jackson C, Snyder P. J., Electroencephalography and event-related potentials as biomarkers of mild cognitive impairment and mild Alzheimer's disease, Alzheimer's & Dementia 4, Duncan C. C, Barry R. J., Connolly J. F., Fischer C, Michie P. T., Nddtdnen R., Polich J., Reinvang I., Van Petten C, Event-related potentials in clinical research: guidelines for eliciting, recording, and quantifying mismatch negativity, P300, and N400. Clin. Neurophysiol. 120, 1883-1908 Olichney, J. M., Yang, J.-C, Taylor, J., Kutas, M. Cognitive event-related potentials: biomarkers of synaptic dysfunction across the stages of Alzheimer's disease. Journal of Alzheimer's Disease, Broglio, S. P., Moore, R. D., & Hillman, C. H. A history of sport-related concussion on event- related brain potential correlates of cognition. International Journal of Psych op hysio logy, Onofrj, M., Thomas, A., lacono, D., Luciano, A. L., & Di lorio, A. The effects of a cholinesterase inhibitor are prominent in patients with fluctuating cognition: a part 3 study of the main mechanism of cholinesterase inhibitors in dementia. Clinical Neuropharmacology, 26(5), Neuronetrix • 1044 East Chestnut Street • Louisville, KY 40204 • 502-561-9040 • www.neuronetrix.com INFO: [email protected] | SALES: [email protected] | SUPPORT: [email protected] EVENT-RELATED POTENTIALS for the evaluation of cognitive function Neuronetrix • 1044 East Chestnut Street • Louisville, KY 40204 • 502-561-9040 • www.neuronetrix.com NOTICE: INVESTIGATIONAL DEVICE ONLY. NOT APPROVED BY THE U.S. FOOD AND DR

Recent scientific studies using complex electrophysiological measures have detected brainwave signatures for many neurological processes. Neuronetrix has translated these scientific advances into an easy-to-use system to rapidly test and evaluate a variety of cognitive functions. The company's COGNISION™ System automatically performs a selection of standardized qEEG/ERP tests, and then uses proprietary pattern recognition algorithms to automatically classify the subject's brainwave signatures. Advanced features include: • Wireless, battery-powered system for use in an office environment • Subject-friendly...