Innovations In Clinical Neuroscience

CNS Summit 2016

A peer-reviewed, evidence-based journal for clinicians in the field of neuroscience

Issue link: http://innovationscns.epubxp.com/i/808251

Contents of this Issue

Navigation

Page 5 of 23

Innovations in CLINICAL NEUROSCIENCE [ V O L U M E 1 4 , N U M B E R 1 – 2 , J A N U A R Y – F E B R U A R Y 2 0 1 7 , S U P P L E M E N T ] S6 (r=0.97 [NN], 0.64 [TST], 0.70 [WASO], 0.69 [Eff]) but NN had the best correlation and the lowest median error ( 0.4% time vs. 1.6% time [TST], 1.5% time [WASO], and 1.3% time [Eff]). Conclusion: Compared to the use of conventional sleep endpoints, the direct measurement of nocturnal scratching d uration with the NN algorithm provided the strongest correlation with the true value and the smallest error. Disclosures/funding: None reported. Development of neurophysiological- based biomarkers for neurodegenerative disease and psychiatric disorders using EEG Presenters: Waninger S 1 , Berka C 1 , Stikic M 1 , Korszen S 1 , Salat D 2 , Verma A 3 Affiliations: 1 Advanced Brain Monitoring, Inc., Carlsbad, California; 2 MGH/MIT/HMS Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital, Charlestown, Massachusetts ; 3 Biogen, Cambridge, Massachusetts Background: Successful drug development for neurodegenerative diseases and psychiatric disorders requires objective, reliable, and accurate measures to evaluate disease progression and therapeutic efficacy. The potential of neurophysiological biomarkers using electroencephalography (EEG) has been highlighted in ongoing studies at Advanced Brain Monitoring on Parkinson's disease (PD), Alzheimer's disease (AD), mild cognitive impairment (MCI), mood disorders, and posttraumatic stress disorder (PTSD). Design: Using our wireless B-Alert X24 system with a standard 10–20 montage, we acquired and analyzed EEG data both during resting state and neurocognitive tasks designed to activate the neural circuits involved in attention, memory, and emotion and elicit event-related potentials (ERPs). For resting state, data were acquired for five minutes with eyes closed (EC) and five minutes with eyes open (EO). These data were decontaminated and converted from the time domain to the frequency domain using Fast Fourier Transform (FFT) to calculate power spectral densities (PSD) grouped into the standard EEG bandwidths (delta, t heta, alpha, beta, and gamma). Results: Comparison of PSD from AD and MCI patients to healthy, age- matched controls indicated distinguishing features, particularly the " slowing" of EEG exemplified by an increase in slow wave bands and a decrease in fast power that is typically observed in patients with cognitive decline. The source of the abnormal EEG in MCI patients was localized to the middle and superior temporal gyrus and fusiform gyrus using low resolution electromagnetic tomography (LORETA). Variables extracted from the resting state data (i.e., absolute PSDs, relative PSDs, and wavelets) are grouped together into a feature vector and the most discriminative variables are selected to construct linear discriminate function analysis (lDFA) models. Application of lDFA to the MCI dataset results in high accuracy and specificity using auto-validation or leave-one-out cross-validation. Although a great deal of information is derived from resting state data, we also have the capability to capture engagement of neural circuits during neurocognitive tasks that stimulate and elicit neural patterns associated with attention, memory and emotion. One such task, three-choice vigilance (3CVT), is a visual choice reaction time task designed to measure sustained attention and target detection. EEG data acquired during the 3-CVT task indicates significantly longer peak latency in the parietal N2 component of the ERP in a PTSD cohort compared to healthy control cohort. Conclusion: These data provide further evidence that PTSD patients have increased difficulty with attentional resources and identifies a potential biomarker for PTSD disease progression. Both resting state and event related EEG data have potential for use as cost efficient, noninvasive pharmacodynamic endpoints in neurodegenerative disease and psychiatric disorder clinical trials of experimental therapeutics. Disclosures/funding: None reported. NetraMark: predicting placebo and drug response for pharma Presenters: Geraci J A ffiliations: NetraMark Corp., Ontario, Canada Objective: We wished to showcase precision medicine through novel machine learning models based on m olecular and psychiatric scale data that can impact clinical trial success through placebo response and drug efficacy prediction. Design: Utilizing data sets, we discovered models of placebo response robust enough to reproduce (within the specific treatment paradigm of a trial) and models that demonstrated the patient population purification process for predicting response in a precise way. Results: We found two models of placebo response that had an accuracy of over 85 percent. For some situations we were able to predict if someone was a placebo responder with an accuracy of over 95 percent. Clinical scales alone were used for one of these models. We also based models on miRNA expression data that were capable of accurately predicting response for a particular subpopulation of major depression patients. This provided evidence that our technology is capable of dealing with heterogeneous patient populations. This could be valuable during Phase 3 scenarios for drug protocols that only work for a portion of the treatment population. Conclusion: NetraMark developed a machine learning system to help pharmaceutical companies who must deal with complex patient populations. NetraMark accomplished this by providing accurate models of placebo and drug response. In situations where the efficacy of a drug is limited to a subpopulation whose effect could be "washed out" by the United States Food and Drug Administration (FDA) statistical paradigm, we provided what we call a Patient Population Purification process. This process is capable of predicting who these patients are with a high level of accuracy. Our unique system has the ability to help companies get potential medications on the market through our approach to precision medicine.

Articles in this issue

Archives of this issue

view archives of Innovations In Clinical Neuroscience - CNS Summit 2016