Agency: Department of Health and Human Services | Branch: | Program: SBIR | Phase: Phase I | Award Amount: 333.15K | Year: 2012
DESCRIPTION (provided by applicant): Increased recognition of the incidence of nonconvulsive seizures (NCSs) in critically ill patients has led to a growing demand for continuous EEG monitoring in Intensive Care Units (ICUs). However, one of the biggest challenges to the expanding use of continuous EEG monitoring in the ICU lies in the difficulty of providing a timely review of clinical data by EEG experts. As a result, though EEG is being recorded continuously, ICU physicians may not be alerted to the occurrence of seizures until several hours later, following thorough review of the raw EEG by specialized personnel. The end result is compromised patient care and the inability to make appropriate real-time treatment decisions. Automated seizure detection software is occasionally used to assist in the EEG review process. However, existing seizure detection software is inadequate for most ICU patients because of the abnormal background EEG and highly variable seizure discharges that occur in encephalopathic patients. These EEG patterns differ greatly from those patterns that occur in epilepsy monitoring units (EMUs). As a result, commercially available software performs poorly when used with critical care patients, resulting in missed seizures and a high incidence of false detections. While available EEG-trending software is more useful, there are significant technical limitations in existing algorithms: 1) inability to show clear changes for bref, focal or slowly evolving, low frequency seizures, 2) low specificity in differentiating NCSs that require urgent treatment from other abnormalities, which are usually not treated with anti-seizure medicines, and 3) limited scientific evidence of clinical utility - none are FDA approved for ICU use. The overall goal of this SBIR project is to develop and commercialize an accurate, reliable, and user-friendly ICU seizure monitoring and alert system, CereScope . The system will feature a novel automated seizure detection algorithm, ICU-ASDA, with a high sensitivity (gt 85percent) and low false detection rate (lt 0.2/hr or 5/day). To enhance the system sensitivity, it will also be interfaced with artifact-reduced novel quantitative EEG (qEEG) trending, a Seizure Index (SI) which facilitates rapid recognition of potentialseizure patterns by visual inspection. CereScope will automatically create and transmit digital graphic files containing detected events for immediate expert review. Having completed the design and training studies for the ICU-ASDA, in this Phase I project we propose a clinical study to statistically evaluate and validate the performance of the algorithm that will meet the FDA's requirements. In addition, we will conduct studies at four Neuro-ICUs to investigate how combining qEEG trending with the results from the detection algorithm can enhance overall performance of the system. The specific aims of this Phase I feasibility study are: 1) Conduct a clinical study to evaluate the performance (sensitivity and false detection rate) of a novel seizure detection algorithm, ICU-ASDA, in EEG recordings from acutely ill adult patients, and 2) Investigate the utility of novel qEEG trends for enhancing sensitivity in identifying NCSs in long-term ICU EEG recordings when used in conjunction with the ICU-ASDA. Successful commercialization of the CereScope system will improve the recognition and management of seizures in critically ill patients. PUBLIC HEALTH RELEVANCE: Increased recognition of the high incidence of seizures in critically ill patients has ledto a growing demand for continuous brain monitoring in Intensive Care Units (ICUs). However, one of the biggest challenges to the expanding use of continuous brain monitoring in the ICU is the difficulty of providing a timely review of the high volumes ofEEG (brain electrical activity signal) data by experts, resulting in an inability to make appropriae real-time treatment decisions and compromised patient care. The overall goal of this SBIR project is to develop a novel system for EEG analysis that willallow ICU physicians, technicians, and nurses to rapidly identify seizures as well as other abnormal changes in brain function.
Optima Neuroscience, Inc. | Date: 2010-04-06
Optima Neuroscience, Inc. | Entity website
Sackellares J.C.,Optima Neuroscience, Inc. |
Shiau D.-S.,Optima Neuroscience, Inc. |
Halford J.J.,Medical University of South Carolina |
LaRoche S.M.,Emory University |
And 2 more authors.
Epilepsy and Behavior | Year: 2011
Because of increased awareness of the high prevalence of nonconvulsive seizures in critically ill patients, use of continuous EEG (cEEG) monitoring is rapidly increasing in ICUs. However, cEEG monitoring is labor intensive, and manual review and interpretation of the EEG are impractical in most ICUs. Effective methods to assist in rapid and accurate detection of nonconvulsive seizures would greatly reduce the cost of cEEG monitoring and enhance the quality of patient care. In this study, we report a preliminary investigation of a novel ICU EEG analysis and seizure detection algorithm. Twenty-four prolonged cEEG recordings were included in this study. Seizure detection sensitivity and specificity were assessed for the new algorithm and for the two commercial seizure detection software systems. The new algorithm performed with a mean sensitivity of 90.4% and a mean false detection rate of 0.066/hour. The two commercial detection products performed with low sensitivities (12.9 and 10.1%) and false detection rates of 1.036/hour and 0.013/hour, respectively. These findings suggest that the novel algorithm has potential to be the basis of clinically useful software that can assist ICU staff in timely identification of nonconvulsive seizures. This study also suggests that currently available seizure detection software does not perform sufficiently in detection of nonconvulsive seizures in critically ill patients. This article is part of a Supplemental Special Issue entitled The Future of Automated Seizure Detection and Prediction. © 2011 Elsevier Inc. Source
Kelly K.M.,Allegheny Singer Research Institute |
Kelly K.M.,Drexel University |
Shiau D.S.,Optima Neuroscience, Inc. |
Kern R.T.,Optima Neuroscience, Inc. |
And 8 more authors.
Clinical Neurophysiology | Year: 2010
Objective: The purpose of this study was to evaluate and validate an offline, automated scalp EEG-based seizure detection system and to compare its performance to commercially available seizure detection software. Methods: The test seizure detection system, IdentEvent™, was developed to enhance the efficiency of post-hoc long-term EEG review in epilepsy monitoring units. It translates multi-channel scalp EEG signals into multiple EEG descriptors and recognizes ictal EEG patterns. Detection criteria and thresholds were optimized in 47 long-term scalp EEG recordings selected for training (47 subjects, ∼3653 h with 141 seizures). The detection performance of IdentEvent was evaluated using a separate test dataset consisting of 436 EEG segments obtained from 55 subjects (∼1200 h with 146 seizures). Each of the test EEG segments was reviewed by three independent epileptologists and the presence or absence of seizures in each epoch was determined by majority rule. Seizure detection sensitivity and false detection rate were calculated for IdentEvent as well as for the comparable detection software (Persyst's Reveal®, version 2008.03.13, with three parameter settings). Bootstrap re-sampling was applied to establish the 95% confidence intervals of the estimates and for the performance comparison between two detection algorithms. Results: The overall detection sensitivity of IdentEvent was 79.5% with a false detection rate (FDR) of 2 per 24 h, whereas the comparison system had 80.8%, 76%, and 74% sensitivity using its three detection thresholds (perception score) with FDRs of 13, 8, and 6 per 24 h, respectively. Bootstrap 95% confidence intervals of the performance difference revealed that the two detection systems had comparable detection sensitivity, but IdentEvent generated a significantly (p< 0.05) smaller FDR. Conclusions: The study validates the performance of the IdentEvent™ seizure detection system. Significance: With comparable detection sensitivity, an improved false detection rate makes the automated seizure detection software more useful in clinical practice. © 2010 International Federation of Clinical Neurophysiology. Source