Javier Echauz

Mountain View Pharmaceuticals, Inc., Menlo Park, California, United States

Are you Javier Echauz?

Claim your profile

Publications (45)67.32 Total impact

  • H. Li · M.R. Garvan · J. Li · J. Echauz · D. Brown · G.J. Vachtsevanos
    [Show abstract] [Hide abstract]
    ABSTRACT: It has been established that corrosion is one of the most important factors causing structural deterioration, loss of metal, and ultimately decrease of product performance and reliability. Corrosion monitoring, accurate detection and interpretation are recognized as key enabling technologies to reduce the impact of corrosion on the integrity of critical aircraft and industrial assets. Interest in corrosion measurement covers a broad spectrum of technical approaches including acoustic, electrical and chemical methods. Surface metrology is an alternative approach used to measure corrosive rate and material loss by obtaining surface topography measurement at micrometer levels. This paper reports results from an experimental investigation of pitting corrosion detection and interpretation on aluminum alloy panels using 3D surface metrology methods, image processing and data mining techniques. Sample panels of AA 7075-T6, an aluminum alloy commonly used in aircraft structures, were coated on one side with a corrosion protection coating and assembled in a lap-joint configuration. Then, a series of accelerated corrosion testing of the lap-joint panels were performed in a cyclic corrosion chamber running ASTM G85-A5 salt fog test. Panel surface characterization was evaluated with laser microscopy and stylus-based profilometry to obtain global and local surface images/characterization. Promising imaging and surface features were extracted and compared between the uncoated and coated panel sides, as well as on the uncoated sides under different corrosion exposure times. In the evaluation process, image processing, information processing and other data mining techniques were utilized. Information processing involves the steps of feature or Condition Indicator extraction and selection. The latter step addresses the problem of selecting those features that are maximally correlated with the actual corrosion state, for the purpose of corrosion detection, localization, quantification and state estimation. The results, verified by mass loss data, confirmed the contention that pits at the panel surfaces formed as a result of electrochemical corrosion attack, and showed that deteriorating pitting corrosion attack correlates with increasing corrosion exposure times. This study is a first step in the process of understanding, assessing and responding to the pitting corrosion and ultimately preventing material failure to insure aircraft structural integrity.
    No preview · Article · Jan 2014
  • Javier Echauz · Stephen Wong · Brian Litt
    [Show abstract] [Hide abstract]
    ABSTRACT: Understanding seizure generation, the transition from interictal to ictal states, and its underlying mechanisms requires continuous electrophysiologic monitoring. Though the duration of monitoring may vary from brief experiments over minutes to months of continuous recording, all recording of this nature requires a similar set of hardware and software tools. This chapter reviews the basic setup and requirements for successful continuous EEG monitoring in vivo and provides a set of computational “tools” that our group has found useful for continuous EEG monitoring in the laboratory. These include methods for seizure detection and basic analysis. References are provided for approaches used by groups involved in this kind of recording in animal models of epilepsy and humans. While not a complete “how to” guide for these procedures, this chapter will provide a good start to groups who are interested in performing this type of recording and data analysis. Key wordsintracranial EEG–seizure detection–signal processing–EEG analysis
    No preview · Chapter · Dec 2009
  • Javier Echauz · Hiram Firpi · George Georgoulas
    [Show abstract] [Hide abstract]
    ABSTRACT: Neurodevices for the management of nervous system disorders have been recognized as most promising through the coming decades. Technological development is being spurred on as drugs and other standard therapies have reached diminishing returns. New data enabled by cutting-edge telemetric devices will spin off new business models, for example, in seizure rhythm management. Implantable neurostimulation devices already exist as adjunct therapy for intractable epilepsy, but paradoxically, age-old feedback control strategies remain largely unknown or underutilized in the field. In this chapter we outline strategies for intelligent feedback control of pathological oscillations. We review the state of the art in implant-able devices for epilepsy and the experimental evidence for improved performance via feedback control. Then we extend an existing body of work from open-loop to continuous feedback control of phase-based models of hypersynchronization. Conversion of the results to practical devices is explored via pseudostate vector reconstruction. We conclude by outlining key components of research for continued progress in this field.
    No preview · Chapter · Dec 2008
  • Source
    David E Snyder · Javier Echauz · David B Grimes · Brian Litt
    [Show abstract] [Hide abstract]
    ABSTRACT: Statistical methods for evaluating seizure prediction algorithms are controversial and a primary barrier to realizing clinical applications. Experts agree that these algorithms must, at a minimum, perform better than chance, but the proper method for comparing to chance is in debate. We derive a statistical framework for this comparison, the expected performance of a chance predictor according to a predefined scoring rule, which is in turn used as the control in a hypothesis test. We verify the expected performance of chance prediction using Monte Carlo simulations that generate random, simulated seizure warnings of variable duration. We propose a new test metric, the difference between algorithm and chance sensitivities given a constraint on proportion of time spent in warning, and use a simple spectral power-based measure to demonstrate the utility of the metric in four patients undergoing intracranial EEG monitoring during evaluation for epilepsy surgery. The methods are broadly applicable to other scoring rules. We present them as an advance in the statistical evaluation of a practical seizure advisory system.
    Full-text · Article · Oct 2008 · Journal of Neural Engineering
  • [Show abstract] [Hide abstract]
    ABSTRACT: Computational neuroscience research in epilepsy encompasses a broad range of scales in space and time. Some of the most promising work in this area focuses on biophysically accurate models of circuits and synapses in brain that give rise to seizures. More and more, computational neuroscientists are embracing opportunities to build anatomically accurate and clinically relevant models of functional networks in brain. Epilepsy is one of the most active areas in translational neuroengineering, with two early devices currently in pivotal clinical trials, and a number of others close behind. Understanding biophenomena such as epileptic seizures and translating research into therapeutic devices ultimately means iterating analysis (a whole broken into parts) and synthesis (parts unified into a whole). The overarching problem is to synthesize a model M that "compresses" all inputs I and paired outputs O observed in an experiment into a function that summarizes how I morphs into O. The function/model M could be a non linear regression, a seizure detector or predictor, a probability estimator, a ruleset, the vector field in the differential equations of motion of a dynamical network, etc. Analysis in this context could be a decomposition of data I or model M into parts that add up to the original (such as a Fourier series), or other projections not necessarily adding up such as arbitrary features. The M somehow captures a scientific target concept and "explains" the data. It also suggests how to 'predict' and "control" the underlying phenomenon.
    No preview · Chapter · Feb 2008
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper introduces a framework for addressing neurological disorders and specifically epilepsy. One percent of the world's population is experiencing epileptic seizures a large percentage of which cannot be cured via medication or surgery. Recent advances in brain research have demonstrated the efficacy of monitoring via intracranial electroencephalogram (IEEG) epileptiform activity and the ability to detect and predict the onset of a seizure. Research is also concerned with the development of means to stimulate the brain in order to stop seizures. We review in this paper, work in the area of monitoring and EEG signal analysis aimed to detect/predict seizures and we propose a closed-loop control scheme to stimulate electrically the source of epileptiform activity with the intent to stop seizures and improve the quality of life of patients suffering from this disorder. Preliminary results are promising and additional research is warranted in this area.
    Full-text · Conference Paper · Jul 2007
  • Hiram Firpi · Erik D Goodman · Javier Echauz
    [Show abstract] [Hide abstract]
    ABSTRACT: Patient-specific epilepsy seizure detectors were designed based on the genetic programming artificial features algorithm, a general-purpose, methodic algorithm comprised by a genetic programming module and a k-nearest neighbor classifier to create synthetic features. Artificial features are an extension to conventional features, characterized by being computer-coded and may not have a known physical meaning. In this paper, artificial features are constructed from the reconstructed state-space trajectories of the intracranial EEG signals intended to reveal patterns indicative of epileptic seizure onset. The algorithm was evaluated in seven patients and validation experiments were carried out using 730.6 hr of EEG recordings. The results with the artificial features compare favorably with previous benchmark work that used a handcrafted feature. Among other results, 88 out of 92 seizures were detected yielding a low false negative rate of 4.35%.
    No preview · Article · Mar 2007 · IEEE Transactions on Biomedical Engineering
  • Hiram Firpi · Erik Goodman · Javier Echauz
    [Show abstract] [Hide abstract]
    ABSTRACT: A general-purpose, systematic algorithm is presented, consisting of a genetic programming module and a k-nearest neighbor classifier to automatically create artificial features--computer-crafted features possibly without a known physical meaning--directly from the reconstructed state-space trajectory of intracranial EEG signals that reveal predictive patterns of epileptic seizures. The algorithm was evaluated with IEEG data from seven patients, with prediction defined over a horizon of 1-5 min before unequivocal electrographic onset. A total of 59 baseline epochs (nonseizures) and 55 preictal epochs (preseizures) were used for validation purposes. Among the results, it is shown that 12 seizures out of 55 were missed while four baseline epochs were misclassified, yielding 79% sensitivity and 93% specificity.
    No preview · Article · Apr 2006 · Annals of Biomedical Engineering
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Increases in accumulated energy on intracranial EEG are associated with oncoming seizures in retrospective studies, supporting the idea that seizures are generated over time. Published seizure prediction methods require comparison to 'baseline' data, sleep staging, and selecting seizures that are not clustered closely in time. In this study, we attempt to remove these constraints by using a continuously adapting energy threshold, and to identify stereotyped energy variations through the seizure cycle (inter-, pre-, post- and ictal periods). Accumulated energy was approximated by using moving averages of signal energy, computed for window lengths of 1 and 20 min, and an adaptive decision threshold. Predictions occurred when energy within the shorter running window exceeded the decision threshold. Predictions for time horizons of less than 3h did not achieve statistical significance in the data sets analyzed that had an average inter-seizure interval ranging from 2.9 to 8.6h. 51.6% of seizures across all patients exhibited stereotyped pre-ictal energy bursting and quiet periods. Accumulating energy alone is not sufficient for predicting seizures using a 20 min running baseline for comparison. Stereotyped energy patterns through the seizure cycle may provide clues to mechanisms underlying seizure generation. Energy-based seizure prediction will require fusion of multiple complimentary features and perhaps longer running averages to compensate for post-ictal and sleep-induced energy changes.
    Full-text · Article · Apr 2005 · Clinical Neurophysiology
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: To develop a prospective method for optimizing seizure prediction, given an array of implanted electrodes and a set of candidate quantitative features computed at each contact location. The method employs a genetic-based selection process, and then tunes a probabilistic neural network classifier to predict seizures within a 10 min prediction horizon. Initial seizure and interictal data were used for training, and the remaining IEEG data were used for testing. The method continues to train and learn over time. Validation of these results over two workshop patients demonstrated a sensitivity of 100%, and 1.1 false positives per hour for Patient E, using a 2.4s block predictor, and a failure of the method on Patient B. This study demonstrates a prospective, exploratory implementation of a seizure prediction method designed to adapt to individual patients with a wide variety of pre-ictal patterns, implanted electrodes and seizure types. Its current performance is limited likely by the small number of input channels and quantitative features employed in this study, and segmentation of the data set into training and testing sets rather than using all continuous data available. This technique theoretically has the potential to address the challenge presented by the heterogeneity of EEG patterns seen in medication-resistant epilepsy. A more comprehensive implementation utilizing all electrode sites, a broader feature library, and automated multi-feature fusion will be required to fully judge the method's potential for predicting seizures.
    Full-text · Article · Apr 2005 · Clinical Neurophysiology
  • Hiram Firpi · Erik Goodman · Javier Echauz
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we propose a general-purpose, systematic algorithm, consisting of a genetic programming module and a k-nearest neighbor classifier to automatically create artificial features (i.e., features that are computer crafted and may not have a known physical meaning) directly from the reconstructed state-space trajectory of the EEG signals that reveal patterns predictive of epileptic seizures. The algorithm was evaluated in three different patients, with prediction defined over a horizon of 5 minutes before unequivocal electrographic onset. Experiments are carried out using 20 baseline epochs (non-seizures) and 18 preictal epochs (pre-seizures). Results show that just two seizures were missed while a perfect classification on the baseline epochs was achieved, yielding a 0.0 false positive per hour.
    No preview · Article · Feb 2005 · Conference proceedings: ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference
  • Source
    Hiram A. Firpi · Erik D. Goodman · Javier Echauz
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we describe a general-purpose, systematic algorithm, consisting of a genetic programming module and a k-nearest neighbor classifier to automatically create artificial features-features that are computer-crafted and may not have a known physical meaning-directly from the reconstructed state-space trajectories of the EEG signals that reveal patterns indicative of epileptic seizure onset. The algorithm was evaluated in three patients and validation experiments were carried out using 267.6 hours of EEG recordings. The results with the artificial features compare favorably with previous benchmark work that used a handcrafted feature.
    Full-text · Conference Paper · Jan 2005
  • Hiram A. Firpi · Erik D. Goodman · Javier Echauz
    [Show abstract] [Hide abstract]
    ABSTRACT: In this paper, we present a general-purpose, systematic algorithm, consisting of a genetic programming module and a k-nearest neighbor classifier, to automatically create multiple artificial features ( i.e., features that are computer-crafted and may not have a known physical meaning) directly from EEG signals, in a process that reveals patterns predictive of epileptic seizures. The algorithm was evaluated in three patients, with prediction defined over a horizon that varies between 1 and 5 minutes before unequivocal electrographic onset of seizure. For one patient, a perfect classification was achieved. For the other two patients, high classification accuracy was reached, predicting three seizures out of four for one, and eleven seizures out of fifteen for the other. For the latter, also, only one normal (non-seizure) signal was misclassified. These results compare favorably with other prediction approaches for patients from the same population.
    No preview · Conference Paper · Jan 2005
  • R Esteller · J Echauz · T Tcheng
    [Show abstract] [Hide abstract]
    ABSTRACT: This study aims to determine whether there are any statistically significant effects in the intracranial EEG signal due to brain electrical stimulation that can be quantified by comparing the line length value computed in windows positioned before and after stimulated abnormal events versus windows before and after non-stimulated abnormal events. The line length feature has been previously demonstrated to preserve waveform dimensionality changes as the ones estimated by Katz's fractal dimension and is a measure sensitive to variations in signal amplitude and frequency, equivalent in some ways to Teager's energy. Brief stimulation bursts of 200 Hz were delivered in response to some detections of abnormal electrographic activity. A total of 35 epileptic patients were analyzed including 15,938 electrographic events, of which 4,584 were electrically stimulated events. The ratio and difference of the post-stimulation versus the pre-stimulation line length values were computed as comparison measures. The average line length ratios in stimulated events versus those in non-stimulated events were lower in 23 out of 35 patients, suggesting that stimulation may have had an effect on electrographic activity. Statistical analysis based on a permutation test indicated the probability of finding this difference by random chance was 5.21%, further suggesting that the line length ratio differences are most likely due to the stimulation effects on the brain that manifest in the electrographic activity.
    No preview · Article · Feb 2004 · Conference proceedings: ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Conference
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Epileptic seizure prediction has steadily evolved from its conception in the 1970s, to proof-of-principle experiments in the late 1980s and 1990s, to its current place as an area of vigorous, clinical and laboratory investigation. As a step toward practical implementation of this technology in humans, we present an individualized method for selecting electroencephalogram (EEG) features and electrode locations for seizure prediction focused on precursors that occur within ten minutes of electrographic seizure onset. This method applies an intelligent genetic search process to EEG signals simultaneously collected from multiple intracranial electrode contacts and multiple quantitative features derived from these signals. The algorithm is trained on a series of baseline and preseizure records and then validated on other, previously unseen data using split sample validation techniques. The performance of this method is demonstrated on multiday recordings obtained from four patients implanted with intracranial electrodes during evaluation for epilepsy surgery. An average probability of prediction (or block sensitivity) of 62.5% was achieved in this group, with an average block false positive (FP) rate of 0.2775 FP predictions/h, corresponding to 90.47% specificity. These findings are presented as an example of a method for training, testing and validating a seizure prediction system on data from individual patients. Given the heterogeneity of epilepsy, it is likely that methods of this type will be required to configure intelligent devices for treating epilepsy to each individual's neurophysiology prior to clinical deployment.
    Full-text · Article · Jun 2003 · IEEE Transactions on Biomedical Engineering
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Brief bursts of focal, low amplitude rhythmic activity have been observed on depth electroencephalogram (EEG) in the minutes before electrographic onset of seizures in human mesial temporal lobe epilepsy. We have found these periods to contain discrete, individualized synchronized activity in patient-specific frequency bands ranging from 20 to 40 Hz. We present a method for detecting and displaying these events using a periodogram of the sign-limited temporal derivative of the EEG signal, denoted joint sign periodogram event characterization transform (JSPECT). When applied to continuous 2-6 day depth-EEG recordings from ten patients with temporal lobe epilepsy, JSPECT demonstrated that these patient-specific EEG events reliably occurred 5-80 s prior to electrical onset of seizures in five patients with focal, unilateral seizure onsets. JSPECT did not reveal this type of activity prior to seizures in five other patients with bilateral, extratemporal or more diffuse seizure onsets on EEG. Patient-specific, localized rhythmic events may play an important role in seizure generation in temporal lobe epilepsy. The JSPECT method efficiently detects these events, and may be useful as part of an automated system for predicting electrical seizure onset in appropriate patients.
    Full-text · Article · May 2003 · IEEE Transactions on Biomedical Engineering
  • [Show abstract] [Hide abstract]
    ABSTRACT: The dramatic success of pacemakers, cardiac defibrillators, cochlear implants and now brain stimulation for movement disorders has kindled enormous interest in translating Neuroengineering research into practical therapy for neurological disease. Epilepsy, which affects 60 million people worldwide, is an excellent target for new medical devices. Recent research indicates that seizures are likely generated over minutes to hours in a stereotyped, individualized fashion. Focal electrical stimulation has been demonstrated to abort or reduce seizures in animal models of epilepsy and now in early pilot trials in humans. The process of turning these exciting new findings into reliable therapeutic devices is taking place in an iterative process in which animal and basic laboratory research proceeds in parallel with FDA-supervised pilot human studies. We present a scheme for quantifying seizure precursors and coupling these measures to brain stimulation to abort seizures. Models of this type provide an exciting opportunity for engineers, neuroscientists and clinicians to collaborate, with unprecedented opportunity to rapidly translate new findings into clinical treatments.
    No preview · Conference Paper · Apr 2003
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Self-organized criticality (SOC) is a property of complex dynamic systems that evolve to a critical state, capable of producing scale-free energy fluctuations. A characteristic feature of dynamical systems exhibiting SOC is the power-law probability distributions that describe the dynamics of energy release. We show experimental evidence for SOC in the epileptic focus of seven patients with medication-resistant temporal lobe epilepsy. In the epileptic focus the probability density of pathological energy fluctuations and the time between these energy fluctuations scale as (energy) and (time), respectively. The power-laws characterizing the probability distributions from these patients are consistent with computer simulations of integrate-and-fire oscillator networks that have been reported recently. These findings provide insight into the neuronal dynamics of epileptic hippocampus and suggest a mechanism for interictal epileptiform fluctuations. The presence of SOC in human epileptic hippocampus may provide a method for identifying the network involved in seizure generation.
    Full-text · Article · Dec 2002 · Neuroreport
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: High-frequency (e.g., gamma 30 to 50 Hz) coherent neural activity has been postulated to underlie binding of independent neural assemblies and thus integrate processing across distributed neuronal networks to achieve a unified conscious experience. Prior studies suggest that gamma activity may play a role in perceptual mechanisms, but design limitations raise concerns. Thus, controversy exists as to the hypothesis that gamma activity is necessary for perceptual awareness. In addition, controversy exists as to whether the primary sensory cortices are involved directly in the mechanisms of conscious perception or just in processes prior to conscious awareness. To investigate the relation of gamma coherence and perception. Digital intracranial electrocorticographic recordings from implanted electrodes were obtained in six patients with intractable epilepsy during a simple somatosensory detection task for near-threshold stimuli applied to the contralateral hand. Signal analyses were then conducted using a quantitative approach that employed two-way Hanning digital bandpass filters to compute running correlations across pairs of channels at various time epochs for each patient and each perception state across multiple bandwidths. Gamma coherence occurs in the primary somatosensory cortex approximately 150 to 300 milliseconds after contralateral hand stimuli that are perceived, but not for nonperceived stimuli, which did not differ in character/intensity or early somatosensory evoked potentials. The results are consistent with the possible direct involvement of primary sensory cortex in elemental awareness and with a role for gamma coherence in conscious perception.
    Full-text · Article · Oct 2002 · Neurology
  • Source
    Brian Litt · Javier Echauz
    [Show abstract] [Hide abstract]
    ABSTRACT: For almost 40 years, neuroscientists thought that epileptic seizures began abruptly, just a few seconds before clinical attacks. There is now mounting evidence that seizures develop minutes to hours before clinical onset. This change in thinking is based on quantitative studies of long digital intracranial electroencephalographic (EEG) recordings from patients being evaluated for epilepsy surgery. Evidence that seizures can be predicted is spread over diverse sources in medical, engineering, and patent publications. Techniques used to forecast seizures include frequency-based methods, statistical analysis of EEG signals, non-linear dynamics (chaos), and intelligent engineered systems. Advances in seizure prediction promise to give rise to implantable devices able to warn of impending seizures and to trigger therapy to prevent clinical epileptic attacks. Treatments such as electrical stimulation or focal drug infusion could be given on demand and might eliminate side-effects in some patients taking antiepileptic drugs long term. Whether closed-loop seizure-prediction and treatment devices will have the profound clinical effect of their cardiological predecessors will depend on our ability to perfect these techniques. Their clinical efficacy must be validated in large-scale, prospective, controlled trials.
    Full-text · Article · Jun 2002 · The Lancet Neurology

Publication Stats

2k Citations
67.32 Total Impact Points

Institutions

  • 2004
    • Mountain View Pharmaceuticals, Inc.
      Menlo Park, California, United States
  • 2002-2003
    • University of Pennsylvania
      • Department of Bioengineering
      Filadelfia, Pennsylvania, United States
  • 1994-2003
    • Georgia Institute of Technology
      • School of Electrical & Computer Engineering
      Atlanta, Georgia, United States
  • 1999-2001
    • University of Puerto Rico at Mayagüez
      • Department of Electrical and Computer Engineering
      Mayaguez, Mayaguez, Puerto Rico
  • 1998
    • University of Puerto Rico at Ponce
      Ponce, Ponce, Puerto Rico