Patents by Inventor Javier Ramón Echauz
Javier Ramón Echauz has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 8849390Abstract: Method and apparatus for improved processing for multi-channel signals. In an exemplary embodiment, an anomaly metric is computed for a multi-channel signal over a time window. The magnitude of the anomaly metric may be used to determine whether an anomaly is present in the multi-channel signal over the time window. In an exemplary embodiment, the anomaly metric may be a condition number associated with the singular values of the multi-channel signal over the time window, as further adjusted by the number of channels to produce a data condition number. Applications of the anomaly metric computation include the scrubbing of signal archives for epileptic seizure detection/prediction/counter-prediction algorithm training, pre-processing of multi-channel signals for real-time monitoring of bio-systems, and boot-up and/or adaptive self-checking of such systems during normal operation.Type: GrantFiled: December 29, 2009Date of Patent: September 30, 2014Assignee: Cyberonics, Inc.Inventors: Javier Ramón Echauz, David E. Snyder, Kent W. Leyde
-
Patent number: 8786624Abstract: Method and apparatus for improved processing for multi-channel signals. In an exemplary embodiment, an anomaly metric is computed for a multi-channel signal over a time window. The magnitude of the anomaly metric may be used to determine whether an anomaly is present in the multi-channel signal over the time window. In an exemplary embodiment, the anomaly metric may be a condition number associated with the singular values of the multi-channel signal over the time window, as further adjusted by the number of channels to produce a data condition number. Applications of the anomaly metric computation include the scrubbing of signal archives for epileptic seizure detection/prediction/counter-prediction algorithm training, pre-processing of multi-channel signals for real-time monitoring of bio-systems, and boot-up and/or adaptive self-checking of such systems during normal operation.Type: GrantFiled: June 2, 2010Date of Patent: July 22, 2014Assignee: Cyberonics, Inc.Inventors: Javier Ramón Echauz, David E. Snyder, Kent W. Leyde
-
Patent number: 8086294Abstract: A method and system for assessing a quality of life index to adjust an implanted device to optimize patient-specific feature signals and treatment therapies. Accumulated energy of intracranial electroencephalogram (IEEG) signals is calculated over multiple data channels during seizures over a fixed time period. Accumulated energy of a treatment control is calculated over the multiple data channels over all times of activation of the implanted device over the fixed time period. The accumulated energy of both the IEEG signals and treatment control are weighted by seizure and treatment factors to determine a quality value for the fixed time period. A quality of life index is determined as a weighted average of current and previous quality values for a plurality of fixed time periods.Type: GrantFiled: August 13, 2007Date of Patent: December 27, 2011Assignee: The Trustees of the University of PennsylvaniaInventors: Javier Ramón Echauz, Brian Litt, Rosana Esteller, George John Vachtsevanos
-
Patent number: 8065011Abstract: An adaptive method and apparatus for forecasting and controlling neurological abnormalities in humans such as seizures or other brain disturbances. The system is based on a multi-level control strategy. Using as inputs one or more types of physiological measures such as brain electrical, chemical or magnetic activity, heart rate, pupil dilation, eye movement, temperature, chemical concentration of certain substances, a feature set is selected off-line from a pre-programed feature library contained in a high level controller within a supervisory control architecture. This high level controller stores the feature library within a notebook or external PC. The supervisory control also contains a knowledge base that is continuously updated at discrete steps with the feedback information coming from an implantable device where the selected feature set (feature vector) is implemented.Type: GrantFiled: August 31, 2006Date of Patent: November 22, 2011Assignee: The Trustees of the University of PennsylvaniaInventors: Javier Ramón Echauz, Brian Litt, Rosana Esteller, George John Vachtsevanos
-
Publication number: 20100302270Abstract: Method and apparatus for improved processing for multi-channel signals. In an exemplary embodiment, an anomaly metric is computed for a multi-channel signal over a time window. The magnitude of the anomaly metric may be used to determine whether an anomaly is present in the multi-channel signal over the time window. In an exemplary embodiment, the anomaly metric may be a condition number associated with the singular values of the multi-channel signal over the time window, as further adjusted by the number of channels to produce a data condition number. Applications of the anomaly metric computation include the scrubbing of signal archives for epileptic seizure detection/prediction/counter-prediction algorithm training, pre-processing of multi-channel signals for real-time monitoring of bio-systems, and boot-up and/or adaptive self-checking of such systems during normal operation.Type: ApplicationFiled: June 2, 2010Publication date: December 2, 2010Inventors: Javier Ramón Echauz, David E. Snyder, Kent W. Leyde
-
Publication number: 20100168604Abstract: Method and apparatus for improved processing for multi-channel signals. In an exemplary embodiment, an anomaly metric is computed for a multi-channel signal over a time window. The magnitude of the anomaly metric may be used to determine whether an anomaly is present in the multi-channel signal over the time window. In an exemplary embodiment, the anomaly metric may be a condition number associated with the singular values of the multi-channel signal over the time window, as further adjusted by the number of channels to produce a data condition number. Applications of the anomaly metric computation include the scrubbing of signal archives for epileptic seizure detection/prediction/counter-prediction algorithm training, pre-processing of multi-channel signals for real-time monitoring of bio-systems, and boot-up and/or adaptive self-checking of such systems during normal operation.Type: ApplicationFiled: December 29, 2009Publication date: July 1, 2010Inventors: Javier Ramon Echauz, David E. Snyder, Kent W. Leyde
-
Patent number: 7333851Abstract: A method and an apparatus for predicting and detecting epileptic seizure onsets within a unified multiresolution probabilistic framework, enabling a portion of the device to automatically deliver a progression of multiple therapies, ranging from benign to aggressive as the probabilities of seizure warrant. Based on novel computational intelligence algorithms, a realistic posterior probability function P(ST|x) representing the probability of one or more seizures starting within the next T minutes, given observations x derived from IEEG or other signals, is periodically synthesized for a plurality of prediction time horizons. When coupled with optimally determined thresholds for alarm or therapy activation, probabilities defined in this manner provide anticipatory time-localization of events in a synergistic logarithmic-like array of time resolutions, thus effectively circumventing the performance vs. prediction-horizon tradeoff of single-resolution systems.Type: GrantFiled: September 12, 2003Date of Patent: February 19, 2008Assignee: The Trustees of the University of PennsylvaniaInventors: Javier Ramón Echauz, Rosana Esteller, Brian Litt, George John Vachtsevanos
-
Patent number: 7146218Abstract: A method and apparatus for forecasting and controlling neurological abnormalities in humans such as seizures or other brain disturbances. The system is based on a multi-level control strategy. Using as inputs one or more types of physiological measures such as brain electrical, chemical or magnetic activity, heart rate, pupil dilation, eye movement, temperature, chemical concentration of certain substances, a feature set is selected off-line from a pre-programmed feature library contained in a high level controller within a supervisory control architecture. This high level controller stores the feature library within a notebook or external PC. The supervisory control also contains a knowledge base that is continuously updated at discrete steps with the feedback information coming from an implantable device where the selected feature set (feature vector) is implemented.Type: GrantFiled: February 4, 2003Date of Patent: December 5, 2006Assignee: The Trustees of the University of PennsylvaniaInventors: Rosana Esteller, Javier Ramón Echauz, Brian Litt, George John Vachtsevanos
-
Publication number: 20040068199Abstract: A method and an apparatus for predicting and detecting epileptic seizure onsets within a unified multiresolution probabilistic framework, enabling a portion of the device to automatically deliver a progression of multiple therapies, ranging from benign to aggressive as the probabilities of seizure warrant. Based on novel computational intelligence algorithms, a realistic posterior probability function P(ST|x) representing the probability of one or more seizures starting within the next T minutes, given observations x derived from IEEG or other signals, is periodically synthesized for a plurality of prediction time horizons. When coupled with optimally determined thresholds for alarm or therapy activation, probabilities defined in this manner provide anticipatory time-localization of events in a synergistic logarithmic-like array of time resolutions, thus effectively circumventing the performance vs. prediction-horizon tradeoff of single-resolution systems.Type: ApplicationFiled: September 12, 2003Publication date: April 8, 2004Applicant: The Trustees of the University of PennsylvaniaInventors: Javier Ramon Echauz, Rosana Esteller, Brian Litt, George John Vachtsevanos
-
Patent number: 6678548Abstract: A method and an apparatus for predicting and detecting epileptic seizure onsets within a unified multiresolution probabilistic framework, enabling a portion of the device to automatically deliver a progression of multiple therapies, ranging from benign to aggressive as the probabilities of seizure warrant. Based on novel computational intelligence algorithms, a realistic posterior probability function P(St|x) representing the probability of one or more seizures starting within the next T minutes, given observations x derived from IEEG or other signals, is periodically synthesized for a plurality of prediction time horizons. When coupled with optimally determined thresholds for alarm or therapy activation, probabilities defined in this manner provide anticipatory time-localization of events in a synergistic logarithmic-like array of time resolutions, thus effectively circumventing the performance vs. prediction-horizon tradeoff of single-resolution systems.Type: GrantFiled: October 20, 2000Date of Patent: January 13, 2004Assignee: The Trustees of the University of PennsylvaniaInventors: Javier Ramón Echauz, Rosana Esteller, Brian Litt, George John Vachtsevanos
-
Publication number: 20030158587Abstract: A method and apparatus for forecasting and controlling neurological abnormalities in humans such as seizures or other brain disturbances. The system is based on a multi-level control strategy. Using as inputs one or more types of physiological measures such as brain electrical, chemical or magnetic activity, heart rate, pupil dilation, eye movement, temperature, chemical concentration of certain substances, a feature set is selected off-line from a pre-programmed feature library contained in a high level controller within a supervisory control architecture. This high level controller stores the feature library within a notebook or external PC. The supervisory control also contains a knowledge base that is continuously updated at discrete steps with the feedback information coming from an implantable device where the selected feature set (feature vector) is implemented.Type: ApplicationFiled: February 4, 2003Publication date: August 21, 2003Applicant: The Trustees of the University of pennsylvaniaInventors: Rosana Esteller, Javier Ramon Echauz, Brian Litt, George John Vachtsevanos
-
Patent number: 6594524Abstract: A method and apparatus for forecasting and controlling neurological abnormalities in humans such as seizures or other brain disturbances. The system is based on a multi-level control strategy. Using as inputs one or more types of physiological measures such as brain electrical, chemical or magnetic activity, heart rate, pupil dilation, eye movement, temperature, chemical concentration of certain substances, a feature set is selected off-line from a pre-programmed feature library contained in a high level controller within a supervisory control architecture. This high level controller stores the feature library within a notebook or external PC. The supervisory control also contains a knowledge base that is continuously updated at discrete steps with the feedback information coming from an implantable device where the selected feature set (feature vector) is implemented.Type: GrantFiled: December 12, 2000Date of Patent: July 15, 2003Assignee: The Trustees of the University of PennsylvaniaInventors: Rosana Esteller, Javier Ramón Echauz, Brian Litt, George John Vachtsevanos
-
Publication number: 20020103512Abstract: A method and apparatus for forecasting and controlling neurological abnormalities in humans such as seizures or other brain disturbances. The system is based on a multi-level control strategy. Using as inputs one or more types of physiological measures such as brain electrical, chemical or magnetic activity, heart rate, pupil dilation, eye movement, temperature, chemical concentration of certain substances, a feature set is selected off-line from a pre-programmed feature library contained in a high level controller within a supervisory control architecture. This high level controller stores the feature library within a notebook or external PC. The supervisory control also contains a knowledge base that is continuously updated at discrete steps with the feedback information coming from an implantable device where the selected feature set (feature vector) is implemented.Type: ApplicationFiled: December 12, 2000Publication date: August 1, 2002Inventors: Javier Ramon Echauz, Brian Litt, Rosana Esteller, George John Vachtsevanos