Patents by Inventor Mika Sarkela
Mika Sarkela 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: 10413254Abstract: In the present invention, a system and associated method is provided for monitoring vital parameters of a patient. The monitoring system includes sensors disposed on the patient and operably connected to a monitor. The parameters that are sensed by the sensors are transmitted to the monitor and compared with alarm thresholds stored within the monitor. The alarm thresholds stored within the monitor are modified by inputs supplied to the monitor regarding the particular condition(s) of the patient being monitored to provide more accurate alarm determinations for the patient. The dynamic adjustment of the alarm threshold during monitoring can be based on a set of proactive inputs to prevent and/or limit the occurrence of unnecessary or clinically irrelevant alarm conditions or a set of reactive inputs that follow immediately after an alarm event is detected, to enable medical personnel to appropriately respond to sensed alarm condition(s).Type: GrantFiled: July 8, 2016Date of Patent: September 17, 2019Assignee: General Electric CompanyInventors: Mika Sarkela, Rene Johannes Coffeng, Kimmo Uutela, Liisa-Maria Järvelä
-
Publication number: 20180008208Abstract: In the present invention, a system and associated method is provided for monitoring vital parameters of a patient. The monitoring system includes sensors disposed on the patient and operably connected to a monitor. The parameters that are sensed by the sensors are transmitted to the monitor and compared with alarm thresholds and operational criteria stored within the monitor. When an alarm condition is sensed by the system, the system can actively solicit patient assistance in the confirmation of the alarm condition based on a set of reactive inputs stored within the system to enable medical personnel to appropriately respond to clinically relevant sensed alarm condition(s).Type: ApplicationFiled: July 8, 2016Publication date: January 11, 2018Inventors: Mika Sarkela, Rene Johannes Coffeng, Kimmo Uutela, Liisa-Maria Järvelä
-
Publication number: 20180008207Abstract: In the present invention, a system and associated method is provided for monitoring vital parameters of a patient. The monitoring system includes sensors disposed on the patient and operably connected to a monitor. The parameters that are sensed by the sensors are transmitted to the monitor and compared with alarm thresholds stored within the monitor. The alarm thresholds stored within the monitor are modified by inputs supplied to the monitor regarding the particular condition(s) of the patient being monitored to provide more accurate alarm determinations for the patient. The dynamic adjustment of the alarm threshold during monitoring can be based on a set of proactive inputs to prevent and/or limit the occurrence of unnecessary or clinically irrelevant alarm conditions or a set of reactive inputs that follow immediately after an alarm event is detected, to enable medical personnel to appropriately respond to sensed alarm condition(s).Type: ApplicationFiled: July 8, 2016Publication date: January 11, 2018Inventors: Mika Sarkela, Rene Johannes Coffeng, Kimmo Uutela, Liisa-Maria Järvelä
-
Patent number: 9579035Abstract: The invention relates to detection of epileptiform activity. In order to accomplish a mechanism with improved specificity to epileptiform activity and with the capability to detect specific type of epileptic patterns, brain wave signal data obtained from a subject is decomposed into at least one predetermined subband, each subband being indicative of a specific type of epileptiform activity. The subband-specific output data obtained represents a time series of a quantitative characteristic of the brain wave signal data. At least one measure is determined for any one or more of the at least one predetermined subband, the at least one measure belonging to a measure set comprising a first measure indicative of the entropy of the subband-specific output data and a second measure indicative of a normalized form of k:th order central moment of the subband-specific output data, where k is an integer higher than three.Type: GrantFiled: December 28, 2006Date of Patent: February 28, 2017Assignee: GENERAL ELECTRIC COMPANYInventor: Mika Sarkela
-
Patent number: 9072482Abstract: Method, apparatus and computer program product for monitoring seizure activity in brain are disclosed. At least one parameter set sequence is derived from brain wave signal data obtained from a subject, wherein each parameter set sequence comprises sequential parameter sets and each parameter set comprises values for at least two signal parameters, the values being derived from the brain wave signal data. A path formed by each of the at least one parameter set sequence in a parameter space is determined, thereby to obtain at least one path. The parameter space is defined by the at least two signal parameters. At least one evolution indicator is calculated, each evolution indicator quantifying the evolution occurred in respective path formed in a given time period in the parameter space. The at least one evolution indicator is then employed to produce an indication of seizure activity in the brain wave signal data.Type: GrantFiled: September 16, 2010Date of Patent: July 7, 2015Assignee: GENERAL ELECTRIC COMPANYInventors: Mika Sarkela, Antti Tolonen
-
Patent number: 8768447Abstract: The invention relates to processing of physiological signal data in patient monitoring. In order to alleviate the problems caused by suppression waveforms in the analysis of physiological signal data, measurement data is derived from a segment of the time series of physiological signal data and valid measurement data is collected from the derived measurement data, thereby to form a set of valid measurement data. The collecting includes selecting measurement data that fulfills at least one predetermined threshold condition. Furthermore, at least a portion of the set of valid measurement data is supplied to a further processing stage when the amount of collected measurement data in the set is at least at a predetermined level. The deriving and collecting may be repeated for consecutive segments of the time series, in which case the supplying is performed for at least some of the consecutive segments of the time series.Type: GrantFiled: January 9, 2007Date of Patent: July 1, 2014Assignee: General Electric CompanyInventors: Miikka Ermes, Mika Särkelä
-
Patent number: 8708905Abstract: A method, device, and computer program product for monitoring the physiological state of a subject is disclosed. A first plurality of physiological signals are acquired from the subject and a second plurality of signal parameters are determined based on the first plurality of physiological signals. Relevant signal information is selected from among the signal information produced and at least one screen page is displayed at a time, thereby to make at least part of the signal information visible to a user. The signal information visible to the user on the at least one screen page may then be revised based on the selection and without user interaction, thereby to accelerate clinical decision-making and to diminish the possibility of undetected changes in the state of the subject.Type: GrantFiled: June 12, 2009Date of Patent: April 29, 2014Assignee: General Electric CompanyInventor: Mika Sarkela
-
Patent number: 8600493Abstract: Method, apparatus and computer program product for monitoring seizure activity in brain are disclosed. At least one parameter set time series is derived from brain wave signal data obtained from a subject, wherein each parameter set sequence comprises sequential parameter sets and each parameter set comprises values for at least two signal parameters, the values being derived from the brain wave signal data. In order to reduce susceptibility to inter-subject variations and to enhance adaptability to each recording, past EEG signal data of the subject is used to determine an envelope object that encompasses the parameter points that sequential parameter sets derived from the past signal data form in a parameter space. A reference point is also determined, whose location in the parameter space depends on the past signal data. At least one new parameter point is then obtained from the subject and an evolution indicator set is determined.Type: GrantFiled: July 25, 2011Date of Patent: December 3, 2013Assignee: General Electric CompanyInventors: Antti Tanner, Mika Särkelä
-
Publication number: 20130030317Abstract: Method, apparatus and computer program product for monitoring seizure activity in brain are disclosed. At least one parameter set time series is derived from brain wave signal data obtained from a subject, wherein each parameter set sequence comprises sequential parameter sets and each parameter set comprises values for at least two signal parameters, the values being derived from the brain wave signal data. In order to reduce susceptibility to inter-subject variations and to enhance adaptability to each recording, past EEG signal data of the subject is used to determine an envelope object that encompasses the parameter points that sequential parameter sets derived from the past signal data form in a parameter space. A reference point is also determined, whose location in the parameter space depends on the past signal data. At least one new parameter point is then obtained from the subject and an evolution indicator set is determined.Type: ApplicationFiled: July 25, 2011Publication date: January 31, 2013Applicant: GENERAL ELECTRIC COMPANYInventors: Antti Tanner, Mika Särkelä
-
Patent number: 8221330Abstract: The invention relates to a method and apparatus for assessing the reactivity observable in a certain physiological signal, especially the EEG signal, of a comatose subject. In order to obtain an objective and a reliable measure of the reactivity automatically and without the presence of a trained EEG specialist, a valid signal model is constructed for an EEG signal obtained from the subject. A time reference corresponding to a stimulus is applied and further signal data is obtained from the time series, the further signal data being subsequent to the time reference. By employing the further signal data, the method tests whether the signal model remains to be a valid signal model for the EEG signal also after the stimulus, and indicates, based on the test, whether reactivity is present in the physiological signal.Type: GrantFiled: November 5, 2010Date of Patent: July 17, 2012Assignee: General Electric CompanyInventors: Mika Sarkela, Juha Virtanen, Hanna E. Viertio-Oja, Tapani Salmi
-
Patent number: 8219187Abstract: In a method and apparatus for providing an indication suitable for assessing a physiological condition of a patient, at least two biosignals are obtained from the patient. The biosignals contain at least one common physiological data component, such as an EEG or EMG component. An analysis of each of the biosignals is carried out to obtain a complexity value for each of the biosignals. Or, the biosignals may be divided into their components and a complexity value is obtained for the biosignal components. Thereafter and on the basis of the complexity values, a complexity value indicative of at least one physiological data component present in the biosignals is selected and utilized to provide the physiological condition assessment indication of the patient.Type: GrantFiled: January 27, 2005Date of Patent: July 10, 2012Assignee: Instrumentarium CorporationInventor: Mika Särkelä
-
Patent number: 8145297Abstract: The invention relates to a method and apparatus for assessing the reactivity observable in a certain physiological signal, especially the EEG signal, of a comatose subject. In order to obtain an objective and a reliable measure of the reactivity automatically and without the presence of a trained EEG specialist, a time reference corresponding to a stimulus is detected and the physiological signal data obtained from the subject is aligned with the time reference. Two sets of values are determined for a measure indicative of the amount of irregularity in the physiological signal data, both sets including at least one value of the said measure and having defined positions with respect to the time reference in time domain. Based on the two sets, the apparatus determines whether reactivity is present in the physiological signal data.Type: GrantFiled: September 19, 2006Date of Patent: March 27, 2012Assignee: General Electric CompanyInventors: Hanna E. Viertiö-Oja, Mika Särkelä, Juha Virtanen, Tapani Salmi
-
Publication number: 20120071779Abstract: Method, apparatus and computer program product for monitoring seizure activity in brain are disclosed. At least one parameter set sequence is derived from brain wave signal data obtained from a subject, wherein each parameter set sequence comprises sequential parameter sets and each parameter set comprises values for at least two signal parameters, the values being derived from the brain wave signal data. A path formed by each of the at least one parameter set sequence in a parameter space is determined, thereby to obtain at least one path. The parameter space is defined by the at least two signal parameters. At least one evolution indicator is calculated, each evolution indicator quantifying the evolution occurred in respective path formed in a given time period in the parameter space. The at least one evolution indicator is then employed to produce an indication of seizure activity in the brain wave signal data.Type: ApplicationFiled: September 16, 2010Publication date: March 22, 2012Applicant: GENERAL ELECTRIC COMPANYInventors: Mika Sarkela, Antti Tolonen
-
Patent number: 8064993Abstract: The invention relates to a method and apparatus for assessing the reactivity observable in a certain physiological signal, especially the EEG signal, of a comatose subject. In order to obtain an objective and a reliable measure of the reactivity automatically and without the presence of a trained EEG specialist, a time reference corresponding to a stimulus is detected and the physiological signal data obtained from the subject is aligned with the time reference. Two sets of values are determined for a measure indicative of the amount of irregularity in the physiological signal data, both sets including at least one value of the said measure and having defined positions with respect to the time reference in time domain. Based on the two sets, the apparatus determines whether reactivity is present in the physiological signal data.Type: GrantFiled: November 14, 2005Date of Patent: November 22, 2011Assignee: General Electric CompanyInventors: Hanna E. Viertiö-Oja, Mika Särkelä, Juha Virtanen, Tapani Salmi
-
Publication number: 20110087127Abstract: The invention relates to a method and apparatus for assessing the reactivity observable in a certain physiological signal, especially the EEG signal, of a comatose subject. In order to obtain an objective and a reliable measure of the reactivity automatically and without the presence of a trained EEG specialist, a valid signal model is constructed for an EEG signal obtained from the subject. A time reference corresponding to a stimulus is applied and further signal data is obtained from the time series, the further signal data being subsequent to the time reference. By employing the further signal data, the method tests whether the signal model remains to be a valid signal model for the EEG signal also after the stimulus, and indicates, based on the test, whether reactivity is present in the physiological signal.Type: ApplicationFiled: November 5, 2010Publication date: April 14, 2011Applicant: GENERAL ELECTRIC COMPANYInventors: Mika Särkelä, Juha Virtanen, Hanna E. Viertiö-Oja, Tapani Salmi
-
Publication number: 20100317931Abstract: A method, device, and computer program product for monitoring the physiological state of a subject is disclosed. A first plurality of physiological signals are acquired from the subject and a second plurality of signal parameters are determined based on the first plurality of physiological signals. Relevant signal information is selected from among the signal information produced and at least one screen page is displayed at a time, thereby to make at least part of the signal information visible to a user. The signal information visible to the user on the at least one screen page may then be revised based on the selection and without user interaction, thereby to accelerate clinical decision-making and to diminish the possibility of undetected changes in the state of the subject.Type: ApplicationFiled: June 12, 2009Publication date: December 16, 2010Applicant: The General Electric CompanyInventor: Mika Sarkela
-
Patent number: 7844324Abstract: The invention relates to a method and apparatus for assessing the reactivity observable in a certain physiological signal, especially the EEG signal, of a comatose subject. In order to obtain an objective and a reliable measure of the reactivity automatically and without the presence of a trained EEG specialist, a valid signal model is constructed for an EEG signal obtained from the subject. A time reference corresponding to a stimulus is applied and further signal data is obtained from the time series, the further signal data being subsequent to the time reference. By employing the further signal data, the method tests whether the signal model remains to be a valid signal model for the EEG signal also after the stimulus, and indicates, based on the test, whether reactivity is present in the physiological signal.Type: GrantFiled: February 14, 2007Date of Patent: November 30, 2010Assignee: The General Electric CompanyInventors: Mika Särkelä, Juha Virtanen, Hanna E. Viertiö-Oja, Tapani Salmi
-
Patent number: 7805187Abstract: The invention relates to a method and apparatus for monitoring the anesthetic state of a subject. Physiological signal data including EEG and possibly also EMG signal components is acquired from a subject and supplied to a monitoring process configured to derive, based on the said data, a state index indicative of the anesthetic state of the subject. In order to extend the applicability of present-day monitoring processes, the operation of the monitoring process is controlled according to whether at least one drug inducing high frequency EEG signal components is administered to the subject. The presence of the high frequency EEG signal components in the physiological signal data may be detected automatically.Type: GrantFiled: July 7, 2005Date of Patent: September 28, 2010Assignee: The General Electric CompanyInventors: Mika Särkelä, Satu Jääskeläinen, Jaakko Långsjö, Anu Maksimow, Elina Salmi, Harry Scheinin
-
Patent number: 7783343Abstract: The invention relates to a method and apparatus for monitoring the cerebral state of a subject. At least one of a first and second parameters is derived from the physiological signal data obtained from the subject, wherein the first parameter is indicative of the sum of spectral values of the physiological signal data in a first frequency band lying above high frequency EEG activity and the second parameter is indicative of the relative magnitudes of a first sum of k-th order spectral values and a second sum of n-th order spectral values. The second sum is calculated over a frequency band lying above high frequency EEG activity (k>2 and n>1). A state index is then formed, which is dependent on the at least one parameter and indicative of the cerebral state of the subject. The first and second parameters may be used in the Bispectral Index (BIS™) algorithm.Type: GrantFiled: July 7, 2005Date of Patent: August 24, 2010Assignee: The General Electric CompanyInventors: Mika Särkelä, Hanna E. Viertiö-Oja, Satu Jääskeläinen, Jaakko Långsjö, Anu Maksimow, Elina Salmi, Harry Scheinin
-
Patent number: 7630758Abstract: The invention relates to a mechanism for detecting whether a sleep state of a subject is due to natural sleep or induced by drugs. An indicator indicative of the activation of the autonomic nervous system of the subject is derived based on cardiovascular signal data measured from the subject and the indicator is employed to identify whether the sleep of the subject is drug-induced sleep or natural sleep. The identification is performed upon detection of a sleep state.Type: GrantFiled: June 22, 2006Date of Patent: December 8, 2009Assignee: General Electric CompanyInventors: Petteri Lapinlampi, Mika Sarkela