Classifications

• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B5/00—Measuring for diagnostic purposes; Identification of persons
  • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
  • A61B5/7235—Details of waveform analysis
  • A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
  • A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B5/00—Measuring for diagnostic purposes; Identification of persons
  • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
  • A61B5/316—Modalities, i.e. specific diagnostic methods
  • A61B5/369—Electroencephalography [EEG]
  • A61B5/377—Electroencephalography [EEG] using evoked responses
  • A61B5/38—Acoustic or auditory stimuli
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B5/00—Measuring for diagnostic purposes; Identification of persons
  • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
  • A61B5/316—Modalities, i.e. specific diagnostic methods
  • A61B5/369—Electroencephalography [EEG]
  • A61B5/372—Analysis of electroencephalograms
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B5/00—Measuring for diagnostic purposes; Identification of persons
  • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
  • A61B5/7235—Details of waveform analysis
  • A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B5/00—Measuring for diagnostic purposes; Identification of persons
  • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
  • A61B5/7271—Specific aspects of physiological measurement analysis
  • A61B5/7275—Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B5/00—Measuring for diagnostic purposes; Identification of persons
  • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
  • A61B5/7271—Specific aspects of physiological measurement analysis
  • A61B5/7278—Artificial waveform generation or derivation, e.g. synthesising signals from measured signals
• • A—HUMAN NECESSITIES
  • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
  • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
  • A61B5/00—Measuring for diagnostic purposes; Identification of persons
  • A61B5/74—Details of notification to user or communication with user or patient ; user input means
  • A61B5/742—Details of notification to user or communication with user or patient ; user input means using visual displays
  • A61B5/743—Displaying an image simultaneously with additional graphical information, e.g. symbols, charts, function plots
• • G—PHYSICS
  • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
  • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
  • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
  • G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients

Definitions

• the present invention relates to methods of generating an indicator for assessing the probability of waking a patient in coma.
• the invention is particularly applicable to the analysis of electrophysiological signals and more particularly electroencephalographic signals.
• the field of the invention relates to the methods of generating graphical indicators and the representation of these indicators in a two-dimensional graph.
• the post-anoxic encephalopathy and its prognosis is evaluated by G electroencephalogram, said EEG.
• G electroencephalogram said EEG.
• the absence of an N20 response to somatosensory evoked potentials after stimulation of the median nerve has a specificity almost equal to 100% to predict the absence of awakening in the adult.
• the real lack of response in ICU patients is difficult to assert because of the electrical environment that generates many artifacts making it extremely difficult to interpret the low amplitude response of the evoked potential in the child and the traumatized head.
• auditory evoked potentials are recorded with electrodes placed on the scalp translating the brain response to repeated and averaged auditory stimulations.
• the "MisMatch Negativity" method known as the MMN, allows to represent a cerebral integration of automatic detection of these infrequent and random stimulations in a continuous series of sounds.
• the MMN method does not represent either a reliable predictive method or easy to use in resuscitation services. It is therefore desirable to define a method for generating a predictive indicator of the state of a patient in a coma, in particular to evaluate a probability of awakening.
• the present invention relates to a method of generating a status indicator of a given patient in a coma, comprising the steps of:
• generating at least one auditory stimulation by generating a sequence of auditory stimuli, said sequence producing evoked potentials in the given patient;
• the estimation of at least one pair of values corresponding to a first parameter and a second parameter extracted from the first acquired signal the calculation of the first parameter comprising an estimate of the variance of the amplitude of the first signal in a predefined time window, the calculation of the second parameter comprising an estimation of the correlation of two segments of the first signal; generating a state indicator defined by the pair of values of the first and second parameters, said values defining coordinates of a point in a reference base.
• An advantage is to determine a representation in which a status indicator of a patient can be used to classify it vis-à-vis a repository with other status indicators corresponding to other patients.
• At least one stimulation comprises at least one auditory stimulus sequence comprising at least one periodic pattern of predefined frequency.
• One advantage is to determine a sequence to optimize the relevance of the indicator.
• such a stimulus is easily reproducible and can serve as a reference for a set of patients.
• the calculation of the first parameter comprises the following steps:
• An advantage of filtering is to obtain a signal whose exploitation is improved.
• the advantage of segmentation is to determine a portion of signal that can be averaged.
• An advantage of the average is to remove a set of artifacts that can disturb the calculation of the variance.
• the calculation of the second parameter comprises the following steps:
• first segmentation of the first signal segment on a third time window generating a plurality of epochs of duration corresponding to the duration of the third window, each of said epochs having a predefined duration and being synchronized with a stimulus of at least one sequence of auditory stimuli;
• second segmentation of the second signal segment on the third time window generating a plurality of epochs of duration corresponding to the duration of the third window, each of said epochs having a predefined duration and being synchronized with a stimulus of at least one sequence of auditory stimuli;
• the first time window and the third time window are of the same duration, corresponding to the inverse of the predefined frequency.
• One advantage is to homogenize the representation of the pair of selected points.
• the second time window and the fourth time window are of substantially equal duration and between 20 ms and 320 ms.
• the duration of the first and second segments is between 5 minutes and 25 minutes, preferably of the order of 10 minutes.
• the generation of the state indicator for said given patient comprises calculating a probability that said state indicator belongs to a predefined class of states from a Gaussian estimator and rules. from Bayes.
• the generation of the state indicator for said given patient comprises calculating a probability that said state indicator belongs to a predefined class of states from the k-neighbor method.
• the method comprises a step of measuring a first distance between said state indicator and a first set of points having coordinates represented in the same reference base and measuring a second distance between said status indicator and a second set of points having coordinates represented in the same reference base.
• the method comprises a step of comparing the first distance and the second distance.
• the state indicator is associated with a probability calculated from a probability classification model or a supervised learning classification method.
• the classification comprises two classes.
• the steps are repeated for a second patient and / or other patient associated with an electroencephalographic signal or recorded data of a database and further comprises:
• said method comprises:
• the present invention furthermore relates to a device comprising a memory for storing data, in particular coordinates of a graph having previously been calculated, and a computer for carrying out operations on signals acquired by a measuring means such as an electrode.
• said calculator making it possible, in particular, to carry out comparison, average calculation or signal correlation operations, characterized in that it implements the steps of the method.
• the present invention further relates to a device for generating a status indicator of a given patient in a coma, comprising:
• a stimulation module configured to generate at least one auditory stimulation by generating a sequence of auditory stimuli, said sequence producing evoked potentials in the given patient;
• an acquisition module configured for acquiring a first electroencephalographic signal produced by said given patient from at least one electrode
• a calculation module configured for estimating at least one pair of values corresponding to a first parameter and a second parameter extracted from the first acquired signal, comprising the estimation of a first pair of values such as the calculation of the first parameter includes an estimate of the variance of the amplitude of the first signal in a predefined time window and the computing the second parameter includes estimating the correlation of two segments of the first signal;
• a generation module configured to generate a status indicator for the or each pair of values of the first and second parameters, said values defining coordinates of a point in a reference base.
• At least one stimulation generated by the stimulation module comprises at least one auditory stimulus sequence comprising at least one periodic pattern of predefined frequency.
• the calculation module is configured to calculate the first parameter of the first pair of values according to the following steps:
• the calculation module is configured to calculate the second parameter of the first pair of values according to the following steps:
• first segmentation of the first signal segment on a third time window (1 s) generating a plurality of epochs of duration corresponding to the duration of the third window, each of said epochs having a predefined duration and being synchronized with a stimulus of less a sequence of auditory stimuli;
• second segmentation of the second signal segment on the third time window (1 s) generating a plurality of epochs of duration corresponding to the duration of the third window, each of said epochs having a predefined duration and being synchronized with a stimulus of less a sequence of auditory stimuli;
• the calculation module is configured for estimating a second pair of values extracted from the first acquired signal, such that the calculation of the first parameter comprises an estimate of the number of local extrems in the first signal in a predefined time window and the calculation of the second parameter comprises the sum of the absolute values of the potential value differences of the first signal between two successive local extremums in a predefined time window, allowing the generation of a second state indicator defined by the second pair of values of the first and second parameters.
• the first time window and the third time window are of the same duration, corresponding to the inverse of the predefined frequency.
• the generation module is configured to generate the status indicator for said given patient from the calculation of a probability that said state indicator belongs to a predefined class of states from a Gaussian estimator, Bayes rules and / or a support vector machine.
• the generation module is configured to generate the status indicator for said given patient from the calculation of a probability that said state indicator belongs to a predefined class of states from the k nearest neighbors method. According to one embodiment, the generation module is configured to generate the state indicator for said given patient from the calculation of a probability that said state indicator belongs to a predefined class of states from the minimum between the probabilities estimated from the k nearest neighbor method, the k nearest weighted neighbor method, the Gaussian estimator, the Bayes rules and / or the support vector machine.
• the generation module is configured to generate the status indicator for said given patient from the calculation of a probability that the first state indicator belongs to a predefined class of states from the k nearest neighbors method; and calculating a probability that the second state indicator belongs to a predefined class of states from the k nearest weighted neighbor method.
• the probability that the patient belongs to a predefined class of states is estimated as the minimum between the probability calculated for the first indicator from the k nearest neighbors method and the calculated probability for the second indicator. state from the k nearest weighted neighbor method.
• a calculation module is configured to measure a first distance between said status indicator and a first set of points having coordinates represented in the same reference base and measuring a second distance between said indicator. state and a second set of points having coordinates represented in the same reference base.
• a calculation module is configured to compare the first distance and the second distance.
• the state indicator is associated with a probability calculated from a probability classification model or a supervised learning classification method.
• the classification comprises two classes.
• a calculation module is configured to repeat the steps for a second patient and / or other patient associated with an electroencephalographic signal or stored data of a database and further implement the following steps:
• the present invention further relates to a system comprising an auditory stimulus generator emitted with a predefined period of time for a predefined duration and an electrode assembly for measuring a cerebral electrical activity of a patient, which system comprises a device for the generation of a status indicator of said patient as described above.
• a subject refers to a mammal, preferably a human.
• a subject may be a "patient", i.e., a warm-blooded animal, more preferably a human, who is waiting for or receiving medical attention or has been / is / will be subject of a medical procedure, or is monitored for the development of a disease.
• the subject is an adult (eg, a subject over the age of 18).
• the subject is a child (e.g., a subject under the age of 18).
• the subject is a man.
• the subject is a woman.
• stimulus or stimuli means any physical, chemical or biological element or any other event, such as an audible or audible or visual event, capable of triggering phenomena in the body, including electrical phenomena, electrophysiological, muscular or endocrine nerves. More particularly, in the context of the invention a stimulus or stimuli will be sound sequences broadcast to a patient in a coma.
• coma refers to a physiological condition of a subject, or patient, who has lost consciousness. In particular, it denotes a prolonged loss of consciousness and / or alertness.
• Figure 1 is a diagram of an embodiment of the system of the invention, showing the main elements implementing the steps of the method of the invention.
• FIG. 2 is a two-dimensional graph according to one embodiment of the invention comprising a distribution of the awakening probabilities according to the invention in which a point generated by the method of the invention is displayed.
• FIG. 3 is a flowchart of one embodiment of the invention in which the main steps of the method of the invention are represented, this embodiment involving a step of comparing data from a patient with a patient. Corpus of recorded data.
• FIG. 4 is a flowchart of an embodiment of the invention in which the main steps of the method of the invention are represented, this embodiment involving a step of graphically representing data from a patient with a corpus of data generated on the same representation.
• Figure 5A is a representation of a signal acquired in the context of the method of the invention.
• Fig. 5B is a representation of a filtered signal resulting from the signal filtering of Fig. 1A in accordance with a step of the method of the invention.
• Figure 5C is a representation of an averaged signal resulting from the averaging of the filtered signal of Figure 5B in accordance with a step of the method of the invention.
• Figure 5D is a representation of a signal resulting from the average of signals acquired from a plurality of electrodes.
• Figure 5E is a representation of a filtered signal resulting from filtering the average signal of Figure 5D in accordance with a step of the method of the invention.
• Figure 5F is a representation of a mean signal resulting from the average in a 500 ms window of the filtered signal of Figure 5E in accordance with a step of the method of the invention.
• FIG. 6A is a two-dimensional graph according to an embodiment of the invention comprising a wake-up probability distribution according to a Gaussian-Bayesian classification method in which a point (s (X), R (X, Y)) generated by the method of the invention is displayed.
• FIG. 6B is a two-dimensional graph according to an embodiment of the invention comprising a wakeup probability distribution according to a k-neighbor classification method in which a point (s (X), R (X, Y)) generated by the method of the invention is displayed.
• FIG. 6C is a two-dimensional graph according to an embodiment of the invention comprising a distribution of the awakening probabilities according to a Gaussian-Bayesian classification method in which a point (NE,
• FIG. 6D is a two-dimensional graph according to an embodiment of the invention comprising a distribution of the awakening probabilities according to a k-Neighbor classification method in which a point (NE,
• FIG 1 shows an embodiment of the system of the invention.
• the system of the invention comprises an GEN SA auditory stimulating generator.
• the generated GSA auditory stimuli are preferably repeated or periodically transmitted.
• a loudspeaker, an enclosure or any other device making it possible to emit a sound or a sound sequence may be used.
• the generator GEN_SA is preferably arranged next to a patient H during its use.
• the system of the invention comprises a set of ELEC electrodes intended to be affixed in contact with a patient, such as a patient H.
• the ELEC electrodes are intended to measure a cerebral activity of the patient H. They make it possible, in particular, to acquire signals Si, Si, Sn and deliver the acquired signals to a calculator K.
• the system of the invention comprises said computer K. The latter is configured to execute instructions for deriving output parameters of the acquired signals Si, Si, Sn by the electrodes ELEC.
• the system of the invention further comprises an AF F display for displaying points in a representation of wakeup probability distributions of a plurality of patients who have been in coma or are still in coma.
• the AFF display makes it possible to display processed data previously acquired from a plurality of patients H having been in the co. These data make it possible to consolidate a distribution of probabilities of awakening or not of a set of patients.
• the AFF display makes it possible to directly deduce a conclusion by reading the position of the generated point within the probability distribution.
• the comparison of a generated point with the position of the other points can be performed with the naked eye by an operator or can be performed automatically by means of a calculator from the calculation of the distance between said points.
• One of the advantages of the invention is to generate a graph in a coordinate system whose axes correspond to parameters deduced from the acquired signals.
• Figure 2 gives an example of a possible representation of a wakeup probability distribution.
• the COORD coordinate system employed may be defined on the abscissa and on the ordinate by spectral parameters or resulting from a processing of the signals acquired by the electrodes.
• the parameters may result from one or more operations on the acquired signals, namely averages, maximum values, standard deviations, variances, correlations, or comparisons or superimpositions of acquired signals.
• the invention relates to a method for estimating a waking indicator of a patient in a coma.
• the method includes generating at least one auditory stimulation by generating a sequence of GSA auditory stimuli.
• the sequence produces evoked potentials in the given patient H in coma.
• Figure 3 shows this step denoted GSA.
• the auditory stimulation is configured to induce a cognitive process in the stimulated subject.
• the human brain is able to extract models or regularities in its environment, for example object A is always followed by object B but never by object C.
• the brain can detect transition probabilities automatically that is, even when the subject's attention is distracted or when the stimuli are presented below the consciousness threshold. Automatic brain responses to a violation of a rule (or regularity) can also be detected if the stimuli are in a near or local time neighborhood (i.e., a few seconds). Incompatible responses can be produced with complex sequences such as a melody or rhythm, even in unconscious subjects.
• the auditory stimulation is caused by the emission of a predefined sound sequence.
• the sequence includes, for example, a series of sounds emitted at regular intervals with the same spectral content.
• the sounds are emitted with a preset fo frequency.
• the repetition period may be for example 1 second. According to various embodiments, the period may be between a few milliseconds and several minutes.
• the sound sequence comprises spectral patterns that evolve as a series of sounds ranging from high notes to low notes or vice versa.
• the sequence is then repeated according to a period of sequences that may range from a few seconds to several hours.
• the transmitted sequence may include noises of different frequencies.
• the sequence can be repeated identically with a few random and infrequent modifications (i.e. deviant stimuli), for example from 10 to 20% of the standard sequences.
• the auditory stimulation comprises a plurality of auditory tests having a predefined test interval, each auditory test consisting of N consecutive auditory stimuli having a predefined duration with a predefined interval between the auditory stimuli.
• the auditory stimulation has a first percentage of standard local tests comprising N identical auditory stimuli and a second percentage of locally deviant tests comprising the same first identical auditory stimuli and the same auditory stimulus as the previous N1 stimuli.
• a sequence is thus composed of a standard sound repeated a number of times, followed by a deviant sound. The comparison to a condition in which all the sounds of the sequence are standard generally reveals the occurrence of the negativity of the discordance.
• the deviant sequence is very common in stimulation, subjects expect the last sound to be deviant.
• the sequence may comprise the emission of a succession of five identical regularly spaced sounds and a note (ie non-deviant stimuli) or a sound having a different spectral content (ie deviant stimulus) .
• a note ie non-deviant stimuli
• a sound having a different spectral content ie deviant stimulus
• An interest in producing a wide variety of sequences is to test different sources of stimulation to constitute a library of sequences to be adapted to the use of the invention. Another interest is to make it possible to produce comparable sequences from one patient to another in order to validate or invalidate particular sequences.
• the method of the invention comprises the acquisition of an electroencephalographic signal, said EEG signal, produced by said patient from at least one electrode system comprising for example at least one active electrode and a reference electrode.
• Figure 3 and Figure 4 show this step denoted ACQ.
• the means for measuring the electroencephalographic signals comprise at least two surface electrodes.
• a first front reference electrode and a second central active electrode (Cz) are arranged on the cranial surface of a patient.
• the means for measuring the electroencephalographic signals comprise at least the electrodes Fz, Cz, C3, C4, T3, T4 according to the system 10-20.
• the electrodes are electrodes intended to be mounted, for example, on a helmet which itself is intended to be worn by a patient.
• the method comprises a step of estimating at least one pair of values corresponding to a first parameter Pi and a second parameter P2. This step is written EST in FIG. 3 and FIG. 4.
• the first parameter Pi and the second parameter P2 are extracted from the first acquired signal Si or from the processed signal after its acquisition, for example, by filtering or averaging. They can for example restore properties of the signals over shorter or shorter times.
• the first parameter Pi can be developed so as to restore a property of the signal over a short period corresponding for example to the duration of the cognitive tasks.
• the first parameter Pi can then be perceived as a local property of the subject's responses.
• the second parameter P2 can be elaborated or chosen by considering properties of the signal over longer periods.
• the first parameter Pi is estimated by performing different operations on an acquired signal Si. It can notably be filtered, segmented, averaged to define a pattern in which a selection of a signal extract is used to calculate an amplitude variance.
• the method comprises a step of filtering the acquired EEG signals.
• FIG 5 A illustrates a representation of an EEG signal acquired 10 wherein displaying the ordinate "P”, the values of the potentials to the electrode Cz, and the abscissa "t", the time in seconds. On the graph are also represented the moments at which the stimulations 12 are generated.
• Figure 5B shows the filtered signal 1 1.
• FIG. 5C represents an averaged response 13 brought back to G time interval [0; 1s] to define epochs.
• the time interval [0; 1s] defines a first time window Fl.
• This first window F1 is configurable according to the embodiment envisaged.
• This preliminary step makes it possible to average the responses in order to highlight the response of P EEG to the stimulations.
• the epochs extracted are all synchronized with the frequency fo at which the stimulations are produced. 8
• the filtering and averaging steps are steps involved for G estimation of the parameter Pi
• an extracted parameter corresponds to the variance s (X) of the amplitude of the signal X (t) in the time interval of 20 to 320 ms. This interval defines a second time window F
• the variance of the amplitude can be calculated from a calculating means such as a calculator.
• the time scale chosen advantageously corresponds to response time scales of neural networks involved in cognitive tasks.
• the time scales considered may be more selective, for example from 60 ms to 200 ms.
• the time interval is divided into different sub-ranges, for example [20; 120 ms], [120 ms; 220ms], [220 ms; 320 ms].
• This subdivision makes it possible, for example, to refine the analyzes by segmenting the responses of the neural networks to differentiated cognitive tasks.
• intermediate calculations of amplitude variances can be made and then combined.
• the calculation of the amplitude variance is carried out over the range of durations ranging from 20 ms to 320 ms.
• the calculation of the variance of the amplitude accounts for the amplitude of the fluctuations represented by the basal activity of the neural networks.
• Variance is used to analyze evoked signals generated by a response to standard periodic auditory stimuli.
• FIG. 2 represents in ordinate the parameter corresponding to the variance of the amplitude of the signal acquired or processed after filtering and averaging.
• the averaging step makes the calculation more reliable because of the different measures taken into account.
• the filtering stage makes it possible to overcome the noise and artefacts that would not result directly from the electrical activity produced by the stimulations.
• the parameter estimation step comprises estimating a parameter rendering a property of the signals over a longer period. It is an indicator resulting from a correlation of two segments SEGi and SEGr of the acquired or processed signals.
• the acquisition time DA is 20 minutes. According to other examples, it may be between a few minutes and several minutes. Preferably the duration chosen is between 10 min and 40 min.
• the acquisition time DA is segmented into two ranges of duration D! substantially equal.
• the two ranges [1; 10] min and [10; 20] min can define two successive ranges for segmenting the first signal Si.
• the number of segmentations can be from three ranges to a few tens of ranges.
• the method includes a step of segmenting each duration segment Di into a plurality of segmented epochs in a predefined time window. This is a third time window Fr. This window is advantageously of the same duration as the first window which made it possible to calculate the parameter Pi.
• the estimation step of the parameter P2 comprises the averaging of the epochs on each of the segmented time windows defined in the preceding paragraph.
• G estimation of the second parameter P2 comprises a generation of two signals, denoted X (t) and Y (t).
• the epochs are defined in the time interval [0; 1] s.
• the normalization of the window Fr may be shorter or longer, such as for example a half-second or two seconds.
• the step of estimating the parameter P2 comprises a calculation of the temporal correlation of these two signals by the function R (X, Y) over a time window F 4 .
• the time window F 4 has a duration substantially equal to that of the second time window F2, that is to say in the interval [20, 320] ms.
• a portion of the signal averaged over the window Fs is used to calculate the temporal correlation R (X, Y).
• the correlation function R can be written as:
• R (X, Yfi [ ⁇ (X (t) - m (X)) ⁇ (Y (t) - m (Y)>] / [ ⁇ X (t) 2 > ⁇ Y (t) 2 >], or ⁇ .> represents the time average and m (X) is the average of the variable X.
• deviant stimuli represent approximately one tenth of the evoked responses.
• the acquired signals of several electrodes are summed and then the average signal obtained is filtered and averaged over a predefined time window F5.
• FIG. 5D illustrates a representation of an average signal resulting from the average of the acquired signals of electrodes Cz, C3, C4 and Fz as a function of time in seconds. On the graph is also represented the moment at which the deviant stimulus is generated, by a vertical line.
• FIG. 5F represents an averaged response brought back to the time interval [0-500 ms] following the emission of a deviating stimulus.
• an extracted parameter corresponds to the number of local extrems NE in said average signal.
• an extracted parameter corresponds to the sum of the absolute values of the differences, between two local and successive extremums, of the potential of the average signal V (ei) according to the formula
• parameters calculated on a time window of 500 ms following a deviant stimulus, make it possible to evaluate the response of the subject to the deviant stimuli.
• the method of the invention makes it possible to define coordinates from a pair of values (Ps; P).
• the point of coordinates ⁇ Pi, P2 ⁇ is generated in a reference base.
• the reference base constitutes a standardized reference frame
• the reference base is materialized by a graph comprising a reference to two axes (Ox), (Oy) defining an abscissa and a ordered.
• the method of the invention makes it possible to define a first coordinate system from the value pair (s (X), R (X, Y) ⁇ and / or a second coordinate system from the value pair ⁇ NE, jAVj ⁇
• the first system is associated with responses to non-deviant stimuli and the second system is associated with the responses evoked by deviant stimuli.
• the method of the invention comprises generating a graph comprising a plurality of points defining a reference base displayed on the same graph.
• Figure 2 shows a first set of ENS J points defining black triangles and belonging to a given first class of states Ci of patients, and a second set ENS? points defining white squares and belonging to a second class C? of given states of patients.
• the two-dimensional representation of the data is obtained by generating a point for a patient H given from the values of the parameters Pi and P? which have been obtained following a phase of auditory tests and measurement of brain activity. This step is denoted GGR in FIGS. 3 and 4.
• FIG. 2 thus represents a plurality of points, each point corresponding to a test performed for a given patient H.
• Figure 2 shows a distribution of H patients who have been in coma or are still in the cornus.
• two time windows of 10 min have been configured with one measurement, in particular by considering the electrode Cz.
• the Ox axis, the correlation R (X, Y), and along the axis Qy, the standard deviation s (X) of the noise that is to say, the fluctuations of the averaged EEG signal.
• the deceased patients are represented by black triangles and constitute the ENSi set.
• Patients who have survived and woke up are represented by white squares and constitute the ENS2 set.
• Figure 3 shows the main steps of an embodiment of the method for generating a status indicator.
• FIG. 4 represents an embodiment of the method of the invention comprising additional steps for associating a probability with the status indicator.
• the invention makes it possible to assign to the state indicator a probability of awakening of the patient H, that is to say a probability that he is coming out of the coma.
• the method of the invention therefore comprises a representation of probabilities on a graph making it possible to assign a given probability as a function of the position of point 2 in the graph.
• the method includes identifying the region of interest RJ for which a subset of selected patients shares an identical probability of belonging to the same class of the classification. predefined, for example in this case Ci or C2. This step is noted ID in Figure 4.
• the method is then able to deduce an association between the point generated on the graph and a waking probability according to the position of the point.
• the method may then comprise an automatic generating step, denoted GPROB, of a probability PR that the first patient H belongs to one class or another.
• FIGS. 6A, 6B, 6C and 6D show the following detailed examples of representations of the probabilities making it possible to calculate the chances that a patient H has to wake up or not from his coma.
• the graph represents a distribution of probabilities and thus generates an indicator in a graph without specifically allowing to deduce a diagnosis.
• the invention does not include generation of a two-dimensional representation but an alternative step which comprises calculating a distance between a new generated point 2 and a set of points ENSi or ENS? of a given class of state.
• a distance such as a Euclidean distance or any other distance that can be used in the context of the invention.
• the distance di d (2, ENSi) defining the distance between point 2 of FIG. 2 from a new patient H and the set ENSi is calculated.
• the distance d 2 d (2, ENS?) Defining the distance between the point 2 of Figure 2 of a new patient H and the EN82 set.
• the two distances di, d2 are then compared and a coefficient is assigned to point 2 which can be, for example, weighted by the measure of the distance or a ratio of the two distances ds, ⁇
• the coefficient can also be interpreted as a probability.
• the method of the invention comprises a step of defining so-called survival regions. This step improves the accuracy of the calculation of the probability that will be assigned to a new point generated in the graph. It also allows you to weight the distance when it is used.
• FIGS. 6A and 6C show a first embodiment in which a statistical classifier is applied in order to be able to assign a probability at any point of the card, or which would be added to the two-dimensional representation Ox and Oy as defined previously with Pi and P 2 .
• the two-dimensional representation is based on the coordinate system js (X), fX, Y) associated with responses to non-deviant stimuli, and in Fig.
• n the mean and the estimated covariance matrix for the two classes Ci (patient alive) and C2 (deceased patient) are represented.
• the probability of each class is calculated empirically using, for example, a maximum likelihood estimator: n
• ns is the number of surviving H patients and n is the number of H patients who died.
• the X (x, y) points associated with surviving patients follow a normal multidimensional distribution.
• conditional probability of having X e Ci and having the coordinates of the point associated with a subject (patient) equal to x, with a probability for class C i (patient alive), is given by: p - - n 1 - n s + n d
• Figures 6B and 6D represent an alternative for establishing a probability distribution on a two-dimensional graph.
• the two-dimensional representation is based on the coordinate system ⁇ s (X), R (X, Y) ⁇ associated with the responses to the non-deviant stimuli, and in FIG. 6D it is based on the coordinate system (NE). ,
• the nearest-k method involves taking k the nearest neighbors into account by calculating a ratio for the probability of belonging to a class.
• the probability of belonging to the class Ci of "survivors" being given the distribution of points x is calculated as the number of neighboring points belonging to the class of "survivors" on the total of K neighboring points. This probability can be calculated empirically by the following relation:
• the method therefore makes it possible to assign a tracking probability to a given patient, for example by visualizing the position of the corresponding point on a two-dimensional representation as shown in FIG. 6A, 6B, 6C or 6D.
• an alternative for establishing a probability distribution on a two-dimensional graph consists in using a supervised learning method, in particular a vector support machine (SVM).
• SVMs solve problems of discrimination, that is, decide which class a sample belongs to.
• the SVM is used to determine the separator hyperplane that best separates the classes Ci and CL.
• the kernel trick is used to overcome the absence of a linear separator present in the species problem, which consists of reconsidering the problem in a larger dimension space. In this higher dimension space, the points associated with the two classes are well separated. If the classes are not well separated, a penalty is associated with each misclassified point.
• the k nearest neighbor method is used to classify responses to deviant stimuli.
• an alternative classification method is used to classify responses to non-deviant stimuli.
• a weighted nearest neighbor method can be used by adding distance-related weights to the points in the data-base.
• ) in a given class among classes Cl and C2 is calculated on the basis of the number of k nearest neighbors Nk (Pt) belonging to the given class which are selected, from the set of pre-existing points, from the Euclidean distance between Pt and each pre-existing point weighted by a weight.
• the weight of each pre-existing point corresponds to the inverse of the distance between Pt and this point.
• the probability distribution of the point Pt associated with the patient H belonging to the class Ci of "survivors” is calculated for each patient H for the coordinates Pts in the first system of the coordinates (s (X), R (X, Y) ⁇ and for the coordinates Pt2 in the second coordinate system ⁇ NE,
• calculating a probability that said state indicator 2 belongs to a predefined class of states Ci, C2 is defined as the minimum between the probabilities estimated from the method of the k nearest neighbors, the weighted k nearest neighbor method, Gaussian estimator, Bayes rules and / or support vector machine.
• the method may comprise a statistical validation step. This step is performed by considering a predetermined number of patients H, for example 20, 30 or 40. In this data validation step, the data corresponding to the new patient is then excluded.
• An interest of the method is to generate a variable that can correspond to a probability of awakening.
• the method when implemented by a computer can then define a prediction tool to predict the survival rate of H patients in coma.

Landscapes

• Health & Medical Sciences (AREA)
• Life Sciences & Earth Sciences (AREA)
• Engineering & Computer Science (AREA)
• Physics & Mathematics (AREA)
• Public Health (AREA)
• General Health & Medical Sciences (AREA)
• Veterinary Medicine (AREA)
• Animal Behavior & Ethology (AREA)
• Surgery (AREA)
• Molecular Biology (AREA)
• Medical Informatics (AREA)
• Heart & Thoracic Surgery (AREA)
• Biophysics (AREA)
• Pathology (AREA)
• Biomedical Technology (AREA)
• Artificial Intelligence (AREA)
• Psychiatry (AREA)
• Physiology (AREA)
• Computer Vision & Pattern Recognition (AREA)
• Signal Processing (AREA)
• Psychology (AREA)
• Evolutionary Computation (AREA)
• Mathematical Physics (AREA)
• Fuzzy Systems (AREA)
• Acoustics & Sound (AREA)
• Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
• Radiology & Medical Imaging (AREA)
• Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)

Applications Claiming Priority (2)

Publications (1)

Family

ID=63683955

Family Applications (1)

Country Status (4)

Families Citing this family (3)

Family Cites Families (4)

• 2018
  • 2018-03-22 FR FR1852473A patent/FR3079129B1/fr active Active
• 2019
  • 2019-03-22 US US16/982,174 patent/US20210022638A1/en active Pending
  • 2019-03-22 EP EP19719344.4A patent/EP3768154A1/de active Pending
  • 2019-03-22 WO PCT/FR2019/050664 patent/WO2019180393A1/fr active Application Filing

Also Published As

Similar Documents

Legal Events