Evaluation of pain disorders via expert system
AssigneeCerebral Diagnostics Canada Incorporated
InventorsMark S. Doidge, Mario Garingo
Life of this patent
Estimating the term…
Abstract
Systems and methods are provided for evaluating a pain disorder. A stimulus is applied to a subject and an evoked potential is obtained from at least one electrogram of the subject. A set of features is extracted from the evoked potential including features from at least two of a set of features representing connectivity between regions of the brain, a set of morphology features, a set of features representing time and frequency, a set of signal decomposition features, and a set of features representing entropy. A clinical parameter relating to a pain disorder is assigned to the subject from the extracted set of features with a machine learning model.
Claims16
A method for diagnosing a mechanical pain disorder comprising:
- applying a stimulus to a subject, the stimulus being associated with the mechanical pain disorder;
- obtaining an evoked potential from at least one electrogram of the subject;
- extracting a set of features from the evoked potential including features from at least two of a set of features representing connectivity between regions of the brain, a set of morphology features, a set of features representing time and frequency, a set of signal decomposition features, and a set of features representing entropy;
- and
- classifying the subject into one of a first class, representing the presence of the mechanical pain disorder, and a second class, representing the absence of the mechanical pain disorder, using the extracted set of features with a machine learning model trained on known training samples taken from a set of subjects whose associated class is known, the set of subjects including subjects belonging to each of the first class and the second class.
A system for diagnosing a mechanical pain disorder comprising:
- a processor;
- and
- a non-transitory computer readable medium, operably connected to the processor, that stores machine readable instructions that are executed by the processor to provide:
- an electrogram interface that receives a recorded evoked potential from an electrogram of a subject, the evoked potential being recorded in response to a stimulus associated with a mechanical pain disorder;
- a feature extractor that extracts a set of features from the evoked potential including features from at least two of a set of features representing connectivity between regions of the brain, a set of morphology features, a set of features representing time and frequency, a set of signal decomposition features, and a set of features representing entropy;
- and
- a machine learning model trained on a set of training samples that each include values for the set of features and a value for the clinical parameter from a set of subjects having a known value for the clinical parameter, that assigns a clinical parameter to the subject from the extracted set of features, the clinical parameter assuming either a first value, representing the presence of the mechanical pain disorder and a second value, representing the absence of the mechanical pain disorder, the set of subjects including subjects having each of the first value for the clinical parameter and the second value for the clinical parameter.
A method for evaluating a pain disorder comprising:
- applying a stimulus to a subject;
- obtaining an evoked potential from at least one electrogram of the subject;
- extracting a set of features from the evoked potential including features from a set of features representing entropy and at least one of a set of features representing connectivity between regions of the brain, a set of morphology features, a set of features representing time and frequency, and a set of signal decomposition features, the set of features representing entropy comprising a Petrosian fractal dimension, a Higuchi fractal dimension, Hjorth parameters, spectral entropy parameters, and a singular value decomposition entropy;
- and
- classifying the subject into one of a first class, representing the presence of the pain disorder, and a second class, representing the absence of the pain disorder, using the extracted set of features with a machine learning model trained on known training samples taken from subjects whose associated class is known.
Dependencies are inferred from the claim text.