Apparatus and method for generating a quality diagnostic of ECG (electrocardiogram) data
Inventors
BADE, Sairam • Mishra, Yash • Verma, Shiva • Vaidya, Suthirth • Kant, Shashi • Prasad, Ashim
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12329543-B1
Publication Date
2025-06-17
Expiration Date
Abstract
An apparatus and method for generating a quality diagnostic of analog ECG (electrocardiogram) data. The apparatus includes at least a processor and a memory communicatively connected to the at least a processor, wherein the memory contains instructions configuring the at least a processor to receive ECG data, extract a plurality of ECG parameters from the ECG data, convert the ECG data to one or more digitized ECG signals, validate the digitized ECG signals, wherein validating includes classifying the plurality of digitized ECG signals to a plurality of preliminary ECG parameters and determining an accuracy status of the extracted plurality of ECG parameters by comparing the plurality of preliminary ECG parameters to the extracted plurality of ECG parameters, and generate a quality diagnostic of the ECG data based on validation of the digitized ECG signals.
Core Innovation
The invention describes an apparatus for generating a quality diagnostic of analog ECG data from an image of ECG data. The apparatus receives an image of ECG data, extracts a plurality of ECG parameters from the image, and converts the image of ECG data to one or more digitized ECG signals.
The apparatus validates the one or more digitized ECG signals by classifying them to a plurality of preliminary ECG parameters. The apparatus determines an accuracy status of the extracted plurality of ECG parameters by comparing the plurality of preliminary ECG parameters to the extracted plurality of ECG parameters, and the accuracy status further comprises a variable indicating accuracy of the plurality of preliminary ECG parameters.
The invention determines an accuracy status using a scoring algorithm using a threshold to determine the accuracy status, wherein the accuracy status comprises one of a pass status and a fail status. The apparatus is configured to generate the threshold by training a threshold classifier with training data correlating a plurality of annotations indicating abnormalities to a plurality of thresholds, inputting the analog ECG data into the threshold classifier, and outputting the threshold from the threshold classifier. Based on the validation of the one or more digitized ECG signals, the apparatus generates a quality diagnostic of the image of ECG data that represents a degree of quality of the image of ECG data.
Claims Coverage
The partial content provides two independent claims: an apparatus claim and a method claim. Across these independent claims, the core coverage includes five inventive features: image-based ECG parameter extraction and digitized-signal conversion, validation by classification to preliminary ECG parameters, comparison-based accuracy status with a variable indicating accuracy, threshold-based pass/fail scoring, and threshold generation by a threshold classifier trained with abnormality annotations.
Image-based quality diagnostic generation for analog ECG data
The apparatus receives an image of ECG data, extracts a plurality of ECG parameters from the image, converts the image of the ECG data to one or more digitized ECG signals, and generates a quality diagnostic of the image of ECG data based on validation of the one or more digitized ECG signals.
Digitized-signal validation via preliminary ECG parameter classification
Validating comprises classifying the one or more digitized ECG signals to a plurality of preliminary ECG parameters and determining an accuracy status of the extracted plurality of ECG parameters by comparing the plurality of preliminary ECG parameters to the extracted plurality of ECG parameters, wherein the accuracy status further comprises a variable indicating accuracy of the plurality of preliminary ECG parameters.
Threshold-based accuracy status with pass/fail scoring
Determining an accuracy status comprises using a scoring algorithm using a threshold to determine the accuracy status, wherein the accuracy status comprises one of a pass status and a fail status.
Threshold classifier trained with abnormality annotations to generate the threshold
The apparatus is configured to generate the threshold by training a threshold classifier with training data correlating a plurality of annotations indicating abnormalities to a plurality of thresholds, inputting the analog ECG data into the threshold classifier, and outputting, by the threshold classifier, the threshold.
Quality diagnostic representing degree of quality after validation
Generating a quality diagnostic of the image of ECG data based on validation of the digitized ECG signals, wherein the quality diagnostic represents a degree of quality of the image of ECG data.
Across the independent apparatus and method claims, the inventive focus is on generating an image-based quality diagnostic for analog ECG by extracting ECG parameters from an image, converting to digitized ECG signals, validating accuracy via classification to preliminary ECG parameters and comparison to extracted parameters, and producing a pass/fail accuracy status using a threshold determined by a threshold classifier trained on abnormality-annotation-correlated thresholds, then outputting a quality diagnostic representing a degree of quality.
Stated Advantages
Generates a quality diagnostic representing a degree of quality of the image of ECG data.
Provides an accuracy status comprising one of a pass status and a fail status, with a variable indicating accuracy of the plurality of preliminary ECG parameters.
Documented Applications
Quality-controlling analog ECG printouts/image-based ECG data to support downstream software as a medical device (SaMD) use in settings where patients receive only ECG printouts.
Interested in licensing this patent?