| CPC A61B 5/341 (2021.01) [A61B 5/343 (2021.01); A61B 5/7253 (2013.01); G16H 50/20 (2018.01); G16H 50/70 (2018.01)] | 16 Claims |
|
1. An apparatus for the improvement of electrocardiogram visualization, wherein the apparatus comprises:
at least one processor; and
a memory communicatively connected to the at least one processor, wherein the memory contains instructions configuring the at least one processor to:
receive a plurality of electrocardiogram signals, wherein the plurality of electrocardiogram signals is generated using at least one sensor of a plurality of sensors connected to a patient;
receive at least one transformation matrix;
transform the plurality of electrocardiogram signals into a cardiac vector as a function of the at least one transformation matrix;
generate a vectorcardiogram image as a function of the cardiac vector, wherein the vectorcardiogram image comprises a representation of the cardiac vector in a three-dimensional (3D) space, wherein the vectorcardiogram includes a time-dependent depiction of the cardiac vector, wherein the time-dependent depiction comprises a video generated as a function of a plurality of contiguous time slices; and
assign at least one diagnostic label to the patient as a function of the vectorcardiogram image, wherein assigning the at least one diagnostic label utilizes an assignment machine-learning model which further comprises:
receiving an assignment training data set, wherein the assignment training data set comprises outputs correlated to inputs, wherein the inputs comprise a plurality of data entries containing vectorcardiogram images and the outputs comprise diagnostic labels;
sanitizing the assignment training data set, wherein sanitizing comprises:
determining an image quality measure for each of the vectorcardiogram images of the assignment training data set;
comparing the image quality measure for each vectorcardiogram image of the assignment training data set against a threshold value; and
rejecting one or more vectorcardiogram images and their correlated outputs from the assignment training data set when the image quality measure of the one or more vectorcardiogram images falls below the threshold value;
training, iteratively, the assignment machine-learning model using the assignment training data set, wherein training the assignment machine-learning model includes retraining the assignment machine-learning model with feedback from previous iterations of the assignment machine-learning model; and
assigning the at least one diagnostic label as a function of the vectorcardiogram image using the trained assignment machine-learning model; and
display the vectorcardiogram image in a graphical format to a healthcare professional or practitioner.
|