TWELVE-LEAD ELECTROCARDIOGRAM USING A THREE-ELECTRODE DEVICE
An apparatus includes an electrocardiograph device having first, second, and third, electrode assemblies with first, second, and third electrodes adapted to measure first, second, and third electrical signals of an individual, respectively. The apparatus further includes a processing device to: determine a Lead I from the first electrical signal and the second electrical signal; determine a Lead II from the second electrical signal and the third electrical signal; generate a Lead III using (Lead III=Lead II−Lead I); determine, using a machine learning model trained using measured twelve-lead ECG data, Leads aVR, aVL, aVF, V 1, V 2, V 3, V 4, V 5, and V 6 based on Lead I, Lead II, and Lead III; and provide Leads Lead I, Lead II, Lead III, aVR, aVL, aVF, V 1, V 2, V 3, V 4, V 5, and V 6 for display on a client device.
1 . An apparatus, comprising:
an electrocardiograph device having first, second, and third, electrode assemblies with first, second, and third electrodes adapted to measure first, second, and third electrical signals of an individual, respectively; and
a processing device to:
determine a Lead I from the first electrical signal and the second electrical signal;
determine a Lead II from the second electrical signal and the third electrical signal;
generate a Lead III using (Lead III=Lead II−Lead I);
determine, using a machine learning model trained using measured twelve-lead ECG data, Leads aVR, aVL, aVF, V 1 , V 2 , V 3 , V 4 , V 5 , and V 6 based on Lead I, Lead II, and Lead III; and
provide Leads Lead I, Lead II, Lead III, aVR, aVL, aVF, V 1 , V 2 , V 3 , V 4 , V 5 , and V 6 for display on a client device.
2 . The apparatus of claim 1 , wherein the Lead II is determined sequentially with Lead I.
3 . The apparatus of claim 2 , wherein the processing device is further to time align Lead I and Lead II.
4 . The apparatus of claim 1 , wherein the Lead II is determined contemporaneously with Lead 1 .
5 . The apparatus of claim 1 , the processing device further to train the machine learning model using the twelve-lead ECG data corresponding to a population of individuals.
6 . The apparatus of claim 5 , the processing device further to preprocess the twelve-lead ECG data to categorize the data based on at least one of: height, gender, weight, or nationality before being used to train the machine learning model.
7 . The apparatus of claim 6 , the processing device further to characterize the twelve-lead ECG data based on a characteristic of the individual.
8 . The apparatus of claim 1 , the processing device further to train the machine learning model only using the twelve-lead ECG data corresponding to the individual.
9 . A method for generating a 12-lead electrocardiogram, the method comprising:
determining a Lead I from a first electrical signal of a first electrode and a second electrical signal of a second electrode;
determining a Lead II from the second electrical signal and a third electrical signal from a third electrode;
generating a Lead III using (Lead III=Lead II−Lead I);
determining leads aVR, aVL and aVF from Leads I and II;
determining, by a processing device using a machine learning model trained using measured twelve-lead ECG data, Leads V 1 , V 2 , V 3 , V 4 , V 5 , and V 6 based on Lead I, Lead II, and Lead III; and
providing leads Lead I, Lead II, Lead III, aVR, aVL, aVF, V 1 , V 2 , V 3 , V 4 , V 5 , and V 6 for display on a client device.
10 . The method of claim 9 , wherein the Lead II is determined sequentially with Lead I.
11 . The method of claim 10 , further comprising time aligning Lead I and Lead II.
12 . The method of claim 9 , wherein the Lead II is determined contemporaneously with Lead I.
13 . The method of claim 9 , further comprising training the machine learning model using the twelve-lead ECG data corresponding to a population of individuals.
14 . The method of claim 13 , further comprising preprocessing the twelve-lead ECG data to categorize the data based on at least one of: height, gender, weight, or nationality before being used to train the machine learning model.
15 . The method of claim 14 , further comprising categorizing the twelve-lead ECG data based on a characteristic of the individual.
16 . The method of claim 9 , further comprising training the machine learning model only using the twelve-lead ECG data corresponding to the individual.
17 . A non-transitory computer-readable storage medium storing instructions, which when executed by a processing device, cause the processing device to:
determine a Lead I from the first electrical signal of a first electrode and the second electrical signal of a second electrode;
determine a Lead II from the second electrical signal and a third electrical signal from a third electrode;
determine a V Lead from a fourth electrical signal;
determine leads aVR, aVL and aVF from Leads I and II;
generate a Lead III using (Lead III=Lead II−Lead I);
determine, by the processing device using a machine learning model trained using measured twelve-lead ECG data, Leads, and remaining V Leads based on Lead I, Lead II, Lead III, and V Lead; and
provide Leads Lead I, Lead II, Lead III, aVR, aVL, aVF, V 1 , V 2 , V 3 , V 4 , V 5 , and V 6 for display on a client device.
18 . The non-transitory computer-readable storage medium of claim 17 , wherein the Lead II is determined contemporaneously with Lead 1 .
19 . The non-transitory computer-readable storage medium of claim 17 , the processing device further to train the machine learning model using the twelve-lead ECG data corresponding to a population of individuals.
20 . The non-transitory computer-readable storage medium of claim 19 , wherein the V Lead is at least one of Lead V 2 or V 5 .