Electronic device and method for predicting blockage of coronary artery
An electronic device and a method for predicting a blockage of a coronary artery are provided. The method includes: obtaining multiple pieces of electrocardiogram (ECG) data respectively corresponding to a coronary artery set; generating multiple first probabilities corresponding to the multiple pieces of electrocardiogram data respectively according to the multiple pieces of electrocardiogram data and a first phase model, generating a first determined result according to the multiple first probabilities, and selecting a first data subset corresponding to a first probability subset from the multiple pieces of electrocardiogram data in response to each one in the first data subset of the multiple first probabilities being greater than a first threshold; generating multiple second probabilities corresponding to the first data subset according to the first data subset and a second phase model, and generating a second determined result according to the multiple second probabilities.
1. An electronic device for predicting a blockage of a coronary artery, comprising:
a transceiver receiving signals, in at least one of a wireless manner and a wired manner, the signals representing a plurality of electrocardiogram (ECG) data from a plurality of ECG leads applied to a patient, the ECG data corresponding to a coronary artery set, the transceiver configured to at least one of filter and amplify the signals;
a storage medium storing a plurality of modules; and
a processor coupled to the storage medium and the transceiver and accessing and executing the plurality of the modules, wherein the plurality of the modules comprise:
a first prediction module, wherein according to the plurality of the electrocardiogram data and at least one first phase model, at least one first probability vector corresponding to the at least one first phase model is generated, a first determined result is generated according to the at least one first probability vector, and in response to each one in a first subset of the at least one first probability vector being greater than a first threshold, a first data subset corresponding to the first subset from the plurality of the electrocardiogram data is selected, wherein the first determined result indicates a probability of a blockage of the coronary artery set, wherein the at least one first phase model and the at least one second phase model correspond to a machine learning algorithm executed by the processor, wherein the first determined result is determined according to a first product of at least one first average element value corresponding to the at least one first probability vector and at least one first weight, wherein the at least one first weight is associated with a performance index of the at least one first phase model;
a second prediction module, wherein according to the first data subset and at least one second phase model, at least one second probability vector corresponding to the at least one second phase model is generated, and a second determined result is generated according to the at least one second probability vector, wherein the second determined result indicates a probability of a blockage of a first coronary artery in the coronary artery set, wherein the first coronary artery comprises at least one of a left main coronary artery, a left anterior descending (LAD) artery, a left circumflex (LCX) artery, and a right coronary artery; and
an output module outputting the first determined result and the second determined result through the transceiver.
2. The electronic device according to claim 1 , wherein the second prediction module selects a second data subset corresponding to a second subset from the first data subset in response to each one in the second subset of the at least one second probability vector being greater than a second threshold, wherein the plurality of the modules further comprise:
a third prediction module, wherein at least one third probability vector corresponding to at least one third phase model is generated according to the second data subset and the at least one third phase model, and a third determined result is generated according to the at least one third probability vector, wherein the third determined result indicates a probability of a first blockage position of the first coronary artery, wherein the at least one third phase model correspond to a machine learning algorithm;
wherein the output module outputs the third determined result through the transceiver.
3. The electronic device according to claim 2 ,
wherein the transceiver receives a plurality of second electrocardiogram data corresponding to the coronary artery set, wherein the plurality of the electrocardiogram data correspond to a first lead, wherein the plurality of the second electrocardiogram data correspond to a second lead,
wherein the first prediction module generates at least one fourth probability vector corresponding to the at least one first phase model according to the plurality of the second electrocardiogram data and the at least one first phase model, and the first determined result is generated according to the at least one first probability vector and the at least one fourth probability vector.
4. The electronic device according to claim 3 ,
wherein the first prediction module selects a fourth data subset corresponding to a fourth subset from the plurality of the second electrocardiogram data in response to each one in the fourth subset of the at least one fourth probability vector being greater than the first threshold,
wherein the second prediction module generates at least one fifth probability vector corresponding to the at least one second phase model according to the fourth data subset and the at least one second phase model, and the second determined result is generated according to the at least one second probability vector and the at least one fifth probability vector.
5. The electronic device according to claim 4 ,
wherein the second prediction module selects a fifth data subset corresponding to a fifth subset from the fourth data subset in response to each one in the fifth subset of the at least one fifth probability vector being greater than the second threshold,
wherein the third prediction module generates at least one sixth probability vector corresponding to the at least one third phase model according to the fifth data subset and the at least one third phase model, and the third determined result is generated according to the at least one third probability vector and the at least one sixth probability vector.
6. The electronic device according to claim 1 ,
wherein the first prediction module performs a baseline wandering removal, a noise removal, and a wavelet transform on a plurality of training data to generate a plurality of first corrected training data, and the at least one first phase model is trained according to the plurality of the first corrected training data.
7. The electronic device according to claim 6 , wherein the first prediction module trains the at least one first phase model according to at least one feature, wherein the at least one feature is associated with at least one as follows:
a P wave, a Q wave, a R wave, an S wave, and a T wave.
8. A method for predicting a blockage of a coronary artery, comprising:
receiving signals, via a transceiver, in at least one of a wireless manner and a wired manner, the signals representing a plurality of electrocardiogram (ECG) data from a plurality of ECG leads applied to a patient, the ECG data corresponding to a coronary artery set;
at least one of filter and amplify the signals to obtain the plurality of ECG data;
generating at least one first probability vector corresponding to at least one first phase model according to the plurality of the electrocardiogram data and the at least one first phase model, generating a first determined result according to the at least one first probability vector, and selecting a first data subset corresponding to a first subset from the plurality of the electrocardiogram data in response to each one in the first subset of the at least one first probability vector being greater than a first threshold, wherein the first determined result indicates a probability of a blockage of the coronary artery set, wherein the at least one first phase model corresponds to a machine learning algorithm executed by a processor, wherein the first determined result is determined according to a first product of at least one first average element value corresponding to the at least one first probability vector and at least one first weight, wherein the at least one first weight is associated with a performance index of the at least one first phase model;
generating at least one second probability vector corresponding to at least one second phase model according to the first data subset and the at least one second phase model, and generating a second determined result according to at least one second probability vector, wherein the second determined result indicates a probability of a blockage of a first coronary artery in the coronary artery set, wherein the first coronary artery comprises at least one of a left main coronary artery, a left anterior descending (LAD) artery, a left circumflex (LCX) artery, and a right coronary artery; and
outputting, via the transceiver, the first determined result and the second determined result.
9. A non-transitory computer readable storage media encoded with instructions that, when executed by a processor cause the processor to:
receive, via a transceiver, in at least one of a wireless manner and a wired manner, a plurality of electrocardiogram (ECG) data from a plurality of ECG leads applied to a patient, the ECG data corresponding to a coronary artery set;
generate at least one first probability vector corresponding to at least one first phase model according to the plurality of the electrocardiogram data and the at least one first phase model, generate a first determined result according to the at least one first probability vector, and select a first data subset corresponding to a first subset from the plurality of the electrocardiogram data in response to each one in the first subset of the at least one first probability vector being greater than a first threshold, wherein the first determined result indicates a probability of a blockage of the coronary artery set, wherein the at least one first phase model corresponds to a machine learning algorithm executed by a processor, wherein the first determined result is determined according to a first product of at least one first average element value corresponding to the at least one first probability vector and at least one first weight, wherein the at least one first weight is associated with a performance index of the at least one first phase model;
generate at least one second probability vector corresponding to at least one second phase model according to the first data subset and the at least one second phase model, and generate a second determined result according to at least one second probability vector, wherein the second determined result indicates a probability of a blockage of a first coronary artery in the coronary artery set, wherein the first coronary artery comprises at least one of a left main coronary artery, a left anterior descending (LAD) artery, a left circumflex (LCX) artery, and a right coronary artery; and
output, via the transceiver, the first determined result and the second determined result.