Performance and Accuracy of an AI Enhanced Smart Watch Single Lead ECG

The ECG interval differences (in milliseconds) between 12 Lead and collected single-lead watch-based ECG for PR, QRS, QT intervals will be determined and compared for each patient.

A physician interpretation of patients' 12 lead ECG and single-lead watch-based ECG will be performed to determined underlying rhythm (i.e. sinus rhythm, atrial fibrillation etc) from each, and the results from these modalities will be compared.

A physician interpretation of the patient's single-lead watch-based ECG will occur as described in "Outcome 2." The results of this ECG interpretation (i.e. sinus rhythm, atrial fibrillation, or inconclusive) will be compared to the watch/app-based rhythm auto-classification for each recorded single-lead watch-based ECG.

A previously developed AI algorithm to predict potential underlying cardiac pathology assess from 12 lead ECG via convolutional neural network will be adapted applied to the ECGs for patients who undergo single-lead watch-based ECG recording. This neural network uses PQRST complexes to yield a probability of heart failure which may not be readily apparent via manual review. Each recorded single-lead watch-based ECG will undergo evaluation by this neural network and will produce a probability of heart failure (0-100%) for each individual patient. This probability will be compared to the AI ECG result (probability 0-100%) from the patient's recently recorded 12 lead ECG which is routinely available for all patients with a recorded 12 lead ECG at our medical system.

A previously developed AI algorithm to predict potential underlying cardiac pathology assess from 12 lead ECG via convolutional neural network will be adapted applied to the ECGs for patients who undergo single-lead watch-based ECG recording. This neural network uses PQRST complexes to yield a probability of silent/paroxysmal atrial fibrillation which may not be readily apparent via manual review. Each recorded single-lead watch-based ECG will undergo evaluation by this neural network and will produce a probability of silent/paroxysmal atrial fibrillation (0-100%) for each individual patient. This probability will be compared to the AI ECG result (probability 0-100%) from the patient's recently recorded 12 lead ECG which is routinely available for all patients with a recorded 12 lead ECG at our medical system.

A previously developed AI algorithm to predict potential underlying cardiac pathology assess from 12 lead ECG via convolutional neural network will be adapted applied to the ECGs for patients who undergo single-lead watch-based ECG recording. This neural network uses PQRST complexes to yield a probability of aortic stenosis which may not be readily apparent via manual review. Each recorded single-lead watch-based ECG will undergo evaluation by this neural network and will produce a probability of aortic stenosis (0-100%) for each individual patient. This probability will be compared to the AI ECG result (probability 0-100%) from the patient's recently recorded 12 lead ECG which is routinely available for all patients with a recorded 12 lead ECG at our medical system.

A previously developed AI algorithm to predict patient age from 12 lead ECG via convolutional neural network will be adapted applied to the ECGs for patients who undergo single-lead watch-based ECG recording. This neural network uses PQRST complexes to yield an ECG-predicted age. Each recorded single-lead watch-based ECG will undergo evaluation by this neural network and determine "ECG age" for each individual patient. This single-lead "ECG age" will be compared to the AI ECG "age" result determined from the patient's recently recorded 12 lead ECG which is routinely available for all patients with a recorded 12 lead ECG at our medical system.

A previously developed AI algorithm to predict potential underlying cardiac pathology assess from 12 lead ECG via convolutional neural network will be adapted applied to the ECGs for patients who undergo single-lead watch-based ECG recording. This neural network uses PQRST complexes to yield a probability of amyloidosis which may not be readily apparent via manual review. Each recorded single-lead watch-based ECG will undergo evaluation by this neural network and will produce a probability of amyloidosis (0-100%) for each individual patient. This probability will be compared to the AI ECG result (probability 0-100%) from the patient's recently recorded 12 lead ECG which is routinely available for all patients with a recorded 12 lead ECG at our medical system.