Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 3 de 3
Filter
Add filters

Database
Language
Document Type
Year range
1.
Ann Noninvasive Electrocardiol ; 26(6): e12872, 2021 11.
Article in English | MEDLINE | ID: covidwho-1319236

ABSTRACT

BACKGROUND: Interval duration measurements (IDMs) were compared between standard 12-lead electrocardiograms (ECGs) and 6-lead ECGs recorded with AliveCor's KardiaMobile 6L, a hand-held mobile device designed for use by patients at home. METHODS: Electrocardiograms were recorded within, on average, 15 min from 705 patients in Mayo Clinic's Windland Smith Rice Genetic Heart Rhythm Clinic. Interpretable 12-lead and 6-lead recordings were available for 685 out of 705 (97%) eligible patients. The most common diagnosis was congenital long QT syndrome (LQTS, 343/685 [50%]), followed by unaffected relatives and patients (146/685 [21%]), and patients with other genetic heart diseases, including hypertrophic cardiomyopathy (36 [5.2%]), arrhythmogenic cardiomyopathy (23 [3.4%]), and idiopathic ventricular fibrillation (14 [2.0%]). IDMs were performed by a central ECG laboratory using lead II with a semi-automated technique. RESULTS: Despite differences in patient position (supine for 12-lead ECGs and sitting for 6-lead ECGs), mean IDMs were comparable, with mean values for the 12-lead and 6-lead ECGs for QTcF, heart rate, PR, and QRS differing by 2.6 ms, -5.5 beats per minute, 1.0 and 1.2 ms, respectively. Despite a modest difference in heart rate, intervals were close enough to allow a detection of clinically meaningful abnormalities. CONCLUSIONS: The 6-lead hand-held device is potentially useful for a clinical follow-up of remote patients, and for a safety follow-up of patients participating in clinical trials who cannot visit the investigational site. This technology may extend the use of 12-lead ECG recordings during the current COVID-19 pandemic as remote patient monitoring becomes more common in virtual or hybrid-design clinical studies.


Subject(s)
Electrocardiography/methods , Heart Diseases/diagnosis , Adult , Electrocardiography, Ambulatory/methods , Female , Humans , Male , Posture , Prospective Studies , Time
2.
Circulation ; 143(13): 1274-1286, 2021 03 30.
Article in English | MEDLINE | ID: covidwho-1180993

ABSTRACT

BACKGROUND: Heart rate-corrected QT interval (QTc) prolongation, whether secondary to drugs, genetics including congenital long QT syndrome, and/or systemic diseases including SARS-CoV-2-mediated coronavirus disease 2019 (COVID-19), can predispose to ventricular arrhythmias and sudden cardiac death. Currently, QTc assessment and monitoring relies largely on 12-lead electrocardiography. As such, we sought to train and validate an artificial intelligence (AI)-enabled 12-lead ECG algorithm to determine the QTc, and then prospectively test this algorithm on tracings acquired from a mobile ECG (mECG) device in a population enriched for repolarization abnormalities. METHODS: Using >1.6 million 12-lead ECGs from 538 200 patients, a deep neural network (DNN) was derived (patients for training, n = 250 767; patients for testing, n = 107 920) and validated (n = 179 513 patients) to predict the QTc using cardiologist-overread QTc values as the "gold standard". The ability of this DNN to detect clinically-relevant QTc prolongation (eg, QTc ≥500 ms) was then tested prospectively on 686 patients with genetic heart disease (50% with long QT syndrome) with QTc values obtained from both a 12-lead ECG and a prototype mECG device equivalent to the commercially-available AliveCor KardiaMobile 6L. RESULTS: In the validation sample, strong agreement was observed between human over-read and DNN-predicted QTc values (-1.76±23.14 ms). Similarly, within the prospective, genetic heart disease-enriched dataset, the difference between DNN-predicted QTc values derived from mECG tracings and those annotated from 12-lead ECGs by a QT expert (-0.45±24.73 ms) and a commercial core ECG laboratory [10.52±25.64 ms] was nominal. When applied to mECG tracings, the DNN's ability to detect a QTc value ≥500 ms yielded an area under the curve, sensitivity, and specificity of 0.97, 80.0%, and 94.4%, respectively. CONCLUSIONS: Using smartphone-enabled electrodes, an AI DNN can predict accurately the QTc of a standard 12-lead ECG. QTc estimation from an AI-enabled mECG device may provide a cost-effective means of screening for both acquired and congenital long QT syndrome in a variety of clinical settings where standard 12-lead electrocardiography is not accessible or cost-effective.


Subject(s)
Artificial Intelligence , Electrocardiography/methods , Heart Diseases/diagnosis , Heart Rate/physiology , Adult , Aged , Area Under Curve , COVID-19/physiopathology , COVID-19/virology , Electrocardiography/instrumentation , Female , Heart Diseases/physiopathology , Humans , Long QT Syndrome/diagnosis , Long QT Syndrome/physiopathology , Male , Middle Aged , Prospective Studies , ROC Curve , SARS-CoV-2/isolation & purification , Sensitivity and Specificity , Smartphone
3.
Circulation ; 143(13): 1274-1286, 2021 03 30.
Article in English | MEDLINE | ID: covidwho-1058120

ABSTRACT

BACKGROUND: Heart rate-corrected QT interval (QTc) prolongation, whether secondary to drugs, genetics including congenital long QT syndrome, and/or systemic diseases including SARS-CoV-2-mediated coronavirus disease 2019 (COVID-19), can predispose to ventricular arrhythmias and sudden cardiac death. Currently, QTc assessment and monitoring relies largely on 12-lead electrocardiography. As such, we sought to train and validate an artificial intelligence (AI)-enabled 12-lead ECG algorithm to determine the QTc, and then prospectively test this algorithm on tracings acquired from a mobile ECG (mECG) device in a population enriched for repolarization abnormalities. METHODS: Using >1.6 million 12-lead ECGs from 538 200 patients, a deep neural network (DNN) was derived (patients for training, n = 250 767; patients for testing, n = 107 920) and validated (n = 179 513 patients) to predict the QTc using cardiologist-overread QTc values as the "gold standard". The ability of this DNN to detect clinically-relevant QTc prolongation (eg, QTc ≥500 ms) was then tested prospectively on 686 patients with genetic heart disease (50% with long QT syndrome) with QTc values obtained from both a 12-lead ECG and a prototype mECG device equivalent to the commercially-available AliveCor KardiaMobile 6L. RESULTS: In the validation sample, strong agreement was observed between human over-read and DNN-predicted QTc values (-1.76±23.14 ms). Similarly, within the prospective, genetic heart disease-enriched dataset, the difference between DNN-predicted QTc values derived from mECG tracings and those annotated from 12-lead ECGs by a QT expert (-0.45±24.73 ms) and a commercial core ECG laboratory [10.52±25.64 ms] was nominal. When applied to mECG tracings, the DNN's ability to detect a QTc value ≥500 ms yielded an area under the curve, sensitivity, and specificity of 0.97, 80.0%, and 94.4%, respectively. CONCLUSIONS: Using smartphone-enabled electrodes, an AI DNN can predict accurately the QTc of a standard 12-lead ECG. QTc estimation from an AI-enabled mECG device may provide a cost-effective means of screening for both acquired and congenital long QT syndrome in a variety of clinical settings where standard 12-lead electrocardiography is not accessible or cost-effective.


Subject(s)
Artificial Intelligence , Electrocardiography/methods , Heart Diseases/diagnosis , Heart Rate/physiology , Adult , Aged , Area Under Curve , COVID-19/physiopathology , COVID-19/virology , Electrocardiography/instrumentation , Female , Heart Diseases/physiopathology , Humans , Long QT Syndrome/diagnosis , Long QT Syndrome/physiopathology , Male , Middle Aged , Prospective Studies , ROC Curve , SARS-CoV-2/isolation & purification , Sensitivity and Specificity , Smartphone
SELECTION OF CITATIONS
SEARCH DETAIL