Citations

Background: Deep learning algorithms derived in homogeneous populations may be poorly generalizable and have the potential to reflect, perpetuate, and even exacerbate racial/ethnic disparities in health and health care. In this study, we aimed to (1) assess whether the performance of a deep learning algorithm designed to detect low left ventricular ejection fraction using the 12-lead ECG varies by race/ethnicity and to (2) determine whether its performance is determined by the derivation population or by racial variation in the ECG. Methods: We performed a retrospective cohort analysis that included 97 829 patients with paired ECGs and echocardiograms. We tested the model performance by race/ethnicity for convolutional neural network designed to identify patients with a left ventricular ejection fraction ≤35% from the 12-lead ECG. Results: The convolutional neural network that was previously derived in a homogeneous population (derivation cohort, n=44 959; 96.2% non-Hispanic white) demonstrated consistent performance to detect low left ventricular ejection fraction across a range of racial/ethnic subgroups in a separate testing cohort (n=52 870): non-Hispanic white (n=44 524; area under the curve [AUC], 0.931), Asian (n=557; AUC, 0.961), black/African American (n=651; AUC, 0.937), Hispanic/Latino (n=331; AUC, 0.937), and American Indian/Native Alaskan (n=223; AUC, 0.938). In secondary analyses, a separate neural network was able to discern racial subgroup category (black/African American [AUC, 0.84], and white, non-Hispanic [AUC, 0.76] in a 5-class classifier), and a network trained only in non-Hispanic whites from the original derivation cohort performed similarly well across a range of racial/ethnic subgroups in the testing cohort with an AUC of at least 0.930 in all racial/ethnic subgroups. Conclusions: Our study demonstrates that while ECG characteristics vary by race, this did not impact the ability of a convolutional neural network to predict low left ventricular ejection fraction from the ECG. We recommend reporting of performance among diverse ethnic, racial, age, and sex groups for all new artificial intelligence tools to ensure responsible use of artificial intelligence in medicine.

Background: Sex and age have long been known to affect the ECG. Several biologic variables and anatomic factors may contribute to sex and age-related differences on the ECG. We hypothesized that a convolutional neural network (CNN) could be trained through a process called deep learning to predict a person’s age and self-reported sex using only 12-lead ECG signals. We further hypothesized that discrepancies between CNN-predicted age and chronological age may serve as a physiological measure of health. Methods: We trained CNNs using 10-second samples of 12-lead ECG signals from 499 727 patients to predict sex and age. The networks were tested on a separate cohort of 275 056 patients. Subsequently, 100 randomly selected patients with multiple ECGs over the course of decades were identified to assess within-individual accuracy of CNN age estimation. Results: Of 275 056 patients tested, 52% were males and mean age was 58.6±16.2 years. For sex classification, the model obtained 90.4% classification accuracy with an area under the curve of 0.97 in the independent test data. Age was estimated as a continuous variable with an average error of 6.9±5.6 years (R-squared =0.7). Among 100 patients with multiple ECGs over the course of at least 2 decades of life, most patients (51%) had an average error between real age and CNN-predicted age of <7 years. Major factors seen among patients with a CNN-predicted age that exceeded chronologic age by >7 years included: low ejection fraction, hypertension, and coronary disease ( P <0.01). In the 27% of patients where correlation was >0.8 between CNN-predicted and chronologic age, no incident events occurred over follow-up (33±12 years). Conclusions: Applying artificial intelligence to the ECG allows prediction of patient sex and estimation of age. The ability of an artificial intelligence algorithm to determine physiological age, with further validation, may serve as a measure of overall health.

AbstractIntroductionEmerging medical technology has allowed for monitoring of heart rhythm abnormalities using smartphone compatible devices. The safety and utility of such devices have not been established in patients with cardiac implantable electronic devices (CIEDs). We sought to assess the safety and compatibility of the Food and Drug Administration‐approved AliveCor Kardia device in patients with CIEDs.Methods and ResultsWe prospectively recruited patients with CIED for a Kardia recording during their routine device interrogation. A recording was obtained in paced and nonpaced states. Adverse clinical events were noted at the time of recording. Electrograms (EGMs) from the cardiac device were obtained at the time of recording to assess for any electromagnetic interference (EMI) introduced by Kardia. Recordings were analyzed for quality and given a score of 3 (interpretable rhythm, no noise), 2 (interpretable rhythm, significant noise) or 1 (uninterpretable). A total of 251 patients were recruited (59% with a pacemaker and 41% with ICD). There were no adverse clinical events noted at the time of recording and no changes to CIED settings. Review of all EGMs revealed no EMI introduced by Kardia. Recordings were correctly interpreted in 90% of paced recordings (183 had a score of 3, 43 of 2, and 25 of 1) and 94.7% of nonpaced recordings (147 of 3, 15 of 2, and 9 of 1).ConclusionThe AliveCor Kardia device has an excellent safety profile when used in conjunction with most CIEDs. The quality of recordings was preserved in this population. The device, therefore, can be considered for heart rhythm monitoring in patients with CIEDs.

AbstractObjectivesWe sought to validate a deep learning algorithm designed to predict an ejection fraction (EF) less than or equal to 35% based on the 12‐lead electrocardiogram (ECG) in a large prospective cohort.BackgroundPatients undergoing routine ECG may have undetected left ventricular (LV) dysfunction that warrants further echocardiographic assessment. However, identification of these patients can be challenging.MethodsWe applied the algorithm to all ECGs interpreted by the Mayo Clinic ECG laboratory in September 2018. The performance of the algorithm was tested among patients with recent echocardiographic assessments of LV function. We also applied the algorithm in patients with no recent echocardiographic assessments of LV function to determine the rate of new “positive screens.”ResultsAmong 16 056 adult patients who underwent routine ECG, 8600 (age 67.1 ± 15.2 years, 45.6% male), had a transthoracic echocardiogram (TTE) and 3874 patients had a TTE and ECG less than 1 month apart. Among these patients, the algorithm was able to detect an EF less than or equal to 35% with 86.8% specificity, 82.5% sensitivity, and 86.5% accuracy, (area under the curve, 0.918). Among 474 “false‐positives screens,” 189 (39.8%) had an EF of 36% to 50%. Among patients with no prior TTE, the algorithm identified 3.5% of the patients with suspected EF less than or equal to 35%. Exploratory analysis suggests false positives could be reduced by assessing NT‐pro‐BNP after the initial “positive screen.”ConclusionsA deep learning algorithm detected depressed LV function with good accuracy in routine practice. Further studies are needed to validate the algorithm in patients with no prior echocardiogram and to assess the impact on echocardiography utilization, cost, and clinical outcomes.

PURPOSE Background parenchymal uptake (BPU), which describes the level of radiotracer uptake in normal fibroglandular tissue on molecular breast imaging (MBI), has been identified as a breast cancer risk factor. Our objective was to develop and validate a deep learning model using image convolution to automatically categorize BPU on MBI. METHODS MBI examinations obtained for clinical and research purposes from 2004 to 2015 were reviewed to classify the BPU pattern using a standardized five-category scale. Two expert radiologists provided interpretations that were used as the reference standard for modeling. The modeling consisted of training and validating a convolutional neural network to predict BPU. Model performance was summarized in data reserved to test the performance of the algorithm at the per-image and per-breast levels. RESULTS Training was performed on 24,639 images from 3,133 unique patients. The model performance on the withheld testing data (6,172 images; 786 patients) was evaluated. Using direct matching on the predicted classification resulted in an accuracy of 69.4% (95% CI, 67.4% to 71.3%), and if prediction within one category was considered, accuracy increased to 96.0% (95% CI, 95.2% to 96.7%). When considering the breast-level prediction of BPU, the accuracy remained strong, with 70.3% (95% CI, 68.0% to 72.6%) and 96.2% (95% CI, 95.3% to 97.2%) for the direct match and allowance for one category, respectively. CONCLUSION BPU provided a robust target for training a convolutional neural network. A validated computer algorithm will allow for objective, reproducible encoding of BPU to foster its integration into risk-stratification algorithms.

Background: Although the hallmark of long-QT syndrome (LQTS) is abnormal cardiac repolarization, there are varying degrees of phenotypic expression and arrhythmic risk. Our aim was to evaluate the performance of a morphological T-wave analysis program in defining breakthrough LQTS arrhythmic risk beyond the QTc value. Methods and Results: We analyzed 407 genetically confirmed patients with LQT1 (n=246; 43% men) and LQT2 (n=161; 41% men) over the mean follow-up period of 6.4±3.9 years. ECG analysis was conducted using a novel, proprietary T-wave analysis program. Time to a LQTS-associated cardiac event was analyzed using Cox proportional hazards regression methods. Twenty-three patients experienced ≥1 defined breakthrough cardiac arrhythmic events with 5- and 10-year event rates of 4% and 7%. Two independent predictors of future LQTS-associated cardiac events from the surface ECG were identified: left slope of T wave in lead V6 (hazard ratio=0.40 [0.24–0.69]; P <0.001) and T-wave center of gravity x axis (last 25% of wave) in lead I (hazard ratio=1.90 [1.21–2.99]; P =0.005), C statistic of 0.77 (0.65–0.89). When added to the QTc (C statistic 0.68 for QTc alone), discrimination improved to 0.78. Genotype analysis showed weaker association between these T-wave variables and LQT1-triggered events while these features were stronger in patients with LQT2 and significantly outperformed the QTc (C statistic, 0.82 [0.71–0.93]). Conclusion: Detailed morphological analysis of the T wave provides novel insights into risk of breakthrough arrhythmic events in LQTS, particularly LQT2. This observation has the potential to guide clinical decision making and further refine risk stratification.

BackgroundProlongation of the QT on the surface electrocardiogram can be due to either genetic or acquired causes. Distinguishing congenital long QT syndrome (LQTS) from acquired QT prolongation has important prognostic and management implications. We aimed to investigate if quantitative T‐wave analysis could provide a tool for the physician to differentiate between congenital and acquired QT prolongation.MethodsPatients were identified through an institution‐wide computer‐based QT screening system which alerts the physician if the QTc ≥ 500 ms. ECGs were retrospectively analyzed with an automated T‐wave analysis program. Congenital LQTS was compared in a 1:3 ratio to those with an identified acquired etiology for QT prolongation (electrolyte abnormality and/or prescription of known QT prolongation medications). Linear discriminant analysis was performed using 10‐fold cross‐validation to statistically test the selected features.ResultsThe 12‐lead ECG of 38 patients with congenital LQTS and 114 patients with drug‐induced and/or electrolyte‐mediated QT prolongation were analyzed. In lead V5, patients with acquired QT prolongation had a shallower T wave right slope (−2,322 vs. −3,593 mV/s), greater T‐peak‐Tend interval (109 vs. 92 ms), and smaller T wave center of gravity on the x axis (290 ms vs. 310 ms; p < .001). These features could distinguish congenital from acquired causes in 77% of cases (sensitivity 90%, specificity 58%).ConclusionT‐wave morphological analysis on lead V5 of the surface ECG could successfully differentiate congenital from acquired causes of QT prolongation.

Background— Congenital long QT syndrome (LQTS) is characterized by QT prolongation. However, the QT interval itself is insufficient for diagnosis, unless the corrected QT interval is repeatedly ≥500 ms without an acquired explanation. Further, the majority of LQTS patients have a corrected QT interval below this threshold, and a significant minority has normal resting corrected QT interval values. Here, we aimed to develop and validate a novel, quantitative T wave morphological analysis program to differentiate LQTS patients from healthy controls. Methods and Results— We analyzed a genotyped cohort of 420 patients (22±16 years, 43% male) with either LQT1 (61%) or LQT2 (39%). ECG analysis was conducted using a novel, proprietary T wave analysis program that quantitates subtle changes in T wave morphology. The top 3 discriminating features in each ECG lead were determined and the lead with the best discrimination selected. Classification was performed using a linear discriminant classifier and validated on an untouched cohort. The top 3 features were Tpeak–Tend interval, T wave left slope, and T wave center of gravity x axis (last 25% of the T wave). Lead V6 had the best discrimination. It could distinguish 86.8% of LQTS patients from healthy controls. Moreover, it distinguished 83.33% of patients with concealed LQTS from controls, despite having essentially identical resting corrected QT interval values. Conclusions— T wave quantitative analysis on the 12-lead surface ECG provides an effective, novel tool to distinguish patients with either LQT1/LQT2 from healthy matched controls. It can provide guidance while mutation-specific genetic testing is in motion for family members.