Search

Background: Inferior biphasic or inverted T waves have been described on a standard 12-lead ECG in some, but not all patients with malignant mitral valve prolapse (MVP). In contrast, complex ventricular ectopy (ComVE) is associated with myocardial fibrosis and increased mortality in MVP and may represent a better marker of arrhythmic risk. We hypothesize that an ECG-based machine-learning model can identify MVP with ComVE and/or myocardial fibrosis on cardiac magnetic resonance (CMR) imaging within a large ECG database beyond traditional ECG criteria. Methods: A deep convolutional neural network (DNN) was trained to detect ComVE using 12 leads in 6,916 ECGs from 569 MVP patients evaluated at the University of California San Francisco (UCSF) between 2012 and 2020. A DNN was also trained using 87 UCSF MVP patients with available contrast CMR to detect late gadolinium enhancement (LGE). Results: The prevalence of ComVE was 160/569 or 28% (20 or 3% with cardiac arrest or sudden arrhythmic death). The area under the curve (AUC) of the DNN to detect ComVE was 0.81 (95% CI, 0.78-0.84) (Figure). AUC remained high even after excluding patients with moderate-severe mitral regurgitation (MR) [0.80 (95% CI, 0.77-0.83)], or with bileaflet MVP [0.81 (95% CI, 0.76-0.85)]. The top ECG segments able to discriminate ComVE vs no ComVE were related to ventricular depolarization and repolarization (early-mid ST and QRS fromV1, V3, and III). LGE in the papillary muscles or basal inferolateral wall was present in 22 of 87 (25%) with available CMR. The AUC for detection of LGE was 0.75 (95% CI, 0.68-0.82). Conclusions: A deep-learning model can detect MVP at risk for ventricular arrhythmias and fibrosis from standard 12-lead ECGs, and can identify novel ECG correlates of arrhythmic risk regardless of leaflet involvement or mitral regurgitation severity. ECG-based deep-learning may help select, within a large echocardiographic database, those MVP patients requiring closer follow-up and/or a CMR.

Introduction: Engagement with home blood pressure monitoring (HBPM) usually declines over time; however, published studies have not described inter-individual variability of HBPM behaviors. We aimed to describe different 1-year patterns of HBPM behaviors, identify predictors of those patterns, and examine the association of HBPM behaviors with BP levels over time. Methods: We analyzed BP records from the Health eHeart (HeH) Study, an ongoing prospective e-cohort study, limiting our analysis to participants with a wireless consumer-purchased device that transmitted date-and time-stamped BP data to the HeH server through a full 12 months of observation starting from the first day they used the device. Participants received no instruction on device use. We applied clustering analysis to identify 1-year HBPM patterns. Results: The sample (N=2099) had a mean age of 52.0±12.0 years and BMI of 28.9±6.5 kg/m 2 ; most were male (89.1%) and White (88.6%). Using clustering algorithms, we found that a model with three patterns fit the data well (Figure); 69.7% were Sporadic Users, 21.2% were Weekly Users, and only 9.1% were Daily Users. Daily Users were older, unemployed, lower income, and more likely to have diabetes, coronary heart disease, and a history of myocardial infarction (p Conclusion: We identified 3 distinct HBPM use patterns, with nearly 10% sustaining a daily use pattern that was associated with lower BP levels despite being in socially and medically higher risk groups.

Background: Automated cardiac image interpretation has the potential to transform clinical practice in multiple ways, including enabling serial assessment of cardiac function by nonexperts in primary care and rural settings. We hypothesized that advances in computer vision could enable building a fully automated, scalable analysis pipeline for echocardiogram interpretation, including (1) view identification, (2) image segmentation, (3) quantification of structure and function, and (4) disease detection. Methods: Using 14 035 echocardiograms spanning a 10-year period, we trained and evaluated convolutional neural network models for multiple tasks, including automated identification of 23 viewpoints and segmentation of cardiac chambers across 5 common views. The segmentation output was used to quantify chamber volumes and left ventricular mass, determine ejection fraction, and facilitate automated determination of longitudinal strain through speckle tracking. Results were evaluated through comparison to manual segmentation and measurements from 8666 echocardiograms obtained during the routine clinical workflow. Finally, we developed models to detect 3 diseases: hypertrophic cardiomyopathy, cardiac amyloid, and pulmonary arterial hypertension. Results: Convolutional neural networks accurately identified views (eg, 96% for parasternal long axis), including flagging partially obscured cardiac chambers, and enabled the segmentation of individual cardiac chambers. The resulting cardiac structure measurements agreed with study report values (eg, median absolute deviations of 15% to 17% of observed values for left ventricular mass, left ventricular diastolic volume, and left atrial volume). In terms of function, we computed automated ejection fraction and longitudinal strain measurements (within 2 cohorts), which agreed with commercial software-derived values (for ejection fraction, median absolute deviation=9.7% of observed, N=6407 studies; for strain, median absolute deviation=7.5%, n=419, and 9.0%, n=110) and demonstrated applicability to serial monitoring of patients with breast cancer for trastuzumab cardiotoxicity. Overall, we found automated measurements to be comparable or superior to manual measurements across 11 internal consistency metrics (eg, the correlation of left atrial and ventricular volumes). Finally, we trained convolutional neural networks to detect hypertrophic cardiomyopathy, cardiac amyloidosis, and pulmonary arterial hypertension with C statistics of 0.93, 0.87, and 0.85, respectively. Conclusions: Our pipeline lays the groundwork for using automated interpretation to support serial patient tracking and scalable analysis of millions of echocardiograms archived within healthcare systems.

Automated cardiac image interpretation has the potential to transform clinical practice in multiple ways, including enabling serial assessment of cardiac function by nonexperts in primary care and rural settings. We hypothesized that advances in computer vision could enable building a fully automated, scalable analysis pipeline for echocardiogram interpretation, including (1) view identification, (2) image segmentation, (3) quantification of structure and function, and (4) disease detection.Using 14 035 echocardiograms spanning a 10-year period, we trained and evaluated convolutional neural network models for multiple tasks, including automated identification of 23 viewpoints and segmentation of cardiac chambers across 5 common views. The segmentation output was used to quantify chamber volumes and left ventricular mass, determine ejection fraction, and facilitate automated determination of longitudinal strain through speckle tracking. Results were evaluated through comparison to manual segmentation and measurements from 8666 echocardiograms obtained during the routine clinical workflow. Finally, we developed models to detect 3 diseases: hypertrophic cardiomyopathy, cardiac amyloid, and pulmonary arterial hypertension.Convolutional neural networks accurately identified views (eg, 96% for parasternal long axis), including flagging partially obscured cardiac chambers, and enabled the segmentation of individual cardiac chambers. The resulting cardiac structure measurements agreed with study report values (eg, median absolute deviations of 15% to 17% of observed values for left ventricular mass, left ventricular diastolic volume, and left atrial volume). In terms of function, we computed automated ejection fraction and longitudinal strain measurements (within 2 cohorts), which agreed with commercial software-derived values (for ejection fraction, median absolute deviation=9.7% of observed, N=6407 studies; for strain, median absolute deviation=7.5%, n=419, and 9.0%, n=110) and demonstrated applicability to serial monitoring of patients with breast cancer for trastuzumab cardiotoxicity. Overall, we found automated measurements to be comparable or superior to manual measurements across 11 internal consistency metrics (eg, the correlation of left atrial and ventricular volumes). Finally, we trained convolutional neural networks to detect hypertrophic cardiomyopathy, cardiac amyloidosis, and pulmonary arterial hypertension with C statistics of 0.93, 0.87, and 0.85, respectively.Our pipeline lays the groundwork for using automated interpretation to support serial patient tracking and scalable analysis of millions of echocardiograms archived within healthcare systems.

Introduction: We aimed to evaluate whether a novel deep neural network (DNN) can predict cardiovascular risk factors from off-the-shelf wearables with a photoplethysmographic (PPG) heart rate sensor and accelerometer. Longitudinal heart rate variability and activity patterns have previously been associated with incident hypertension, diabetes, and sleep apnea, conditions which are frequently undiagnosed. Methods: Health eHeart, an IRB-approved UCSF study, enrolled 6,115 active users of the Cardiogram app for Apple Watch. Heart rate and step counts were collected for a period of 1 to 53 weeks (mean=8.9). Data from 70% of participants (33,628 person-weeks of data) was used to train a semi-supervised, multi-task DNN with both convolutional and recurrent layers to simultaneously predict prevalent hypertension, sleep apnea, and diabetes. Test performance characteristics were estimated using the remaining 30% of participants. Results: Mean age was 42.3 ± 12.1, 69% male. 2,230 (36.5%) of participants had hypertension, 1,016 (16.6%) had sleep apnea, and 462 (7.6%) had diabetes. In the validation set, the DNN outperformed a baseline logistic regression model incorporating age, sex, and beta blocker use, predicting prevalent hypertension with a c-statistic of 0.819 (95% CI 0.76-0.88; with an optimal operating point yielding 84.8% sensitivity and 63.6% specificity) vs a baseline c-statistic of 0.682 (95% CI 0.60-0.76), and prevalent sleep apnea with a c-statistic of 0.902 (95% CI 0.85-0.95; with an optimal operating point yielding 90.4% sensitivity and 59.8% specificity) vs a baseline c-statistic of 0.459 (95% CI 0.39-0.53). Results were not statistically significant for diabetes. Conclusions: Our DNN demonstrates surprisingly good prediction of hypertension and sleep apnea given that its only inputs are heart rate and step count. Whether such DNNs can provide durable and portable predictions for these conditions in other study samples is worth pursuing.

Introduction: While mHealth platforms can enable rapid participant recruitment, the first 5 ResearchKit apps retained less than 10% of daily participants after the first 90 days, whereas well-optimized consumer mobile apps like Instagram and Twitter retain 31% and 48%, respectively. We proposed to apply design principles from the world of consumer internet to achieve high engagement and retention in a mHealth study. Methods: We enrolled 14,011 users of Cardiogram for Apple Watch app into the Health eHeart Study, an IRB-approved study at UCSF. We applied 3 key design principles to drive engagement and retention. First, give valuable insights back to user—e.g., notify users of abnormal heart rate spikes, and show when exercise caused a lower resting heart rate trend—using Gottman’s ratio: for every negative insight, give 5 positive ones. Second, minimize latency so users’ data updates many times per day. Third, use simple user interfaces that easily visualize trends and provide insights in small digestible formats. Results: Mean age was 42.3 ± 12.1, 31% were women. Seven days after app install, 64% of participants were active; 63% were active after 30 days, and 54% after 90 days. Retention was consistent across age groups—day 90 retention was 52% for 20-40 y.o., 55% for 40-60, and 49% for above 60. Refreshing data as frequently as possible had the highest impact on user engagement—in A/B testing, where heart rate visualizations were updated less frequently, we saw 20.9% drop in daily active users (51951 to 41094) within 7 days. The ratio of daily to monthly active users, a key measure of engagement, is 69.8% in our study, while average mHealth app is 8%. Conclusions: By applying design techniques from consumer mobile apps, we achieved day 90 retention 5x higher than the best ResearchKit app, showing that mHealth studies can retain large cohorts of participants and collect unique ambulatory health data with high engagement, improving the impact of mobile health interventions.

Introduction: In 2012, there were 39 million physician visits for hypertension (HTN), but only 53% of patients have hypertension under control. Remote management coupled with mobile health platforms may help improve communication, medication titration, care team feedback and patient experience. We conducted an observational study in order to evaluate the performance of mobile app-facilitated, team-based remote HTN management program on HTN control, time to control, and time spent under control. Methods: The HIPSTER study was an observational study conducted by the UCSF Division of Cardiology and School of Pharmacy in collaboration with Vital Labs Inc. We enrolled 120 consecutive patients from the UCSF Cardiology clinic who were aged ≥18 years with a diagnosis of essential or co-morbid HTN. Participants downloaded the Vital Labs smart phone application (app) and utilized a home blood pressure cuff to measure blood pressure at least once-daily. The app scheduled blood pressure reminders, allowed for virtual communication via direct messaging, and provided access to patient data. Based on the daily, remote BP measurements, pharmacists performed rapid-cycle medication management for patients remotely, in coordination with study cardiologists. Results: Of 120 patients enrolled, 59% were male, and 10% were between 18-35y, 43% between 36-64y, and 45% >64y. At the time of enrollment, 17.5% of patients were not on any antihypertensive medication. After 6 month follow-up, 84% of patients met their JNC8 goal. Patients took an average of 17 days to achieve BP control, and patients remained under control for 74% of the study duration. Conclusions: Using a mobile-app facilitated remote HTN management protocol, 84% of patients met their JNC8 BP goal, versus an estimated 53% nationally. Compared to prior reports that cite an average of 3.2 months to reach BP goal in real-world practice-based settings, patients in our study achieved JNC8 BP goal within 17 days from enrollment. A mobile app-facilitated remote HTN management platform, coupled with team-based care, can be used to increase achievement of BP control and decrease the time required to achieve BP control. Future directions include examining the generalizability of these findings through randomized studies.

Background: Moderate consumption of alcohol may provide protection against myocardial infarction and mortality, but also likely increases blood pressure and incidence of atrial fibrillation. Despite the absence of rigorous controlled trials on the actual cardiovascular benefits of alcohol, the lay press frequently portrays alcohol as “heart healthy” (HH). No study to date has described individuals’ perceptions regarding the health effects of alcohol, how they gained this perception, nor how that perception may influence behavior. Methods: We performed a cross-sectional analysis of data obtained between March 8, 2013 to September 29, 2014 from consecutive participants enrolled in the Health eHeart Study, a prospective, internet-based cohort study. The characteristics of participants that reported alcohol as HH were determined. Results: A total of 5,417 participants answered questions regarding their perception of alcohol. Thirty percent (n=1,707) viewed alcohol as HH, 39% (n=2,157) viewed it as bad for the heart, and 31% (n=1,718) were unsure. Of those reporting alcohol as HH, 78% cited lay press as a source of their knowledge, 14% cited their doctor, and 92% reported that red wine exclusively was HH. In adjusted analyses, older age, higher education, higher income, and United States residence were associated with a perception of alcohol as HH (Figure). Those with a history of heart failure (HF) were significantly less likely to cite alcohol as HH. Compared to those who did not report alcohol as HH, those who perceived alcohol as HH consumed more alcohol (median 5 drinks per week, IQR 2-8 vs. median 3 drinks, IQR 1-7, p=0.001; adjusted: 10% more alcohol per week, 95% CI 1-20% more, p=0.02). Conclusions: Among more than 5,000 consecutive Health eHeart participants, approximately one third believe alcohol is HH and one third believes it is not. Those who believe alcohol is HH were of higher socioeconomic status, more likely to be American, less likely to have HF, and reported drinking more alcohol.