Search

ImportanceUnderstanding left ventricular ejection fraction (LVEF) during coronary angiography can assist in disease management.ObjectiveTo develop an automated approach to predict LVEF from left coronary angiograms.Design, Setting, and ParticipantsThis was a cross-sectional study with external validation using patient data from December 12, 2012, to December 31, 2019, from the University of California, San Francisco (UCSF). Data were randomly split into training, development, and test data sets. External validation data were obtained from the University of Ottawa Heart Institute. Included in the analysis were all patients 18 years or older who received a coronary angiogram and transthoracic echocardiogram (TTE) within 3 months before or 1 month after the angiogram.ExposureA video-based deep neural network (DNN) called CathEF was used to discriminate (binary) reduced LVEF (≤40%) and to predict (continuous) LVEF percentage from standard angiogram videos of the left coronary artery. Guided class-discriminative gradient class activation mapping (GradCAM) was applied to visualize pixels in angiograms that contributed most to DNN LVEF prediction.ResultsA total of 4042 adult angiograms with corresponding TTE LVEF from 3679 UCSF patients were included in the analysis. Mean (SD) patient age was 64.3 (13.3) years, and 2212 patients were male (65%). In the UCSF test data set (n = 813), the video-based DNN discriminated (binary) reduced LVEF (≤40%) with an area under the receiver operating characteristic curve (AUROC) of 0.911 (95% CI, 0.887-0.934); diagnostic odds ratio for reduced LVEF was 22.7 (95% CI, 14.0-37.0). DNN-predicted continuous LVEF had a mean absolute error (MAE) of 8.5% (95% CI, 8.1%-9.0%) compared with TTE LVEF. Although DNN-predicted continuous LVEF differed 5% or less compared with TTE LVEF in 38.0% (309 of 813) of test data set studies, differences greater than 15% were observed in 15.2% (124 of 813). In external validation (n = 776), video-based DNN discriminated (binary) reduced LVEF (≤40%) with an AUROC of 0.906 (95% CI, 0.881-0.931), and DNN-predicted continuous LVEF had an MAE of 7.0% (95% CI, 6.6%-7.4%). Video-based DNN tended to overestimate low LVEFs and underestimate high LVEFs. Video-based DNN performance was consistent across sex, body mass index, low estimated glomerular filtration rate (≤45), presence of acute coronary syndromes, obstructive coronary artery disease, and left ventricular hypertrophy.Conclusion and relevanceThis cross-sectional study represents an early demonstration of estimating LVEF from standard angiogram videos of the left coronary artery using video-based DNNs. Further research can improve accuracy and reduce the variability of DNNs to maximize their clinical utility.

Chest pain is a common clinical complaint for which myocardial injury is the primary concern and is associated with significant morbidity and mortality. To aid providers’ decision-making, we aimed to analyze the electrocardiogram (ECG) using a deep convolutional neural network (CNN) to predict serum troponin I (TnI) from ECGs. We developed a CNN using 64,728 ECGs from 32,479 patients who underwent ECG within 2 h prior to a serum TnI laboratory result at the University of California, San Francisco (UCSF). In our primary analysis, we classified patients into groups of TnI

The global burden of diabetes is rapidly increasing, from 451 million people in 2019 to 693 million by 20451. The insidious onset of type 2 diabetes delays diagnosis and increases morbidity2. Given the multifactorial vascular effects of diabetes, we hypothesized that smartphone-based photoplethysmography could provide a widely accessible digital biomarker for diabetes. Here we developed a deep neural network (DNN) to detect prevalent diabetes using smartphone-based photoplethysmography from an initial cohort of 53,870 individuals (the ‘primary cohort’), which we then validated in a separate cohort of 7,806 individuals (the ‘contemporary cohort’) and a cohort of 181 prospectively enrolled individuals from three clinics (the ‘clinic cohort’). The DNN achieved an area under the curve for prevalent diabetes of 0.766 in the primary cohort (95% confidence interval: 0.750–0.782; sensitivity 75%, specificity 65%) and 0.740 in the contemporary cohort (95% confidence interval: 0.723–0.758; sensitivity 81%, specificity 54%). When the output of the DNN, called the DNN score, was included in a regression analysis alongside age, gender, race/ethnicity and body mass index, the area under the curve was 0.830 and the DNN score remained independently predictive of diabetes. The performance of the DNN in the clinic cohort was similar to that in other validation datasets. There was a significant and positive association between the continuous DNN score and hemoglobin A1c (P ≤ 0.001) among those with hemoglobin A1c data. These findings demonstrate that smartphone-based photoplethysmography provides a readily attainable, non-invasive digital biomarker of prevalent diabetes. A deep neural network applied to smartphone-based vascular imaging can detect diabetes, opening new possibilities for non-invasive diagnosis.

Background: Atrial fibrillation (AF), a common cause of stroke, often is asymptomatic. Smartphones and smartwatches can detect AF using heart rate patterns inferred using photoplethysmography (PPG); however, enhanced accuracy is required to reduce false positives in screening populations. Objective: The purpose of this study was to test the hypothesis that a deep learning algorithm given raw, smartwatch-derived PPG waveforms would discriminate AF from normal sinus rhythm better than algorithms using heart rate alone. Methods: Patients presenting for cardioversion of AF (n = 51) were given wrist-worn fitness trackers containing PPG sensors (Jawbone Health). Standard 12-lead electrocardiograms over-read by board-certified cardiac electrophysiologists were used as the reference standard. The accuracy of PPG signals to discriminate AF from sinus rhythm was evaluated by conventional measures of heart rate variability, a long short-term memory (LSTM) neural network given heart rate data only, and a deep convolutional-recurrent neural net (DNN) given the raw PPG data. Results: From among 51 patients with persistent AF (age 63.6 ± 11.3 years; 78% male; 88% white), we randomly assigned 40 to train and 11 to test the algorithms. Whereas logistic regression analysis of heart rate variability yielded an area under the receiver operating characteristic curve (AUC) of 0.717 (sensitivity 0.741; specificity 0.584), the LSTM model given heart rate data exhibited AUC of 0.954 (sensitivity 0.810; specificity 0.921), and the DNN model given raw PPG data yielded the highest AUC of 0.983 (sensitivity 0.985; specificity 0.880). Conclusion: A deep learning model given the raw PPG-based signal resulted in AF detection with high accuracy, performing better than conventional analyses relying on heart rate series data alone.

Background Atrial fibrillation (AF), a common cause of stroke, often is asymptomatic. Smartphones and smartwatches can detect AF using heart rate patterns inferred using photoplethysmography (PPG); however, enhanced accuracy is required to reduce false positives in screening populations. Objective The purpose of this study was to test the hypothesis that a deep learning algorithm given raw, smartwatch-derived PPG waveforms would discriminate AF from normal sinus rhythm better than algorithms using heart rate alone. Methods Patients presenting for cardioversion of AF (n = 51) were given wrist-worn fitness trackers containing PPG sensors (Jawbone Health). Standard 12-lead electrocardiograms over-read by board-certified cardiac electrophysiologists were used as the reference standard. The accuracy of PPG signals to discriminate AF from sinus rhythm was evaluated by conventional measures of heart rate variability, a long short-term memory (LSTM) neural network given heart rate data only, and a deep convolutional-recurrent neural net (DNN) given the raw PPG data. Results From among 51 patients with persistent AF (age 63.6 ± 11.3 years; 78% male; 88% white), we randomly assigned 40 to train and 11 to test the algorithms. Whereas logistic regression analysis of heart rate variability yielded an area under the receiver operating characteristic curve (AUC) of 0.717 (sensitivity 0.741; specificity 0.584), the LSTM model given heart rate data exhibited AUC of 0.954 (sensitivity 0.810; specificity 0.921), and the DNN model given raw PPG data yielded the highest AUC of 0.983 (sensitivity 0.985; specificity 0.880). Conclusion A deep learning model given the raw PPG-based signal resulted in AF detection with high accuracy, performing better than conventional analyses relying on heart rate series data alone.

Summary A recent study by Karwath et al.1 in The Lancet applied machine learning-based cluster analysis to pooled data from nine double-blind, randomized controlled trials of beta blockers, identifying subgroups of efficacy in patients with sinus rhythm and atrial fibrillation., A recent study by Karwath et al.1 in The Lancet applied machine learning-based cluster analysis to pooled data from nine double-blind, randomized controlled trials of beta blockers, identifying subgroups of efficacy in patients with sinus rhythm and atrial fibrillation.

BackgroundMitral valve prolapse (MVP) is a common valvulopathy, with a subset of MVP patients developing sudden cardiac death or cardiac arrest. Complex ventricular ectopy (ComVE) represents a marker of arrhythmic risk that is associated with myocardial fibrosis and increased mortality in MVP. We hypothesize that an ECG-based machine-learning model can identify MVP with ComVE and/or myocardial fibrosis on cardiac magnetic resonance (CMR) imaging.MethodsA deep convolutional neural network (CNN) was trained to detect ComVE using 6,916 12-lead ECGs from 569 MVP patients evaluated at the University of California San Francisco (UCSF) between 2012 and 2020. A separate CNN was also trained to detect late gadolinium enhancement (LGE) using 87 ECGs from MVP patients with contrast CMR.Results: The prevalence of ComVE was 160/569 or 28% (20 patients or 3% had cardiac arrest or sudden cardiac death). The area under the curve (AUC) of the CNN to detect ComVE was 0.81 (95% CI, 0.78-0.84). 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 21 (24%) of 87 patients with available CMR. The AUC for detection of LGE was 0.75 (95% CI, 0.68-0.82).ConclusionsStandard 12-lead ECGs analyzed with machine learning can detect MVP at risk for ventricular arrhythmias and fibrosis and can identify novel ECG correlates of arrhythmic risk regardless of leaflet involvement or mitral regurgitation severity. ECG-based CNNs may help select those MVP patients requiring closer follow-up and/or a CMR.

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.

Background Heart failure (HF) is a leading cause of cardiac morbidity among women, whose risk factors differ from those in men. We used machine-learning approaches to develop risk- prediction models for incident HF in a cohort of postmenopausal women from the Women’s Health Initiative (WHI). Methods We used 2 machine-learning methods—Least Absolute Shrinkage and Selection Operator (LASSO) and Classification and Regression Trees (CART)—to perform variable selection on 1227 baseline WHI variables for the primary outcome of incident HF. These variables were then used to construct separate Cox proportional hazard models, and we compared these results, using receiver-operating characteristic (ROC) curve analysis, against a comparator model built using variables from the Atherosclerosis Risk in Communities (ARIC) HF prediction model. We analyzed 43,709 women who had 2222 incident HF events; median follow-up was 14.3 years. Results LASSO selected 10 predictors, and CART selected 11 predictors. The highest correlation between selected variables was 0.46. In addition to selecting well-established predictors such as age, myocardial infarction, and smoking, novel predictors included physical function, number of pregnancies, number of previous live births and age at menopause. In ROC analysis, the CART-derived model had the highest C-statistic of 0.83 (95% confidence interval [CI], 0.81-0.85), followed by LASSO 0.82 (95% CI, 0.81-0.84) and ARIC 0.73 (95% CI, 0.70-0.76). Conclusions Machine-learning approaches can be used to develop HF risk-prediction models that can have better discrimination compared with an established HF risk model and may provide a basis for investigating novel HF predictors.

BACKGROUND: A growing body of evidence has demonstrated that pulmonary arterial capacitance (PAC) is the strongest hemodynamic predictor of clinical outcomes across a wide spectrum of cardiovascular disease, including pulmonary hypertension and heart failure. We hypothesized that a ratio of right ventricular stroke volume (RVOT VTI) to the associated peak arterial systolic pressure (PASP) could function as a reliable non-invasive surrogate for PAC. METHODS. We performed a prospective study of patients undergoing simultaneous transthoracic echocardiography and right heart catheterization (RHC) for various clinical indications. Measurements of the RVOT VTI/PASP ratio from echocardiographic measurements were compared against PAC calculated from RHC measurements. Correlation coefficients and Bland-Altman analysis compared the RVOT VTI/PASP ratio with PAC. RESULTS. Forty-five subjects were enrolled, 38% were female and mean age was 54 years (SD 13 years). The reason for referral to RHC was most commonly post-heart transplant surveillance (40%), followed by heart failure (22%), and pulmonary hypertension (18%). Pre-capillary pulmonary hypertension was present in 18%, isolated post-capillary pulmonary hypertension was present in 13%, and combined pre-and post-capillary pulmonary hypertension was present in 29%. The RVOT VTI/PASP ratio was obtainable in the majority of patients (78%), and Pearson’s correlation demonstrated moderately-strong association between PAC and the RVOT VTI/PASP ratio, r = 0.75 (P

Recent advances in machine learning (ML) have made it possible to analyze high-dimensional and complex data-such as free text, images, waveforms, videos, and sound-in an automated manner by successfully learning complex associations within these data. Cardiovascular medicine is particularly well poised to take advantage of these ML advances, due to the widespread digitization of medical data and the large number of diagnostic tests used to evaluate cardiovascular disease. Various ML approaches have successfully been applied to cardiovascular tests and diseases to automate interpretation, accurately perform measurements, and, in some cases, predict novel diagnoses from less invasive tests, effectively expanding the utility of more widely accessible diagnostic tests. Here, we present examples of some impactful advances in cardiovascular medicine using ML across a variety of modalities, with a focus on deep learning applications.

IMPORTANCE: Millions of clinicians rely daily on automated preliminary electrocardiogram (ECG) interpretation. Critical comparisons of machine learning–based automated analysis against clinically accepted standards of care are lacking. OBJECTIVE: To use readily available 12-lead ECG data to train and apply an explainability technique to a convolutional neural network (CNN) that achieves high performance against clinical standards of care. DESIGN, SETTING, AND PARTICIPANTS: This cross-sectional study was conducted using data from January 1, 2003, to December 31, 2018. Data were obtained in a commonly available 12-lead ECG format from a single-center tertiary care institution. All patients aged 18 years or older who received ECGs at the University of California, San Francisco, were included, yielding a total of 365 009 patients. Data were analyzed from January 1, 2019, to March 2, 2021. EXPOSURES: A CNN was trained to predict the presence of 38 diagnostic classes in 5 categories from 12-lead ECG data. A CNN explainability technique called LIME (Linear Interpretable Model-Agnostic Explanations) was used to visualize ECG segments contributing to CNN diagnoses. MAIN OUTCOMES AND MEASURES: Area under the receiver operating characteristic curve (AUC), sensitivity, and specificity were calculated for the CNN in the holdout test data set against cardiologist clinical diagnoses. For a second validation, 3 electrophysiologists provided consensus committee diagnoses against which the CNN, cardiologist clinical diagnosis, and MUSE (GE Healthcare) automated analysis performance was compared using the F1 score; AUC, sensitivity, and specificity were also calculated for the CNN against the consensus committee. RESULTS: A total of 992 748 ECGs from 365 009 adult patients (mean [SD] age, 56.2 [17.6] years; 183 600 women [50.3%]; and 175 277 White patients [48.0%]) were included in the analysis. In 91 440 test data set ECGs, the CNN demonstrated an AUC of at least 0.960 for 32 of 38 classes (84.2%). Against the consensus committee diagnoses, the CNN had higher frequency-weighted mean F1 scores than both cardiologists and MUSE in all 5 categories (CNN frequency-weighted F1 score for rhythm, 0.812; conduction, 0.729; chamber diagnosis, 0.598; infarct, 0.674; and other diagnosis, 0.875). For 32 of 38 classes (84.2%), the CNN had AUCs of at least 0.910 and demonstrated comparable F1 scores and higher sensitivity than cardiologists, except for atrial fibrillation (CNN F1 score, 0.847 vs cardiologist F1 score, 0.881), junctional rhythm (0.526 vs 0.727), premature ventricular complex (0.786 vs 0.800), and Wolff-Parkinson-White (0.800 vs 0.842). Compared with MUSE, the CNN had higher F1 scores for all classes except supraventricular tachycardia (CNN F1 score, 0.696 vs MUSE F1 score, 0.714). The LIME technique highlighted physiologically relevant ECG segments. CONCLUSIONS AND RELEVANCE: The results of this cross-sectional study suggest that readily available ECG data can be used to train a CNN algorithm to achieve comparable performance to clinical cardiologists and exceed the performance of MUSE automated analysis for most diagnoses, with some exceptions. The LIME explainability technique applied to CNNs highlights physiologically relevant ECG segments that contribute to the CNN’s diagnoses.

Excess alcohol use is an important determinant of death and disability. Machine learning (ML)-driven interventions leveraging smart-breathalyzer data may help reduce these harms. We developed a digital phenotype of long-term smart-breathalyzer behavior to predict individuals’ breath alcohol concentration (BrAC) levels trained on data from a smart breathalyzer. We analyzed roughly one million datapoints from 33,452 users of a commercial smart-breathalyzer device, collected between 2013 and 2017. For validation, we analyzed the associations between state-level observed smart-breathalyzer BrAC levels and impaired-driving motor vehicle death rates. Behavioral, geolocation-based, and time-series-derived features were fed to an ML algorithm using training (70% of the cohort), development (10% of the cohort), and test (20% of the cohort) sets to predict the likelihood of a BrAC exceeding the legal driving limit (0.08 g/dL). States with higher average BrAC levels had significantly higher alcohol-related driving death rates, adjusted for the number of users per state B (SE) = 91.38 (15.16), p

IMPORTANCE: Long QT syndrome (LQTS) is characterized by prolongation of the QT interval and is associated with an increased risk of sudden cardiac death. However, although QT interval prolongation is the hallmark feature of LQTS, approximately 40% of patients with genetically confirmed LQTS have a normal corrected QT (QTc) at rest. Distinguishing patients with LQTS from those with a normal QTc is important to correctly diagnose disease, implement simple LQTS preventive measures, and initiate prophylactic therapy if necessary. OBJECTIVE: To determine whether artificial intelligence (AI) using deep neural networks is better than the QTc alone in distinguishing patients with concealed LQTS from those with a normal QTc using a 12-lead electrocardiogram (ECG). DESIGN, SETTING, AND PARTICIPANTS: A diagnostic case-control study was performed using all available 12-lead ECGs from 2059 patients presenting to a specialized genetic heart rhythm clinic. Patients were included if they had a definitive clinical and/or genetic diagnosis of type 1, 2, or 3 LQTS (LQT1, 2, or 3) or were seen because of an initial suspicion for LQTS but were discharged without this diagnosis. A multilayer convolutional neural network was used to classify patients based on a 10-second, 12-lead ECG, AI-enhanced ECG (AI-ECG). The convolutional neural network was trained using 60% of the patients, validated in 10% of the patients, and tested on the remaining patients (30%). The study was conducted from January 1, 1999, to December 31, 2018. MAIN OUTCOMES AND MEASURES: The goal of the study was to test the ability of the convolutional neural network to distinguish patients with LQTS from those who were evaluated for LQTS but discharged without this diagnosis, especially among patients with genetically confirmed LQTS but a normal QTc value at rest (referred to as genotype positive/phenotype negative LQTS, normal QT interval LQTS, or concealed LQTS). RESULTS: Of the 2059 patients included, 1180 were men (57%); mean (SD) age at first ECG was 21.6 (15.6) years. All 12-lead ECGs from 967 patients with LQTS and 1092 who were evaluated for LQTS but discharged without this diagnosis were included for AI-ECG analysis. Based on the ECG-derived QTc alone, patients were classified with an area under the curve (AUC) value of 0.824 (95% CI, 0.79-0.858); using AI-ECG, the AUC was 0.900 (95% CI, 0.876-0.925). Furthermore, in the subset of patients who had a normal resting QTc (

BackgroundIn the absence of universal testing, effective therapies, or vaccines, identifying risk factors for viral infection, particularly readily modifiable exposures and behaviors, is required to identify effective strategies against viral infection and transmission.MethodsWe conducted a world-wide mobile application-based prospective cohort study available to English speaking adults with a smartphone. We collected self-reported characteristics, exposures, and behaviors, as well as smartphone-based geolocation data. Our main outcome was incident symptoms of viral infection, defined as fevers and chills plus one other symptom previously shown to occur with SARS-CoV-2 infection, determined by daily surveys.FindingsAmong 14, 335 participants residing in all 50 US states and 93 different countries followed for a median 21 days (IQR 10-26 days), 424 (3%) developed incident viral symptoms. In pooled multivariable logistic regression models, female biological sex (odds ration [OR] 1.75, 95% CI 1.39-2.20, pInterpretationWhile several immutable characteristics were associated with the risk of developing viral symptoms, multiple immediately modifiable exposures and habits that influence risk were also observed, potentially identifying readily accessible strategies to mitigate risk in the Covid-19 era.FundingThis study was funded by IU2CEB021881-01 and 3U2CEB021881-05S1 from the NIH/ NIBIB to Drs. Marcus, Olgin, and Pletcher.Research in contextEvidence before this studyPredictors of incident viral infection have been determined largely from cross-sectional studies prone to recall bias among individuals representing geographically constrained regions, and most were conducted before the era of the current Covid-19 pandemic.Added value of this studyWe conducted a world-wide, mobile application-based, longitudinal cohort study utilizing time-updated predictors and outcomes, providing novel and current information regarding risk-factors for incident viral symptoms based on real-time information in the era of Covid-19.Implications of all the available evidenceThese data suggest that certain immutable characteristics influence the risk for incident viral symptoms, while smoking cessation, physical distancing to avoid contact with individuals outside the household, regular exercise, and sanitizing one’s phone may each help mitigate the risk of viral infection.

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.

Although traditional approaches to biomarker discovery have elucidated key molecular markers that have improved drug selection (precision medicine), the discovery of biomarkers that inform optimal dose selection (precision dosing) continues to be a challenge in many therapeutic areas. Larger and more diverse study populations are necessary to discover additional biomarkers that provide the resolution needed for a more tailored dose. To generate and accommodate large datasets of drug response phenotypes, time‐ and cost‐efficient strategies are necessary. In particular, a multitude of technological advances that originated for purposes outside of biomedical research (electronic health records, direct‐to‐consumer genetic testing, social media, mobile devices, and machine learning) have made it easier to communicate, connect, and gather information from consumers. Although these technologies have been used with success in the health sciences for an array of purposes, these resources have not been fully capitalized on for precision dosing. This perspective will touch on how these innovations can be used as data sources, data collection tools, and data processing tools for drug‐response phenotypes with a unique focus on advancing biomarker‐driven precision dosing.

Author(s): Tison, Geoffrey H; Avram, Robert; Kuhar, Peter; Abreau, Sean; Marcus, Greg M; Pletcher, Mark J; Olgin, Jeffrey E

The risks of industrial pollutants are well documented,1 but few studies have examined the public health consequences of climate change–related events such as wildfires. The health benefits of physical activity and harms of sedentary behavior are well established.2,3 Although air pollution has been associated with self-reported reductions in physical activity, such ascertainment may be prone to recall bias.4,5 Accelerometer-based trackers have become increasingly used to estimate physical activity and can accurately measure step counts.6

Machine learning (ML) has been increasingly used within cardiology, particularly in the domain of cardiovascular imaging. Due to the inherent complexity and flexibility of ML algorithms, inconsistencies in the model performance and interpretation may occur. Several review articles have been recently published that introduce the fundamental principles and clinical application of ML for cardiologists. This paper builds on these introductory principles and outlines a more comprehensive list of crucial responsibilities that need to be completed when developing ML models. This paper aims to serve as a scientific foundation to aid investigators, data scientists, authors, editors, and reviewers involved in machine learning research with the intent of uniform reporting of ML investigations. An independent multidisciplinary panel of ML experts, clinicians, and statisticians worked together to review the theoretical rationale underlying 7 sets of requirements that may reduce algorithmic errors and biases. Finally, the paper summarizes a list of reporting items as an itemized checklist that highlights steps for ensuring correct application of ML models and the consistent reporting of model specifications and results. It is expected that the rapid pace of research and development and the increased availability of real-world evidence may require periodic updates to the checklist. ispartof: Jacc-Cardiovascular Imaging vol:13 issue:9 pages:2017-2035 ispartof: location:United States status: published

The number of cardiovascular imaging studies is growing exponentially, and so is the need to improve clinical workflow efficiency and avoid missed diagnoses. With the availability and use of large datasets, artificial intelligence (AI) has the potential to improve patient care at every stage of the imaging chain. Current literature indicates that in the short-term, AI has the capacity to reduce human error and save time in the clinical workflow through automated segmentation of cardiac structures. In the future, AI may expand the informational value of diagnostic images based on images alone or a combination of images and clinical variables, thus facilitating disease detection, prognosis, and decision making. This review describes the role of AI, specifically machine learning, in multimodality imaging, including echocardiography, nuclear imaging, computed tomography, and cardiac magnetic resonance, and highlights current uses of AI as well as potential challenges to its widespread implementation.

BACKGROUND Commercially acquired wearable activity trackers such as the Fitbit provide objective, accurate measurements of physically active time and step counts, but it is unclear whether these measurements are more clinically meaningful than self-reported physical activity. OBJECTIVE The aim of this study was to compare self-reported physical activity to Fitbit-measured step counts and then determine which is a stronger predictor of BMI by using data collected over the same period reflecting comparable physical activities. METHODS We performed a cross-sectional analysis of data collected by the Health eHeart Study, a large mobile health study of cardiovascular health and disease. Adults who linked commercially acquired Fitbits used in free-living conditions with the Health eHeart Study and completed an International Physical Activity Questionnaire (IPAQ) between 2013 and 2019 were enrolled (N=1498). Fitbit step counts were used to quantify time by activity intensity in a manner comparable to the IPAQ classifications of total active time and time spent being sedentary, walking, or doing moderate activities or vigorous activities. Fitbit steps per day were computed as a measure of the overall activity for exploratory comparisons with IPAQ-measured overall activity (metabolic equivalent of task [MET]-h/wk). Measurements of physical activity were directly compared by Spearman rank correlation. Strengths of associations with BMI for Fitbit versus IPAQ measurements were compared using multivariable robust regression in the subset of participants with BMI and covariates measured. RESULTS Correlations between synchronous paired measurements from Fitbits and the IPAQ ranged in strength from weak to moderate (0.09-0.48). In the subset with BMI and covariates measured (n=586), Fitbit-derived predictors were generally stronger predictors of BMI than self-reported predictors. For example, an additional hour of Fitbit-measured vigorous activity per week was associated with nearly a full point reduction in BMI (–0.84 kg/m2, 95% CI –1.35 to –0.32) in adjusted analyses, whereas the association between self-reported vigorous activity measured by IPAQ and BMI was substantially smaller in magnitude (–0.17 kg/m2, 95% CI –0.34 to –0.00; P CONCLUSIONS Fitbit-measured physical activity was more strongly associated with BMI than self-reported physical activity, particularly for moderate activity, vigorous activity, and summary measures of total activity. Consumer-marketed wearable activity trackers such as the Fitbit may be useful for measuring health-relevant physical activity in clinical practice and research.

Background Regular physical activity is an important determinant of cardiovascular health and quality of life. Previous investigations examining the association between exercise and atrial fibrillation (AF) have been limited by self-reported, retrospectively collected activity data. Objective The purpose of this study was to objectively quantify differences in daily physical activity among individuals with and those without AF using electronic wearable activity trackers. Methods Daily exercise data were directly obtained from wrist-worn activity trackers (Fitbit, San Francisco, CA) among participants in the Health eHeart (HeH) study. Average daily step count was compared between individuals with and those without AF both before and after adjusting for comorbidities. AF severity was quantified using the Atrial Fibrillation Effect on QualiTy of Life (AFEQT) survey. Results Among 171,284 HeH study participants, 3333 individuals (234 with AF [7%]) submitted activity data. In unadjusted analysis, AF participants ambulated an average of 723 fewer steps per day (95% confidence interval [CI] 292–1154; P = .001) compared to individuals without AF. After adjustment for demographics and comorbid diseases, participants with AF demonstrated 591 fewer steps per day (95% CI 149–1033; P = .009). Among AF patients, AF severity was associated with less physical activity. For each single point decrease in AFEQT score (corresponding to more symptomatic AF), physical activity decreased by a mean 24 steps per day (95% CI 1–46; P = .04). Conclusion Objective, automatically collected step count data demonstrate that individuals with AF engage in significantly less average daily physical activity. In addition, worsening AF symptom severity is associated with reduced daily exercise.

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.

Purpose Methamphetamine-Associated Pulmonary Arterial Hypertension (Meth-APAH) is recognized as a definite cause of PAH. Given that methamphetamine use induces both myocardial dysfunction and pulmonary vascular remodeling, we sought to assess differences in echocardiographic and hemodynamic parameters between patients with Meth-APAH and other patients with Group 1 PAH. Methods We performed a retrospective single-center cohort study of patients with Group 1 PAH in whom the first right heart catheterization (RHC) was performed within two months of a transthoracic echocardiogram (TTE). We extracted demographics and clinical data from the electronic medical record, including diagnostic etiology of PAH determined by the treating physician. TTE and RHC parameters were analyzed using Student's t-test and the Chi-Square test. We assessed time to first hospitalization and to death using Cox-proportional hazards modeling, adjusted for age, gender, and race. Results Of 302 patients, 57 had Meth-APAH. Patients with Meth-APAH were older (53 vs 49 years, p=0.05), more likely to be male (47% vs 39%, p=0.03), white (64.5% vs 46.7%, p=0.03), and to have a history of smoking (61% vs 35%, p Conclusion Patients with Meth-APAH are a unique subset of Group 1 PAH, with less favorable hemodynamics than other diagnostic etiologies and evidence of greater right ventricular dysfunction. Better understanding of how methamphetamine use causes myocardial dysfunction is necessary to understand the pathogenesis of Meth-APAH.

Background: The ECG remains the most widely used diagnostic test for characterization of cardiac structure and electrical activity. We hypothesized that parallel advances in computing power, machine learning algorithms, and availability of large-scale data could substantially expand the clinical inferences derived from the ECG while at the same time preserving interpretability for medical decision-making. Methods and Results: We identified 36 186 ECGs from the University of California, San Francisco database that would enable training of models for estimation of cardiac structure or function or detection of disease. We segmented the ECG into standard component waveforms and intervals using a novel combination of convolutional neural networks and hidden Markov models and evaluated this segmentation by comparing resulting electrical intervals against 141 864 measurements produced during the clinical workflow. We then built a patient-level ECG profile, a 725-element feature vector and used this profile to train and interpret machine learning models for examples of cardiac structure (left ventricular mass, left atrial volume, and mitral annulus e-prime) and disease (pulmonary arterial hypertension, hypertrophic cardiomyopathy, cardiac amyloid, and mitral valve prolapse). ECG measurements derived from the convolutional neural network-hidden Markov model segmentation agreed with clinical estimates, with median absolute deviations as a fraction of observed value of 0.6% for heart rate and 4% for QT interval. Models trained using patient-level ECG profiles enabled surprising quantitative estimates of left ventricular mass and mitral annulus e′ velocity (median absolute deviation of 16% and 19%, respectively) with good discrimination for left ventricular hypertrophy and diastolic dysfunction as binary traits. Model performance using our approach for disease detection demonstrated areas under the receiver operating characteristic curve of 0.94 for pulmonary arterial hypertension, 0.91 for hypertrophic cardiomyopathy, 0.86 for cardiac amyloid, and 0.77 for mitral valve prolapse. Conclusions: Modern machine learning methods can extend the 12-lead ECG to quantitative applications well beyond its current uses while preserving the transparency that is so fundamental to clinical care.

The global burden of diabetes is rapidly increasing, from 451 million people in 2019 to 693 million by 2045

Background Commercially acquired wearable activity trackers such as the Fitbit provide objective, accurate measurements of physically active time and step counts, but it is unclear whether these measurements are more clinically meaningful than self-reported physical activity. Objective The aim of this study was to compare self-reported physical activity to Fitbit-measured step counts and then determine which is a stronger predictor of BMI by using data collected over the same period reflecting comparable physical activities. Methods We performed a cross-sectional analysis of data collected by the Health eHeart Study, a large mobile health study of cardiovascular health and disease. Adults who linked commercially acquired Fitbits used in free-living conditions with the Health eHeart Study and completed an International Physical Activity Questionnaire (IPAQ) between 2013 and 2019 were enrolled (N=1498). Fitbit step counts were used to quantify time by activity intensity in a manner comparable to the IPAQ classifications of total active time and time spent being sedentary, walking, or doing moderate activities or vigorous activities. Fitbit steps per day were computed as a measure of the overall activity for exploratory comparisons with IPAQ-measured overall activity (metabolic equivalent of task [MET]-h/wk). Measurements of physical activity were directly compared by Spearman rank correlation. Strengths of associations with BMI for Fitbit versus IPAQ measurements were compared using multivariable robust regression in the subset of participants with BMI and covariates measured. Results Correlations between synchronous paired measurements from Fitbits and the IPAQ ranged in strength from weak to moderate (0.09-0.48). In the subset with BMI and covariates measured (n=586), Fitbit-derived predictors were generally stronger predictors of BMI than self-reported predictors. For example, an additional hour of Fitbit-measured vigorous activity per week was associated with nearly a full point reduction in BMI (–0.84 kg/m2, 95% CI –1.35 to –0.32) in adjusted analyses, whereas the association between self-reported vigorous activity measured by IPAQ and BMI was substantially smaller in magnitude (–0.17 kg/m2, 95% CI –0.34 to –0.00; P Conclusions Fitbit-measured physical activity was more strongly associated with BMI than self-reported physical activity, particularly for moderate activity, vigorous activity, and summary measures of total activity. Consumer-marketed wearable activity trackers such as the Fitbit may be useful for measuring health-relevant physical activity in clinical practice and research.