Publications

BACKGROUND: The rapidly expanding digital health landscape offers innovative opportunities for improving health care delivery and patient outcomes; however, regulatory and clinical frameworks for evaluating their key features, effectiveness, and outcomes are lacking. Cardiovascular and mental health apps represent 2 prominent categories within this space. While mental health apps have been extensively studied, limited research exists on the quality and effectiveness of cardiovascular care apps. Despite their potential, both categories of apps face criticism for a lack of clinical evidence, insufficient privacy safeguards, and underuse of smartphone-specific features alluding to larger shortcomings in the field.

OBJECTIVE: This study extends the use of the MINDApps framework to compare the quality of cardiovascular and mental health apps framework to compare the quality of cardiovascular and mental health apps with regard to data security, data collection, and evidence-based support to identify strengths, limitations, and broader shortcomings across these domains in the digital health landscape.

METHODS: We conducted a systematic review of the Apple App Store and Google Play Store, querying for cardiovascular care apps. Apps were included if they were updated within the past 90 days, available in English, and did not require a health care provider's referral. Cardiovascular care apps were matched to mental health apps by platform compatibility and cost. Apps were evaluated using the M-Health Index & Navigation Database (MIND; MINDApps), a comprehensive tool based on the American Psychiatric Association's app evaluation model. The framework includes 105 objective questions across 6 categories of quality, including privacy, clinical foundation, and engagement. Statistical differences between the 2 groups were assessed using two-proportion Z-tests.

RESULTS: In total, 48 cardiovascular care apps and 48 matched mental health apps were analyzed. The majority of apps in both categories included a privacy policy; yet, the majority in both samples shared user data with third-party companies. Evidence for effectiveness was limited, with only 2 (4%) cardiovascular care apps and 5 (10%) mental health apps meeting this criterion. Cardiovascular care apps were significantly more likely to be used in external devices such as smartphone-based electrocardiograms and blood pressure monitors.

CONCLUSIONS: Both categories lack robust clinical foundations and face substantial privacy challenges. Cardiovascular apps have the potential to revolutionize patient monitoring; yet, their limited evidence base and privacy concerns highlight opportunities for improvement. Findings demonstrate the broader applicability of the MINDApps framework in evaluating apps across medical fields and stress the significant shortcomings in the app marketplace for cardiovascular and mental health. Future work should prioritize evidence-based app development, privacy safeguards, and the integration of innovative smartphone functionalities to ensure that health apps are safe and effective for patient use.

BACKGROUND: Leadless pacemakers (LPM) have been shown to be safe and effective alternatives to transvenous pacing systems. Few studies have evaluated the incidence and associated costs of post-implant complications. The objectives of this study were to assess risk factors and causes for 1-year mortality and all-cause readmission, as well as characterize the total cost of care associated with index procedures and readmissions.

METHODS: LPM procedures, including inpatient and outpatient encounters, were captured in the Healthcare Cost and Utilization Project data in Florida, Maryland, and New York from 2016 to 2020 with 1-year follow-up through 2021. Cox proportional hazards regression was used to identify patient demographics, facility volume, and comorbid risk factors for 1-year all-cause readmission and in-hospital mortality. Costs of inpatient cases and readmission were captured.

METHODS: Among 7127 patients receiving LPM, 3% died during the initial episode of care. The 1-year all-cause readmission rate was 45.9%, and the in-hospital mortality rate was 8.8%. Comorbid heart failure (CHF), atrial fibrillation/flutter, chronic kidney disease, and diabetes increased the risk of 1-year all-cause readmission and in-hospital mortality (p < 0.05). CHF was the most common cause of readmission (17%). Inpatient cases resulted in a cost of $257 million, with readmissions increasing costs by 44.4%.

CONCLUSIONS: The large healthcare expenditure derives from high rates of readmission and in-hospital mortality, with readmissions potentially representing a modifiable target. CHF is a prominent cause of poor outcomes, which suggests the need to consider the overlapping roles of conduction system pacing, goal-directed medical therapy, and close clinical follow-up.

BACKGROUND AND AIMS: Valvular heart disease (VHD) is a significant source of morbidity and mortality, though early intervention can improve outcomes. This study aims to develop artificial intelligence-enhanced electrocardiography (AI-ECG) models to diagnose and predict future moderate or severe regurgitant VHDs (rVHDs), including mitral regurgitation (MR), tricuspid regurgitation (TR), and aortic regurgitation (AR).

METHODS: The AI-ECG models were developed in a data set of 988 618 ECG and transthoracic echocardiogram pairs from 400 882 patients from Zhongshan Hospital, Shanghai, China. The AI-ECG models used a residual convolutional neural network with a discrete-time survival loss function. External evaluation was performed in outpatients from a secondary care data set from Beth Israel Deaconess Medical Center, Boston, USA, consisting of 34 214 patients with linked echocardiography.

RESULTS: In the internal test set, the AI-ECG models accurately predicted future significant MR [C-index 0.774, 95% confidence interval (CI) 0.753-0.792], AR (0.691, 95% CI 0.657-0.720), and TR (0.793, 95% CI 0.777-0.808). In age- and sex-adjusted Cox models, the highest risk quartile had a hazard ratio (HR) of 7.6 (95% CI 5.8-9.9, P < .0001) for risk of future significant MR, compared with the lowest risk quartile. For future AR and TR, the equivalent HRs were 3.8 (95% CI 2.7-5.5) and 9.9 (95% CI 7.5-13.0), respectively. These findings were confirmed in the transnational external test set. Imaging association analyses demonstrated AI-ECG predictions were associated with subclinical chamber remodelling.

CONCLUSIONS: This study developed AI-ECG models to diagnose and predict rVHDs and validated the models in a transnational and ethnically distinct cohort. The AI-ECG models could be utilized to guide surveillance echocardiography in patients at risk of future rVHDs, to facilitate early detection and intervention.

BACKGROUND: Abnormal ventricular depolarization, evident as a broad QRS complex on an ECG, is traditionally categorized into left bundle-branch block (LBBB) and right bundle-branch block or nonspecific intraventricular conduction delay. This categorization, although physiologically accurate, may fail to capture the nuances of diseases subtypes.

METHODS: We used unsupervised machine learning to identify and characterize novel broad QRS phenogroups. First, we trained a variational autoencoder on 1.1 million ECGs and discovered 51 latent features that showed high disentanglement and ECG reconstruction accuracy. We then extracted these features from 42 538 ECGs with QRS durations >120 milliseconds and employed a reversed graph embedding method to model population heterogeneity as a tree structure with different branches representing phenogroups.

RESULTS: Six phenogroups were identified, including phenogroups of right bundle-branch block and LBBB with varying risk of cardiovascular disease and mortality. The higher risk right bundle-branch block phenogroup exhibited increased risk of cardiovascular death (adjusted hazard ratio [aHR], 1.46 [1.30-1.63], P<0.0001) and all-cause mortality (aHR, 1.24 [1.16-1.33], P<0.0001) compared with the baseline phenogroup. Within LBBB ECGs, tree position predicted future cardiovascular disease risk differentially. Additionally, for subjects with LBBB undergoing cardiac resynchronization therapy, tree position predicted cardiac resynchronization therapy response independent of covariates, including QRS duration (adjusted odds ratio [aOR], 0.47 [0.25-0.86], P<0.05).

CONCLUSIONS: Our findings challenge the current paradigm, highlighting the potential for these phenogroups to enhance cardiac resynchronization therapy patient selection for subjects with LBBB and guide investigation and follow-up strategies for subjects with higher risk right bundle-branch block.

AIMS: Many research databases with anonymized patient data contain electrocardiograms (ECGs) from which traditional identifiers have been removed. We evaluated the ability of artificial intelligence (AI) methods to determine the similarity between ECGs and assessed whether they have the potential to be misused to re-identify individuals from anonymized datasets.

METHODS AND RESULTS: We utilized a convolutional Siamese neural network (SNN) architecture, which derives a Euclidean distance similarity metric between two input ECGs. A secondary care dataset of 864 283 ECGs (72 455 subjects) was used. Siamese neural network-electrocardiogram (SNN-ECG) achieves an accuracy of 91.68% when classifying between 2 689 124 same-subject pairs and 2 689 124 different-subject pairs. This performance increases to 93.61% and 95.97% in outpatient and normal ECG subsets. In a simulated 'motivated intruder' test, SNN-ECG can identify individuals from large datasets. In datasets of 100, 1000, 10 000, and 20 000 ECGs, where only one ECG is also from the reference individual, it achieves success rates of 79.2%, 62.6%, 45.0%, and 40.0%, respectively. If this was random, the success would be 1%, 0.1%, 0.01%, and 0.005%, respectively. Additional basic information, like subject sex or age-range, enhances performance further. We also found that, on the subject level, ECG pair similarity is clinically relevant; greater ECG dissimilarity associates with all-cause mortality [hazard ratio, 1.22 (1.21-1.23), P < 0.0001] and is additive to an AI-ECG model trained for mortality prediction.

CONCLUSION: Anonymized ECGs retain information that may facilitate subject re-identification, raising privacy and data protection concerns. However, SNN-ECG models also have positive uses and can enhance risk prediction of cardiovascular disease.

BACKGROUND: Use of pulmonary vein isolation (PVI) to treat atrial fibrillation continues to increase. Despite great interest in leveraging administrative data for real-world analyses, contemporary procedural codes for identifying PVI have not been evaluated.

METHODS AND RESULTS: In this observational retrospective cohort study, inpatient PVIs were identified among US Medicare fee-for-service beneficiaries using Current Procedural Terminology (CPT) code 93656 in Carrier Line Files. Each patient was matched with their claims from Medicare Provider Analysis and Review to compare CPT with International Classification of Diseases, Tenth Revision, Procedure Coding System (ICD-10-PCS) claims submitted by health care facilities to bill for PVIs. We performed the reverse for commonly matched ICD-10-PCS codes, to identify corresponding CPT-billed procedures. Finally, we reviewed institutional cases for additional comparison of CPT and ICD-10-PCS assignation for PVI. We identified 25 617 inpatient PVIs from January 2017 to December 2021, of which 18 165 (71%) were linked to Medicare Provider Analysis and Review. Of these, 16 672 (92%) were billed as ICD-10-PCS 02583ZZ: "Destruction of Conduction Mechanism, Percutaneous Approach." The reverse process yielded heterogeneous results: among 75 003 procedures billed as ICD-10-PCS 02583ZZ, only 15 691 (21%) matched with CPT 93656 (PVI), as several other unrelated procedures were billed under this ICD-10-PCS code. Institutional case review confirmed the greater specificity of CPT codes.

CONCLUSIONS: The ICD-10-PCS code associated with CPT-billed PVI procedures actually referred to ablation of the atrioventricular junction. Yet this ICD-10-PCS code also matched with a wide range of other procedures distinct from PVI. We conclude that ICD-10-PCS codes alone are not sensitive nor specific for identifying PVI in claims and cannot be reliably used in isolation for health services research on this important procedure.

The electrocardiogram (ECG) can capture obesity-related cardiac changes. Artificial intelligence-enhanced ECG (AI-ECG) can identify subclinical disease. We trained an AI-ECG model to predict body mass index (BMI) from the ECG alone. Developed from 512,950 12-lead ECGs from the Beth Israel Deaconess Medical Center (BIDMC), a secondary care cohort, and validated on UK Biobank (UKB) (n = 42,386), the model achieved a Pearson correlation coefficient (r) of 0.65 and 0.62, and an R2 of 0.43 and 0.39 in the BIDMC cohort and UK Biobank, respectively for AI-ECG BMI vs. measured BMI. We found delta-BMI, the difference between measured BMI and AI-ECG-predicted BMI (AI-ECG-BMI), to be a biomarker of cardiometabolic health. The top tertile of delta-BMI showed increased risk of future cardiometabolic disease (BIDMC: HR 1.15, p < 0.001; UKB: HR 1.58, p < 0.001) and diabetes mellitus (BIDMC: HR 1.25, p < 0.001; UKB: HR 2.28, p < 0.001) after adjusting for covariates including measured BMI. Significant enhancements in model fit, reclassification and improvements in discriminatory power were observed with the inclusion of delta-BMI in both cohorts. Phenotypic profiling highlighted associations between delta-BMI and cardiometabolic diseases, anthropometric measures of truncal obesity, and pericardial fat mass. Metabolic and proteomic profiling associates delta-BMI positively with valine, lipids in small HDL, syntaxin-3, and carnosine dipeptidase 1, and inversely with glutamine, glycine, colipase, and adiponectin. A genome-wide association study revealed associations with regulators of cardiovascular/metabolic traits, including SCN10A, SCN5A, EXOG and RXRG. In summary, our AI-ECG-BMI model accurately predicts BMI and introduces delta-BMI as a non-invasive biomarker for cardiometabolic risk stratification.

BACKGROUND: Myocardial electrical heterogeneity is critical for normal cardiac electromechanical function, but abnormal or excessive electrical heterogeneity is proarrhythmic. The spatial ventricular gradient (SVG), a vectorcardiographic measure of electrical heterogeneity, has been associated with arrhythmic events during long-term follow-up, but its relationship with short-term inducibility of ventricular arrhythmias (VAs) is unclear.

OBJECTIVE: This study was designed to determine associations between SVG and inducible VAs during electrophysiology study.

METHODS: A retrospective study was conducted of adults without prior sustained VA, cardiac arrest, or implantable cardioverter-defibrillator who underwent ventricular stimulation for evaluation of syncope and nonsustained ventricular tachycardia or for risk stratification before primary prevention implantable cardioverter-defibrillator implantation. The 12-lead electrocardiograms were converted into vectorcardiograms, and SVG magnitude (SVGmag) and direction (azimuth and elevation) were calculated. Odds of inducible VA were regressed by logistic models.

RESULTS: Of 143 patients (median age, 69 years; 80% male; median left ventricular ejection fraction [LVEF], 47%; 52% myocardial infarction), 34 (23.8%) had inducible VAs. Inducible patients had lower median LVEF (38% vs 50%; P < .0001), smaller SVGmag (29.5 vs 39.4 mV·ms; P = .0099), and smaller cosine SVG azimuth (cosSVGaz; 0.64 vs 0.89; P = .0007). When LVEF, SVGmag, and cosSVGaz were dichotomized at their medians, there was a 39-fold increase in adjusted odds (P = .002) between patients with all low LVEF, SVGmag, and cosSVGaz (65% inducible) compared with patients with all high LVEF, SVGmag, and cosSVGaz (4% [n = 1] inducible). After multivariable adjustment, SVGmag, cosSVGaz, and sex but not LVEF or other characteristics remained associated with inducible VAs.

CONCLUSION: Assessment of electrical heterogeneity by SVG, which reflects abnormal electrophysiologic substrate, adds to LVEF and identifies patients at high and low risk of inducible VA at electrophysiology study.