RESUMO
BACKGROUND: Patients with hypertrophic cardiomyopathy (HCM) are at risk of sudden death, and individuals with ≥1 major risk markers are considered for primary prevention implantable cardioverter-defibrillators. Guidelines recommend cardiac magnetic resonance (CMR) imaging to identify high-risk imaging features. However, CMR imaging is resource intensive and is not widely accessible worldwide. OBJECTIVE: The purpose of this study was to develop electrocardiogram (ECG) deep-learning (DL) models for the identification of patients with HCM and high-risk imaging features. METHODS: Patients with HCM evaluated at Tufts Medical Center (N = 1930; Boston, MA) were used to develop ECG-DL models for the prediction of high-risk imaging features: systolic dysfunction, massive hypertrophy (≥30 mm), apical aneurysm, and extensive late gadolinium enhancement. ECG-DL models were externally validated in a cohort of patients with HCM from the Amrita Hospital HCM Center (N = 233; Kochi, India). RESULTS: ECG-DL models reliably identified high-risk features (systolic dysfunction, massive hypertrophy, apical aneurysm, and extensive late gadolinium enhancement) during holdout testing (c-statistic 0.72, 0.83, 0.93, and 0.76) and external validation (c-statistic 0.71, 0.76, 0.91, and 0.68). A hypothetical screening strategy using echocardiography combined with ECG-DL-guided selective CMR use demonstrated a sensitivity of 97% for identifying patients with high-risk features while reducing the number of recommended CMRs by 61%. The negative predictive value with this screening strategy for the absence of high-risk features in patients without ECG-DL recommendation for CMR was 99.5%. CONCLUSION: In HCM, novel ECG-DL models reliably identified patients with high-risk imaging features while offering the potential to reduce CMR testing requirements in underresourced areas.
RESUMO
BACKGROUND: Cardiovascular disease is the leading cause of noncancer mortality for breast cancer survivors. Data are limited regarding patient-level atherosclerotic cardiovascular disease (ASCVD) risk estimation and preventive medication use. This study aimed to characterize ASCVD risk and longitudinal preventive medication use for a cohort of patients with nonmetastatic breast cancer. PATIENTS AND METHODS: This retrospective cohort study included 326 patients at an academic medical center in Boston, Massachusetts diagnosed with nonmetastatic breast cancer or ductal carcinoma in situ from January 2009 through December 2015. Patient demographics, clinical characteristics, laboratory studies, medication exposure, and incident cardiovascular outcomes were collected. Estimated 10-year ASCVD risk was calculated for all patients from nonlaboratory clinical parameters. RESULTS: Median follow up time was 6.5 years (IQR 5.0, 8.1). At cancer diagnosis, 23 patients (7.1%) had established ASCVD. Among those without ASCVD, 10-year estimated ASCVD risk was ≥20% for 77 patients (25.4%) and 7.5% to <20% for 114 patients (37.6%). Two-hundred and sixteen patients (66.3%) had an indication for lipid-lowering therapy at cancer diagnosis, 123 of whom (57.0%) received a statin during the study. Among 100 patients with ASCVD or estimated 10-year ASCVD risk ≥20%, 92 (92.0%) received an antihypertensive medication during the study. Clinic blood pressure >140/90 mmHg was observed in 33.0% to 55.6% of these patients at each follow up assessment. CONCLUSION: A majority of patients in this breast cancer cohort had an elevated risk of ASCVD at the time of cancer diagnosis. Modifiable ASCVD risk factors were frequently untreated or uncontrolled in the years following cancer treatment.