Medina-Inojosa, Jose R.

Background Bicuspid aortic valve (BAV) is the most common congenital heart defect, associated with a lifetime morbidity burden exceeding 80% and an estimated 7% probability of transmission to first-degree relatives. Hence, echocardiographic screening of relatives is recommended. The aim of our study is to develop an artificial intelligence-enabled electrocardiogram (AI-ECG) model for the detection of BAV. Methods Between January 1, 1990, and June 30, 2023, the Mayo Clinic healthcare system database was searched for patients aged ≥18 years with echocardiograms performed for family history of BAV, abnormal auscultation, a BAV-related diagnosis, or to rule out the condition, and with an electrocardiogram (ECG) obtained within 6 months. Cases were patients with a confirmed BAV diagnosis, and controls were those with normal aortic valves. ECGs were randomly assigned into training (80%), internal validation (10%), and test (10%) groups. The AI-ECG model was built using Keras under TensorFlow. Results A total of 13,065 valid ECG–echocardiogram pairs were included (mean [SD] age, 58 [17] years; 44% women), with a median time of 1 day (interquartile range, 0–3 days) between studies. With a 45% BAV prevalence in the test group ( n = 1301), the area under the curve was 0.704, positive predictive value (PPV) 60.1%, and negative predictive value (NPV) 69.4%. At a prevalence of 7%, the NPV increased to 96.1%, but the PPV decreased to 12.2%. Conclusions In this retrospective cohort and using the current AI-ECG model, BAV detection showed modest diagnostic performance and limited standalone clinical utility, suggesting that ECG-only screening for BAV may require additional modalities or more refined phenotyping.

Obesity and hypertension independently promote pathological left ventricular remodelling (LVR) and left ventricular hypertrophy (LVH), but to what extent they do so when they do not coexist is unclear. We used data from the Cardiovision Brno 2030 study to assess—for the first time in a region where no investigations have been previously carried out—the independent association of obesity and hypertension with LV geometry, and to evaluate the effects of hypertension in normal weight patients and the effects of obesity in normotensive patients. Overall, 433 individuals, aged 25–65 years, with no history of cardiovascular disease and/or antihypertensive treatment, were stratified into four groups according to BMI and hypertension: normal weight non-hypertensive (NWNH), normal weight hypertensive (NWH), overweight/obese non-hypertensive (ONH) and overweight/obese hypertensive (OH). LVR was classified as normal, concentric LVR (cLVR), concentric LVH (cLVH) or eccentric LVH (eLVH). Linear regression analysis demonstrated that body mass index (BMI) and systolic blood pressure (SBP) are the main predictors of LV mass and that they interact: SBP had a stronger effect in overweight/obese (β = 0.195; p = 0.033) compared to normal weight patients (β = 0.134; p = 0.048). Hypertension increased the odds of cLVR (OR = 1.78; 95%CI = 1.04–3.06; p = 0.037) and cLVH (OR = 8.20; 95% CI = 2.35–28.66; p = 0.001), independent of age, sex and BMI. Stratified analyses showed that NWH had a greater odd of cLVH (OR = 7.96; 95%CI = 1.70–37.08; p = 0.008) and cLVR (OR = 1.62; 95%CI = 1.02–3.34; p = 0.047) than NWNH. In the absence of hypertension, obesity was not associated with LVM and abnormal LV geometry, suggesting that it is not per se a determinant of LVR. Thus, antihypertensive therapy still remains the first-line approach against LVH in hypertensive patients, though weight loss interventions might be helpful in those who are obese.