Machine-reported ECG right axis deviation or right ventricular hypertrophy was associated with echocardiographic pulmonary hypertension phenotypes (OR 2.04; 95% CI 1.84-2.26).
Observational (n=42,078)
Does machine-reported ECG RAD or RVH predict echocardiographic pulmonary hypertension phenotypes and right-heart abnormalities in hospitalized patients?
Machine-reported ECG RAD/RVH is highly specific but insensitive for echocardiographic pulmonary hypertension, meaning it can support but not exclude the diagnosis.
Odds Ratio: 2.04 (95% CI 1.84–2.26)
Absolute Event Rate: 30% vs 18.8%
PURPOSE: Machine-reported electrocardiographic findings suggesting right-heart strain are routinely generated during electrocardiogram (ECG) acquisition, but their relationship to echocardiographic pulmonary hypertension phenotypes and right-heart abnormalities remains incompletely defined. This study evaluated whether machine-reported right axis deviation (RAD) or right ventricular hypertrophy (RVH) is associated with echocardiographic pulmonary hypertension phenotypes and right-heart abnormalities in hospitalized patients. METHODS: This retrospective observational study used linked MIMIC-IV-ECG and MIMIC-IV-ECHO data. Echocardiograms were linked to the closest ECG obtained from 7 days before echocardiography through the time of echocardiography. The primary exposure was machine-reported RAD or RVH. The primary outcome was Echo-PH specific, a composite echo-derived phenotype including tricuspid regurgitation velocity greater than 3.4 m/s, moderate or severe pulmonary hypertension text, or right ventricular pressure overload. Logistic regression adjusted for demographics, comorbidities, and ICU status, with patient-level cluster-robust standard errors. RESULTS: The cohort included 68 905 ECG-echocardiography pairs from 42 078 patients; 2815 pairs were RAD/RVH-positive. For Echo-PH specific, RAD/RVH had sensitivity 7.5%, specificity 96.7%, positive predictive value 35.5%, and negative predictive value 81.4%. RAD/RVH remained associated with Echo-PH specific after full adjustment using cluster-robust standard errors (odds ratio, 2.04; 95% confidence interval, 1.84-2.26). The adjusted probability of Echo-PH specific was 18.8% without RAD/RVH and 30.0% with RAD/RVH. CONCLUSION: Machine-reported ECG RAD/RVH was highly specific but insensitive for echocardiographic pulmonary hypertension phenotypes and right-heart abnormalities. These routine ECG findings may serve as supportive clues to echocardiographic right-heart disease but should not be used to exclude it.
Yoshihiro Fuchigami (Wed,) conducted a observational in Pulmonary hypertension phenotypes and right-heart abnormalities (n=42,078). Machine-reported right axis deviation (RAD) or right ventricular hypertrophy (RVH) vs. Without RAD/RVH was evaluated on Echo-PH specific (composite echo-derived phenotype including tricuspid regurgitation velocity >3.4 m/s, moderate or severe pulmonary hypertension text, or right ventricular pressure overload) (OR 2.04, 95% CI 1.84-2.26). Machine-reported ECG right axis deviation or right ventricular hypertrophy was associated with echocardiographic pulmonary hypertension phenotypes (OR 2.04; 95% CI 1.84-2.26).