Back

12-lead Electrocardiogram in Hospitalized COVID 19 Patients

Shokr, M.; Chehab, O.; Ajam, M.; Singh, M.; Ashraf, S.; Dawdy, J.; Pahuja, M.; Reddy, V.; Subahi, A.; Alraies, M. C.; Afonso, L.; Lieberman, R.

2021-02-01 cardiovascular medicine
10.1101/2021.01.29.21250407 medRxiv
Show abstract

COVID-19 pandemic resulted in considerable morbidity and mortality. We analyzed 345 Electrocardiograms of 100 COVID-19 patients admitted to our tertiary care center in Detroit, during the initial month of Covid-19. Findings were correlated with mortality, cardiac injury and inflammatory markers. Our cohort included 61% males and 77% African Americans. The median age and BMI were 66 years (57-74) and 31 kg/m2 (26.1-39), respectively. We observed atrial arrhythmias in 29% of the patients (17% new onset), First degree heart block in 12%, ST-T segment changes in 17%, S1Q3T3 pattern in 19%, premature ventricular complexes in 23%, premature atrial complexes in 13%, Q waves in 27%, T wave inversion in 42% of the cases. While presence of premature atrial complexes or left atrial abnormality correlated with mortality (P = 0.02 & 0.03, respectively), other findings did not show significant correlation in this small cohort of patients.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.