Using the Cerner COVID-19 de-identified dataset, we identified patients with COVID-19 infection and MG (COVID-19MG) using ICD-10-CM. We compared outcomes of COVID-19MG to: COVID-19 patients without MG (COVID-19WMG), non-COVID-19 patients with MG (non-COVID-19MG), and non-COVID-19 patients without MG (non-COVID-19WMG).

Among a total of 117,496 patients, 25,261 were diagnosed with COVID-19. The incidence of MG was higher in COVID-19 patients compared to non-COVID-19 patients (0.087% vs 0.07%). The mean hospital length of stay (LoS) in days was significantly higher in COVID-19MG compared to COVID-19NMG and non-COVID-19MG as well as non-COVID-19WMG, respectively, 7.0; 5.4; 3.0; 2.57 (p<0.05). Discharge rate to skilled nursing facilities (SNF) and to hospices were significantly higher in COVID-19MG compared to COVID-19WMG and non-COVID-19MG as well as non-COVID-19WMG, respectively, 8.3%, 8.3%; 6.9%, 3.2%; 2%, 0.5%; 1.85%, 0.35% (p<0.05). Due to the small number of COVID-19MG patients, there was no statistically significant difference (95% confidence level) in the mortality rates of COVID-19MG, COVID-19NMG, non-COVID-19MG, and non-COVID-19WMG. These rates were, respectively, 22.7%, 8.5%, 8.7%, and 3.5%.

Our study demonstrated that MG in COVID-19 is associated with factors of poor prognosis: longer LoS and a higher rate of discharge to SNF and hospices. Work is in progress to assess factors of poor prognosis in COVID-19 patients with MG. Risk stratification machine learning (ML)-based models are also under development to predict the likelihood of ICU admission, mechanical ventilation, prolonged LoS, and death of COVID-19 patients with MG.