Characteristics, Outcomes, and Trends of Patients With COVID-19–Related Critical Illness at a Learning Health System in the United States

Anesi, George L; Jablonski, Juliane; Harhay, Michael O.; Atkins, Joshua H.; Bajaj, Jasmeet; Baston, Cameron; Brennan, Patrick J.; Candeloro, Christina; Catalano, Lauren M; Cereda, Maurizio; Chandler, John; Christie, Jason D.; Collins, Tara; Courtright, Katherine R.; Fuchs, Barry D.; Gordon, Emily K.; Greenwood, John C.; Gudowski, Steven W; Hanish, Asaf; Hanson, C. William; Heuer, Monica; Kinniry, Paul; Kornfield, Zev Noah; Kruse, Gregory; Lane‐Fall, Meghan; Martin, Niels D.; Mikkelsen, Mark E.; Negoianu, Dan; Pascual, José L.; Patel, Monica; Pugliese, Steven C.; Qasim, Zaffer; Reilly, John P.; Salmon, J; Schweickert, William D.; Scott, Michael J.; Shashaty, Michael G. S.; Sicoutris, Corinna; Wang, John K; Wang, Wei; Wani, Arshad A.; Anderson, Brian J.; Gutsche, Jacob T.

doi:10.7326/m20-5327

Cited by 111 publications

(121 citation statements)

References 31 publications

Supporting

Mentioning

108

Contrasting

Unclassified

Order By: Relevance

“…Though the exact reason for this change with the temporal validation cohort is uncertain, there are a number of reasons that can be speculated. Mortality for COVID-19 has decreased overtime 30 which may have led to differences in predictive variables. The reasons for this decrease in mortality are not well understood.…”

Section: Discussionmentioning

confidence: 99%

Comparing machine learning algorithms for predicting ICU admission and mortality in COVID-19

et al. 2021

View full text Add to dashboard Cite

As predicting the trajectory of COVID-19 is challenging, machine learning models could assist physicians in identifying high-risk individuals. This study compares the performance of 18 machine learning algorithms for predicting ICU admission and mortality among COVID-19 patients. Using COVID-19 patient data from the Mass General Brigham (MGB) Healthcare database, we developed and internally validated models using patients presenting to the Emergency Department (ED) between March-April 2020 (n = 3597) and further validated them using temporally distinct individuals who presented to the ED between May-August 2020 (n = 1711). We show that ensemble-based models perform better than other model types at predicting both 5-day ICU admission and 28-day mortality from COVID-19. CRP, LDH, and O2 saturation were important for ICU admission models whereas eGFR <60 ml/min/1.73 m2, and neutrophil and lymphocyte percentages were the most important variables for predicting mortality. Implementing such models could help in clinical decision-making for future infectious disease outbreaks including COVID-19.

show abstract

Section: Discussionmentioning

confidence: 99%

Comparing machine learning algorithms for predicting ICU admission and mortality in COVID-19

et al. 2021

View full text Add to dashboard Cite

show abstract

“…While much higher infection numbers, and in some countries more deaths were seen, a substantial decrease in the case fatality rate (CFR) was observed (https://www.ft.com/content/b3801b63-fbdb-433b-9a46-217405b1109f). It is interesting to note that research reported the CFR decreased during the first wave, indicating that Covid-19 severity might lessen with time ( Schmidt et al, 2021 ; Anesi et al, 2021 ). Prior studies, however, only examined the declining CFR in hospitalized patients during the first wave.…”

Section: Introductionmentioning

confidence: 99%

Relative risks of COVID-19 fatality between the first and second waves of the pandemic in Ontario, Canada

Hsu

Chang²,

Gross³

et al. 2021

International Journal of Infectious Diseases

View full text Add to dashboard Cite

Objectives To examine whether the case fatality rate (CFR) of coronavirus disease 2019 (Covid-19) decreased overtime, and whether the Covid-19 testing rate is a driving factor for the changes if the CFR decreased. Methods Analyzing Covid-19 cases, deaths, and tests in Ontario, Canada, we compared the CFR between the first wave and the second wave across 26 Public Health Units in Ontario. We also explored whether a high testing rate was associated with a large CFR decrease. Results The first wave CFR ranged from 0.004 to 0.146; whereas the second wave CFR ranged from 0.003 to 0.034. The pooled RR estimate of the second wave Covid-19 case fatality, compared to first wave, was 0.24 (95% CI: 0.19-0.32). Additionally, Covid-19 testing percentages were not associated with the estimated RR (p-value = 0.246). Conclusions The Covid-19 CFR decreased profoundly in Ontario during the second wave, and Covid-19 testing was not a driving factor for this decrease.

show abstract

“…Mortality rates for those who require mechanical ventilation have ranged from as high as 90% early in the pandemic to 30-50% in more recent cohorts [2,3,5,[7][8][9][10][11][12][13].…”

mentioning

confidence: 99%

Incidence, Characteristics, and Outcomes of Ventilator-associated Events during the COVID-19 Pandemic

Weinberger

Rhee

2022

Annals ATS

View full text Add to dashboard Cite

show abstract

Characteristics, Outcomes, and Trends of Patients With COVID-19–Related Critical Illness at a Learning Health System in the United States

Abstract: In a large health system in the United States, investigators examined whether mortality, receipt of mechanical ventilation, and patient acuity changed over time among adult patients with COVID-19–related critical illness admitted to intensive care units.

Cited by 111 publications

References 31 publications

Comparing machine learning algorithms for predicting ICU admission and mortality in COVID-19

Comparing machine learning algorithms for predicting ICU admission and mortality in COVID-19

Relative risks of COVID-19 fatality between the first and second waves of the pandemic in Ontario, Canada

Incidence, Characteristics, and Outcomes of Ventilator-associated Events during the COVID-19 Pandemic

Contact Info

Product

Resources

About