Identifying and quantifying robust risk factors for mortality in critically ill patients with COVID-19 using quantile regression

Linli, Zeqiang; Chen, Yinyin; Tian, Guo‐Liang; Guo, Shuixia; Yu, Fei

doi:10.1016/j.ajem.2020.08.090

Cited by 7 publications

(4 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From these parameters, pH, P / F ratio, and driving pressure demonstrate increasing importance over the course of IMV. Studies investigating the role of these predictors in critically ill COVID-19 patients are limited, but did identify pH as an important predictor [ 23 ]. No studies are available looking at the role of these predictors throughout the course of ICU admission.…”

Section: Discussionmentioning

confidence: 99%

Risk factors for adverse outcomes during mechanical ventilation of 1152 COVID-19 patients: a multicenter machine learning study with highly granular data from the Dutch Data Warehouse

Fleuren

Tonutti²,

Bruin³

et al. 2021

ICMx

View full text Add to dashboard Cite

Background The identification of risk factors for adverse outcomes and prolonged intensive care unit (ICU) stay in COVID-19 patients is essential for prognostication, determining treatment intensity, and resource allocation. Previous studies have determined risk factors on admission only, and included a limited number of predictors. Therefore, using data from the highly granular and multicenter Dutch Data Warehouse, we developed machine learning models to identify risk factors for ICU mortality, ventilator-free days and ICU-free days during the course of invasive mechanical ventilation (IMV) in COVID-19 patients. Methods The DDW is a growing electronic health record database of critically ill COVID-19 patients in the Netherlands. All adult ICU patients on IMV were eligible for inclusion. Transfers, patients admitted for less than 24 h, and patients still admitted at time of data extraction were excluded. Predictors were selected based on the literature, and included medication dosage and fluid balance. Multiple algorithms were trained and validated on up to three sets of observations per patient on day 1, 7, and 14 using fivefold nested cross-validation, keeping observations from an individual patient in the same split. Results A total of 1152 patients were included in the model. XGBoost models performed best for all outcomes and were used to calculate predictor importance. Using Shapley additive explanations (SHAP), age was the most important demographic risk factor for the outcomes upon start of IMV and throughout its course. The relative probability of death across age values is visualized in Partial Dependence Plots (PDPs), with an increase starting at 54 years. Besides age, acidaemia, low P/F-ratios and high driving pressures demonstrated a higher probability of death. The PDP for driving pressure showed a relative probability increase starting at 12 cmH2O. Conclusion Age is the most important demographic risk factor of ICU mortality, ICU-free days and ventilator-free days throughout the course of invasive mechanical ventilation in critically ill COVID-19 patients. pH, P/F ratio, and driving pressure should be monitored closely over the course of mechanical ventilation as risk factors predictive of these outcomes.

show abstract

Section: Discussionmentioning

confidence: 99%

Risk factors for adverse outcomes during mechanical ventilation of 1152 COVID-19 patients: a multicenter machine learning study with highly granular data from the Dutch Data Warehouse

Fleuren

Tonutti²,

Bruin³

et al. 2021

ICMx

View full text Add to dashboard Cite

show abstract

“…Due to its relationship with the inflammatory response and severity of COVID-19 manifestations, hypocalcemia has been related to a higher mortality. Several study cohorts demonstrated the relation between lower Ca++ levels at hospital admission and higher risk of in-hospital and 28-day mortality [91,120,121]. Limiting severe acute hypocalcemia could protect from CV and neurological complications that may be fatal.…”

Section: Calciummentioning

confidence: 99%

The Mutual Relationship among Cardiovascular Diseases and COVID-19: Focus on Micronutrients Imbalance

et al. 2022

View full text Add to dashboard Cite

Micronutrients are ions and vitamins humbly required by the human body. They play a main role in several physiological mechanisms and their imbalance is strongly associated with potentially-fatal complications. Micronutrient imbalance is associated with many cardiovascular diseases, such as arrythmias, heart failure, and ischemic heart disease. It has been also observed in coronavirus disease 2019 (COVID-19), particularly in most severe patients. The relationship between cardiovascular diseases and COVID-19 is mutual: the latter triggers cardiovascular disease onset and worsening while patients with previous cardiovascular disease may develop a more severe form of COVID-19. In addition to the well-known pathophysiological mechanisms binding COVID-19 and cardiovascular diseases together, increasing importance is being given to the impact of micronutrient alterations, often present during COVID-19 and able to affect the balance responsible for a good functioning of the cardiovascular system. In particular, hypokalemia, hypomagnesemia, hyponatremia, and hypocalcemia are strongly associated with worse outcome, while vitamin A and D deficiency are associated with thromboembolic events in COVID-19. Thus, considering how frequent the cardiovascular involvement is in patients with COVID-19, and how it majorly affects their prognosis, this manuscript provides a comprehensive review on the role of micronutrient imbalance in the interconnection between COVID-19 and cardiovascular diseases.

show abstract

“…The study by Liu et al [9], in 107 patients, showed that CorrCa levels are associated with a poor outcome evaluated by a composite variable that included the need for mechanical ventilation, ICU admission or death, but they do not provide data on the individual components of the composite variable. Other studies have linked low Ca levels with pro-inflammatory markers, multiple organ injuries and the severity of the disease [10,[27][28][29][30][31].…”

Section: Univariate Analysismentioning

confidence: 99%

Serum Calcium, Magnesium, and Phosphorus Levels in Patients with COVID-19: Relationships with Poor Outcome and Mortality

et al. 2022

View full text Add to dashboard Cite

In this retrospective study to assess the impact of serum corrected calcium (CorrCa), magnesium (Mg) and phosphorus (P) levels, all adult patients with laboratory-confirmed COVID-19 hospitalized during 2020 were included. Poor outcome was considered in patients who presented need for mechanical ventilation, intensive care unit (ICU) admission, or in-hospital mortality. We analyzed 2473 patients (956 females) aged (mean±SD) 63.4±15.9 years. During admission, 169 patients (6.8%) required mechanical ventilation, 205 (8.3%) were admitted to the ICU, and 270 (10.9%) died. Composite variable of poor outcome, defined as need for mechanical ventilation, ICU admission or death, was present in 434 (17.5%) patients. In univariate analysis, the need for mechanical ventilation was positively related to Mg levels (OR 8.37, 95% CI 3.62–19.33; p<0.001); ICU admission was related to CorrCa (OR 0.49, 95% CI 0.25–0.99; p=0.049) and Mg levels (OR 5.81, 95% CI 2.74–12.35; p<0.001); and in-hospital mortality was related to CorrCa (OR 1.73, 95% CI 1.14–2.64; p=0.011). The composite variable of poor outcome was only related to Mg (OR 2.68, 95% CI 1.54–4.68; p=0.001). However, in multivariate analysis only CorrCa was significantly related to the need for mechanical ventilation (OR 0.19, 95% CI 0.05–0.72; p=0.014) and ICU admission (OR 0.25; 95% CI 0.09–0.66; p=0.005), but not with in-hospital mortality or the composite variable. In conclusion, CorrCa can be used as a simple and reliable marker of poor outcome in patients with COVID-19, although not to predict the risk of in-hospital mortality.

show abstract

Identifying and quantifying robust risk factors for mortality in critically ill patients with COVID-19 using quantile regression

Cited by 7 publications

References 28 publications

Risk factors for adverse outcomes during mechanical ventilation of 1152 COVID-19 patients: a multicenter machine learning study with highly granular data from the Dutch Data Warehouse

Risk factors for adverse outcomes during mechanical ventilation of 1152 COVID-19 patients: a multicenter machine learning study with highly granular data from the Dutch Data Warehouse

The Mutual Relationship among Cardiovascular Diseases and COVID-19: Focus on Micronutrients Imbalance

Serum Calcium, Magnesium, and Phosphorus Levels in Patients with COVID-19: Relationships with Poor Outcome and Mortality

Contact Info

Product

Resources

About