Dataset Information

Predictors of intubation and mortality in COVID-19 patients: a retrospective study

ABSTRACT:

Background

Estimating the risk of intubation and mortality among COVID-19 patients can help clinicians triage these patients and allocate resources more efficiently. Thus, here we sought to identify the risk factors associated with intubation and intra-hospital mortality in a cohort of COVID-19 patients hospitalized due to hypoxemic acute respiratory failure (ARF).

Results

We included retrospectively a total of 187 patients admitted to the subintensive and intensive care units of the University Hospital “Maggiore della Carità” of Novara between March 1st and April 30th, 2020. Based on these patients’ demographic characteristics, early clinical and laboratory variables, and quantitative chest computerized tomography (CT) findings, we developed two random forest (RF) models able to predict intubation and intra-hospital mortality. Variables independently associated with intubation were C-reactive protein (p < 0.001), lactate dehydrogenase level (p = 0.018) and white blood cell count (p = 0.026), while variables independently associated with mortality were age (p < 0.001), other cardiovascular diseases (p = 0.029), C-reactive protein (p = 0.002), lactate dehydrogenase level (p = 0.018), and invasive mechanical ventilation (p = 0.001). On quantitative chest CT analysis, ground glass opacity, consolidation, and fibrosis resulted significantly associated with patient intubation and mortality. The major predictors for both models were the ratio between partial pressure of arterial oxygen and fraction of inspired oxygen, age, lactate dehydrogenase, C-reactive protein, glycemia, CT quantitative parameters, lymphocyte count, and symptom onset.

Conclusions

Altogether, our findings confirm previously reported demographic, clinical, hemato-chemical, and radiologic predictors of adverse outcome among COVID-19-associated hypoxemic ARF patients. The two newly developed RF models herein described show an overall good level of accuracy in predicting intra-hospital mortality and intubation in our study population. Thus, their future development and implementation may help not only identify patients at higher risk of deterioration more effectively but also rebalance the disproportion between resources and demand.

Supplementary Information

The online version contains supplementary material available at 10.1186/s44158-021-00016-5.

SUBMITTER: Cena T

PROVIDER: S-EPMC8626752 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundFirst reported case of Severe acute respiratory syndrome-related coronavirus 2 (SARS-CoV-2) in Kazakhstan was identified in March 2020. Many specialized tertiary hospitals in Kazakhstan including National Research Cardiac Surgery Center (NRCSC) were re-organized to accept coronavirus disease 2019 (COVID-19) infected patients during summer months of 2020. Although many studies from worldwide reported their experience in treating patients with COVID-19, there are limited data available from the Central Asia countries. The aim of this study is to identify predictors of mortality associated with COVID-19 in NRCSC tertiary hospital in Nur-Sultan, Kazakhstan.MethodsThis is a retrospective cohort study of patients admitted to the NRCSC between June 1st-August 31st 2020 with COVID-19. Demographic, clinical and laboratory data were collected from electronic records. In-hospital mortality was assessed as an outcome. Patients were followed-up until in-hospital death or discharge from the hospital. Descriptive statistics and factors associated with mortality were assessed using univariate and multivariate logistic regression models.ResultsTwo hundred thirty-nine admissions were recorded during the follow-up period. Mean age was 57 years and 61% were males. Median duration of stay at the hospital was 8 days and 34 (14%) patients died during the hospitalization. Non-survivors were more likely to be admitted later from the disease onset, with higher fever, lower oxygen saturation and increased respiratory rate compared to survivors. Leukocytosis, lymphopenia, anemia, elevated liver and kidney function tests, hypoproteinemia, elevated inflammatory markers (C-reactive protein (CRP), ferritin, and lactate dehydrogenase (LDH)) and coagulation tests (fibrinogen, D-dimer, international normalized ratio (INR), and activated partial thromboplastin time (aPTT)) at admission were associated with mortality. Age (OR 1.2, CI:1.01-1.43), respiratory rate (OR 1.38, CI: 1.07-1.77), and CRP (OR 1.39, CI: 1.04-1.87) were determined to be independent predictors of mortality.ConclusionThis study describes 14% mortality rate from COVID-19 in the tertiary hospital. Many abnormal clinical and laboratory variables at admission were associated with poor outcome. Age, respiratory rate and CRP were found to be independent predictors of mortality. Our finding would help healthcare providers to predict the risk factors associated with high risk of mortality. Further investigations involving large cohorts should be provided to support our findings.

Project description:BackgroundCOVID-19 remains a major healthcare concern. Vital signs are routinely measured on admission and may provide an early, cost-effective indicator of outcome - more so in developing countries where such data is scarce. We sought to describe the association between six routinely measured admission vital signs and COVID-19 mortality, and secondarily to derive potential applications for resource-limited settings.MethodsRetrospective analysis of consecutive patients admitted to King Edward VIII Hospital, South Africa, with COVID-19 during June-September 2020 was undertaken. The sample was subdivided into survivors and non-survivors and comparisons made in terms of demographics and admission vital signs. Univariate and multivariate analysis of predictor variables identified associations with in-hospital mortality, with the resulting multivariate regression model evaluated for its predictive ability with receiver operating characteristic (ROC) curve analysis.ResultsThe 236 participants enrolled comprised 153(77.54%) survivors and 53(22.46%) non-survivors. Most participants were Black African(87.71%) and female(59.75%) with a mean age of 53.08(16.96) years. The non-survivor group demonstrated a significantly lower median/mean for admission oxygen saturation (%) [87(78-95) vs. 96(90-98)] and diastolic BP (mmHg) [70.79(14.66) vs. 76.3(12.07)], and higher median for admission respiratory rate (breaths/minute) [24(20-28) vs. 20(20-23)] and glucose (mmol/l) [10.2(6.95-16.25) vs. 7.4(5.5-9.8)]. Age, oxygen saturation, respiratory rate, glucose and diastolic BP were found to be significantly associated with mortality on univariate analysis. A log rank test revealed significantly lower survival rates in patients with an admission oxygen saturation < 90% compared with ≥90% (p = 0.001). Multivariate logistic regression revealed a significant relationship between age and oxygen saturation with in-hospital mortality (OR 1.047; 95% CI 1.016-1.080; p = 0.003 and OR 0.922; 95% CI 0.880-0.965; p = 0.001 respectively). A ROC curve analysis generated an area under the curve (AUC) of 0.778 (p < 0.001) when evaluating the predictive ability of oxygen saturation, respiratory rate, glucose and diastolic BP for in-hospital death. This improved to an AUC of 0.832 (p < 0.001) with the inclusion of age.ConclusionA multivariate regression model comprising admission oxygen saturation, respiratory rate, glucose and diastolic BP (with/without age) demonstrated promising predictive capacity, and may provide a cost-effective means for early prognostication of patients admitted with COVID-19 in resource-limited settings.

Project description:BackgroundThe novel coronavirus SARS-CoV-2 and its associated disease, COVID-19, have caused worldwide disruption, leading countries to take drastic measures to address the progression of the disease. As SARS-CoV-2 continues to spread, hospitals are struggling to allocate resources to patients who are most at risk. In this context, it has become important to develop models that can accurately predict the severity of infection of hospitalized patients to help guide triage, planning, and resource allocation.ObjectiveThe aim of this study was to develop accurate models to predict the mortality of hospitalized patients with COVID-19 using basic demographics and easily obtainable laboratory data.MethodsWe performed a retrospective study of 375 hospitalized patients with COVID-19 in Wuhan, China. The patients were randomly split into derivation and validation cohorts. Regularized logistic regression and support vector machine classifiers were trained on the derivation cohort, and accuracy metrics (F1 scores) were computed on the validation cohort. Two types of models were developed: the first type used laboratory findings from the entire length of the patient's hospital stay, and the second type used laboratory findings that were obtained no later than 12 hours after admission. The models were further validated on a multicenter external cohort of 542 patients.ResultsOf the 375 patients with COVID-19, 174 (46.4%) died of the infection. The study cohort was composed of 224/375 men (59.7%) and 151/375 women (40.3%), with a mean age of 58.83 years (SD 16.46). The models developed using data from throughout the patients' length of stay demonstrated accuracies as high as 97%, whereas the models with admission laboratory variables possessed accuracies of up to 93%. The latter models predicted patient outcomes an average of 11.5 days in advance. Key variables such as lactate dehydrogenase, high-sensitivity C-reactive protein, and percentage of lymphocytes in the blood were indicated by the models. In line with previous studies, age was also found to be an important variable in predicting mortality. In particular, the mean age of patients who survived COVID-19 infection (50.23 years, SD 15.02) was significantly lower than the mean age of patients who died of the infection (68.75 years, SD 11.83; P<.001).ConclusionsMachine learning models can be successfully employed to accurately predict outcomes of patients with COVID-19. Our models achieved high accuracies and could predict outcomes more than one week in advance; this promising result suggests that these models can be highly useful for resource allocation in hospitals.