Dataset Information

Clinical predictors of COVID-19 mortality.

ABSTRACT: BACKGROUND:The coronavirus disease 2019 (COVID-19) pandemic has affected over millions of individuals and caused hundreds of thousands of deaths worldwide. It can be difficult to accurately predict mortality among COVID-19 patients presenting with a spectrum of complications, hindering the prognostication and management of the disease. METHODS:We applied machine learning techniques to clinical data from a large cohort of 5,051 COVID-19 patients treated at the Mount Sinai Health System in New York City, the global COVID-19 epicenter, to predict mortality. Predictors were designed to classify patients into Deceased or Alive mortality classes and were evaluated in terms of the area under the receiver operating characteristic (ROC) curve (AUC score). FINDINGS:Using a development cohort (n=3,841) and a systematic machine learning framework, we identified a COVID-19 mortality predictor that demonstrated high accuracy (AUC=0.91) when applied to test sets of retrospective (n= 961) and prospective (n=249) patients. This mortality predictor was based on five clinical features: age, minimum O2 saturation during encounter, type of patient encounter (inpatient vs. various types of outpatient and telehealth encounters), hydroxychloroquine use, and maximum body temperature. INTERPRETATION:An accurate and parsimonious COVID-19 mortality predictor based on five features may have utility in clinical settings to guide the management and prognostication of patients affected by this disease.

SUBMITTER: Yadaw AS

PROVIDER: S-EPMC7273288 | biostudies-literature | 2020 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Clinical predictors of COVID-19 mortality.

Yadaw Arjun S AS Li Yan-Chak YC Bose Sonali S Iyengar Ravi R Bunyavanich Supinda S Pandey Gaurav G

medRxiv : the preprint server for health sciences 20200522

<h4>Background</h4>The coronavirus disease 2019 (COVID-19) pandemic has affected over millions of individuals and caused hundreds of thousands of deaths worldwide. It can be difficult to accurately predict mortality among COVID-19 patients presenting with a spectrum of complications, hindering the prognostication and management of the disease.<h4>Methods</h4>We applied machine learning techniques to clinical data from a large cohort of 5,051 COVID-19 patients treated at the Mount Sinai Health Sy ...[more]

PMID: 32511520

Similar Datasets

Project description: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.

Project description:Background and aimsOlder people have higher rates of comorbidities and may experience more severe inflammatory responses; therefore, are at higher risk of death. Herein, we aimed to systematically review the mortality in coronavirus disease 2019 (COVID-19) patients and its predictors in this age group.MethodsWe searched PubMed, Web of Science, and Science Direct using relevant keywords. Retrieved records underwent a two-step screening process consisting of title/abstract and full-text screenings to identify the eligible studies.ResultsSummarizing findings of 35 studies demonstrated that older patients have higher mortality rates compared to the younger population. A review of articles revealed that increasing age, body mass index, a male gender, dementia, impairment or dependency in daily activities, presence of consolidations on chest X-ray, hypoxemic respiratory failure, and lower oxygen saturation at admission were risk factors for death. High d-dimer levels, 25-hydroxy vitamin D serum deficiencies, high C-reactive protein (≥5 mg/L) levels plus any other abnormalities of lymphocyte, higher blood urea nitrogen or lactate dehydrogenase, and higher platelet count were predictors of poor prognosis and mortality in the elderly. Studies have also shown that previous treatment with renin-angiotensin-aldosterone system inhibitors, pharmacological treatments of respiratory disorders, antibiotics, corticosteroids, vitamin K antagonist, antihistamines, azithromycin, Itolizumab (an anti-CD6 monoclonal antibody) in combination with other antivirals reduces COVID-19 worsening and mortality. Vaccination against seasonal influenza might also reduce COVID-19 mortality.ConclusionOverall, a critical consideration is necessary for the care and management of COVID-19 in the aged population considering the drastic contrasts in manifestation and prognosis compared to other age groups. Mortality from COVID-19 is independently associated with the patient's age. Elderly patients with COVID-19 are more vulnerable to poor outcomes. Thus, strict preventive measures, timely diagnosis, and aggressive therapeutic/nontherapeutic care are of great importance to reduce acute respiratory distress syndrome and severe complications in older people.

Project description:Coronavirus disease-2019 (COVID-19) was declared as a pandemic by WHO in March 2020. SARS-CoV-2 causes a wide range of illness from asymptomatic to life-threatening. There is an essential need to identify biomarkers to predict disease severity and mortality during the earlier stages of the disease, aiding treatment and allocation of resources to improve survival. The aim of this study was to identify at the time of SARS-COV-2 infection patients at high risk of developing severe disease associated with low survival using blood parameters, including inflammation and coagulation mediators, vital signs, and pre-existing comorbidities. This cohort included 89 multi-ethnic COVID-19 patients recruited between July 14th and October 20th 2020 in Doha, Qatar. According to clinical severity, patients were grouped into severe (n=33), mild (n=33) and asymptomatic (n=23). Common routine tests such as complete blood count (CBC), glucose, electrolytes, liver and kidney function parameters and markers of inflammation, thrombosis and endothelial dysfunction including complement component split product C5a, Interleukin-6, ferritin and C-reactive protein were measured at the time COVID-19 infection was confirmed. Correlation tests suggest that C5a is a predictive marker of disease severity and mortality, in addition to 40 biological and physiological parameters that were found statistically significant between survivors and non-survivors. Survival analysis showed that high C5a levels, hypoalbuminemia, lymphopenia, elevated procalcitonin, neutrophilic leukocytosis, acute anemia along with increased acute kidney and hepatocellular injury markers were associated with a higher risk of death in COVID-19 patients. Altogether, we created a prognostic classification model, the CAL model (C5a, Albumin, and Lymphocyte count) to predict severity with significant accuracy. Stratification of patients using the CAL model could help in the identification of patients likely to develop severe symptoms in advance so that treatments can be targeted accordingly.

Dataset Information

Clinical predictors of COVID-19 mortality.

Publications

Clinical predictors of COVID-19 mortality.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure