Early prediction of level-of-care requirements in patients with COVID-19

Hao, Boran; Sotudian, Shahabeddin; Wang, Taiyao; Xu, Tingting; Hu, Yang; Gaitanidis, Apostolos; Breen, Kerry; Velmahos, George C.; Paschalidis, Ioannis Ch.

doi:10.7554/elife.60519

Cited by 55 publications

(63 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different ML models have been proposed to predict risk of developing severe complications and mortality (15)(16)(17)(18)(19)(20)(21)(22)(23)(24)(25)(26)(27). This is important since there are limited resources compared to the increasing number of COVID-19 patients.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Based Clinical Decision Support System for Early COVID-19 Mortality Prediction

Karthikeyan

Garg

Vinod

et al. 2021

Front. Public Health

View full text Add to dashboard Cite

The coronavirus disease 2019 (COVID-19), caused by the virus SARS-CoV-2, is an acute respiratory disease that has been classified as a pandemic by the World Health Organization (WHO). The sudden spike in the number of infections and high mortality rates have put immense pressure on the public healthcare systems. Hence, it is crucial to identify the key factors for mortality prediction to optimize patient treatment strategy. Different routine blood test results are widely available compared to other forms of data like X-rays, CT-scans, and ultrasounds for mortality prediction. This study proposes machine learning (ML) methods based on blood tests data to predict COVID-19 mortality risk. A powerful combination of five features: neutrophils, lymphocytes, lactate dehydrogenase (LDH), high-sensitivity C-reactive protein (hs-CRP), and age helps to predict mortality with 96% accuracy. Various ML models (neural networks, logistic regression, XGBoost, random forests, SVM, and decision trees) have been trained and performance compared to determine the model that achieves consistently high accuracy across the days that span the disease. The best performing method using XGBoost feature importance and neural network classification, predicts with an accuracy of 90% as early as 16 days before the outcome. Robust testing with three cases based on days to outcome confirms the strong predictive performance and practicality of the proposed model. A detailed analysis and identification of trends was performed using these key biomarkers to provide useful insights for intuitive application. This study provide solutions that would help accelerate the decision-making process in healthcare systems for focused medical treatments in an accurate, early, and reliable manner.

show abstract

Section: Introductionmentioning

confidence: 99%

Machine Learning Based Clinical Decision Support System for Early COVID-19 Mortality Prediction

Karthikeyan

Garg

Vinod

et al. 2021

Front. Public Health

View full text Add to dashboard Cite

show abstract

“…COVID-19 disease is classified by different guidelines into mild, moderate and severe categories or severe and non-severe categories. These different disease categories have different clinical presentations, levels of medical care, quarantine place and perception by the community (Epidemiology Working Group for NCIP Epidemic Response, 2020, Hao et al, 2020; Verity et al, 2020; WHO, 2020). Patients with mild COVID-19 were quarantined at home (according to the protocol of the Egyptian Ministry of Health and Population) [12], thus they had time and possibility to use informational support.…”

Section: Discussionmentioning

confidence: 99%

Psychiatric morbidities and Coping strategies in patients with different Coronavirus disease-2019 severities and chronic medical diseases: A multicenter cross-sectional study

Shousha

Madbouly

Afify³

et al. 2020

Preprint

View full text Add to dashboard Cite

COVID-19 patients, especially those with chronic medical illnesses (CMI), may use different coping strategies, to reduce their psychological distress while facing the COVID-19 infection. The aim was to compare anxiety, depression and coping styles between patients infected with COVID-19 disease with and without CMI during the peak of COVID-19 disease in Egypt. This is a cross sectional study, that included an online survey consisting of Arabic versions of General Health Questionnaire-12, Taylor Manifest Anxiety Scale (TMAS), Beck Depression Inventory (BDI) and Brief-COPE scale. Questionnaires were distributed to adult patients with a confirmed diagnosis of SARS-CoV-2 virus infection during their quarantine in Egypt. One hundred ninety-nine patients responded to the survey, where 46.73% of them had CMI. Religion, emotional support, use of informational support and acceptance were the most used coping strategies by participants. Avoidant coping strategies were frequently used by divorced patients, home quarantined individuals, patients who developed COVID-19 related anxiety/depression and patients who didn’t receive hydroxyl-chloroquine. Approach strategies were frequently used by patients with mild COVID-19. Understanding the used coping strategies has implications for how individuals might be helped to manage their illness during the current presentation and intervene with development of serious long-term mental health conditions.

show abstract

“…Hence prediction of ICU admission has been frequently investigated in studies addressing diagnostic and prognostic models for COVID-19 (5). Among the variables potentially useful for such a purpose, clinical features yielded mixed results (6)(7)(8)(9)(10)(11)(12), while blood laboratory and arterial gas analysis features generally improved the overall prediction capacity (8,10,11,(13)(14)(15)(16).…”

Section: Introductionmentioning

confidence: 99%

The incremental value of computed tomography of COVID-19 pneumonia in predicting ICU admission

Bartolucci

Benelli

Betti

et al. 2021

Preprint

View full text Add to dashboard Cite

RationaleTriage is crucial for patient’s management and estimation of the required Intensive Care Unit (ICU) beds is fundamental for Health Systems during the COVID-19 pandemic.ObjectiveTo assess whether chest Computed Tomography (CT) of COVID-19 pneumonia has an incremental role in predicting patient’s admission to ICU.MethodsWe performed volumetric and texture analysis of the areas of the affected lung in CT of 115 outpatients with COVID-19 infection presenting to the Emergency Room with dyspnea and unresponsive hypoxyemia. Admission blood laboratory including lymphocyte count, serum lactate dehydrogenase, D-dimer and C-Reactive Protein and the ratio between the arterial partial pressure of oxygen and inspired oxygen were collected. By calculating the areas under the receiver-operating characteristic curves (AUC), we compared the performance of blood laboratory-arterial gas analyses features alone and combined with the CT features in two hybrid models (Hybrid radiological and Hybrid radiomics)for predicting ICU admission. Following a machine learning approach, 63 patients were allocated to the training and 52 to the validation set.Measurements and Main ResultsTwenty-nine (25%) of patients were admitted to ICU. The Hybrid radiological model comprising the lung %consolidation performed significantly (p=0.04) better in predicting ICU admission in the validation (AUC=0.82; 95%Confidence Interval 0.68-0.95) set than the blood laboratory-arterial gas analyses features alone (AUC=0.71; 95%Confidence Interval 0.56-0.86). A risk calculator for ICU admission was derived and is available at:https://github.com/cgplab/covidappConclusionsThe volume of the consolidated lung in CT of patients with COVID-19 pneumonia has a mild but significant incremental value in predicting ICU admission.

show abstract

Early prediction of level-of-care requirements in patients with COVID-19

Cited by 55 publications

References 28 publications

Machine Learning Based Clinical Decision Support System for Early COVID-19 Mortality Prediction

Machine Learning Based Clinical Decision Support System for Early COVID-19 Mortality Prediction

Psychiatric morbidities and Coping strategies in patients with different Coronavirus disease-2019 severities and chronic medical diseases: A multicenter cross-sectional study

The incremental value of computed tomography of COVID-19 pneumonia in predicting ICU admission

Contact Info

Product

Resources

About