Development and validation of an early warning score (EWAS) for predicting clinical deterioration in patients with coronavirus disease 2019

Guo, Yabing; Liu, Yingxia; Lu, Jiatao; Fan, Rong; Zhang, Fuchun; Yin, Xueru; Liu, Zhihong; Zeng, Qinglang; Yuan, Jing; Hu, Shufang; Wang, Qiongya; Liao, Baolin; Huang, Mingxing; Yin, Sichun; Zhang, Xilin; Xu, Rui; Lin, Zhanzhou; Zhao, B; He, Ridong; Liang, Mingzhu; Zhang, Zheng; Liu, Li; Sun, Jian; Tang, Lu; Deng, Liqun; Xia, Jinyu; Tang, Xiaoping; Liu, Lei; Hou, Jinlin

doi:10.1101/2020.04.17.20064691

Cited by 24 publications

(23 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The dramatic increase in CRP levels can serve as a potential biomarker to guide prognosis and treatment of inflammation. Increased CRP levels predict severity in patients with COVID-19, signifies an increased risk of death, which often features in predictive models for patient prognosis [28, 29]. SpO 2 is an indicator of respiratory functions and demonstrates variations in arterial oxygenation to indicate hypoxemia in patients to a certain extent.…”

Section: Discussionmentioning

confidence: 99%

Predictive indicators of severe COVID-19 independent of comorbidities and advanced age: a nested case−control study

Marmar

et al. 2020

Epidemiol. Infect.

View full text Add to dashboard Cite

To determine what exacerbate severity of the COVID-19 among patients without comorbidities and advanced age and investigate potential clinical indicators for early surveillance, we adopted a nested case−control study, design in which severe cases (case group, n = 67) and moderate cases (control group, n = 67) of patients diagnosed with COVID-19 without comorbidities, with ages ranging from 18 to 50 years who admitted to Wuhan Tongji Hospital were matched based on age, sex and BMI. Demographic and clinical characteristics, and risk factors associated with severe symptoms were analysed. Percutaneous oxygen saturation (SpO2), lymphocyte counts, C-reactive protein (CRP) and IL-10 were found closely associated with severe COVID-19. The adjusted multivariable logistic regression analyses revealed that the independent risk factors associated with severe COVID-19 were CRP (OR 2.037, 95% CI 1.078–3.847, P = 0.028), SpO2 (OR 1.639, 95% CI 0.943–2.850, P = 0.080) and lymphocyte (OR 1.530, 95% CI 0.850–2.723, P = 0.148), whereas the changes exhibited by indicators influenced incidence of disease severity. Males exhibited higher levels of indicators associated with inflammation, myocardial injury and kidney injury than the females. This study reveals that increased CRP levels and decreased SpO2 and lymphocyte counts could serve as potential indicators of severe COVID-19, independent of comorbidities, advanced age and sex. Males could at higher risk of developing severe symptoms of COVID-19 than females.

show abstract

Section: Discussionmentioning

confidence: 99%

Predictive indicators of severe COVID-19 independent of comorbidities and advanced age: a nested case−control study

Marmar

et al. 2020

Epidemiol. Infect.

View full text Add to dashboard Cite

show abstract

“…-Important differences in the de nition of severe disease: most of the predictive models developed in China [37,40,41] use the de nition recommended by the National Health Commission of China, that is broader than ours. In this Chinese de nition, a ratio of arterial oxygen pressure to inspiratory oxygen fraction (Pa/Fi) less than 300 is a su cient criterion to diagnose severe pneumonia.…”

Section: Discussionmentioning

confidence: 97%

Prognosis of COVID-19 Pneumonia Can Be Early Predicted Combining Age-Adjusted Charlson Comorbidity Index, CRB Score and Baseline Oxygen Saturation.

Nuevo-Ortega

Reina-Artacho

Dominguez-Moreno

et al. 2021

Preprint

View full text Add to dashboard Cite

Background: In potentially severe diseases in general and COVID-19 in particular, it is vital to early identify those patients who are going to develop complications. The last update of a recent living systematic review dedicated to predictive models in COVID-19,[1] critically appraises 145 models, 8 of them focused on prediction of severe disease and 23 on mortality. Unfortunately, in all 145 models, they found a risk of bias significant enough to finally "not recommend any for clinical use". Authors suggest concentrating on avoiding biases in sampling and prioritising the study of already identified predictive factors, rather than the identification of new ones that are often dependent on the database. Our objective is to develop a model to predict which patients with COVID-19 pneumonia are at high risk of developing severe illness or dying, using basic and validated clinical tools.Methods: prospective cohort of consecutive patients admitted in a teaching hospital during the “first wave” of the COVID-19 pandemic. Follow-up to discharge from hospital. Multiple logistic regression selecting variables according to clinical and statistical criteria. Results: 404 consecutive patients were evaluated, 392 (97%) completed follow-up. Mean age was 61 years; 59% were men. The median burden of comorbidity was 2 points in the Age-adjusted Charlson Comorbidity Index, CRB was abnormal in 18% of patients and basal oxygen saturation on admission lower than 90% in 18%. A model composed of Age-adjusted Charlson Comorbidity Index, CRB score and basal oxygen saturation can predict unfavorable evolution or death with an area under the ROC curve of 0.85 (95% CI: 0.80-0.89), and 0.90 (95% CI: 0.86 to 0.94), respectively.Conclusion: prognosis of COVID-19 pneumonia can be predicted in the out-of-hospital environment using two classic prognostic scales and a pocket pulse oximeter.

show abstract

“…Indeed, AI technologies related to COVID-19 outcomes are emerging, as indicated in a recent published systematic review, with a majority of these studies conducted in China [ 13 ]. Predictive models using rule-based scoring tools and machine learning approaches have been applied to predict clinical deterioration in hospitalized patients and support health care providers in triaging patients when resources are limited [ 14 - 19 ]. However, there are many concerns and barriers to making this a reality [ 20 ], including uncertainty in the risk factors associated with disease progression, a limited number of patients whose data can be used to train and test models, and no public data sets available to test and validate models outside of a single health care setting.…”

Section: Introductionmentioning

confidence: 99%

Learning From Past Respiratory Infections to Predict COVID-19 Outcomes: Retrospective Study

Sang¹,

Sun²,

Coquet³

et al. 2021

J Med Internet Res

View full text Add to dashboard Cite

Background For the clinical care of patients with well-established diseases, randomized trials, literature, and research are supplemented with clinical judgment to understand disease prognosis and inform treatment choices. In the void created by a lack of clinical experience with COVID-19, artificial intelligence (AI) may be an important tool to bolster clinical judgment and decision making. However, a lack of clinical data restricts the design and development of such AI tools, particularly in preparation for an impending crisis or pandemic. Objective This study aimed to develop and test the feasibility of a “patients-like-me” framework to predict the deterioration of patients with COVID-19 using a retrospective cohort of patients with similar respiratory diseases. Methods Our framework used COVID-19–like cohorts to design and train AI models that were then validated on the COVID-19 population. The COVID-19–like cohorts included patients diagnosed with bacterial pneumonia, viral pneumonia, unspecified pneumonia, influenza, and acute respiratory distress syndrome (ARDS) at an academic medical center from 2008 to 2019. In total, 15 training cohorts were created using different combinations of the COVID-19–like cohorts with the ARDS cohort for exploratory purposes. In this study, two machine learning models were developed: one to predict invasive mechanical ventilation (IMV) within 48 hours for each hospitalized day, and one to predict all-cause mortality at the time of admission. Model performance was assessed using the area under the receiver operating characteristic curve (AUROC), sensitivity, specificity, positive predictive value, and negative predictive value. We established model interpretability by calculating SHapley Additive exPlanations (SHAP) scores to identify important features. Results Compared to the COVID-19–like cohorts (n=16,509), the patients hospitalized with COVID-19 (n=159) were significantly younger, with a higher proportion of patients of Hispanic ethnicity, a lower proportion of patients with smoking history, and fewer patients with comorbidities (P<.001). Patients with COVID-19 had a lower IMV rate (15.1 versus 23.2, P=.02) and shorter time to IMV (2.9 versus 4.1 days, P<.001) compared to the COVID-19–like patients. In the COVID-19–like training data, the top models achieved excellent performance (AUROC>0.90). Validating in the COVID-19 cohort, the top-performing model for predicting IMV was the XGBoost model (AUROC=0.826) trained on the viral pneumonia cohort. Similarly, the XGBoost model trained on all 4 COVID-19–like cohorts without ARDS achieved the best performance (AUROC=0.928) in predicting mortality. Important predictors included demographic information (age), vital signs (oxygen saturation), and laboratory values (white blood cell count, cardiac troponin, albumin, etc). Our models had class imbalance, which resulted in high negative predictive values and low positive predictive values. Conclusions We provided a feasible framework for modeling patient deterioration using existing data and AI technology to address data limitations during the onset of a novel, rapidly changing pandemic.

show abstract

Development and validation of an early warning score (EWAS) for predicting clinical deterioration in patients with coronavirus disease 2019

Cited by 24 publications

References 21 publications

Predictive indicators of severe COVID-19 independent of comorbidities and advanced age: a nested case−control study

Predictive indicators of severe COVID-19 independent of comorbidities and advanced age: a nested case−control study

Prognosis of COVID-19 Pneumonia Can Be Early Predicted Combining Age-Adjusted Charlson Comorbidity Index, CRB Score and Baseline Oxygen Saturation.

Learning From Past Respiratory Infections to Predict COVID-19 Outcomes: Retrospective Study

Contact Info

Product

Resources

About