Risk prediction for poor outcome and death in hospital in-patients with COVID-19: derivation in Wuhan, China and external validation in London, UK

Abstract

Research in contextEvidence before this study Several prognostic models for predicting mortality risk, progression to severe disease, or length of hospital stay in COVID-19 have been published. 1 Commonly reported predictors of severe prognosis in patients with COVID-19 include age, sex, computed tomography scan features, C-reactive protein (CRP), lactic dehydrogenase, and lymphocyte count. Symptoms (notably dyspnoea) and comorbidities (e.g. chronic lung disease, cardiovascular disease and hypertension) are also reported to have associations with poor prognosis. 2 However, most studies have not described the study population or intended use of prediction models, and external validation is rare and to date done using datasets originating from different Wuhan hospitals. 3 Given different patterns of testing and organisation of healthcare pathways, external validation in datasets from other countries is required. Added value of this studyThis study used data from Wuhan, China to derive and internally validate multivariable models to predict poor outcome and death in COVID-19 patients after hospital admission, with external validation using data from King's College Hospital, London, UK. Mortality and poor outcome occurred in 4.3% and 9.7% of patients in Wuhan, compared to 34.1% and 42.9% of patients in London. Models based on age, sex and simple routinely available laboratory tests (lymphocyte count, neutrophil count, platelet count, CRP and creatinine) had good discrimination and calibration in internal validation, but performed only moderately well in external validation. Models based on age, sex, symptoms and comorbidity were adequate in internal validation for poor outcome (ICU admission or death) but had poor performance for death alone. Implications of all the available evidenceThis study and others find that relatively simple risk prediction models using demographic, clinical and laboratory data perform well in internal validation but at best moderately in external validation, either because derivation and external validation populations are small (Xie et al 3 ) and/or because they vary greatly in casemix and severity (our study). There are three decision points where risk prediction may be most useful: (1) deciding who to test; (2) deciding which patients in the community are at high-risk of poor outcomes; and (3) identifying patients at high-risk at the point of hospital admission. Larger studies focusing on particular decision points, with rapid external validation in multiple datasets are needed. A key gap is risk prediction tools for use in community triage (decisions to admit, or to keep at home with varying intensities of follow-up including telemonitoring) or in low income settings where laboratory tests may not be routinely available at the point of decision-making. This requires systematic data collection in community and low-income settings to derive and evaluate appropriate models. AbstractBackground

A Risk Score to Predict Admission to the Intensive Care Unit in Patients with COVID-19: the ABC-GOALS score

“…28 Also, the Charlson comorbidity index offers the advantage of integrating several comorbidities into one score that has been previously associated with survival. 17 Among clinical symptoms, dyspnea or shortness of breath is the most consistently reported symptom associated with Covid-19 severity and mortality 5,8,11,29 and was independently associated with ICU admission in this study. Obesity is a long-recognized factor for severe pulmonary infections 30 and has been consistently associated with adverse outcomes in Covid-19.…”

“…However, the clinical score remains to be externally validated, as some reported models based exclusively on demographic (but not physical examination) information have been shown to decrease their performance after external validation. 11 The scores integrating clinical with laboratory (ABC-GOALS cl ) and imaging (ABC-GOALS clx ) findings seem to perform better for prediction of admission to an ICU. Both models include values of glucose, lactate dehydrogenase, and oxygenation at admission that have been previously reported to be associated with prognosis in Covid-19.…”

“…age, comorbidities and symptoms); [5][6][7][8][9][10] vital signs obtained from triage evaluation (e.g. respiratory rate and arterial pressure); 11,12 laboratory abnormalities including inflammatory, coagulation and organ-specific studies (e.g. lactate dehydrogenase, D-dimer, fibrinogen, cardiac troponins, liver function tests, among others), 5,6,[8][9][10]13 and lung imaging findings (e.g.…”

Risk factors for mortality among hospitalized patients with COVID-19

“…Most prognostic models are based on data from China [19][20][21][22][23][24], although others have been developed with data from the United Kingdom [25,26], Mexico [27], South Korea [28], Israel [29], the U.S. [30][31][32]), and a mix of countries [33]. Our study differs from the other U.S. studies in that it includes a broader cohort of patients encompassing all geographic regions.…”

Severity Prediction for COVID-19 Patients via Recurrent Neural Networks

“…To fight against the pandemic and mitigate the burden, numerous efforts have been made by scientists to develop risk prediction models for COVID-19 patients. Prognostic models, among the important risk prediction models, has been developed to predict risks of mortality 1 – 3 and progression to severe status 4 – 6 for COVID-19 patients. Commonly used predictors for those COVID-19 prognostic models include comorbidities, age, sex, lab test results (e.g., lymphocyte count, C reactive protein, and creatinine), and radiologic imaging features 7 .…”