ABSTRACT
Background: Patients (pts) with cancer are at increased risk of severe COVID-19 infection and death. Due to COVID-19 outcome heterogeneity, accurate assessment of pts is crucial. Early identification of pts who are likely to deteriorate allows timely discussions regarding escalation of care. Likewise, safe home management will reduce risk of nosocomial infection. To aid clinical decisionmaking, we developed a model to help determine which pts should be admitted vs. managed as an outpatient and which pts are likely to have severe COVID-19. Methods: Pts with active solid or haematological cancer presenting with symptoms/asymptomatic and testing positive for SARS-CoV-2 in Europe and USA were identified following institutional board approval. Clinical and laboratory data were extracted from pt records. Clinical outcome measures were discharge within 24 hours, requirement for oxygen at any stage during admission and death. Random Forest (RF) algorithm was used for model derivation as it compared favourably vs. lasso regression. Relevant clinical features were identified using recursive feature elimination based on SHAP. Internal validation (bootstrapping) with multiple imputations for missing data (maximum ≤2) were used for performance evaluation. Cost function determined cut-offs were defined for admission/death. The final CORONET model was trained on the entire cohort. Results: Model derivation set comprised 672 pts (393 male, 279 female, median age 71). 83% had solid cancers, 17% haematological. Predictive features were selected based on clinical relevance and data availability, supported by recursive feature elimination based on SHAP. RF model using haematological cancer, solid cancer stage, no of comorbidities, National Early Warning Score 2 (NEWS2), neutrophil:lymphocyte ratio, platelets, CRP and albumin achieved AUROC for admission 0.79 (+/-0.03) and death 0.75 (+/-0.02). RF explanation using SHAP revealed NEWS2 and C-reactive protein as the most important features predicting COVID-19 severity. In the entire cohort, CORONET recommended admission of 96% of patients requiring oxygen and 99% of patients who died. We then built a decision support tool using the model, which aids clinical decisions by presenting model predictions and explaining key contributing features. Conclusions: We have developed a model and tool available athttps://coronet.manchester.ac.uk/ to predict which pts with cancer and COVID-19 require hospital admission and are likely to have a severe disease course. CORONET is being continuously refined and validated over time.
ABSTRACT
BACKGROUND: Cancer patients are at increased risk of death from severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Cancer and its treatment affect many haematological and biochemical parameters, therefore we analysed these prior to and during coronavirus disease 2019 (COVID-19) and correlated them with outcome. PATIENTS AND METHODS: Consecutive patients with cancer testing positive for SARS-CoV-2 in centres throughout the United Kingdom were identified and entered into a database following local governance approval. Clinical and longitudinal laboratory data were extracted from patient records. Data were analysed using Mann-Whitney U test, Fisher's exact test, Wilcoxon signed rank test, logistic regression, or linear regression for outcomes. Hierarchical clustering of heatmaps was performed using Ward's method. RESULTS: In total, 302 patients were included in three cohorts: Manchester (n = 67), Liverpool (n = 62), and UK (n = 173). In the entire cohort (N = 302), median age was 69 (range 19-93 years), including 163 males and 139 females; of these, 216 were diagnosed with a solid tumour and 86 with a haematological cancer. Preinfection lymphopaenia, neutropaenia and lactate dehydrogenase (LDH) were not associated with oxygen requirement (O2) or death. Lymphocyte count (P < 0.001), platelet count (P = 0.03), LDH (P < 0.0001) and albumin (P < 0.0001) significantly changed from preinfection to during infection. High rather than low neutrophils at day 0 (P = 0.007), higher maximal neutrophils during COVID-19 (P = 0.026) and higher neutrophil-to-lymphocyte ratio (NLR; P = 0.01) were associated with death. In multivariable analysis, age (P = 0.002), haematological cancer (P = 0.034), C-reactive protein (P = 0.004), NLR (P = 0.036) and albumin (P = 0.02) at day 0 were significant predictors of death. In the Manchester/Liverpool cohort 30 patients have restarted therapy following COVID-19, with no additional complications requiring readmission. CONCLUSION: Preinfection biochemical/haematological parameters were not associated with worse outcome in cancer patients. Restarting treatment following COVID-19 was not associated with additional complications. Neutropaenia due to cancer/treatment is not associated with COVID-19 mortality. Cancer therapy, particularly in patients with solid tumours, need not be delayed or omitted due to concerns that treatment itself increases COVID-19 severity.