ABSTRACT
BACKGROUND: Older adults have worse outcomes following hospitalisation with COVID-19, but within this group there is substantial variation. Although frailty and comorbidity are key determinants of mortality, it is less clear which specific manifestations of frailty and comorbidity are associated with the worst outcomes. OBJECTIVE: We aimed to identify the key comorbidities and domains of frailty that were associated with in-hospital mortality in older patients with COVID-19 using models developed using machine learning algorithms. METHODS: This was a retrospective study that used the Hospital Episode Statistics administrative dataset from 1st March 2020 to 28th February 2021 for hospital patients in England aged 65 years and over. The dataset was split into separate training (70%), test (15%) and validation (15%) datasets during model development. Global frailty was assessed using the Hospital Frailty Risk Score (HFRS) and specific domain of frailty identified using the Dr Foster Global Frailty Scale (GFS). Comorbidity was assessed using the Charlson Comorbidity Index (CCI). Additional features employed in the random forest algorithms included age, sex, deprivation, ethnicity, discharge month and year, geographical region, hospital trust, disease severity, International Statistical Classification of Disease and Related Health Problems 10th edition codes recorded during the admission. Features were selected, pre-processed and inputted into a series of random forest classification algorithms developed to identify factors strongly associated with in-hospital mortality. Two models were developed, the first model included the demographic, hospital-related and disease related items described above and individual GFS domains and CCI items. The second model was as the first but replaced the GFS domains and CCI items with the HFRS as a global measure of frailty. Model performance was assessed using the area under the receiver operating characteristic (AUROC) curve and measures of model accuracy. RESULTS: In total 215,831 patients were included. The model containing the individual GFS domains and CCI items had an AUROC curve for in-hospital mortality of 90% and a predictive accuracy of 83%. The model containing the HFRS had a similar performance (AUROC curve 90%, predictive accuracy 82%). The most important frailty items in the GFS were dementia/delirium, falls/fractures and pressure ulcers/weight loss. The most-important comorbidity items in the CCI were cancer, heart failure and renal disease. CONCLUSIONS: The physical manifestation of frailty and comorbidity, particularly a history of cognitive impairment and falls, may be useful in identification of patients who may need additional support during hospitalization with COVID-19.
ABSTRACT
BACKGROUND: A key first step in optimising COVID-19 patient outcomes during future case-surges is to learn from the experience within individual hospitals during the early stages of the pandemic. The aim of this study was to investigate the extent of variation in COVID-19 outcomes between National Health Service (NHS) hospital trusts and regions in England using data from March-July 2020. METHODS: This was a retrospective observational study using the Hospital Episode Statistics administrative dataset. Patients aged ≥ 18 years who had a diagnosis of COVID-19 during a hospital stay in England that was completed between March 1st and July 31st, 2020 were included. In-hospital mortality was the primary outcome of interest. In secondary analysis, critical care admission, length of stay and mortality within 30 days of discharge were also investigated. Multilevel logistic regression was used to adjust for covariates. FINDINGS: There were 86,356 patients with a confirmed diagnosis of COVID-19 included in the study, of whom 22,944 (26.6%) died in hospital with COVID-19 as the primary cause of death. After adjusting for covariates, the extent of the variation in-hospital mortality rates between hospital trusts and regions was relatively modest. Trusts with the largest baseline number of beds and a greater proportion of patients admitted to critical care had the lowest in-hospital mortality rates. INTERPRETATION: There is little evidence of clustering of deaths within hospital trusts. There may be opportunities to learn from the experience of individual trusts to help prepare hospitals for future case-surges.