Reinterpreting survival analysis in the universal approximator age (preprint)

Survival analysis is an integral part of the statistical toolbox. However, while most domains of classical statistics have embraced deep learning, survival analysis only recently gained some minor attention from the deep learning community. This recent development is likely in part motivated by the COVID-19 pandemic. We aim to provide the tools needed to fully harness the potential of survival analysis in deep learning. On the one hand, we discuss how survival analysis connects to classification and regression. On the other hand, we provide technical tools. We provide a new loss function, evaluation metrics, and the first universal approximating network that provably produces survival curves without numeric integration. We show that the loss function and model outperform other approaches using a large numerical study.

Unquantifiably low aldosterone concentrations are prevalent in hospitalised COVID-19 patients but may not be revealed by chemiluminescent immunoassay (preprint)

Objective: Previous studies have reported conflicting findings regarding aldosterone levels in patients hospitalised with COVID-19. We therefore used the gold-standard technique of liquid chromatography tandem mass-spectrometry (LCMSMS) to address this uncertainty. Design: All patients admitted to Cambridge University Hospitals with COVID-19 between March 10, 2020 and May 13, 2021, and in whom a stored blood sample was available for analysis, were eligible for inclusion. Methods: Aldosterone was measured by LCMSMS and by immunoassay; cortisol and renin were determined by immunoassay. Results: Using LCMSMS, aldosterone was below the limit of detection (<70 pmol/L) in 74 (58.7%) patients. Importantly, this finding was discordant with results obtained using a commonly employed clinical immunoassay (Liaison Diasorin), which over-estimated aldosterone compared to the LCMSMS assay (intercept 14.1 [95% CI -34.4 to 54.1] + slope 3.16 [95% CI 2.09 to 4.15] pmol/L). The magnitude of this discrepancy did not clearly correlate with markers of kidney or liver function. Solvent extraction prior to immunoassay improved the agreement between methods (intercept -14.9 [95% CI -31.9 to -4.3] and slope 1.0 [95% CI 0.89 to 1.02] pmol/L) suggesting the presence of a water-soluble metabolite causing interference in the direct immunoassay. We also replicated a previous finding that blood cortisol concentrations were often increased, with increased mortality in the group with serum cortisol levels >744 nmol/L (p=0.005). Conclusion: When measured by LCMSMS, aldosterone was found to be profoundly low in a significant proportion of patients with COVID-19 at the time of hospital admission. This has likely not been detected previously due to high levels of interference with immunoassays in patients with COVID-19, and this merits further prospective investigation.

Validation of the 4C Deterioration Model for COVID-19 in a UK teaching hospital during Wave 2 (preprint)

The 4C Deterioration model was developed and validated on data collected in UK hospitals until August 26, 2020, but has not yet been validated in the presence of SARS-CoV-2 variants and novel treatment regimens that have emerged subsequently. In this first validation study of the 4C Deterioration model on patients admitted between August 27, 2020 and April 16, 2021 we found, despite a slightly overestimation of risk, that the discrimination (area under the curve 0.75, 95% CI 0.71-0.78) and calibration of the model remained consistent with the development study, strengthening the evidence for adopting this model into clinical practice.

Development and Validation of a Dynamic 48-Hour In-Hospital Mortality Risk Stratification for COVID-19 in a UK Teaching Hospital: A Retrospective Cohort Study (preprint)

Background: While numerous point-of-admission disease severity models for COVID-19 have been proposed, disease stratification that accounts for changes in a patient’s condition while in hospital is urgently needed to facilitate patient management and resource allocation.Methods: We developed a prognostic model for 48-hour in-hospital mortality using 473 consecutive patients with COVID-19 presenting to a UK hospital between March 1 and September 12, 2020; and temporally validated using data on 405 patients presenting between September 13, 2020 and January 3, 2021.The primary outcome was all-cause in-hospital mortality. We additionally considered the competing risks of discharge from hospital and transfer to a tertiary Intensive Care Unit for extracorporeal membrane oxygenation. We adopted a landmarking approach to dynamic prediction that accounts for competing risks and informative missingness, and selected predictors using penalised regression. The model estimates, at any point during a hospital visit, the probability of in-hospital mortality during the next 48 hours.Results: Our final model includes age, Clinical Frailty Scale score, heart rate, respiratory rate, SpO2/FiO2 ratio, white cell count, presence of acidosis (pH < 7.35) and Interleukin-6. Internal validation achieved an AUROC of 0.90 (95% CI 0.87–0.93) and temporal validation gave an AUROC of 0.91 (95% CI 0.88-0.95). Interpretation: Our model uniquely incorporates both static risk factors (e.g. age) and evolving clinical and laboratory data, to provide a dynamic risk prediction model that adapts to both sudden and gradual changes in an individual patient’s clinical condition. External validation outside the study hospital will be required before adoption.Funding: NIHR Cambridge Biomedical Research Centre, UKRI Medical Research CouncilDeclaration of Interest: None to declare. Ethical Approval: The study was approved by a UK Health Research Authority ethics committee (20/WM/0125). Patient consent was waived because the de-identified data presented here were collected during routine clinical practice; there was no requirement for informed consent.

Development and validation of a dynamic 48-hour in-hospital prognostic risk stratification for COVID-19 in a UK teaching hospital: a retrospective cohort study (preprint)

We propose a prognostic dynamic risk stratification for 48-hour in-hospital mortality in patients with COVID-19, using demographics and routinely-collected observations and laboratory tests: age, Clinical Frailty Scale score, heart rate, respiratory rate, SpO2/FiO2 ratio, white cell count, acidosis (pH < 7.35) and Interleukin-6. We train and validate the model using data from a UK teaching hospital, adopting a landmarking approach that accounts for competing risks and informative missingness. Internal validation of the model on the first wave of patients presenting between March 1 and September 12, 2020 achieves an AUROC of 0.90 (95% CI 0.87-0.93). Temporal validation on patients presenting between September 13, 2020 and January 1, 2021 gives an AUROC of 0.91 (95% CI 0.88-0.95). The resulting mortality stratification tool has the potential to provide physicians with an assessment of a patient's evolving prognosis throughout the course of active hospital treatment.

Clinical Features, Inpatient Trajectories and Frailty in Older Inpatients With COVID-19: A Retrospective Observational Study. (preprint)

Introduction: We describe the clinical features and inpatient trajectories of older adults hospitalized with COVID-19, and explore relationships with frailty. Methods: This retrospective observational study included older adults admitted as an emergency to a University Hospital who were diagnosed with COVID-19. Patient characteristics and hospital outcomes, primarily inpatient death or death within 14 days of discharge, were described for the whole cohort and by frailty status. Associations with mortality were further evaluated using Cox Proportional Hazards Regression (Hazard Ratio [HR], 95% Confidence Interval). Results: 214 patients (94 women) were included of whom 142 (66.4%) were frail with a median Clinical Frailty Scale (CFS) score of 6. Frail compared to non-frail patients were more likely to present with atypical symptoms including new or worsening confusion (45.1% vs 20.8%, p<0.001) and were more likely to die (66% vs 16%, p=0.001). Older age, being male, presenting with high illness acuity and high frailty were independent predictors of death and a dose-response association between frailty and mortality was observed (CFS 1-4: reference; CFS 5-6: HR 1.78, 95% CI 0.90, 3.53; CFS 7-8: HR 2.57, 95% CI 1.26, 5.24). Conclusions: Clinicians should have a low threshold for testing for COVID-19 in older and frail patients during periods of community viral transmission and diagnosis should prompt early advanced care planning.

Clinical features and inpatient trajectories of older inpatients with COVID-19: a retrospective observational study. (preprint)

Background: A comprehensive description of the clinical characteristics, inpatient trajectory and relationship with frailty of older inpatients admitted with COVID-19 is essential in the management of older adults during the COVID-19 pandemic. The aim of this study was to describe the clinical features and inpatient trajectory of older inpatients with confirmed COVID -19. Methods: This was a retrospective observational study of hospitalised older adults. Subjects include unscheduled medical admissions of older inpatients to a University Hospital with laboratory and clinically confirmed COVID-19. The primary outcome was death during the inpatient stay or within 14 days of discharge after a maximum follow up time of 45 days. The characteristics of the cohort were described in detail as a whole and by frailty status. Results: 214 patients were included in this study with a mean length of stay of 11 days (Range 6 to 18 days), of whom 140 (65.4%) patients were discharged and 74 (34.6%) patients died in hospital. 142 (66.4%) patients were frail with median Clinical Frailty Scale (CFS) score of 6. Frail patients were more likely to present with atypical symptoms including new or worsening confusion compared to non-frail patients (20.8% vs 45.1%, p<0.001) and were more likely to die in hospital or within 14 days of discharge (66% vs 16%, p=0.001). Older age, being male, presenting with high illness acuity and high frailty were all independently associated with higher risk of death and a dose response association between higher frailty and higher mortality was observed. Conclusions: Older adult inpatients with COVID-19 infection are likely to present with atypical symptoms, experience delirium and have a high mortality, especially if they are also living with frailty. Clinicians should have a low threshold for testing for COVID-19 in older and frail patients presenting to hospital as an emergency during periods when there is community transmission of COVID-19 and, when diagnosed, this should prompt early advanced care planning with the patient and family.