Background: Within the UK, COVID-19 has contributed towards over 103,000 deaths. Although multiple risk factors for COVID-19 have been identified, using this data to improve clinical care has proven challenging. The main aim of this study is to develop a reliable, multivariable predictive model for COVID-19 in-patient outcomes, thus enabling risk-stratification and earlier clinical decision-making. Methods: Anonymised data consisting of 44 independent predictor variables from 355 adults diagnosed with COVID-19, at a UK hospital, was manually extracted from electronic patient records for retrospective, case–control analysis. Primary outcomes included inpatient mortality, required ventilatory support, and duration of inpatient treatment. Pulmonary embolism sequala was the only secondary outcome. After balancing data, key variables were feature selected for each outcome using random forests. Predictive models were then learned and constructed using Bayesian networks. Results: The proposed probabilistic models were able to predict, using feature selected risk factors, the probability of the mentioned outcomes. Overall, our findings demonstrate reliable, multivariable, quantitative predictive models for four outcomes, which utilise readily available clinical information for COVID-19 adult inpatients. Further research is required to externally validate our models and demonstrate their utility as risk stratification and clinical decision-making tools.

To support the global restart of elective surgery, data from an international prospective cohort study of 8492 patients (69 countries) was analysed using artificial intelligence (machine learning techniques) to develop a predictive score for mortality in surgical patients with SARS-CoV-2. We found that patient rather than operation factors were the best predictors and used these to create the COVIDsurg Mortality Score (https://covidsurgrisk.app). Our data demonstrates that it is safe to restart a wide range of surgical services for selected patients.

Background This study aimed to determine the impact of pulmonary complications on death after surgery both before and during the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pandemic. Methods This was a patient-level, comparative analysis of two, international prospective cohort studies: one before the pandemic (January–October 2019) and the second during the SARS-CoV-2 pandemic (local emergence of COVID-19 up to 19 April 2020). Both included patients undergoing elective resection of an intra-abdominal cancer with curative intent across five surgical oncology disciplines. Patient selection and rates of 30-day postoperative pulmonary complications were compared. The primary outcome was 30-day postoperative mortality. Mediation analysis using a natural-effects model was used to estimate the proportion of deaths during the pandemic attributable to SARS-CoV-2 infection. Results This study included 7402 patients from 50 countries; 3031 (40.9 per cent) underwent surgery before and 4371 (59.1 per cent) during the pandemic. Overall, 4.3 per cent (187 of 4371) developed postoperative SARS-CoV-2 in the pandemic cohort. The pulmonary complication rate was similar (7.1 per cent (216 of 3031) versus 6.3 per cent (274 of 4371); P = 0.158) but the mortality rate was significantly higher (0.7 per cent (20 of 3031) versus 2.0 per cent (87 of 4371); P < 0.001) among patients who had surgery during the pandemic. The adjusted odds of death were higher during than before the pandemic (odds ratio (OR) 2.72, 95 per cent c.i. 1.58 to 4.67; P < 0.001). In mediation analysis, 54.8 per cent of excess postoperative deaths during the pandemic were estimated to be attributable to SARS-CoV-2 (OR 1.73, 1.40 to 2.13; P < 0.001). Conclusion Although providers may have selected patients with a lower risk profile for surgery during the pandemic, this did not mitigate the likelihood of death through SARS-CoV-2 infection. Care providers must act urgently to protect surgical patients from SARS-CoV-2 infection.

No abstract

No abstract