ObjectiveDevelop and validate models that predict mortality of patients diagnosed with COVID-19 admitted to the hospital.DesignRetrospective cohort study.SettingA multicentre cohort across 10 Dutch hospitals including patients from 27 February to 8 June 2020.ParticipantsSARS-CoV-2 positive patients (age ≥18) admitted to the hospital.Main outcome measures21-day all-cause mortality evaluated by the area under the receiver operator curve (AUC), sensitivity, specificity, positive predictive value and negative predictive value. The predictive value of age was explored by comparison with age-based rules used in practice and by excluding age from the analysis.Results2273 patients were included, of whom 516 had died or discharged to palliative care within 21 days after admission. Five feature sets, including premorbid, clinical presentation and laboratory and radiology values, were derived from 80 features. Additionally, an Analysis of Variance (ANOVA)-based data-driven feature selection selected the 10 features with the highest F values: age, number of home medications, urea nitrogen, lactate dehydrogenase, albumin, oxygen saturation (%), oxygen saturation is measured on room air, oxygen saturation is measured on oxygen therapy, blood gas pH and history of chronic cardiac disease. A linear logistic regression and non-linear tree-based gradient boosting algorithm fitted the data with an AUC of 0.81 (95% CI 0.77 to 0.85) and 0.82 (0.79 to 0.85), respectively, using the 10 selected features. Both models outperformed age-based decision rules used in practice (AUC of 0.69, 0.65 to 0.74 for age >70). Furthermore, performance remained stable when excluding age as predictor (AUC of 0.78, 0.75 to 0.81).ConclusionBoth models showed good performance and had better test characteristics than age-based decision rules, using 10 admission features readily available in Dutch hospitals. The models hold promise to aid decision-making during a hospital bed shortage.

Purpose Inhibition of dipeptidyl peptidase (DPP-)4 could reduce coronavirus disease 2019 (COVID-19) severity by reducing inflammation and enhancing tissue repair beyond glucose lowering. We aimed to assess this in a prospective cohort study. Methods We studied in 565 patients with type 2 diabetes in the CovidPredict Clinical Course Cohort whether use of a DPP-4 inhibitor prior to hospital admission due to COVID-19 was associated with improved clinical outcomes. Using crude analyses and propensity score matching (on age, sex and BMI), 28 patients using a DPP-4 inhibitor were identified and compared to non-users. Results No differences were found in the primary outcome mortality (matched-analysis = odds-ratio: 0,94 [95% confidence interval: 0,69 – 1,28], p-value: 0,689) or any of the secondary outcomes (ICU admission, invasive ventilation, thrombotic events or infectious complications). Additional analyses comparing users of DPP-4 inhibitors with subgroups of non-users (subgroup 1: users of metformin and sulphonylurea; subgroup 2: users of any insulin combination), allowing to correct for diabetes severity, did not yield different results. Conclusions We conclude that outpatient use of a DPP-4 inhibitor does not affect the clinical outcomes of patients with type 2 diabetes who are hospitalized because of COVID-19 infection.

Background The objective of this study was to describe the prevalence, incidence, prognostic factors, and outcomes of venous thromboembolism in critically ill patients receiving contemporary thrombosis prophylaxis. Methods We conducted a pooled analysis of two prospective cohort studies. The outcomes of interest were in-hospital pulmonary embolism or lower extremity deep vein thrombosis (PE-LDVT), in-hospital nonleg deep vein thrombosis (NLDVT), and 90-day mortality. Multivariable logistic regression analysis was used to evaluate the association between predefined baseline prognostic factors and PE-LDVT or NLDVT. Cox regression analysis was used to evaluate the association between PE-LDVT or NLDVT and 90-day mortality. Results A total of 2208 patients were included. The prevalence of any venous thromboembolism during 3 months before ICU admission was 3.6% (95% CI 2.8–4.4%). Out of 2166 patients, 47 (2.2%; 95% CI 1.6–2.9%) developed PE-LDVT and 38 patients (1.8%; 95% CI 1.2–2.4%) developed NLDVT. Renal replacement therapy (OR 3.5 95% CI 1.4–8.6), respiratory failure (OR 2.0; 95% CI 1.1–3.8), and previous VTE (OR 3.6; 95% CI 1.7–7.7) were associated with PE-LDVT. Central venous catheters (OR 5.4; 95% CI 1.7–17.8) and infection (OR 2.2; 95% CI 1.1–4.3) were associated with NLDVT. Occurrence of PE-LDVT but not NLDVT was associated with increased 90-day mortality (HR 2.7; 95% CI 1.6–4.6, respectively, 0.92; 95% CI 0.41–2.1). Conclusion Thrombotic events are common in critically ill patients, both before and after ICU admittance. Development of PE-LDVT but not NLDVT was associated with increased mortality. Prognostic factors for developing PE-LDVT or NLDVT despite prophylaxis can be identified at ICU admission and may be used to select patients at higher risk in future randomized clinical trials. Trial registration NCT03773939.

Introduction Determining the optimal timing for extubation can be challenging in the intensive care. In this study, we aim to identify predictors for extubation failure in critically ill patients with COVID-19. Methods We used highly granular data from 3464 adult critically ill COVID patients in the multicenter Dutch Data Warehouse, including demographics, clinical observations, medications, fluid balance, laboratory values, vital signs, and data from life support devices. All intubated patients with at least one extubation attempt were eligible for analysis. Transferred patients, patients admitted for less than 24 h, and patients still admitted at the time of data extraction were excluded. Potential predictors were selected by a team of intensive care physicians. The primary and secondary outcomes were extubation without reintubation or death within the next 7 days and within 48 h, respectively. We trained and validated multiple machine learning algorithms using fivefold nested cross-validation. Predictor importance was estimated using Shapley additive explanations, while cutoff values for the relative probability of failed extubation were estimated through partial dependence plots. Results A total of 883 patients were included in the model derivation. The reintubation rate was 13.4% within 48 h and 18.9% at day 7, with a mortality rate of 0.6% and 1.0% respectively. The grandient-boost model performed best (area under the curve of 0.70) and was used to calculate predictor importance. Ventilatory characteristics and settings were the most important predictors. More specifically, a controlled mode duration longer than 4 days, a last fraction of inspired oxygen higher than 35%, a mean tidal volume per kg ideal body weight above 8 ml/kg in the day before extubation, and a shorter duration in assisted mode (< 2 days) compared to their median values. Additionally, a higher C-reactive protein and leukocyte count, a lower thrombocyte count, a lower Glasgow coma scale and a lower body mass index compared to their medians were associated with extubation failure. Conclusion The most important predictors for extubation failure in critically ill COVID-19 patients include ventilatory settings, inflammatory parameters, neurological status, and body mass index. These predictors should therefore be routinely captured in electronic health records.

Objective To establish whether one can build a mortality prediction model for COVID-19 patients based solely on demographics and comorbidity data that outperforms age alone. Such a model could be a precursor to implementing smart lockdowns and vaccine distribution strategies. Methods The training cohort comprised 2337 COVID-19 inpatients from nine hospitals in The Netherlands. The clinical outcome was death within 21 days of being discharged. The features were derived from electronic health records collected during admission. Three feature selection methods were used: LASSO, univariate using a novel metric, and pairwise (age being half of each pair). 478 patients from Belgium were used to test the model. All modeling attempts were compared against an age-only model. Results In the training cohort, the mortality group’s median age was 77 years (interquartile range = 70–83), higher than the non-mortality group (median = 65, IQR = 55–75). The incidence of former/active smokers, male gender, hypertension, diabetes, dementia, cancer, chronic obstructive pulmonary disease, chronic cardiac disease, chronic neurological disease, and chronic kidney disease was higher in the mortality group. All stated differences were statistically significant after Bonferroni correction. LASSO selected eight features, novel univariate chose five, and pairwise chose none. No model was able to surpass an age-only model in the external validation set, where age had an AUC of 0.85 and a balanced accuracy of 0.77. Conclusion When applied to an external validation set, we found that an age-only mortality model outperformed all modeling attempts (curated on www.covid19risk.ai) using three feature selection methods on 22 demographic and comorbid features.

Objective To compare survival of subjects with COVID-19 treated in hospitals that either did or did not routinely treat patients with hydroxychloroquine or chloroquine. Methods We analysed data of COVID-19 patients treated in 9 hospitals in the Netherlands. Inclusion dates ranged from February 27 th 2020, to May 15 th , when the Dutch national guidelines no longer supported the use of (hydroxy)chloroquine. Seven hospitals routinely treated subjects with (hydroxy)chloroquine, two hospitals did not. Primary outcome was 21-day all-cause mortality. We performed a survival analysis using log-rank test and Cox-regression with adjustment for age, sex and covariates based on premorbid health, disease severity, and the use of steroids for adult respiratory distress syndrome, including dexamethasone. Results Among 1949 included subjects, 21-day mortality was 21.5% in 1596 subjects treated in hospitals that routinely prescribed (hydroxy)chloroquine, and 15.0% in 353 subjects that were treated in hospitals that did not. In the adjusted Cox-regression models this difference disappeared, with an adjusted hazard ratio of 1.09 (95%CI 0.81-1.47). When stratified by actually received treatment in individual subjects, the use of (hydroxy)chloroquine was associated with an increased 21-day mortality (HR 1.58; 95%CI 1.24-2.02) in the full model. Conclusions After adjustment for confounders, mortality was not significantly different in hospitals that routinely treated patients with (hydroxy)chloroquine, compared with hospitals that did not. We compared outcomes of hospital strategies rather than outcomes of individual patients to reduce the chance of indication bias. This study adds evidence against the use of (hydroxy)chloroquine in hospitalised patients with COVID-19.

Background The identification of risk factors for adverse outcomes and prolonged intensive care unit (ICU) stay in COVID-19 patients is essential for prognostication, determining treatment intensity, and resource allocation. Previous studies have determined risk factors on admission only, and included a limited number of predictors. Therefore, using data from the highly granular and multicenter Dutch Data Warehouse, we developed machine learning models to identify risk factors for ICU mortality, ventilator-free days and ICU-free days during the course of invasive mechanical ventilation (IMV) in COVID-19 patients. Methods The DDW is a growing electronic health record database of critically ill COVID-19 patients in the Netherlands. All adult ICU patients on IMV were eligible for inclusion. Transfers, patients admitted for less than 24 h, and patients still admitted at time of data extraction were excluded. Predictors were selected based on the literature, and included medication dosage and fluid balance. Multiple algorithms were trained and validated on up to three sets of observations per patient on day 1, 7, and 14 using fivefold nested cross-validation, keeping observations from an individual patient in the same split. Results A total of 1152 patients were included in the model. XGBoost models performed best for all outcomes and were used to calculate predictor importance. Using Shapley additive explanations (SHAP), age was the most important demographic risk factor for the outcomes upon start of IMV and throughout its course. The relative probability of death across age values is visualized in Partial Dependence Plots (PDPs), with an increase starting at 54 years. Besides age, acidaemia, low P/F-ratios and high driving pressures demonstrated a higher probability of death. The PDP for driving pressure showed a relative probability increase starting at 12 cmH2O. Conclusion Age is the most important demographic risk factor of ICU mortality, ICU-free days and ventilator-free days throughout the course of invasive mechanical ventilation in critically ill COVID-19 patients. pH, P/F ratio, and driving pressure should be monitored closely over the course of mechanical ventilation as risk factors predictive of these outcomes.

Supplemental Digital Content is available in the text.