Utilization of Palliative Care for Patients with COVID-19 and Acute Kidney Injury during a COVID-19 Surge.

BACKGROUND AND OBJECTIVES: AKI is a common complication of coronavirus disease 2019 (COVID-19) and is associated with high mortality. Palliative care, a specialty that supports patients with serious illness, is valuable for these patients but is historically underutilized in AKI. The objectives of this paper are to describe the use of palliative care in patients with AKI and COVID-19 and their subsequent health care utilization. DESIGN, SETTING, PARTICIPANTS, & MEASUREMENTS: We conducted a retrospective analysis of New York University Langone Health electronic health data of COVID-19 hospitalizations between March 2, 2020 and August 25, 2020. Regression models were used to examine characteristics associated with receiving a palliative care consult. RESULTS: Among patients with COVID-19 (n=4276; 40%), those with AKI (n=1310; 31%) were more likely than those without AKI (n=2966; 69%) to receive palliative care (AKI without KRT: adjusted odds ratio, 1.81; 95% confidence interval, 1.40 to 2.33; P<0.001; AKI with KRT: adjusted odds ratio, 2.45; 95% confidence interval, 1.52 to 3.97; P<0.001), even after controlling for markers of critical illness (admission to intensive care units, mechanical ventilation, or modified sequential organ failure assessment score); however, consults came significantly later (10 days from admission versus 5 days; P<0.001). Similarly, 66% of patients initiated on KRT received palliative care versus 37% (P<0.001) of those with AKI not receiving KRT, and timing was also later (12 days from admission versus 9 days; P=0.002). Despite greater use of palliative care, patients with AKI had a significantly longer length of stay, more intensive care unit admissions, and more use of mechanical ventilation. Those with AKI did have a higher frequency of discharges to inpatient hospice (6% versus 3%) and change in code status (34% versus 7%) than those without AKI. CONCLUSIONS: Palliative care was utilized more frequently for patients with AKI and COVID-19 than historically reported in AKI. Despite high mortality, consultation occurred late in the hospital course and was not associated with reduced initiation of life-sustaining interventions. PODCAST: This article contains a podcast at https://www.asn-online.org/media/podcast/CJASN/2022_02_24_CJN11030821.mp3.

Trends and Risk Factors of In-Hospital Mortality of Patients with COVID-19 in Germany: Results of a Large Nationwide Inpatient Sample.

Unselected data of nationwide studies of hospitalized patients with COVID-19 are still sparse, but these data are of outstanding interest to avoid exceeding hospital capacities and overloading national healthcare systems. Thus, we sought to analyze seasonal/regional trends, predictors of in-hospital case-fatality, and mechanical ventilation (MV) in patients with COVID-19 in Germany. We used the German nationwide inpatient samples to analyze all hospitalized patients with a confirmed COVID-19 diagnosis in Germany between 1 January and 31 December in 2020. We analyzed data of 176,137 hospitalizations of patients with confirmed COVID-19-infection. Among those, 31,607 (17.9%) died, whereby in-hospital case-fatality grew exponentially with age. Overall, age ≥ 70 years (OR 5.91, 95%CI 5.70-6.13, p < 0.001), pneumonia (OR 4.58, 95%CI 4.42-4.74, p < 0.001) and acute respiratory distress syndrome (OR 8.51, 95%CI 8.12-8.92, p < 0.001) were strong predictors of in-hospital death. Most COVID-19 patients were treated in hospitals in urban areas (n = 92,971) associated with the lowest case-fatality (17.5%), as compared to hospitals in suburban (18.3%) or rural areas (18.8%). MV demand was highest in November/December 2020 (32.3%, 20.3%) in patients between the 6th and 8th age decade. In the first age decade, 78 of 1861 children (4.2%) with COVID-19-infection were treated with MV, and five of them died (0.3%). The results of our study indicate seasonal and regional variations concerning the number of COVID-19 patients, necessity of MV, and case fatality in Germany. These findings may help to ensure the flexible allocation of intensive care (human) resources, which is essential for managing enormous societal challenges worldwide to avoid overloaded regional healthcare systems.

Clinical Trends Among U.S. Adults Hospitalized With COVID-19, March to December 2020 : A Cross-Sectional Study.

BACKGROUND: The COVID-19 pandemic has caused substantial morbidity and mortality. OBJECTIVE: To describe monthly clinical trends among adults hospitalized with COVID-19. DESIGN: Pooled cross-sectional study. SETTING: 99 counties in 14 states participating in the Coronavirus Disease 2019-Associated Hospitalization Surveillance Network (COVID-NET). PATIENTS: U.S. adults (aged ≥18 years) hospitalized with laboratory-confirmed COVID-19 during 1 March to 31 December 2020. MEASUREMENTS: Monthly hospitalizations, intensive care unit (ICU) admissions, and in-hospital death rates per 100 000 persons in the population; monthly trends in weighted percentages of interventions, including ICU admission, mechanical ventilation, and vasopressor use, among an age- and site-stratified random sample of hospitalized case patients. RESULTS: Among 116 743 hospitalized adults with COVID-19, the median age was 62 years, 50.7% were male, and 40.8% were non-Hispanic White. Monthly rates of hospitalization (105.3 per 100 000 persons), ICU admission (20.2 per 100 000 persons), and death (11.7 per 100 000 persons) peaked during December 2020. Rates of all 3 outcomes were highest among adults aged 65 years or older, males, and Hispanic or non-Hispanic Black persons. Among 18 508 sampled hospitalized adults, use of remdesivir and systemic corticosteroids increased from 1.7% and 18.9%, respectively, in March to 53.8% and 74.2%, respectively, in December. Frequency of ICU admission, mechanical ventilation, and vasopressor use decreased from March (37.8%, 27.8%, and 22.7%, respectively) to December (20.5%, 12.3%, and 12.8%, respectively); use of noninvasive respiratory support increased from March to December. LIMITATION: COVID-NET covers approximately 10% of the U.S. population; findings may not be generalizable to the entire country. CONCLUSION: Rates of COVID-19-associated hospitalization, ICU admission, and death were highest in December 2020, corresponding with the third peak of the U.S. pandemic. The frequency of intensive interventions for management of hospitalized patients decreased over time. These data provide a longitudinal assessment of clinical trends among adults hospitalized with COVID-19 before widespread implementation of COVID-19 vaccines. PRIMARY FUNDING SOURCE: Centers for Disease Control and Prevention.

Using machine learning for predicting intensive care unit resource use during the COVID-19 pandemic in Denmark.

The COVID-19 pandemic has put massive strains on hospitals, and tools to guide hospital planners in resource allocation during the ebbs and flows of the pandemic are urgently needed. We investigate whether machine learning (ML) can be used for predictions of intensive care requirements a fixed number of days into the future. Retrospective design where health Records from 42,526 SARS-CoV-2 positive patients in Denmark was extracted. Random Forest (RF) models were trained to predict risk of ICU admission and use of mechanical ventilation after n days (n = 1, 2, …, 15). An extended analysis was provided for n = 5 and n = 10. Models predicted n-day risk of ICU admission with an area under the receiver operator characteristic curve (ROC-AUC) between 0.981 and 0.995, and n-day risk of use of ventilation with an ROC-AUC between 0.982 and 0.997. The corresponding n-day forecasting models predicted the needed ICU capacity with a coefficient of determination (R2) between 0.334 and 0.989 and use of ventilation with an R2 between 0.446 and 0.973. The forecasting models performed worst, when forecasting many days into the future (for large n). For n = 5, ICU capacity was predicted with ROC-AUC 0.990 and R2 0.928, and use of ventilator was predicted with ROC-AUC 0.994 and R2 0.854. Random Forest-based modelling can be used for accurate n-day forecasting predictions of ICU resource requirements, when n is not too large.

The evolution of the ventilatory ratio is a prognostic factor in mechanically ventilated COVID-19 ARDS patients.

BACKGROUND: Mortality due to COVID-19 is high, especially in patients requiring mechanical ventilation. The purpose of the study is to investigate associations between mortality and variables measured during the first three days of mechanical ventilation in patients with COVID-19 intubated at ICU admission. METHODS: Multicenter, observational, cohort study includes consecutive patients with COVID-19 admitted to 44 Spanish ICUs between February 25 and July 31, 2020, who required intubation at ICU admission and mechanical ventilation for more than three days. We collected demographic and clinical data prior to admission; information about clinical evolution at days 1 and 3 of mechanical ventilation; and outcomes. RESULTS: Of the 2,095 patients with COVID-19 admitted to the ICU, 1,118 (53.3%) were intubated at day 1 and remained under mechanical ventilation at day three. From days 1 to 3, PaO2/FiO2 increased from 115.6 [80.0-171.2] to 180.0 [135.4-227.9] mmHg and the ventilatory ratio from 1.73 [1.33-2.25] to 1.96 [1.61-2.40]. In-hospital mortality was 38.7%. A higher increase between ICU admission and day 3 in the ventilatory ratio (OR 1.04 [CI 1.01-1.07], p = 0.030) and creatinine levels (OR 1.05 [CI 1.01-1.09], p = 0.005) and a lower increase in platelet counts (OR 0.96 [CI 0.93-1.00], p = 0.037) were independently associated with a higher risk of death. No association between mortality and the PaO2/FiO2 variation was observed (OR 0.99 [CI 0.95 to 1.02], p = 0.47). CONCLUSIONS: Higher ventilatory ratio and its increase at day 3 is associated with mortality in patients with COVID-19 receiving mechanical ventilation at ICU admission. No association was found in the PaO2/FiO2 variation.

Association of intensity of ventilation with 28-day mortality in COVID-19 patients with acute respiratory failure: insights from the PRoVENT-COVID study.

BACKGROUND: The intensity of ventilation, reflected by driving pressure (ΔP) and mechanical power (MP), has an association with outcome in invasively ventilated patients with or without acute respiratory distress syndrome (ARDS). It is uncertain if a similar association exists in coronavirus disease 2019 (COVID-19) patients with acute respiratory failure. METHODS: We aimed to investigate the impact of intensity of ventilation on patient outcome. The PRoVENT-COVID study is a national multicenter observational study in COVID-19 patients receiving invasive ventilation. Ventilator parameters were collected a fixed time points on the first calendar day of invasive ventilation. Mean dynamic ΔP and MP were calculated for individual patients at time points without evidence of spontaneous breathing. A Cox proportional hazard model, and a double stratification analysis adjusted for confounders were used to estimate the independent associations of ΔP and MP with outcome. The primary endpoint was 28-day mortality. RESULTS: In 825 patients included in this analysis, 28-day mortality was 27.5%. ΔP was not independently associated with mortality (HR 1.02 [95% confidence interval 0.88-1.18]; P = 0.750). MP, however, was independently associated with 28-day mortality (HR 1.17 [95% CI 1.01-1.36]; P = 0.031), and increasing quartiles of MP, stratified on comparable levels of ΔP, had higher risks of 28-day mortality (HR 1.15 [95% CI 1.01-1.30]; P = 0.028). CONCLUSIONS: In this cohort of critically ill invasively ventilated COVID-19 patients with acute respiratory failure, we show an independent association of MP, but not ΔP with 28-day mortality. MP could serve as one prognostic biomarker in addition to ΔP in these patients. Efforts aiming at limiting both ΔP and MP could translate in a better outcome. Trial registration Clinicaltrials.gov (study identifier NCT04346342).

Convalescent plasma for COVID-19: a meta-analysis, trial sequential analysis, and meta-regression.

BACKGROUND: Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)-specific antibodies, particularly those preventing interaction between the viral spike receptor-binding domain and the host angiotensin-converting enzyme 2 receptor, may prevent viral entry into host cells and disease progression. METHODS: We performed a systematic review, meta-analysis, trial sequential analysis (TSA), and meta-regression of RCTs to evaluate the benefit of convalescent plasma for COVID-19. The primary outcome was 28-30 day mortality. Secondary outcomes included need for mechanical ventilation and ICU admission. Data sources were PubMed, Embase, MedRxiv, and the Cochrane library on July 2, 2021. RESULTS: We identified 17 RCTs that recruited 15 587 patients with 8027 (51.5%) allocated to receive convalescent plasma. Convalescent plasma use was not associated with a mortality benefit (24.7% vs 25.5%; odds ratio [OR]=0.94 [0.85-1.04]; P=0.23; I2=4%; TSA adjusted confidence interval [CI], 0.84-1.05), or reduction in need for mechanical ventilation (15.7% vs 15.4%; OR=1.01 [0.92-1.11]; P=0.82; I2=0%; TSA adjusted CI, 0.91-1.13), or ICU admission (22.4% vs 16.7%; OR=0.80 [0.21-3.09]; P=0.75; I2=63%; TSA adjusted CI, 0.0-196.05). Meta-regression did not reveal association with titre of convalescent plasma, timing of administration, or risk of death and treatment effect (P>0.05). Risk of bias was high in most studies. CONCLUSIONS: In patients with COVID-19, there was no clear mortality benefit associated with convalescent plasma treatment. In patients with mild disease, convalescent plasma did not prevent either the need for mechanical ventilation or ICU admission. CLINICAL TRIAL REGISTRATION: CRD42021234201 (PROSPERO).

Effect of prone positioning on oxygenation and static respiratory system compliance in COVID-19 ARDS vs. non-COVID ARDS.

BACKGROUND: Prone positioning is recommended for patients with moderate-to-severe acute respiratory distress syndrome (ARDS) receiving mechanical ventilation. While the debate continues as to whether COVID-19 ARDS is clinically different from non-COVID ARDS, there is little data on whether the physiological effects of prone positioning differ between the two conditions. We aimed to compare the physiological effect of prone positioning between patients with COVID-19 ARDS and those with non-COVID ARDS. METHODS: We retrospectively compared 23 patients with COVID-19 ARDS and 145 patients with non-COVID ARDS treated using prone positioning while on mechanical ventilation. Changes in PaO2/FiO2 ratio and static respiratory system compliance (Crs) after the first session of prone positioning were compared between the two groups: first, using all patients with non-COVID ARDS, and second, using subgroups of patients with non-COVID ARDS matched 1:1 with patients with COVID-19 ARDS for baseline PaO2/FiO2 ratio and static Crs. We also evaluated whether the response to the first prone positioning session was associated with the clinical outcome. RESULTS: When compared with the entire group of patients with non-COVID ARDS, patients with COVID-19 ARDS showed more pronounced improvement in PaO2/FiO2 ratio [adjusted difference 39.3 (95% CI 5.2-73.5) mmHg] and static Crs [adjusted difference 3.4 (95% CI 1.1-5.6) mL/cmH2O]. However, these between-group differences were not significant when the matched samples (either PaO2/FiO2-matched or compliance-matched) were analyzed. Patients who successfully discontinued mechanical ventilation showed more remarkable improvement in PaO2/FiO2 ratio [median 112 (IQR 85-144) vs. 35 (IQR 6-52) mmHg, P = 0.003] and static compliance [median 5.7 (IQR 3.3-7.7) vs. - 1.0 (IQR - 3.7-3.0) mL/cmH2O, P = 0.006] after prone positioning compared with patients who did not. The association between oxygenation and Crs responses to prone positioning and clinical outcome was also evident in the adjusted competing risk regression. CONCLUSIONS: In patients with COVID-19 ARDS, prone positioning was as effective in improving respiratory physiology as in patients with non-COVID ARDS. Thus, it should be actively considered as a therapeutic option. The physiological response to the first session of prone positioning was predictive of the clinical outcome of patients with COVID-19 ARDS.

Personalized mechanical ventilation in acute respiratory distress syndrome.

A personalized mechanical ventilation approach for patients with adult respiratory distress syndrome (ARDS) based on lung physiology and morphology, ARDS etiology, lung imaging, and biological phenotypes may improve ventilation practice and outcome. However, additional research is warranted before personalized mechanical ventilation strategies can be applied at the bedside. Ventilatory parameters should be titrated based on close monitoring of targeted physiologic variables and individualized goals. Although low tidal volume (VT) is a standard of care, further individualization of VT may necessitate the evaluation of lung volume reserve (e.g., inspiratory capacity). Low driving pressures provide a target for clinicians to adjust VT and possibly to optimize positive end-expiratory pressure (PEEP), while maintaining plateau pressures below safety thresholds. Esophageal pressure monitoring allows estimation of transpulmonary pressure, but its use requires technical skill and correct physiologic interpretation for clinical application at the bedside. Mechanical power considers ventilatory parameters as a whole in the optimization of ventilation setting, but further studies are necessary to assess its clinical relevance. The identification of recruitability in patients with ARDS is essential to titrate and individualize PEEP. To define gas-exchange targets for individual patients, clinicians should consider issues related to oxygen transport and dead space. In this review, we discuss the rationale for personalized approaches to mechanical ventilation for patients with ARDS, the role of lung imaging, phenotype identification, physiologically based individualized approaches to ventilation, and a future research agenda.

Efficacy and safety of inhaled nitric oxide in the treatment of severe/critical COVID-19 patients: A systematic review.

OBJECTIVE: Present systematic review aimed to analyze the effect of inhaled nitric oxide (iNO) in the treatment of severe COVID-19 and to compare it to standard of care (SOC), antiviral medications, and other medicines. MATERIALS AND METHODS: Medline (PubMed), Scopus, Embase, Ovid, Web of Science, Science Direct, Wiley Online Library, BioRxiv and MedRxiv, and Cochrane (up to April 20, 2021) were the search databases. Two reviewers (SK and CK) independently selected the electronic published literature that studied the effect of nitric oxide with SOC or control. The clinical and physiological outcomes such as prevention of progressive systemic de-oxygenation/clinical improvement, mortality, duration of mechanical ventilation, improvement in pulmonary arterial pressure, and adverse events were assessed. RESULTS: The 14 retrospective/protective studies randomly assigning 423 patients met the inclusion criteria. Cumulative study of the selected articles showed that iNO has a mild impact on ventilation time or ventilator-free days. iNO has increased the partial pressure of oxygen/fraction of inspired oxygen ratio of fraction of inspired oxygen in a few patients as compared to baseline. However, in most of the studies, it does not have better outcome when compared to the baseline improvement. CONCLUSIONS: In patients with COVID-19 with acute respiratory distress syndrome, nitric oxide is linked to a slight increase in oxygenation but has no effect on mortality.

Guillain-Barré Syndrome following ChAdOx1-S/nCoV-19 Vaccine.

As of April 22, 2021, around 1.5 million individuals in three districts of Kerala, India had been vaccinated with COVID-19 vaccines. Over 80% of these individuals (1.2 million) received the ChAdOx1-S/nCoV-19 vaccine. In this population, during this period of 4 weeks (mid-March to mid-April 2021), we observed seven cases of Guillain-Barre syndrome (GBS) that occurred within 2 weeks of the first dose of vaccination. All seven patients developed severe GBS. The frequency of GBS was 1.4- to 10-fold higher than that expected in this period for a population of this magnitude. In addition, the frequency of bilateral facial weakness, which typically occurs in <20% of GBS cases, suggests a pattern associated with the vaccination. While the benefits of vaccination substantially outweigh the risk of this relatively rare outcome (5.8 per million), clinicians should be alert to this possible adverse event, as six out of seven patients progressed to areflexic quadriplegia and required mechanical ventilatory support. ANN NEUROL 2021;90:312-314.

Effects of COVID-19 on in-hospital cardiac arrest: incidence, causes, and outcome - a retrospective cohort study.

BACKGROUND: Severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2), an emerging virus, has caused a global pandemic. Coronavirus disease 2019 (COVID-19), caused by SARS-CoV-2, has led to high hospitalization rates worldwide. Little is known about the occurrence of in-hospital cardiac arrest (IHCA) and high mortality rates have been proposed. The aim of this study was to investigate the incidence, characteristics and outcome of IHCA during the pandemic in comparison to an earlier period. METHODS: This was a retrospective analysis of data prospectively recorded during 3-month-periods 2019 and 2020 at the University Medical Centre Hamburg-Eppendorf (Germany). All consecutive adult patients with IHCA were included. Clinical parameters, neurological outcomes and organ failure/support were assessed. RESULTS: During the study period hospital admissions declined from 18,262 (2019) to 13,994 (2020) (- 23%). The IHCA incidence increased from 4.6 (2019: 84 IHCA cases) to 6.6 (2020: 93 IHCA cases)/1000 hospital admissions. Median stay before IHCA was 4 (1-9) days. Demographic characteristics were comparable in both periods. IHCA location shifted towards the ICU (56% vs 37%, p < 0.01); shockable rhythm (VT/VF) (18% vs 29%, p = 0.05) and defibrillation were more frequent in the pandemic period (20% vs 35%, p < 0.05). Resuscitation times, rates of ROSC and post-CA characteristics were comparable in both periods. The severity of illness (SAPS II/SOFA), frequency of mechanical ventilation and frequency of vasopressor therapy after IHCA were higher during the 2020 period. Overall, 43 patients (12 with & 31 without COVID-19), presented with respiratory failure at the time of IHCA. The Horowitz index and resuscitation time were significantly lower in patients with COVID-19 (each p < 0.01). Favourable outcomes were observed in 42 and 10% of patients with and without COVID-19-related respiratory failure, respectively. CONCLUSION: Hospital admissions declined during the pandemic, but a higher incidence of IHCA was observed. IHCA in patients with COVID-19 was a common finding. Compared to patients with non-COVID-19-related respiratory failure, the outcome was improved.

Preexisting respiratory diseases and clinical outcomes in COVID-19: a multihospital cohort study on predominantly African American population.

BACKGROUND: Comorbidities play a key role in severe disease outcomes in COVID-19 patients. However, the literature on preexisting respiratory diseases and COVID-19, accounting for other possible confounders, is limited. The primary objective of this study was to determine the association between preexisting respiratory diseases and severe disease outcomes among COVID-19 patients. Secondary aim was to investigate any correlation between smoking and clinical outcomes in COVID-19 patients. METHODS:  This is a multihospital retrospective cohort study on 1871 adult patients between March 10, 2020, and June 30, 2020, with laboratory confirmed COVID-19 diagnosis. The main outcomes of the study were severe disease outcomes i.e. mortality, need for mechanical ventilation, and intensive care unit (ICU) admission. During statistical analysis, possible confounders such as age, sex, race, BMI, and comorbidities including, hypertension, coronary artery disease, congestive heart failure, diabetes, any history of cancer and prior liver disease, chronic kidney disease, end-stage renal disease on dialysis, hyperlipidemia and history of prior stroke, were accounted for. RESULTS:  A total of 1871 patients (mean (SD) age, 64.11 (16) years; 965(51.6%) males; 1494 (79.9%) African Americans; 809 (43.2%) with ≥ 3 comorbidities) were included in the study. During their stay at the hospital, 613 patients (32.8%) died, 489 (26.1%) needed mechanical ventilation, and 592 (31.6%) required ICU admission. In fully adjusted models, patients with preexisting respiratory diseases had significantly higher mortality (adjusted Odds ratio (aOR), 1.36; 95% CI, 1.08-1.72; p = 0.01), higher rate of ICU admission (aOR, 1.34; 95% CI, 1.07-1.68; p = 0.009) and increased need for mechanical ventilation (aOR, 1.36; 95% CI, 1.07-1.72; p = 0.01). Additionally, patients with a history of smoking had significantly higher need for ICU admission (aOR, 1.25; 95% CI, 1.01-1.55; p = 0.03) in fully adjusted models. CONCLUSION:  Preexisting respiratory diseases are an important predictor for mortality and severe disease outcomes, in COVID-19 patients. These results can help facilitate efficient resource allocation for critical care services.

COVID-19-associated acute respiratory distress syndrome (CARDS): Current knowledge on pathophysiology and ICU treatment - A narrative review.

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) induces coronavirus-19 disease (COVID-19) and is a major health concern. Following two SARS-CoV-2 pandemic "waves," intensive care unit (ICU) specialists are treating a large number of COVID19-associated acute respiratory distress syndrome (ARDS) patients. From a pathophysiological perspective, prominent mechanisms of COVID19-associated ARDS (CARDS) include severe pulmonary infiltration/edema and inflammation leading to impaired alveolar homeostasis, alteration of pulmonary physiology resulting in pulmonary fibrosis, endothelial inflammation (endotheliitis), vascular thrombosis, and immune cell activation. Although the syndrome ARDS serves as an umbrella term, distinct, i.e., CARDS-specific pathomechanisms and comorbidities can be noted (e.g., virus-induced endotheliitis associated with thromboembolism) and some aspects of CARDS can be considered ARDS "atypical." Importantly, specific evidence-based medical interventions for CARDS (with the potential exception of corticosteroid use) are currently unavailable, limiting treatment efforts to mostly supportive ICU care. In this article, we will discuss the underlying pulmonary pathophysiology and the clinical management of CARDS. In addition, we will outline current and potential future treatment approaches.

Clinically applicable approach for predicting mechanical ventilation in patients with COVID-19.

BACKGROUND: Patients with coronavirus disease 2019 (COVID-19) requiring mechanical ventilation have high mortality and resource utilisation. The ability to predict which patients may require mechanical ventilation allows increased acuity of care and targeted interventions to potentially mitigate deterioration. METHODS: We included hospitalised patients with COVID-19 in this single-centre retrospective observational study. Our primary outcome was mechanical ventilation or death within 24 h. As clinical decompensation is more recognisable, but less modifiable, as the prediction window shrinks, we also assessed 4, 8, and 48 h prediction windows. Model features included demographic information, laboratory results, comorbidities, medication administration, and vital signs. We created a Random Forest model, and assessed performance using 10-fold cross-validation. The model was compared with models derived from generalised estimating equations using discrimination. RESULTS: Ninety-three (23%) of 398 patients required mechanical ventilation or died within 14 days of admission. The Random Forest model predicted pending mechanical ventilation with good discrimination (C-statistic=0.858; 95% confidence interval, 0.841-0.874), which is comparable with the discrimination of the generalised estimating equation regression. Vitals sign data including SpO2/FiO2 ratio (Random Forest Feature Importance Z-score=8.56), ventilatory frequency (5.97), and heart rate (5.87) had the highest predictive utility. In our highest-risk cohort, the number of patients needed to identify a single new case was 3.2, and for our second quintile it was 5.0. CONCLUSION: Machine learning techniques can be leveraged to improve the ability to predict which patients with COVID-19 are likely to require mechanical ventilation, identifying unrecognised bellwethers and providing insight into the constellation of accompanying signs of respiratory failure in COVID-19.