Machine learning enabled detection of COVID-19 pneumonia using exhaled breath analysis: a proof-of-concept study.

Detection of the severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) relies on real-time-reverse-transcriptase polymerase chain reaction (RT-PCR) on nasopharyngeal swabs. The false-negative rate of RT-PCR can be high when viral burden and infection is localized distally in the lower airways and lung parenchyma. An alternate safe, simple and accessible method for sampling the lower airways is needed to aid in the early and rapid diagnosis of COVID-19 pneumonia. In a prospective unblinded observational study, patients admitted with a positive RT-PCR and symptoms of SARS-CoV-2 infection were enrolled from three hospitals in Ontario, Canada. Healthy individuals or hospitalized patients with negative RT-PCR and without respiratory symptoms were enrolled into the control group. Breath samples were collected and analyzed by laser absorption spectroscopy (LAS) for volatile organic compounds (VOCs) and classified by machine learning (ML) approaches to identify unique LAS-spectra patterns (breathprints) for SARS-CoV-2. Of the 135 patients enrolled, 115 patients provided analyzable breath samples. Using LAS-breathprints to train ML classifier models resulted in an accuracy of 72.2%-81.7% in differentiating between SARS-CoV2 positive and negative groups. The performance was consistent across subgroups of different age, sex, body mass index, SARS-CoV-2 variants, time of disease onset and oxygen requirement. The overall performance was higher than compared to VOC-trained classifier model, which had an accuracy of 63%-74.7%. This study demonstrates that a ML-based breathprint model using LAS analysis of exhaled breath may be a valuable non-invasive method for studying the lower airways and detecting SARS-CoV-2 and other respiratory pathogens. The technology and the ML approach can be easily deployed in any setting with minimal training. This will greatly improve access and scalability to meet surge capacity; allow early and rapid detection to inform therapy; and offers great versatility in developing new classifier models quickly for future outbreaks.

Hospitalised COVID-19 outcomes are predicted by hypoxaemia and pneumonia phenotype irrespective of the timing of their emergence.

Despite the known clinical importance of hypoxemia and pneumonia, there is a paucity of evidence for these variables with respect to risk of mortality and short-term outcomes among those hospitalised with COVID-19. OBJECTIVE: Describe the prevalence and clinical course of patients hospitalised with COVID-19 based on oxygenation and pneumonia status at presentation and determine the incidence of emergent hypoxaemia or radiographic pneumonia during admission. METHODS: A retrospective study was conducted using a Canadian regional registry. Patients were stratified according to hypoxaemia/pneumonia phenotype and prevalence. Clinical parameters were compared between phenotypes using χ2 and one-way Analysis of variance (ANOVA). Cox analysis estimated adjusted Hazard Ratios (HR) for associations between disease outcomes and phenotypes. RESULTS: At emergency department (ED) admission, the prevalence of pneumonia and hypoxaemia was 43% and 50%, respectively, and when stratified to phenotypes: 28.2% hypoxaemia+/pneumonia+, 22.2% hypoxaemia+/pneumonia-, 14.5% hypoxaemia-/pneumonia+ and 35.1% hypoxaemia-/pneumonia-. Mortality was 31.1% in the hypoxaemia+/pneumonia- group and 26.3% in the hypoxaemia+/pneumonia+ group. Hypoxaemia with pneumonia and without pneumonia predicted higher probability of death. Hypoxaemia either <24 hours or ≥24 hours after hospitalisation predicted higher mortality and need for home oxygen compared with those without hypoxaemia. Patients with early hypoxaemia had higher probability of Intensive care unit (ICU) admission compared with those with late hypoxaemia. CONCLUSION: Mortality in COVID-19 infection is predicted by hypoxaemia with or without pneumonia and was greatest in patients who initially presented with hypoxaemia. The emergence of hypoxaemia was predicted by radiographic pneumonia. Patients with early and emergent hypoxaemia had similar mortality but were less likely to be admitted to ICU. There may be delayed identification of hypoxaemia, which prevents timely escalation of care.

Functional recovery following hospitalisation of patients diagnosed with COVID-19: a protocol for a longitudinal cohort study.

INTRODUCTION: COVID-19 is an international public health crisis with more than 132 million infections worldwide. Beyond acute infection, emerging data indicate patients diagnosed with COVID-19 may experience persistent sequelae similar to survivors of sepsis or acute respiratory syndromes, including mobility limitations and fatigue. However, there is limited evidence on the trajectory of functional recovery in those hospitalised with COVID-19. The primary aim of the Coronavirus Registry Functional Recovery (COREG-FR) study is to understand the trajectory of functional recovery among individuals hospitalised for COVID-19 over the medium (up to 6 months) and longer term (6-12 months) that will guide clinical care and optimal management of serious COVID-19 illness and recovery. METHODS AND ANALYSIS: COREG-FR is a multicentre longitudinal cohort study. We will enrol a minimum of 211 adults age 18 years and older with COVID-19 from five hospitals. Participants will be followed from admission to hospital as an inpatient, to hospital discharge, and at 3-month, 6-month, 9-month and up to 12-month post-hospital discharge. We will conduct telephone interviews at ward admission and discharge, and telephone interviews plus in-person assessments of physical function and lung function at all remaining follow-ups. Our primary outcome is the Activity Measure for Post-Acute Care mobility scale measured at all time points. We will conduct linear mixed effects regression analyses to explore determinants of functional outcomes after COVID-19 illness. Subgroup analyses based on age (≤65 vs >65 years), frailty status (Clinical Frailty Scale score ≤4 vs >5) and variants of concern will be conducted. ETHICS AND DISSEMINATION: COREG-FR has been approved by Research Ethics Boards at participating sites. We will disseminate this work through peer-reviewed manuscripts, presentations at national and international meetings and through the established COREG website (www.coregontario.ca). COREG-FR is designed as a data platform for future studies evaluating COVID-19 recovery. TRIAL REGISTRATION NUMBER: NCT04602260; Pre-results.

White Paper on Early Critical Care Services in Low Resource Settings.

This White Paper has been formally accepted for support by the International Federation for Emergency Medicine (IFEM) and by the World Federation of Intensive and Critical Care (WFICC), put forth by a multi-specialty group of intensivists and emergency medicine providers from low- and low-middle-income countries (LMICs) and high-income countries (HiCs) with the aim of 1) defining the current state of caring for the critically ill in low-resource settings (LRS) within LMICs and 2) highlighting policy options and recommendations for improving the system-level delivery of early critical care services in LRS. LMICs have a high burden of critical illness and worse patient outcomes than HICs, hence, the focus of this White Paper is on the care of critically ill patients in the early stages of presentation in LMIC settings. In such settings, the provision of early critical care is challenged by a fragmented health system, costs, a health care workforce with limited training, and competing healthcare priorities. Early critical care services are defined as the early interventions that support vital organ function during the initial care provided to the critically ill patient-these interventions can be performed at any point of patient contact and can be delivered across diverse settings in the healthcare system and do not necessitate specialty personnel. Currently, a single "best" care delivery model likely does not exist in LMICs given the heterogeneity in local context; therefore, objective comparisons of quality, efficiency, and cost-effectiveness between varying models are difficult to establish. While limited, there is data to suggest that caring for the critically ill may be cost effective in LMICs, contrary to a widely held belief. Drawing from locally available resources and context, strengthening early critical care services in LRS will require a multi-faceted approach, including three core pillars: education, research, and policy. Education initiatives for physicians, nurses, and allied health staff that focus on protocolized emergency response training can bridge the workforce gap in the short-term; however, each country's current human resources must be evaluated to decide on the duration of training, who should be trained, and using what curriculum. Understanding the burden of critical Illness, best practices for resuscitation, and appropriate quality metrics for different early critical care services implementation models in LMICs are reliant upon strengthening the regional research capacity, therefore, standard documentation systems should be implemented to allow for registry use and quality improvement. Policy efforts at a local, national and international level to strengthen early critical care services should focus on funding the building blocks of early critical care services systems and promoting the right to access early critical care regardless of the patient's geographic or financial barriers. Additionally, national and local policies describing ethical dilemmas involving the withdrawal of life-sustaining care should be developed with broad stakeholder representation based on local cultural beliefs as well as the optimization of limited resources.

External validation of the 4C mortality score among COVID-19 patients admitted to hospital in Ontario, Canada: a retrospective study.

Risk prediction scores are important tools to support clinical decision-making for patients with coronavirus disease (COVID-19). The objective of this paper was to validate the 4C mortality score, originally developed in the United Kingdom, for a Canadian population, and to examine its performance over time. We conducted an external validation study within a registry of COVID-19 positive hospital admissions in the Kitchener-Waterloo and Hamilton regions of southern Ontario between March 4, 2020 and June 13, 2021. We examined the validity of the 4C score to prognosticate in-hospital mortality using the area under the receiver operating characteristic curve (AUC) with 95% confidence intervals calculated via bootstrapping. The study included 959 individuals, of whom 224 (23.4%) died in-hospital. Median age was 72 years and 524 individuals (55%) were male. The AUC of the 4C score was 0.77, 95% confidence interval 0.79-0.87. Overall mortality rates across the pre-defined risk groups were 0% (Low), 8.0% (Intermediate), 27.2% (High), and 54.2% (Very High). Wave 1, 2 and 3 values of the AUC were 0.81 (0.76, 0.86), 0.74 (0.69, 0.80), and 0.76 (0.69, 0.83) respectively. The 4C score is a valid tool to prognosticate mortality from COVID-19 in Canadian hospitals and can be used to prioritize care and resources for patients at greatest risk of death.

Incidence and Outcomes of Acute Kidney Injury in Patients Admitted to Hospital With COVID-19: A Retrospective Cohort Study.

BACKGROUND: The incidence of acute kidney injury (AKI) in patients with COVID-19 and its association with mortality and disease severity is understudied in the Canadian population. OBJECTIVE: To determine the incidence of AKI in a cohort of patients with COVID-19 admitted to medicine and intensive care unit (ICU) wards, its association with in-hospital mortality, and disease severity. Our aim was to stratify these outcomes by out-of-hospital AKI and in-hospital AKI. DESIGN: Retrospective cohort study from a registry of patients with COVID-19. SETTING: Three community and 3 academic hospitals. PATIENTS: A total of 815 patients admitted to hospital with COVID-19 between March 4, 2020, and April 23, 2021. MEASUREMENTS: Stage of AKI, ICU admission, mechanical ventilation, and in-hospital mortality. METHODS: We classified AKI by comparing highest to lowest recorded serum creatinine in hospital and staged AKI based on the Kidney Disease: Improving Global Outcomes (KDIGO) system. We calculated the unadjusted and adjusted odds ratio for the stage of AKI and the outcomes of ICU admission, mechanical ventilation, and in-hospital mortality. RESULTS: Of the 815 patients registered, 439 (53.9%) developed AKI, 253 (57.6%) presented with AKI, and 186 (42.4%) developed AKI in-hospital. The odds of ICU admission, mechanical ventilation, and death increased as the AKI stage worsened. Stage 3 AKI that occurred during hospitalization increased the odds of death (odds ratio [OR] = 7.87 [4.35, 14.23]). Stage 3 AKI that occurred prior to hospitalization carried an increased odds of death (OR = 5.28 [2.60, 10.73]). LIMITATIONS: Observational study with small sample size limits precision of estimates. Lack of nonhospitalized patients with COVID-19 and hospitalized patients without COVID-19 as controls limits causal inferences. CONCLUSIONS: Acute kidney injury, whether it occurs prior to or after hospitalization, is associated with a high risk of poor outcomes in patients with COVID-19. Routine assessment of kidney function in patients with COVID-19 may improve risk stratification. TRIAL REGISTRATION: The study was not registered on a publicly accessible registry because it did not involve any health care intervention on human participants.

Characteristics and outcomes of patients with COVID-19 admitted to hospital and intensive care in the first phase of the pandemic in Canada: a national cohort study.

BACKGROUND: Clinical data on patients admitted to hospital with coronavirus disease 2019 (COVID-19) provide clinicians and public health officials with information to guide practice and policy. The aims of this study were to describe patients with COVID-19 admitted to hospital and intensive care, and to investigate predictors of outcome to characterize severe acute respiratory infection. METHODS: This observational cohort study used Canadian data from 32 selected hospitals included in a global multisite cohort between Jan. 24 and July 7, 2020. Adult and pediatric patients with a confirmed diagnosis of COVID-19 who received care in an intensive care unit (ICU) and a sampling of up to the first 60 patients receiving care on hospital wards were included. We performed descriptive analyses of characteristics, interventions and outcomes. The primary analyses examined in-hospital mortality, with secondary analyses of the length of hospital and ICU stay. RESULTS: Between January and July 2020, among 811 patients admitted to hospital with a diagnosis of COVID-19, the median age was 64 (interquartile range [IQR] 53-75) years, 495 (61.0%) were men, 46 (5.7%) were health care workers, 9 (1.1%) were pregnant, 26 (3.2%) were younger than 18 years and 9 (1.1%) were younger than 5 years. The median time from symptom onset to hospital admission was 7 (IQR 3-10) days. The most common symptoms on admission were fever, shortness of breath, cough and malaise. Diabetes, hypertension and cardiac, kidney and respiratory disease were the most common comorbidities. Among all patients, 328 received care in an ICU, admitted a median of 0 (IQR 0-1) days after hospital admission. Critically ill patients received treatment with invasive mechanical ventilation (88.8%), renal replacement therapy (14.9%) and extracorporeal membrane oxygenation (4.0%); 26.2% died. Among those receiving mechanical ventilation, 31.2% died. Age was an influential predictor of mortality (odds ratio per additional year of life 1.06, 95% confidence interval 1.03-1.09). INTERPRETATION: Patients admitted to hospital with COVID-19 commonly had fever, respiratory symptoms and comorbid conditions. Increasing age was associated with the development of critical illness and death; however, most critically ill patients in Canada, including those requiring mechanical ventilation, survived and were discharged from hospital.

Inflammatory biomarkers as independent prognosticators of 28-day mortality for COVID-19 patients admitted to general medicine or ICU wards: a retrospective cohort study.

Inflammatory biomarkers may be associated with disease severity and increased mortality in COVID-19 patients but have not been studied in North American populations. We sought to determine whether a set of commonly ordered inflammatory biomarkers can predict 28-day mortality. We analyzed a multi-centered (four) COVID-19 registry cohort from March 4th to December 7th, 2020. This cohort included COVID-19-positive patients admitted to medical wards or intensive care units. Patients presenting to the emergency department for COVID-19 symptoms and then subsequently discharged were also included. We performed Cox-regression analysis to measure whether commonly used biomarkers were associated with an increased 28-day mortality. Of 336 COVID-19-positive patients, 267 required hospital admission, and 69 were seen in the emergency room and discharged. The median age was 63 years (IQR 80-50) and the female-to-male ratio was 49:51. Derivation of internally validated cut-offs suggested that C-reactive protein ≥ 78.4 mg/L, neutrophil-to-lymphocyte ratio ≥ 6.1, lymphocyte-to-white blood cell ratio < 0.127, and a modified Glasgow prognostic score equal to 2 vs. 1 or 0 were associated with the highest increased risk of 28-day mortality. We provide early estimates of cut-off values for inflammatory biomarkers and indices measured at the time of admission that may be useful to clinicians for predicting 28-day mortality in North American COVID-19 patients.

Feasibility of the modified sequential organ function assessment score in a resource-constrained setting: a prospective observational study.

BACKGROUND: Sub-Saharan Africa has a great burden of critical illness with limited health care resources. We evaluated the feasibility and utility of the modified Sequential Organ Function Assessment (mSOFA) score in assessing morbidity and mortality in the National Referral Hospital's intensive care unit (ICU) for one year. METHODS: We conducted a prospective, observational cohort study on patients above 12 years of age admitted to the ICU at Mulago Hospital (Kampala, Uganda). All SOFA scores were determined at admission and at 48 h. We modified the SOFA score by replacing the PaO2/FiO2 ratio with SPO2/FiO2. The primary outcome was ICU mortality. RESULTS: This ICU cohort of 118 patients had a mean age of 37 years and an ICU mortality rate of 46.6%. Non-survivors had higher initial (7.7 SD 3.8 vs. 5.5 SD 3.3; p = 0.007), mean (8.1 SD 3.9 vs 4.7 SD 2.6; p < 0.001) and highest mSOFA scores (9.4 SD 4.2 vs. 5.8 SD 3.2; p < 0.001), with an increase of 1.0 (SD 3.1) mSOFA on average after 48 h when compared to survivors (p < 0.001). The area under the receiver operating characteristic curves for each mSOFA category was: initial-0.68, mean-0.76, highest-0.76 and delta mSOFA-0.74. Multivariate logistic regression analysis showed no significant association between mSOFA scores and mortality. CONCLUSION: Our results confirm that calculation of the mSOFA score is feasible for an ICU population in a resource-limited country. More data are needed to test for an association between mSOFA and mortality.

Modified Early Warning Score (MEWS) Identifies Critical Illness among Ward Patients in a Resource Restricted Setting in Kampala, Uganda: A Prospective Observational Study.

INTRODUCTION: Providing optimal critical care in developing countries is limited by lack of recognition of critical illness and lack of essential resources. The Modified Early Warning Score (MEWS), based on physiological parameters, is validated in adult medical and surgical patients as a predictor of mortality. The objective of this study performed in Uganda was to determine the prevalence of critical illness on the wards as defined by the MEWS, to evaluate the MEWS as a predictor of death, and to describe additional risk factors for mortality. METHODS: We conducted a prospective observational study at Mulago National Referral Teaching Hospital in Uganda. We included medical and surgical ward patients over 18 years old, excluding patients discharged the day of enrolment, obstetrical patients, and patients who self-discharged prior to study completion. Over a 72-hour study period, we collected demographic and vital signs, and calculated MEWS; at 7-days we measured outcomes. Patients discharged prior to 7 days were assumed to be alive at study completion. Descriptive and inferential statistical analyses were performed. RESULTS: Of 452 patients, the median age was 40.5 (IQR 29-54) years, 53.3% were male, 24.3% were HIV positive, and 45.1% had medical diagnoses. MEWS ranged from 0 to 9, with higher scores representing hemodynamic instability. The median MEWS was 2 [IQR 1-3] and the median length of hospital stay was 9 days [IQR 4-24]. In-hospital mortality at 7-days was 5.5%; 41.4% of patients were discharged and 53.1% remained on the ward. Mortality was independently associated with medical admission (OR: 7.17; 95% CI: 2.064-24.930; p = 0.002) and the MEWS ≥ 5 (OR: 5.82; 95% CI: 2.420-13.987; p<0.0001) in the multivariable analysis. CONCLUSION: There is a significant burden of critical illness at Mulago Hospital, Uganda. Implementation of the MEWS could provide a useful triage tool to identify patients at greatest risk of death. Future research should include refinement of MEWS for low-resource settings, and development of appropriate interventions for patients identified to be at high risk of death based on early warning scores.