A 12-hospital prospective evaluation of a clinical decision support prognostic algorithm based on logistic regression as a form of machine learning to facilitate decision making for patients with suspected COVID-19.

OBJECTIVE: To prospectively evaluate a logistic regression-based machine learning (ML) prognostic algorithm implemented in real-time as a clinical decision support (CDS) system for symptomatic persons under investigation (PUI) for Coronavirus disease 2019 (COVID-19) in the emergency department (ED). METHODS: We developed in a 12-hospital system a model using training and validation followed by a real-time assessment. The LASSO guided feature selection included demographics, comorbidities, home medications, vital signs. We constructed a logistic regression-based ML algorithm to predict "severe" COVID-19, defined as patients requiring intensive care unit (ICU) admission, invasive mechanical ventilation, or died in or out-of-hospital. Training data included 1,469 adult patients who tested positive for Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) within 14 days of acute care. We performed: 1) temporal validation in 414 SARS-CoV-2 positive patients, 2) validation in a PUI set of 13,271 patients with symptomatic SARS-CoV-2 test during an acute care visit, and 3) real-time validation in 2,174 ED patients with PUI test or positive SARS-CoV-2 result. Subgroup analysis was conducted across race and gender to ensure equity in performance. RESULTS: The algorithm performed well on pre-implementation validations for predicting COVID-19 severity: 1) the temporal validation had an area under the receiver operating characteristic (AUROC) of 0.87 (95%-CI: 0.83, 0.91); 2) validation in the PUI population had an AUROC of 0.82 (95%-CI: 0.81, 0.83). The ED CDS system performed well in real-time with an AUROC of 0.85 (95%-CI, 0.83, 0.87). Zero patients in the lowest quintile developed "severe" COVID-19. Patients in the highest quintile developed "severe" COVID-19 in 33.2% of cases. The models performed without significant differences between genders and among race/ethnicities (all p-values > 0.05). CONCLUSION: A logistic regression model-based ML-enabled CDS can be developed, validated, and implemented with high performance across multiple hospitals while being equitable and maintaining performance in real-time validation.

Characterizing COVID-19 clinical phenotypes and associated comorbidities and complication profiles.

PURPOSE: Heterogeneity has been observed in outcomes of hospitalized patients with coronavirus disease 2019 (COVID-19). Identification of clinical phenotypes may facilitate tailored therapy and improve outcomes. The purpose of this study is to identify specific clinical phenotypes across COVID-19 patients and compare admission characteristics and outcomes. METHODS: This is a retrospective analysis of COVID-19 patients from March 7, 2020 to August 25, 2020 at 14 U.S. hospitals. Ensemble clustering was performed on 33 variables collected within 72 hours of admission. Principal component analysis was performed to visualize variable contributions to clustering. Multinomial regression models were fit to compare patient comorbidities across phenotypes. Multivariable models were fit to estimate associations between phenotype and in-hospital complications and clinical outcomes. RESULTS: The database included 1,022 hospitalized patients with COVID-19. Three clinical phenotypes were identified (I, II, III), with 236 [23.1%] patients in phenotype I, 613 [60%] patients in phenotype II, and 173 [16.9%] patients in phenotype III. Patients with respiratory comorbidities were most commonly phenotype III (p = 0.002), while patients with hematologic, renal, and cardiac (all p<0.001) comorbidities were most commonly phenotype I. Adjusted odds of respiratory, renal, hepatic, metabolic (all p<0.001), and hematological (p = 0.02) complications were highest for phenotype I. Phenotypes I and II were associated with 7.30-fold (HR:7.30, 95% CI:(3.11-17.17), p<0.001) and 2.57-fold (HR:2.57, 95% CI:(1.10-6.00), p = 0.03) increases in hazard of death relative to phenotype III. CONCLUSION: We identified three clinical COVID-19 phenotypes, reflecting patient populations with different comorbidities, complications, and clinical outcomes. Future research is needed to determine the utility of these phenotypes in clinical practice and trial design.

Implementation of an Anticoagulation Practice Guideline for COVID-19 via a Clinical Decision Support System in a Large Academic Health System and Its Evaluation: Observational Study.

BACKGROUND: Studies evaluating strategies for the rapid development, implementation, and evaluation of clinical decision support (CDS) systems supporting guidelines for diseases with a poor knowledge base, such as COVID-19, are limited. OBJECTIVE: We developed an anticoagulation clinical practice guideline (CPG) for COVID-19, which was delivered and scaled via CDS across a 12-hospital Midwest health care system. This study represents a preplanned 6-month postimplementation evaluation guided by the RE-AIM (Reach, Effectiveness, Adoption, Implementation, and Maintenance) framework. METHODS: The implementation outcomes evaluated were reach, adoption, implementation, and maintenance. To evaluate effectiveness, the association of CPG adherence on hospital admission with clinical outcomes was assessed via multivariable logistic regression and nearest neighbor propensity score matching. A time-to-event analysis was conducted. Sensitivity analyses were also conducted to evaluate the competing risk of death prior to intensive care unit (ICU) admission. The models were risk adjusted to account for age, gender, race/ethnicity, non-English speaking status, area deprivation index, month of admission, remdesivir treatment, tocilizumab treatment, steroid treatment, BMI, Elixhauser comorbidity index, oxygen saturation/fraction of inspired oxygen ratio, systolic blood pressure, respiratory rate, treating hospital, and source of admission. A preplanned subgroup analysis was also conducted in patients who had laboratory values (D-dimer, C-reactive protein, creatinine, and absolute neutrophil to absolute lymphocyte ratio) present. The primary effectiveness endpoint was the need for ICU admission within 48 hours of hospital admission. RESULTS: A total of 2503 patients were included in this study. CDS reach approached 95% during implementation. Adherence achieved a peak of 72% during implementation. Variation was noted in adoption across sites and nursing units. Adoption was the highest at hospitals that were specifically transformed to only provide care to patients with COVID-19 (COVID-19 cohorted hospitals; 74%-82%) and the lowest in academic settings (47%-55%). CPG delivery via the CDS system was associated with improved adherence (odds ratio [OR] 1.43, 95% CI 1.2-1.7; P<.001). Adherence with the anticoagulation CPG was associated with a significant reduction in the need for ICU admission within 48 hours (OR 0.39, 95% CI 0.30-0.51; P<.001) on multivariable logistic regression analysis. Similar findings were noted following 1:1 propensity score matching for patients who received adherent versus nonadherent care (21.5% vs 34.3% incidence of ICU admission within 48 hours; log-rank test P<.001). CONCLUSIONS: Our institutional experience demonstrated that adherence with the institutional CPG delivered via the CDS system resulted in improved clinical outcomes for patients with COVID-19. CDS systems are an effective means to rapidly scale a CPG across a heterogeneous health care system. Further research is needed to investigate factors associated with adherence at low and high adopting sites and nursing units.

Metformin and risk of mortality in patients hospitalised with COVID-19: a retrospective cohort analysis.

BACKGROUND: Type 2 diabetes and obesity, as states of chronic inflammation, are risk factors for severe COVID-19. Metformin has cytokine-reducing and sex-specific immunomodulatory effects. Our aim was to identify whether metformin reduced COVID-19-related mortality and whether sex-specific interactions exist. METHODS: In this retrospective cohort analysis, we assessed de-identified claims data from UnitedHealth Group (UHG)'s Clinical Discovery Claims Database. Patient data were eligible for inclusion if they were aged 18 years or older; had type 2 diabetes or obesity (defined based on claims); at least 6 months of continuous enrolment in 2019; and admission to hospital for COVID-19 confirmed by PCR, manual chart review by UHG, or reported from the hospital to UHG. The primary outcome was in-hospital mortality from COVID-19. The independent variable of interest was home metformin use, defined as more than 90 days of claims during the year before admission to hospital. Covariates were comorbidities, medications, demographics, and state. Heterogeneity of effect was assessed by sex. For the Cox proportional hazards, censoring was done on the basis of claims made after admission to hospital up to June 7, 2020, with a best outcome approach. Propensity-matched mixed-effects logistic regression was done, stratified by metformin use. FINDINGS: 6256 of the 15 380 individuals with pharmacy claims data from Jan 1 to June 7, 2020 were eligible for inclusion. 3302 (52·8%) of 6256 were women. Metformin use was not associated with significantly decreased mortality in the overall sample of men and women by either Cox proportional hazards stratified model (hazard ratio [HR] 0·887 [95% CI 0·782-1·008]) or propensity matching (odds ratio [OR] 0·912 [95% CI 0·777-1·071], p=0·15). Metformin was associated with decreased mortality in women by Cox proportional hazards (HR 0·785, 95% CI 0·650-0·951) and propensity matching (OR 0·759, 95% CI 0·601-0·960, p=0·021). There was no significant reduction in mortality among men (HR 0·957, 95% CI 0·82-1·14; p=0·689 by Cox proportional hazards). INTERPRETATION: Metformin was significantly associated with reduced mortality in women with obesity or type 2 diabetes who were admitted to hospital for COVID-19. Prospective studies are needed to understand mechanism and causality. If findings are reproducible, metformin could be widely distributed for prevention of COVID-19 mortality, because it is safe and inexpensive. FUNDING: National Heart, Lung, and Blood Institute; Agency for Healthcare Research and Quality; Patient-Centered Outcomes Research Institute; Minnesota Learning Health System Mentored Training Program, M Health Fairview Institutional Funds; National Center for Advancing Translational Sciences; and National Cancer Institute.

Characterizing COVID-19 Clinical Phenotypes and Associated Comorbidities and Complication Profiles.

BACKGROUND: There is limited understanding of heterogeneity in outcomes across hospitalized patients with coronavirus disease 2019 (COVID-19). Identification of distinct clinical phenotypes may facilitate tailored therapy and improve outcomes. OBJECTIVE: Identify specific clinical phenotypes across COVID-19 patients and compare admission characteristics and outcomes. DESIGN, SETTINGS, AND PARTICIPANTS: Retrospective analysis of 1,022 COVID-19 patient admissions from 14 Midwest U.S. hospitals between March 7, 2020 and August 25, 2020. METHODS: Ensemble clustering was performed on a set of 33 vitals and labs variables collected within 72 hours of admission. K-means based consensus clustering was used to identify three clinical phenotypes. Principal component analysis was performed on the average covariance matrix of all imputed datasets to visualize clustering and variable relationships. Multinomial regression models were fit to further compare patient comorbidities across phenotype classification. Multivariable models were fit to estimate the association between phenotype and in-hospital complications and clinical outcomes. Main outcomes and measures: Phenotype classification (I, II, III), patient characteristics associated with phenotype assignment, in-hospital complications, and clinical outcomes including ICU admission, need for mechanical ventilation, hospital length of stay, and mortality. RESULTS: The database included 1,022 patients requiring hospital admission with COVID-19 (median age, 62.1 [IQR: 45.9-75.8] years; 481 [48.6%] male, 412 [40.3%] required ICU admission, 437 [46.7%] were white). Three clinical phenotypes were identified (I, II, III); 236 [23.1%] patients had phenotype I, 613 [60%] patients had phenotype II, and 173 [16.9%] patients had phenotype III. When grouping comorbidities by organ system, patients with respiratory comorbidities were most commonly characterized by phenotype III (p=0.002), while patients with hematologic (p<0.001), renal (p<0.001), and cardiac (p<0.001) comorbidities were most commonly characterized by phenotype I. The adjusted odds of respiratory (p<0.001), renal (p<0.001), and metabolic (p<0.001) complications were highest for patients with phenotype I, followed by phenotype II. Patients with phenotype I had a far greater odds of hepatic (p<0.001) and hematological (p=0.02) complications than the other two phenotypes. Phenotypes I and II were associated with 7.30-fold (HR: 7.30, 95% CI: (3.11-17.17), p<0.001) and 2.57-fold (HR: 2.57, 95% CI: (1.10-6.00), p=0.03) increases in the hazard of death, respectively, when compared to phenotype III. CONCLUSION: In this retrospective analysis of patients with COVID-19, three clinical phenotypes were identified. Future research is urgently needed to determine the utility of these phenotypes in clinical practice and trial design.