Federated Learning for Sparse Bayesian Models with Applications to Electronic Health Records and Genomics.

Federated learning is becoming increasingly more popular as the concern of privacy breaches rises across disciplines including the biological and biomedical fields. The main idea is to train models locally on each server using data that are only available to that server and aggregate the model (not data) information at the global level. While federated learning has made significant advancements for machine learning methods such as deep neural networks, to the best of our knowledge, its development in sparse Bayesian models is still lacking. Sparse Bayesian models are highly interpretable with natural uncertain quantification, a desirable property for many scientific problems. However, without a federated learning algorithm, their applicability to sensitive biological/biomedical data from multiple sources is limited. Therefore, to fill this gap in the literature, we propose a new Bayesian federated learning framework that is capable of pooling information from different data sources without breaching privacy. The proposed method is conceptually simple to understand and implement, accommodates sampling heterogeneity (i.e., non-iid observations) across data sources, and allows for principled uncertainty quantification. We illustrate the proposed framework with three concrete sparse Bayesian models, namely, sparse regression, Markov random field, and directed graphical models. The application of these three models is demonstrated through three real data examples including a multi-hospital COVID-19 study, breast cancer protein-protein interaction networks, and gene regulatory networks.

Thromboprophylaxis in people hospitalized with COVID-19: Assessing intermediate or standard doses in a retrospective cohort study.

Background and Objectives: Current clinical guidelines recommend thromboprophylaxis for adults hospitalized with coronavirus disease 2019 (COVID-19), yet it is unknown whether higher doses of thromboprophylaxis offer benefits beyond standard doses. Methods: We studied electronic health records from 50 091 adults hospitalized with COVID-19 in the United States between February 2020 and February 2021. We compared standard (enoxaparin 30 or 40 mg/day, fondaparinux 2.5 mg, or heparin 5000 units twice or thrice per day) versus intermediate (enoxaparin 30 or 40 mg twice daily, or up to 1.2 mg/kg of body weight daily, heparin 7500 units thrice per day or heparin 10 000 units twice or thrice per day) thromboprophylaxis. We separately examined risk of escalation to therapeutic anticoagulation, severe disease (first occurrence of high-flow nasal cannula, noninvasive positive pressure ventilation or invasive mechanical ventilation), and death. To summarize risk, we present hazard ratios (HRs) with 95% confidence intervals (CIs) using adjusted time-dependent Cox proportional hazards regression models. Results: People whose first dose was high intensity were younger, more often obese, and had greater oxygen support requirements. Intermediate dose thromboprophylaxis was associated with increased risk of therapeutic anticoagulation (HR, 3.39; 95% CI, 3.22-3.57), severe disease (HR, 1.22; 95% CI, 1.17-1.28), and death (HR, 1.37; 95% CI, 1.21-1.55). Increased risks associated with intermediate-dose thromboprophylaxis persisted in subgroup and sensitivity analyses varying populations and definitions of exposures, outcomes, and covariates. Conclusions: Our findings do not support routine use of intermediate-dose thromboprophylaxis to prevent clinical worsening, severe disease, or death among adults hospitalized with COVID-19.

Racial and Ethnic Discrepancy in Pulse Oximetry and Delayed Identification of Treatment Eligibility Among Patients With COVID-19.

Importance: Pulse oximetry guides triage and therapy decisions for COVID-19. Whether reported racial inaccuracies in oxygen saturation measured by pulse oximetry are present in patients with COVID-19 and associated with treatment decisions is unknown. Objective: To determine whether there is differential inaccuracy of pulse oximetry by race or ethnicity among patients with COVID-19 and estimate the association of such inaccuracies with time to recognition of eligibility for oxygen threshold-specific COVID-19 therapies. Design, Setting, and Participants: This retrospective cohort study of clinical data from 5 referral centers and community hospitals in the Johns Hopkins Health System included patients with COVID-19 who self-identified as Asian, Black, Hispanic, or White. Exposures: Concurrent measurements (within 10 minutes) of oxygen saturation levels in arterial blood (SaO2) and by pulse oximetry (SpO2). Main Outcomes and Measures: For patients with concurrent SpO2 and SaO2 measurements, the proportion with occult hypoxemia (SaO2<88% with concurrent SpO2 of 92%-96%) was compared by race and ethnicity, and a covariate-adjusted linear mixed-effects model was produced to estimate the association of race and ethnicity with SpO2 and SaO2 difference. This model was applied to identify a separate sample of patients with predicted SaO2 levels of 94% or less before an SpO2 level of 94% or less or oxygen treatment initiation. Cox proportional hazards models were used to estimate differences by race and ethnicity in time to recognition of eligibility for guideline-recommended COVID-19 therapies, defined as an SpO2 level of 94% or less or oxygen treatment initiation. The median delay among individuals who ultimately had recognition of eligibility was then compared. Results: Of 7126 patients with COVID-19, 1216 patients (63 Asian [5.2%], 478 Black [39.3%], 215 Hispanic [17.7%], and 460 White [37.8%] individuals; 507 women [41.7%]) had 32 282 concurrently measured SpO2 and SaO2. Occult hypoxemia occurred in 19 Asian (30.2%), 136 Black (28.5%), and 64 non-Black Hispanic (29.8%) patients compared with 79 White patients (17.2%). Compared with White patients, SpO2 overestimated SaO2 by an average of 1.7% among Asian (95% CI, 0.5%-3.0%), 1.2% among Black (95% CI, 0.6%-1.9%), and 1.1% among non-Black Hispanic patients (95% CI, 0.3%-1.9%). Separately, among 1903 patients with predicted SaO2 levels of 94% or less before an SpO2 level of 94% or less or oxygen treatment initiation, compared with White patients, Black patients had a 29% lower hazard (hazard ratio, 0.71; 95% CI, 0.63-0.80), and non-Black Hispanic patients had a 23% lower hazard (hazard ratio, 0.77; 95% CI, 0.66-0.89) of treatment eligibility recognition. A total of 451 patients (23.7%) never had their treatment eligibility recognized, most of whom (247 [54.8%]) were Black. Among the remaining 1452 (76.3%) who had eventual recognition of treatment eligibility, Black patients had a median delay of 1.0 hour (95% CI, 0.23-1.9 hours; P = .01) longer than White patients. There was no significant median difference in delay between individuals of other racial and ethnic minority groups and White patients. Conclusions and Relevance: The results of this cohort study suggest that racial and ethnic biases in pulse oximetry accuracy were associated with greater occult hypoxemia in Asian, Black, and non-Black Hispanic patients with COVID-19, which was associated with significantly delayed or unrecognized eligibility for COVID-19 therapies among Black and Hispanic patients. This disparity may contribute to worse outcomes among Black and Hispanic patients with COVID-19.

Real-World Effectiveness of Remdesivir in Adults Hospitalized With Coronavirus Disease 2019 (COVID-19): A Retrospective, Multicenter Comparative Effectiveness Study.

BACKGROUND: There is an urgent need to understand the real-world effectiveness of remdesivir in the treatment of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). METHODS: This was a retrospective comparative effectiveness study. Individuals hospitalized in a large private healthcare network in the United States from 23 February 2020 through 11 February 2021 with a positive test for SARS-CoV-2 and ICD-10 diagnosis codes consistent with symptomatic coronavirus disease 2019 (COVID-19) were included. Remdesivir recipients were matched to controls using time-dependent propensity scores. The primary outcome was time to improvement with a secondary outcome of time to death. RESULTS: Of 96 859 COVID-19 patients, 42 473 (43.9%) received at least 1 remdesivir dose. The median age of remdesivir recipients was 65 years, 23 701 (55.8%) were male, and 22 819 (53.7%) were non-White. Matches were found for 18 328 patients (43.2%). Remdesivir recipients were significantly more likely to achieve clinical improvement by 28 days (adjusted hazard ratio [aHR] 1.19, 95% confidence interval [CI], 1.16-1.22). Remdesivir patients on no oxygen (aHR 1.30, 95% CI, 1.22-1.38) or low-flow oxygen (aHR 1.23, 95% CI, 1.19-1.27) were significantly more likely to achieve clinical improvement by 28 days. There was no significant impact on the likelihood of mortality overall (aHR 1.02, 95% CI, .97-1.08). Remdesivir recipients on low-flow oxygen were significantly less likely to die than controls (aHR 0.85, 95% CI, .77-.92; 28-day mortality 8.4% [865 deaths] for remdesivir patients, 12.5% [1334 deaths] for controls). CONCLUSIONS: These results support the use of remdesivir for hospitalized COVID-19 patients on no or low-flow oxygen. Routine initiation of remdesivir in more severely ill patients is unlikely to be beneficial.

The Effectiveness of High-Flow Nasal Cannula in Coronavirus Disease 2019 Pneumonia: A Retrospective Cohort Study.

OBJECTIVES: High-flow nasal cannula is widely used in acute hypoxemic respiratory failure due to coronavirus disease 2019, yet data regarding its effectiveness is lacking. More evidence is needed to guide patient selection, timing of high-flow nasal cannula initiation, and resource allocation. We aimed to assess time to discharge and time to death in severe coronavirus disease 2019 in patients treated with high-flow nasal cannula compared with matched controls. We also evaluated the ability of the respiratory rate-oxygenation ratio to predict progression to invasive mechanical ventilation. DESIGN: Time-dependent propensity score matching was used to create pairs of individuals who were then analyzed in a Cox proportional-hazards regression model to estimate high-flow nasal cannula's effect on time to discharge and time to death. A secondary analysis excluded high-flow nasal cannula patients intubated within 6 hours of admission. A Cox proportional-hazards regression model was used to assess risk of invasive mechanical ventilation among high-flow nasal cannula patients stratified by respiratory rate-oxygenation. SETTING: The five hospitals of the Johns Hopkins Health System. PATIENTS: All patients who were admitted with a laboratory-confirmed diagnosis of coronavirus disease 2019 were eligible for inclusion. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: High-flow nasal cannula was associated with longer median time to discharge: 10.6 days (interquartile range, 7.1-15.8 d) versus 7.8 days (interquartile range, 4.9-12.1 d). Respiratory rate-oxygenation index performed poorly in predicting ventilation or death. In the primary analysis, there was no significant association between high-flow nasal cannula and hazard of death (adjusted hazard ratio, 0.79; 95% CI, 0.57-1.09). Excluding patients intubated within 6 hours of admission, high-flow nasal cannula was associated with reduced hazard of death (adjusted hazard ratio, 0.67; 95% CI, 0.45-0.99). CONCLUSIONS: Among unselected patients with severe coronavirus disease 2019 pneumonia, high-flow nasal cannula was not associated with a statistically significant reduction in hazard of death. However, in patients not mechanically ventilated within 6 hours of admission, high-flow nasal cannula was associated with a significantly reduced hazard of death.

Peripheral Plasma Cells Associated with Mortality Benefit in Severe COVID-19: A Marker of Disease Resolution.

BACKGROUND: Cytokines seen in severe coronavirus disease 2019 (COVID-19) are associated with proliferation, differentiation, and survival of plasma cells. Plasma cells are not routinely found in peripheral blood, though may produce virus-neutralizing antibodies in COVID-19 later in the course of an infection. METHODS: Using the Johns Hopkins COVID-19 Precision Medicine Analytics Platform Registry, we identified hospitalized adult patients with confirmed severe acute respiratory coronavirus 2 (SARS-CoV-2) infection and stratified by presence of plasma cells and World Health Organization (WHO) disease severity. To identify plasma cells, we employed a sensitive flow cytometric screening method for highly fluorescent lymphocytes and confirmed these microscopically. Cox regression models were used to evaluate time to death and time to clinical improvement by the presence of plasma cells in patients with severe disease. RESULTS: Of 2301 hospitalized patients with confirmed infection, 371 had plasma cells identified. Patients with plasma cells were more likely to have severe disease, though 86.6% developed plasma cells after onset of severe disease. In patients with severe disease, after adjusting for age, sex, body mass index, race, and other covariates associated with disease severity, patients with plasma cells had a reduced hazard of death (adjusted hazard ratio: 0.57; 95% confidence interval: 0.38-0.87; P value: .008). There was no significant association with the presence of plasma cells and time to clinical improvement. CONCLUSIONS: Patients with severe disease who have detectable plasma cells in the peripheral blood have improved mortality despite adjusting for known covariates associated with disease severity in COVID-19. Further investigation is warranted to understand the role of plasma cells in the immune response to COVID-19.

Comparison of Time to Clinical Improvement With vs Without Remdesivir Treatment in Hospitalized Patients With COVID-19.

Importance: Clinical effectiveness data on remdesivir are urgently needed, especially among diverse populations and in combination with other therapies. Objective: To examine whether remdesivir administered with or without corticosteroids for treatment of coronavirus disease 2019 (COVID-19) is associated with more rapid clinical improvement in a racially/ethnically diverse population. Design, Setting, and Participants: This retrospective comparative effectiveness research study was conducted from March 4 to August 29, 2020, in a 5-hospital health system in the Baltimore, Maryland, and Washington, DC, area. Of 2483 individuals with confirmed severe acute respiratory syndrome coronavirus 2 infection assessed by polymerase chain reaction, those who received remdesivir were matched to infected individuals who did not receive remdesivir using time-invariant covariates (age, sex, race/ethnicity, Charlson Comorbidity Index, body mass index, and do-not-resuscitate or do-not-intubate orders) and time-dependent covariates (ratio of peripheral blood oxygen saturation to fraction of inspired oxygen, blood pressure, pulse, temperature, respiratory rate, C-reactive protein level, complete white blood cell count, lymphocyte count, albumin level, alanine aminotransferase level, glomerular filtration rate, dimerized plasmin fragment D [D-dimer] level, and oxygen device). An individual in the remdesivir group with k days of treatment was matched to a control patient who stayed in the hospital at least k days (5 days maximum) beyond the matching day. Exposures: Remdesivir treatment with or without corticosteroid administration. Main Outcomes and Measures: The primary outcome was rate of clinical improvement (hospital discharge or decrease of 2 points on the World Health Organization severity score), and the secondary outcome, mortality at 28 days. An additional outcome was clinical improvement and time to death associated with combined remdesivir and corticosteroid treatment. Results: Of 2483 consecutive admissions, 342 individuals received remdesivir, 184 of whom also received corticosteroids and 158 of whom received remdesivir alone. For these 342 patients, the median age was 60 years (interquartile range, 46-69 years), 189 (55.3%) were men, and 276 (80.7%) self-identified as non-White race/ethnicity. Remdesivir recipients had a shorter time to clinical improvement than matched controls without remdesivir treatment (median, 5.0 days [interquartile range, 4.0-8.0 days] vs 7.0 days [interquartile range, 4.0-10.0 days]; adjusted hazard ratio, 1.47 [95% CI, 1.22-1.79]). Remdesivir recipients had a 28-day mortality rate of 7.7% (22 deaths) compared with 14.0% (40 deaths) among matched controls, but this difference was not statistically significant in the time-to-death analysis (adjusted hazard ratio, 0.70; 95% CI, 0.38-1.28). The addition of corticosteroids to remdesivir was not associated with a reduced hazard of death at 28 days (adjusted hazard ratio, 1.94; 95% CI, 0.67-5.57). Conclusions and Relevance: In this comparative effectiveness research study of adults hospitalized with COVID-19, receipt of remdesivir was associated with faster clinical improvement in a cohort of predominantly non-White patients. Remdesivir plus corticosteroid administration did not reduce the time to death compared with remdesivir administered alone.

Development of Severe COVID-19 Adaptive Risk Predictor (SCARP), a Calculator to Predict Severe Disease or Death in Hospitalized Patients With COVID-19.

BACKGROUND: Predicting the clinical trajectory of individual patients hospitalized with coronavirus disease 2019 (COVID-19) is challenging but necessary to inform clinical care. The majority of COVID-19 prognostic tools use only data present upon admission and do not incorporate changes occurring after admission. OBJECTIVE: To develop the Severe COVID-19 Adaptive Risk Predictor (SCARP) (https://rsconnect.biostat.jhsph.edu/covid_trajectory/), a novel tool that can provide dynamic risk predictions for progression from moderate disease to severe illness or death in patients with COVID-19 at any time within the first 14 days of their hospitalization. DESIGN: Retrospective observational cohort study. SETTINGS: Five hospitals in Maryland and Washington, D.C. PATIENTS: Patients who were hospitalized between 5 March and 4 December 2020 with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) confirmed by nucleic acid test and symptomatic disease. MEASUREMENTS: A clinical registry for patients hospitalized with COVID-19 was the primary data source; data included demographic characteristics, admission source, comorbid conditions, time-varying vital signs, laboratory measurements, and clinical severity. Random forest for survival, longitudinal, and multivariate (RF-SLAM) data analysis was applied to predict the 1-day and 7-day risks for progression to severe disease or death for any given day during the first 14 days of hospitalization. RESULTS: Among 3163 patients admitted with moderate COVID-19, 228 (7%) became severely ill or died in the next 24 hours; an additional 355 (11%) became severely ill or died in the next 7 days. The area under the receiver-operating characteristic curve (AUC) for 1-day risk predictions for progression to severe disease or death was 0.89 (95% CI, 0.88 to 0.90) and 0.89 (CI, 0.87 to 0.91) during the first and second weeks of hospitalization, respectively. The AUC for 7-day risk predictions for progression to severe disease or death was 0.83 (CI, 0.83 to 0.84) and 0.87 (CI, 0.86 to 0.89) during the first and second weeks of hospitalization, respectively. LIMITATION: The SCARP tool was developed by using data from a single health system. CONCLUSION: Using the predictive power of RF-SLAM and longitudinal data from more than 3000 patients hospitalized with COVID-19, an interactive tool was developed that rapidly and accurately provides the probability of an individual patient's progression to severe illness or death on the basis of readily available clinical information. PRIMARY FUNDING SOURCE: Hopkins inHealth and COVID-19 Administrative Supplement for the HHS Region 3 Treatment Center from the Office of the Assistant Secretary for Preparedness and Response.

Tocilizumab for the Treatment of COVID-19 Among Hospitalized Patients: A Matched Retrospective Cohort Analysis.

BACKGROUND: There is currently no single treatment that mitigates all harms caused by severe acute respiratory syndrome coronavirus 2 infection. Tocilizumab, an interleukin-6 antagonist, may have a role as an adjunctive immune-modulating therapy. METHODS: This was an observational retrospective study of hospitalized adult patients with confirmed coronavirus disease 2019 (COVID-19). The intervention group comprised patients who received tocilizumab; the comparator arm was drawn from patients who did not receive tocilizumab. The primary outcome was all-cause mortality censored at 28 days; secondary outcomes were all-cause mortality at discharge, time to clinical improvement, and rates of secondary infections. Marginal structural Cox models via inverse probability treatment weights were applied to estimate the effect of tocilizumab. A time-dependent propensity score-matching method was used to generate a 1:1 match for tocilizumab recipients; infectious diseases experts then manually reviewed these matched charts to identify secondary infections. RESULTS: This analysis included 90 tocilizumab recipients and 1669 controls. Under the marginal structural Cox model, tocilizumab was associated with a 62% reduced hazard of death (adjusted hazard ratio [aHR], 0.38; 95% CI, 0.21 to 0.70) and no change in time to clinical improvement (aHR, 1.13; 95% CI, 0.68 to 1.87). The 1:1 matched data set also showed a lower mortality rate (27.8% vs 34.4%) and reduced hazards of death (aHR, 0.47; 95% CI, 0.25 to 0.88). Elevated inflammatory markers were associated with reduced hazards of death among tocilizumab recipients compared with controls. Secondary infection rates were similar between the 2 groups. CONCLUSIONS: Tocilizumab may provide benefit in a subgroup of patients hospitalized with COVID-19 who have elevated biomarkers of hyperinflammation, without increasing the risk of secondary infection.