Anti-PF4 antibodies associated with disease severity in COVID-19.

Severe COVID-19 is characterized by a prothrombotic state associated with thrombocytopenia, with microvascular thrombosis being almost invariably present in the lung and other organs at postmortem examination. We evaluated the presence of antibodies to platelet factor 4 (PF4)-polyanion complexes using a clinically validated immunoassay in 100 hospitalized patients with COVID-19 with moderate or severe disease (World Health Organization score, 4 to 10), 25 patients with acute COVID-19 visiting the emergency department, and 65 convalescent individuals. Anti-PF4 antibodies were detected in 95 of 100 hospitalized patients with COVID-19 (95.0%) irrespective of prior heparin treatment, with a mean optical density value of 0.871 ± 0.405 SD (range, 0.177 to 2.706). In contrast, patients hospitalized for severe acute respiratory disease unrelated to COVID-19 had markedly lower levels of the antibodies. In a high proportion of patients with COVID-19, levels of all three immunoglobulin (Ig) isotypes tested (IgG, IgM, and IgA) were simultaneously elevated. Antibody levels were higher in male than in female patients and higher in African Americans and Hispanics than in White patients. Anti-PF4 antibody levels were correlated with the maximum disease severity score and with significant reductions in circulating platelet counts during hospitalization. In individuals convalescent from COVID-19, the antibody levels returned to near-normal values. Sera from patients with COVID-19 induced higher levels of platelet activation than did sera from healthy blood donors, but the results were not correlated with the levels of anti-PF4 antibodies. These results demonstrate that the vast majority of patients with severe COVID-19 develop anti-PF4 antibodies, which may play a role in the clinical complications of COVID-19.

Racial variability in immune responses only partially explains differential systemic sclerosis disease severity.

OBJECTIVE: To understand if autoantibodies account for racial variation in disease severity, we compared autoantibody distribution and associated phenotype between self-identified black and white systemic sclerosis (SSc) patients. METHODS: 803 black and 2178 white SSc patients had systematic testing for autoantibodies using Euroimmun (centromere (ACA), RNA-polymerase III (POLR3), Scl70, PM/Scl, NOR90, Th/To, Ku, U3RNP and Ro52) and commercial ELISA (U1RNP). In this observational study, logistic regression was performed to assess the association between self-identified race and outcomes, adjusting for autoantibodies. To estimate whether the effect of race was mediated by autoantibody status, race coefficients from multivariate models including and excluding autoantibodies were compared. RESULTS: Anti-Scl70, anti-U1RNP, anti-U3RNP, anti-Th/To, anti-Ku and anti-NOR90 were more common in the black cohort than in the white cohort, which was enriched for ACA, anti-POLR3 and anti-PM/Scl. Black individuals had a higher prevalence of severe Raynaud's, skin, lung, gastrointestinal and renal disease whereas white individuals had a higher prevalence of severe heart and muscle disease. Adjusting for autoantibodies decreased the effect of race on outcome for telangiectasias, forced vital capacity <70%, pulmonary hypertension and severe lung, heart, muscle and gastrointestinal disease by 11%-44% and increased the association between race and renal crisis and severe kidney disease by 37%-52%. CONCLUSIONS: This study is the largest systematic analysis of autoantibody responses in a geographically diverse population of black SSc patients. Black and white individuals with SSc have distinct autoantibody profiles. Autoantibodies explain only a fraction of the effect of race on clinical outcomes, suggesting other factors contribute to disparate outcomes between these groups.

Impact of Severe Acute Respiratory Syndrome Coronavirus 2 Variants on Inpatient Clinical Outcome.

BACKGROUND: Prior observation has shown differences in COVID-19 hospitalization risk between SARS-CoV-2 variants, but limited information describes hospitalization outcomes. METHODS: Inpatients with COVID-19 at 5 hospitals in the eastern United States were included if they had hypoxia, tachypnea, tachycardia, or fever, and SARS-CoV-2 variant data, determined from whole-genome sequencing or local surveillance inference. Analyses were stratified by history of SARS-CoV-2 vaccination or infection. The average effect of SARS-CoV-2 variant on 28-day risk of severe disease, defined by advanced respiratory support needs, or death was evaluated using models weighted on propensity scores derived from baseline clinical features. RESULTS: Severe disease or death within 28 days occurred for 977 (29%) of 3369 unvaccinated patients and 269 (22%) of 1230 patients with history of vaccination or prior SARS-CoV-2 infection. Among unvaccinated patients, the relative risk of severe disease or death for Delta variant compared with ancestral lineages was 1.30 (95% confidence interval [CI]: 1.11-1.49). Compared with Delta, the risk for Omicron patients was .72 (95% CI: .59-.88) and compared with ancestral lineages was .94 (.78-1.1). Among Omicron and Delta infections, patients with history of vaccination or prior SARS-CoV-2 infection had half the risk of severe disease or death (adjusted hazard ratio: .40; 95% CI: .30-.54), but no significant outcome difference by variant. CONCLUSIONS: Although risk of severe disease or death for unvaccinated inpatients with Omicron was lower than with Delta, it was similar to ancestral lineages. Severe outcomes were less common in vaccinated inpatients, with no difference between Delta and Omicron infections.

DNA Sequencing to Detect Residual Disease in Adults With Acute Myeloid Leukemia Prior to Hematopoietic Cell Transplant.

Importance: Preventing relapse for adults with acute myeloid leukemia (AML) in first remission is the most common indication for allogeneic hematopoietic cell transplant. The presence of AML measurable residual disease (MRD) has been associated with higher relapse rates, but testing is not standardized. Objective: To determine whether DNA sequencing to identify residual variants in the blood of adults with AML in first remission before allogeneic hematopoietic cell transplant identifies patients at increased risk of relapse and poorer overall survival compared with those without these DNA variants. Design, Setting, and Participants: In this retrospective observational study, DNA sequencing was performed on pretransplant blood from patients aged 18 years or older who had undergone their first allogeneic hematopoietic cell transplant during first remission for AML associated with variants in FLT3, NPM1, IDH1, IDH2, or KIT at 1 of 111 treatment sites from 2013 through 2019. Clinical data were collected, through May 2022, by the Center for International Blood and Marrow Transplant Research. Exposure: Centralized DNA sequencing of banked pretransplant remission blood samples. Main Outcomes and Measures: The primary outcomes were overall survival and relapse. Day of transplant was considered day 0. Hazard ratios were reported using Cox proportional hazards regression models. Results: Of 1075 patients tested, 822 had FLT3 internal tandem duplication (FLT3-ITD) and/or NPM1 mutated AML (median age, 57.1 years, 54% female). Among 371 patients in the discovery cohort, the persistence of NPM1 and/or FLT3-ITD variants in the blood of 64 patients (17.3%) in remission before undergoing transplant was associated with worse outcomes after transplant (2013-2017). Similarly, of the 451 patients in the validation cohort who had undergone transplant in 2018-2019, 78 patients (17.3%) with residual NPM1 and/or FLT3-ITD variants had higher rates of relapse at 3 years (68% vs 21%; difference, 47% [95% CI, 26% to 69%]; HR, 4.32 [95% CI, 2.98 to 6.26]; P < .001) and decreased survival at 3 years (39% vs 63%; difference, -24% [2-sided 95% CI, -39% to -9%]; HR, 2.43 [95% CI, 1.71 to 3.45]; P < .001). Conclusions and Relevance: Among patients with acute myeloid leukemia in first remission prior to allogeneic hematopoietic cell transplant, the persistence of FLT3 internal tandem duplication or NPM1 variants in the blood at an allele fraction of 0.01% or higher was associated with increased relapse and worse survival compared with those without these variants. Further study is needed to determine whether routine DNA-sequencing testing for residual variants can improve outcomes for patients with acute myeloid leukemia.

Heterogeneity of Age-Related Neural Hyperactivity along the CA3 Transverse Axis.

Age-related memory deficits are correlated with neural hyperactivity in the CA3 region of the hippocampus. Abnormal CA3 hyperactivity in aged rats has been proposed to contribute to an imbalance between pattern separation and pattern completion, resulting in overly rigid representations. Recent evidence of functional heterogeneity along the CA3 transverse axis suggests that proximal CA3 supports pattern separation while distal CA3 supports pattern completion. It is not known whether age-related CA3 hyperactivity is uniformly represented along the CA3 transverse axis. We examined the firing rates of CA3 neurons from young and aged, male, Long-Evans rats along the CA3 transverse axis. Consistent with prior studies, young CA3 cells showed an increasing gradient in mean firing rate from proximal to distal CA3. However, aged CA3 cells showed an opposite, decreasing trend, in that CA3 cells in aged rats were hyperactive in proximal CA3, but possibly hypoactive in distal CA3, compared with young (Y) rats. We suggest that, in combination with altered inputs from the entorhinal cortex and dentate gyrus (DG), the proximal CA3 region of aged rats may switch from its normal function that reflects the pattern separation output of the DG and instead performs a computation that reflects an abnormal bias toward pattern completion. In parallel, distal CA3 of aged rats may create weaker attractor basins that promote abnormal, bistable representations under certain conditions.SIGNIFICANCE STATEMENT Prior work suggested that age-related CA3 hyperactivity enhances pattern completion, resulting in rigid representations. Implicit in prior studies is the notion that hyperactivity is present throughout a functionally homogeneous CA3 network. However, more recent work has demonstrated functional heterogeneity along the CA3 transverse axis, in that proximal CA3 is involved in pattern separation and distal CA3 is involved in pattern completion. Here, we show that age-related hyperactivity is present only in proximal CA3, with potential hypoactivity in distal CA3. This result provides new insight in the role of CA3 in age-related memory impairments, suggesting that the rigid representations in aging result primarily from dysfunction of computational circuits involving the dentate gyrus (DG) and proximal CA3.

Regularized Bayesian transfer learning for population-level etiological distributions.

Computer-coded verbal autopsy (CCVA) algorithms predict cause of death from high-dimensional family questionnaire data (verbal autopsy) of a deceased individual, which are then aggregated to generate national and regional estimates of cause-specific mortality fractions. These estimates may be inaccurate if CCVA is trained on non-local training data different from the local population of interest. This problem is a special case of transfer learning, i.e., improving classification within a target domain (e.g., a particular population) with the classifier trained in a source-domain. Most transfer learning approaches concern individual-level (e.g., a person's) classification. Social and health scientists such as epidemiologists are often more interested with understanding etiological distributions at the population-level. The sample sizes of their data sets are typically orders of magnitude smaller than those used for common transfer learning applications like image classification, document identification, etc. We present a parsimonious hierarchical Bayesian transfer learning framework to directly estimate population-level class probabilities in a target domain, using any baseline classifier trained on source-domain, and a small labeled target-domain dataset. To address small sample sizes, we introduce a novel shrinkage prior for the transfer error rates guaranteeing that, in absence of any labeled target-domain data or when the baseline classifier is perfectly accurate, our transfer learning agrees with direct aggregation of predictions from the baseline classifier, thereby subsuming the default practice as a special case. We then extend our approach to use an ensemble of baseline classifiers producing an unified estimate. Theoretical and empirical results demonstrate how the ensemble model favors the most accurate baseline classifier. We present data analyses demonstrating the utility of our approach.

Social Determinants of Health Influence Future Health Care Costs in the Medicaid Cohort of the District of Columbia Study.

Policy Points Social determinants of health are an important predictor of future health care costs. Medicaid must partner with other sectors to address the underlying causes of its beneficiaries' poor health and high health care spending. CONTEXT: Social determinants of health are an important predictor of future health care costs but little is known about their impact on Medicaid spending. This study analyzes the role of social determinants of health (SDH) in predicting future health care costs for adult Medicaid beneficiaries with similar past morbidity burdens and past costs. METHODS: We enrolled into a prospective cohort study 8,892 adult Medicaid beneficiaries who presented for treatment at an emergency department or clinic affiliated with two hospitals in Washington, DC, between September 2017 and December 31, 2018. We used SDH information measured at enrollment to categorize our participants into four social risk classes of increasing severity. We used Medicaid claims for a 2-year period; 12 months pre- and post-study enrollment to measure past and future morbidity burden according to the Adjusted Clinical Groups system. We also used the Medicaid claims data to characterize total annual Medicaid costs one year prior to and one year after study enrollment. RESULTS: The 8,892 participants were primarily female (66%) and Black (91%). For persons with similar past morbidity burdens and past costs (p < 0.01), the future morbidity burden was significantly higher in the upper two social risk classes (1.15 and 2.04, respectively) compared with the lowest one. Mean future health care spending was significantly higher in the upper social risk classes compared with the lowest one ($2,713, $11,010, and $17,710, respectively) and remained significantly higher for the two highest social risk classes ($1,426 and $3,581, respectively), given past morbidity burden and past costs (p < 0.01). When we controlled for future morbidity burden (measured concurrently with future costs), social risk class was no longer a significant predictor of future health care costs. CONCLUSIONS: SDH are statistically significant predictors of future morbidity burden and future costs controlling for past morbidity burden and past costs. Further research is needed to determine whether current payment systems adequately account for differences in the care needs of highly medically and socially complex patients.

A data quality assessment of the first four years of malaria reporting in the Senegal DHIS2, 2014-2017.

BACKGROUND: As the global burden of malaria decreases, routine health information systems (RHIS) have become invaluable for monitoring progress towards elimination. The District Health Information System, version 2 (DHIS2) has been widely adopted across countries and is expected to increase the quality of reporting of RHIS. In this study, we evaluated the quality of reporting of key indicators of childhood malaria from January 2014 through December 2017, the first 4 years of DHIS2 implementation in Senegal. METHODS: Monthly data on the number of confirmed and suspected malaria cases as well as tests done were extracted from the Senegal DHIS2. Reporting completeness was measured as the number of monthly reports received divided by the expected number of reports in a given year. Completeness of indicator data was measured as the percentage of non-missing indicator values. We used a quasi-Poisson model with natural cubic spline terms of month of reporting to impute values missing at the facility level. We used the imputed values to take into account the percentage of malaria cases that were missed due to lack of reporting. Consistency was measured as the absence of moderate and extreme outliers, internal consistency between related indicators, and consistency of indicators over time. RESULTS: In contrast to public facilities of which 92.7% reported data in the DHIS2 system during the study period, only 15.3% of the private facilities used the reporting system. At the national level, completeness of facility reporting increased from 84.5% in 2014 to 97.5% in 2017. The percentage of expected malaria cases reported increased from 76.5% in 2014 to 94.7% in 2017. Over the study period, the percentage of malaria cases reported across all districts was on average 7.5% higher (P < 0.01) during the rainy season relative to the dry season. Reporting completeness rates were lower among hospitals compared to health centers and health posts. The incidence of moderate and extreme outlier values was 5.2 and 2.3%, respectively. The number of confirmed malaria cases increased by 15% whereas the numbers of suspected cases and tests conducted more than doubled from 2014 to 2017 likely due to a policy shift towards universal testing of pediatric febrile cases. CONCLUSIONS: The quality of reporting for malaria indicators in the Senegal DHIS2 has improved over time and the data are suitable for use to monitor progress in malaria programs, with an understanding of their limitations. Senegalese health authorities should maintain the focus on broader adoption of DHIS2 reporting by private facilities, the sustainability of district-level data quality reviews, facility-level supervision and feedback mechanisms at all levels of the health system.

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.

Patient Trajectories Among Persons Hospitalized for COVID-19 : A Cohort Study.

BACKGROUND: Risk factors for progression of coronavirus disease 2019 (COVID-19) to severe disease or death are underexplored in U.S. cohorts. OBJECTIVE: To determine the factors on hospital admission that are predictive of severe disease or death from COVID-19. DESIGN: Retrospective cohort analysis. SETTING: Five hospitals in the Maryland and Washington, DC, area. PATIENTS: 832 consecutive COVID-19 admissions from 4 March to 24 April 2020, with follow-up through 27 June 2020. MEASUREMENTS: Patient trajectories and outcomes, categorized by using the World Health Organization COVID-19 disease severity scale. Primary outcomes were death and a composite of severe disease or death. RESULTS: Median patient age was 64 years (range, 1 to 108 years); 47% were women, 40% were Black, 16% were Latinx, and 21% were nursing home residents. Among all patients, 131 (16%) died and 694 (83%) were discharged (523 [63%] had mild to moderate disease and 171 [20%] had severe disease). Of deaths, 66 (50%) were nursing home residents. Of 787 patients admitted with mild to moderate disease, 302 (38%) progressed to severe disease or death: 181 (60%) by day 2 and 238 (79%) by day 4. Patients had markedly different probabilities of disease progression on the basis of age, nursing home residence, comorbid conditions, obesity, respiratory symptoms, respiratory rate, fever, absolute lymphocyte count, hypoalbuminemia, troponin level, and C-reactive protein level and the interactions among these factors. Using only factors present on admission, a model to predict in-hospital disease progression had an area under the curve of 0.85, 0.79, and 0.79 at days 2, 4, and 7, respectively. LIMITATION: The study was done in a single health care system. CONCLUSION: A combination of demographic and clinical variables is strongly associated with severe COVID-19 disease or death and their early onset. The COVID-19 Inpatient Risk Calculator (CIRC), using factors present on admission, can inform clinical and resource allocation decisions. 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.

Outcome-Stratified Analysis of Biomarker Trajectories for Patients Infected With Severe Acute Respiratory Syndrome Coronavirus 2.

Longitudinal trajectories of vital signs and biomarkers during hospital admission of patients with COVID-19 remain poorly characterized despite their potential to provide critical insights about disease progression. We studied 1884 patients with severe acute respiratory syndrome coronavirus 2 infection from April 3, 2020, to June 25, 2020, within 1 Maryland hospital system and used a retrospective longitudinal framework with linear mixed-effects models to investigate relevant biomarker trajectories leading up to 3 critical outcomes: mechanical ventilation, discharge, and death. Trajectories of 4 vital signs (respiratory rate, ratio of oxygen saturation (Spo2) to fraction of inspired oxygen (Fio2), pulse, and temperature) and 4 laboratory values (C-reactive protein (CRP), absolute lymphocyte count (ALC), estimated glomerular filtration rate, and D-dimer) clearly distinguished the trajectories of patients with COVID-19. Before any ventilation, log(CRP), log(ALC), respiratory rate, and Spo2-to-Fio2 ratio trajectories diverge approximately 8-10 days before discharge or death. After ventilation, log(CRP), log(ALC), respiratory rate, Spo2-to-Fio2 ratio, and estimated glomerular filtration rate trajectories again diverge 10-20 days before death or discharge. Trajectories improved until discharge and remained unchanged or worsened until death. Our approach characterizes the distribution of biomarker trajectories leading up to competing outcomes of discharge versus death. Moving forward, this model can contribute to quantifying the joint probability of biomarkers and outcomes when provided clinical data up to a given moment.

Latent Class Analysis to Represent Social Determinant of Health Risk Groups in the Medicaid Cohort of the District of Columbia.

OBJECTIVE: To develop distinct social risk profiles based on social determinants of health (SDH) information and to determine whether these social risk groups varied in terms of health, health care utilization, and costs. METHODS: We prospectively enrolled 8943 beneficiaries insured by the District of Columbia Medicaid program between September 2017 and December 2018. Participants completed a SDH survey and we obtained their Medicaid claims data for a 2-year period before study enrollment. We used latent class analysis (LCA) to identify distinct social risk profiles based on their SDH responses. We assessed the relationship among different SDH as well as the relationship among the social risk classes and health, health care use and costs. RESULTS: The majority of SDH were moderately to strongly correlated with one another. LCA yielded 4 distinct social risk groups. Group 1 reported the least social risks with the most employed. Group 2 was distinguished by financial strain and housing instability with fewer employed. Group 3 were mostly unemployed with limited car and internet access. Group 4 had the most social risks and most unemployed. The social risk groups demonstrated meaningful differences in health, acute care utilization, and health care costs with group 1 having the best health outcomes and group 4 the worst (P<0.05). CONCLUSIONS: LCA is a practical method of aggregating correlated SDH data into a finite number of distinct social risk groups. Understanding the constellation of social challenges that patients face is critical when attempting to address their social needs and improve health outcomes.

A Bayesian approach to restricted latent class models for scientifically structured clustering of multivariate binary outcomes.

This paper presents a model-based method for clustering multivariate binary observations that incorporates constraints consistent with the scientific context. The approach is motivated by the precision medicine problem of identifying autoimmune disease patient subsets or classes who may require different treatments. We start with a family of restricted latent class models or RLCMs. However, in the motivating example and many others like it, the unknown number of classes and the definition of classes using binary states are among the targets of inference. We use a Bayesian approach to RLCMs in order to use informative prior assumptions on the number and definitions of latent classes to be consistent with scientific knowledge so that the posterior distribution tends to concentrate on smaller numbers of clusters and sparser binary patterns. The paper derives a posterior sampling algorithm based on Markov chain Monte Carlo with split-merge updates to efficiently explore the space of clustering allocations. Through simulations under the assumed model and realistic deviations from it, we demonstrate greater interpretability of results and superior finite-sample clustering performance for our method compared to common alternatives. The methods are illustrated with an analysis of protein data to detect clusters representing autoantibody classes among scleroderma patients.

Predicting clinical events using Bayesian multivariate linear mixed models with application to scleroderma.

BACKGROUND: Scleroderma is a serious chronic autoimmune disease in which a patient's disease state manifests in several irregularly spaced longitudinal measures of lung, heart, skin, and other organ systems. Threshold crossings of pulmonary and cardiac measures indicate potentially life-threatening key clinical events including interstitial lung disease (ILD), cardiomyopathy, and pulmonary hypertension (PH). The statistical challenge is to accurately and precisely predict these events by using all of the clinical history for the patient at hand and for a reference population of patients. METHODS: We use a Bayesian mixed model approach to simultaneously characterize each individual's future trajectories for several biomarkers. We estimate this model using a large population of patients from the Johns Hopkins Scleroderma Center Research Registry. The joint probabilities of critical lung and heart events are then calculated as a byproduct of the mixed model. RESULTS: The performance of this approach is substantially better than standard, more common alternatives. In order to predict an individual's risks in a clinical setting, we also develop a cross-validated, sequential prediction (CVSP) algorithm. As additional data are observed during a patient's visit, the algorithm sequentially produces updated predictions for the future longitudinal trajectories and for ILD, cardiomyopathy, and PH. The updated prediction distributions with little additional computing, for example within an electronic health record (EHR). CONCLUSIONS: This method that generates real-time personalized risk estimates has been implemented within the electronic health record system for clinical testing. To our knowledge, this work represents the first approach to compute personalized risk estimates for multiple scleroderma complications.

The Influence of Social Determinants of Health on Emergency Departments Visits in a Medicaid Sample.

STUDY OBJECTIVE: We evaluate the relationship between social determinants of health and emergency department (ED) visits in the Medicaid Cohort of the District of Columbia. METHODS: We conducted a retrospective cohort analysis of 8,943 adult Medicaid beneficiaries who completed a social determinants of health survey at study enrollment. We merged the social determinants of health data with participants' Medicaid claims data for up to 24 months before enrollment. Using latent class analysis, we grouped our participants into 4 distinct social risk classes based on similar responses to the social determinants of health questions. We classified ED visits as primary care treatable or ED care needed, using the Minnesota algorithm. We calculated the adjusted log relative primary care treatable and ED care needed visit rates among the social risk classes by using generalized linear mixed-effects models. RESULTS: The majority (71%) of the 49,111 ED visits made by the 8,943 participants were ED care needed. The adjusted log relative rate of both primary care treatable and ED care needed visit rates increased with each higher (worse) social risk class compared with the lowest class. Participants in the highest social risk class (ie, unemployed and many social risks) had a log relative primary care treatable and ED care needed rate of 39% (range 28% to 50%) and 29% (range 21% to 38%), respectively, adjusted for age, sex, and illness severity. CONCLUSION: There is a strong relationship between social determinants of health and ED utilization in this Medicaid sample that is worth investigating in other Medicaid samples and patient populations.

Estimating autoantibody signatures to detect autoimmune disease patient subsets.

Autoimmune diseases are characterized by highly specific immune responses against molecules in self-tissues. Different autoimmune diseases are characterized by distinct immune responses, making autoantibodies useful for diagnosis and prediction. In many diseases, the targets of autoantibodies are incompletely defined. Although the technologies for autoantibody discovery have advanced dramatically over the past decade, each of these techniques generates hundreds of possibilities, which are onerous and expensive to validate. We set out to establish a method to greatly simplify autoantibody discovery, using a pre-filtering step to define subgroups with similar specificities based on migration of radiolabeled, immunoprecipitated proteins on sodium dodecyl sulfate (SDS) gels and autoradiography [Gel Electrophoresis and band detection on Autoradiograms (GEA)]. Human recognition of patterns is not optimal when the patterns are complex or scattered across many samples. Multiple sources of errors-including irrelevant intensity differences and warping of gels-have challenged automation of pattern discovery from autoradiograms.In this article, we address these limitations using a Bayesian hierarchical model with shrinkage priors for pattern alignment and spatial dewarping. The Bayesian model combines information from multiple gel sets and corrects spatial warping for coherent estimation of autoantibody signatures defined by presence or absence of a grid of landmark proteins. We show the pre-processing creates more clearly separated clusters and improves the accuracy of autoantibody subset detection via hierarchical clustering. Finally, we demonstrate the utility of the proposed methods with GEA data from scleroderma patients.

Clinical risk prediction with random forests for survival, longitudinal, and multivariate (RF-SLAM) data analysis.

BACKGROUND: Clinical research and medical practice can be advanced through the prediction of an individual's health state, trajectory, and responses to treatments. However, the majority of current clinical risk prediction models are based on regression approaches or machine learning algorithms that are static, rather than dynamic. To benefit from the increasing emergence of large, heterogeneous data sets, such as electronic health records (EHRs), novel tools to support improved clinical decision making through methods for individual-level risk prediction that can handle multiple variables, their interactions, and time-varying values are necessary. METHODS: We introduce a novel dynamic approach to clinical risk prediction for survival, longitudinal, and multivariate (SLAM) outcomes, called random forest for SLAM data analysis (RF-SLAM). RF-SLAM is a continuous-time, random forest method for survival analysis that combines the strengths of existing statistical and machine learning methods to produce individualized Bayes estimates of piecewise-constant hazard rates. We also present a method-agnostic approach for time-varying evaluation of model performance. RESULTS: We derive and illustrate the method by predicting sudden cardiac arrest (SCA) in the Left Ventricular Structural (LV) Predictors of Sudden Cardiac Death (SCD) Registry. We demonstrate superior performance relative to standard random forest methods for survival data. We illustrate the importance of the number of preceding heart failure hospitalizations as a time-dependent predictor in SCA risk assessment. CONCLUSIONS: RF-SLAM is a novel statistical and machine learning method that improves risk prediction by incorporating time-varying information and accommodating a large number of predictors, their interactions, and missing values. RF-SLAM is designed to easily extend to simultaneous predictions of multiple, possibly competing, events and/or repeated measurements of discrete or continuous variables over time. TRIAL REGISTRATION: LV Structural Predictors of SCD Registry (clinicaltrials.gov, NCT01076660), retrospectively registered 25 February 2010.

Nested partially latent class models for dependent binary data; estimating disease etiology.

The Pneumonia Etiology Research for Child Health (PERCH) study seeks to use modern measurement technology to infer the causes of pneumonia for which gold-standard evidence is unavailable. Based on case-control data, the article describes a latent variable model designed to infer the etiology distribution for the population of cases, and for an individual case given her measurements. We assume each observation is drawn from a mixture model for which each component represents one disease class. The model conisidered here addresses a major limitation of the traditional latent class approach by taking account of residual dependence among multivariate binary outcomes given disease class, hence reducing estimation bias, retaining efficiency and offering more valid inference. Such "local dependence" on each subject is induced in the model by nesting latent subclasses within each disease class. Measurement precision and covariation can be estimated using the control sample for whom the class is known. In a Bayesian framework, we use stick-breaking priors on the subclass indicators for model-averaged inference across different numbers of subclasses. Assessment of model fit and individual diagnosis are done using posterior samples drawn by Gibbs sampling. We demonstrate the utility of the method on simulated and on the motivating PERCH data.

Addressing the Analytic Challenges of Cross-Sectional Pediatric Pneumonia Etiology Data.

Despite tremendous advances in diagnostic laboratory technology, identifying the pathogen(s) causing pneumonia remains challenging because the infected lung tissue cannot usually be sampled for testing. Consequently, to obtain information about pneumonia etiology, clinicians and researchers test specimens distant to the site of infection. These tests may lack sensitivity (eg, blood culture, which is only positive in a small proportion of children with pneumonia) and/or specificity (eg, detection of pathogens in upper respiratory tract specimens, which may indicate asymptomatic carriage or a less severe syndrome, such as upper respiratory infection). While highly sensitive nucleic acid detection methods and testing of multiple specimens improve sensitivity, multiple pathogens are often detected and this adds complexity to the interpretation as the etiologic significance of results may be unclear (ie, the pneumonia may be caused by none, one, some, or all of the pathogens detected). Some of these challenges can be addressed by adjusting positivity rates to account for poor sensitivity or incorporating test results from controls without pneumonia to account for poor specificity. However, no classical analytic methods can account for measurement error (ie, sensitivity and specificity) for multiple specimen types and integrate the results of measurements for multiple pathogens to produce an accurate understanding of etiology. We describe the major analytic challenges in determining pneumonia etiology and review how the common analytical approaches (eg, descriptive, case-control, attributable fraction, latent class analysis) address some but not all challenges. We demonstrate how these limitations necessitate a new, integrated analytical approach to pneumonia etiology data.

Should Controls With Respiratory Symptoms Be Excluded From Case-Control Studies of Pneumonia Etiology? Reflections From the PERCH Study.

Many pneumonia etiology case-control studies exclude controls with respiratory illness from enrollment or analyses. Herein we argue that selecting controls regardless of respiratory symptoms provides the least biased estimates of pneumonia etiology. We review 3 reasons investigators may choose to exclude controls with respiratory symptoms in light of epidemiologic principles of control selection and present data from the Pneumonia Etiology Research for Child Health (PERCH) study where relevant to assess their validity. We conclude that exclusion of controls with respiratory symptoms will result in biased estimates of etiology. Randomly selected community controls, with or without respiratory symptoms, as long as they do not meet the criteria for case-defining pneumonia, are most representative of the general population from which cases arose and the least subject to selection bias.