Search

Abstract Post marketing safety surveillance depends in part on the ability to detect concerning clinical events at scale. Spontaneous reporting might be an effective component of safety surveillance, but it requires awareness and understanding among healthcare professionals to achieve its potential. Reliance on readily available structured data such as diagnostic codes risks under-coding and imprecision. Clinical textual data might bridge these gaps, and natural language processing (NLP) has been shown to aid in scalable phenotyping across healthcare records in multiple clinical domains. In this study, we developed and validated a novel incident phenotyping approach using unstructured clinical textual data agnostic to Electronic Health Record (EHR) and note type. It’s based on a published, validated approach (PheRe) used to ascertain social determinants of health and suicidality across entire healthcare records. To demonstrate generalizability, we validated this approach on two separate phenotypes that share common challenges with respect to accurate ascertainment: (1) suicide attempt; (2) sleep-related behaviors. With samples of 89,428 records and 35,863 records for suicide attempt and sleep-related behaviors, respectively, we conducted silver standard (diagnostic coding) and gold standard (manual chart review) validation. We showed Area Under the Precision-Recall Curve of ~ 0.77 (95% CI 0.75–0.78) for suicide attempt and AUPR ~ 0.31 (95% CI 0.28–0.34) for sleep-related behaviors. We also evaluated performance by coded race and demonstrated differences in performance by race differed across phenotypes. Scalable phenotyping models, like most healthcare AI, require algorithmovigilance and debiasing prior to implementation.

Rationale and Objective: Acute kidney injury (AKI) is a common complication among hospitalized adults, but AKI prediction and prevention among adults has proved challenging. We used machine learning to update the nephrotoxic injury negated by just-in time action (NINJA), a pediatric program that predicts nephrotoxic AKI, to improve accuracy among adults. Study Design: A retrospective cohort study. Setting and Population: Adults admitted for > 48 hours to the University of Iowa Hospital from 2017 to 2022. Exposure: A NINJA high-nephrotoxin exposure (≥3 nephrotoxins on 1 day or intravenous aminoglycoside or vancomycin for ≥3 days). Outcomes: AKI within 48 hours of high-nephrotoxin exposure. Analytical Approach: We collected 85 variables, including demographics, laboratory tests, vital signs, and medications. AKI was defined as a serum creatinine increase of ≥0.3 mg/dL. A gated recurrent unit (GRU)-based recurrent neural network (RNN) was trained on 85% of the data, and then tested on the remaining 15%. Model performance was evaluated with precision, recall, negative predictive value, and area under the curve. We used an artificial neural network to determine risk factor importance. Results: There were 14,480 patients, 18,180 admissions, and 37,300 high-nephrotoxin exposure events meeting inclusion criteria. In the testing cohort, 29% of exposures developed AKI within 48 hours. The RNN-GRU model predicted AKI with a precision of 0.60, reducing the number of false alerts from 2.5 to 0.7 per AKI case. Lowest hemoglobin, lowest blood pressure, and highest white blood cell count were the most important variables in the artificial neural network model. Acyclovir, piperacillin-tazobactam, calcineurin inhibitors, and angiotensin-converting enzyme inhibitor/angiotensin receptor blockers were the most important medications. Limitations: Clinical variables and medications were not exhaustive, drug levels or dosing were not incorporated, and Iowa’s racial makeup may limit generalizability. Conclusions: Our RNN-GRU model substantially reduced the number of false alerts for nephrotoxic AKI, which may facilitate NINJA translation to adult hospitals by providing more targeted intervention. Plain-Language Summary: Nephrotoxic acute kidney injury (AKI) is common and can potentially be prevented through preemptive adjustments of medications, as demonstrated by the success of the nephrotoxic injury negated by just-in time action (NINJA) program in pediatric populations. Translation of NINJA to the adult population has been challenging, and major barriers include high alert volume in adults that can lead to high resource utilization and alert fatigue. To address this issue, we developed a machine learning model for nephrotoxic AKI in adults that reduced the number of false alerts per AKI event from 2.5 to 0.7, which can enhance future NINJA implementation in adults by allowing for a more targeted intervention with fewer alerts and more efficient resource utilization.

To explore threats and opportunities and to chart a path for safely navigating the rapid changes that generative artificial intelligence (AI) will bring to clinical research, the Duke Clinical Research Institute convened a multidisciplinary think tank in January 2024. Leading experts from academia, industry, nonprofits, and government agencies highlighted the potential opportunities of generative AI in automation of documentation, strengthening of participant and community engagement, and improvement of trial accuracy and efficiency. Challenges include technical hurdles, ethical dilemmas, and regulatory uncertainties. Success is expected to require establishing rigorous data management and security protocols, fostering integrity and trust among stakeholders, and sharing information about the safety and effectiveness of AI applications. Meeting insights point towards a future where, through collaboration and transparency, generative AI will help to shorten the translational pipeline and increase the inclusivity and equitability of clinical research.

Electronic health records (EHRs) have emerged as resources for both the identification of adverse drug events (ADEs) and general population health surveillance, however questions remain around how best to utilize EHR data for drug safety signal identification. While the majority of signal identification research has utilized spontaneous reports and health insurance claims, these data also have limitations. Pharmacovigilance approaches combining EHR data with other data sources have the potential to address many of the shortcomings of individual sources. This mini-review seeks to provide an overview of some of the recent research leveraging EHR data in combination with spontaneous reports, claims data, and other pharmacovigilance data sources for drug safety signal identification. Studies have shown that combining EHR data with these and other sources is often beneficial compared to the use of a single source alone, however the synergism or friction introduced is insufficiently explored in current literature. Our review explores how EHR data benefits signal identification when used in combination with other sources, what methods have been applied, and what considerations have previously been noted. Finally, we identify gaps in current research and highlight important considerations for future work using multiple real world data sources for drug safety surveillance.

Abstract Introduction Acute kidney injury (AKI) is associated with increased risk of heart failure (HF). Determining the type of HF experienced by AKI survivors (heart failure with preserved or reduced ejection fraction, HFpEF or HFrEF) could suggest potential mechanisms underlying the association and opportunities for improving post-AKI care. Methods In this retrospective study of adults within the Vanderbilt University health system with a diagnosis of HF, we tested whether AKI events in the two years preceding incident HF associated more with HFpEF or HFrEF while controlling for known predictors. HF outcomes were defined by administrative codes and classified as HFpEF or HFrEF by echocardiogram data. We used multivariable logistic regression models to estimate the effects of AKI on the odds of incident HFpEF versus HFrEF. Results AKI (all stages) trended towards a preferential association with HFpEF in adjusted analyses (adjusted OR 0.80, 95% CI 0.63 – 1.01). Stage 1 AKI was associated with higher odds of HFpEF that was statistically significant (adjusted OR 0.62, 95% CI 0.43 – 0.88), whereas stages 2–3 AKI showed a trend toward HFrEF that did not reach statistical significance (adjusted OR 1.11, 95% CI 0.76 – 1.63). Conclusions AKI as a binary outcome trended towards a preferential association with HFpEF. Stage 1 AKI was associated with higher odds of HFpEF, whereas stage 2–3 trended towards an association with HFrEF that did not meet statistical significance. Different mechanisms may predominate in incident HF following mild versus more severe AKI. Close follow-up with particular attention to volume status and cardiac function after discharge is warranted after even mild AKI.

Abstract Background Despite efforts to enhance the quality of medication prescribing in outpatient settings, potentially inappropriate prescribing remains common, particularly in unscheduled settings where patients can present with infectious and pain-related complaints. Two of the most commonly prescribed medication classes in outpatient settings with frequent rates of potentially inappropriate prescribing include antibiotics and nonsteroidal anti-inflammatory drugs (NSAIDs). In the setting of persistent inappropriate prescribing, we sought to understand a diverse set of perspectives on the determinants of inappropriate prescribing of antibiotics and NSAIDs in the Veterans Health Administration. Methods We conducted a qualitative study guided by the Consolidated Framework for Implementation Research and Theory of Planned Behavior. Semi-structured interviews were conducted with clinicians, stakeholders, and Veterans from March 1, 2021 through December 31, 2021 within the Veteran Affairs Health System in unscheduled outpatient settings at the Tennessee Valley Healthcare System. Stakeholders included clinical operations leadership and methodological experts. Audio-recorded interviews were transcribed and de-identified. Data coding and analysis were conducted by experienced qualitative methodologists adhering to the Consolidated Criteria for Reporting Qualitative Studies guidelines. Analysis was conducted using an iterative inductive/deductive process. Results We conducted semi-structured interviews with 66 participants: clinicians (N = 25), stakeholders (N = 24), and Veterans (N = 17). We identified six themes contributing to potentially inappropriate prescribing of antibiotics and NSAIDs: 1) Perceived versus actual Veterans expectations about prescribing; 2) the influence of a time-pressured clinical environment on prescribing stewardship; 3) Limited clinician knowledge, awareness, and willingness to use evidence-based care; 4) Prescriber uncertainties about the Veteran condition at the time of the clinical encounter; 5) Limited communication; and 6) Technology barriers of the electronic health record and patient portal. Conclusions The diverse perspectives on prescribing underscore the need for interventions that recognize the detrimental impact of high workload on prescribing stewardship and the need to design interventions with the end-user in mind. This study revealed actionable themes that could be addressed to improve guideline concordant prescribing to enhance the quality of prescribing and to reduce patient harm.

Objective: Assigning outcome labels to large observational data sets in a timely and accurate manner, particularly when outcomes are rare or not directly ascertainable, remains a significant challenge within biomedical informatics. We examined whether noisy labels generated from subject matter experts’ heuristics using heterogenous data types within a data programming paradigm could provide outcomes labels to a large, observational data set. We chose the clinical condition of opioid-induced respiratory depression for our use case because it is rare, has no administrative codes to easily identify the condition, and typically requires at least some unstructured text to ascertain its presence. Materials and methods: Using de-identified electronic health records of 52,861 post-operative encounters, we applied a data programming paradigm (implemented in the Snorkel software) for the development of a machine learning classifier for opioid-induced respiratory depression. Our approach included subject matter experts creating 14 labeling functions that served as noisy labels for developing a probabilistic Generative model. We used probabilistic labels from the Generative model as outcome labels for training a Discriminative model on the source data. We evaluated performance of the Discriminative model with a hold-out test set of 599 independently-reviewed patient records. Results: The final Discriminative classification model achieved an accuracy of 0.977, an F1 score of 0.417, a sensitivity of 1.0, and an AUC of 0.988 in the hold-out test set with a prevalence of 0.83% (5/599). Discussion: All of the confirmed Cases were identified by the classifier. For rare outcomes, this finding is encouraging because it reduces the number of manual reviews needed by excluding visits/patients with low probabilities. Conclusion: Application of a data programming paradigm with expert-informed labeling functions might have utility for phenotyping clinical phenomena that are not easily ascertainable from highly-structured data.

Abstract Background Validating new algorithms, such as methods to disentangle intrinsic treatment risk from risk associated with experiential learning of novel treatments, often requires knowing the ground truth for data characteristics under investigation. Since the ground truth is inaccessible in real world data, simulation studies using synthetic datasets that mimic complex clinical environments are essential. We describe and evaluate a generalizable framework for injecting hierarchical learning effects within a robust data generation process that incorporates the magnitude of intrinsic risk and accounts for known critical elements in clinical data relationships. Methods We present a multi-step data generating process with customizable options and flexible modules to support a variety of simulation requirements. Synthetic patients with nonlinear and correlated features are assigned to provider and institution case series. The probability of treatment and outcome assignment are associated with patient features based on user definitions. Risk due to experiential learning by providers and/or institutions when novel treatments are introduced is injected at various speeds and magnitudes. To further reflect real-world complexity, users can request missing values and omitted variables. We illustrate an implementation of our method in a case study using MIMIC-III data for reference patient feature distributions. Results Realized data characteristics in the simulated data reflected specified values. Apparent deviations in treatment effects and feature distributions, though not statistically significant, were most common in small datasets (n

Abstract Given the growing number of prediction algorithms developed to predict COVID-19 mortality, we evaluated the transportability of a mortality prediction algorithm using a multi-national network of healthcare systems. We predicted COVID-19 mortality using baseline commonly measured laboratory values and standard demographic and clinical covariates across healthcare systems, countries, and continents. Specifically, we trained a Cox regression model with nine measured laboratory test values, standard demographics at admission, and comorbidity burden pre-admission. These models were compared at site, country, and continent level. Of the 39,969 hospitalized patients with COVID-19 (68.6% male), 5717 (14.3%) died. In the Cox model, age, albumin, AST, creatine, CRP, and white blood cell count are most predictive of mortality. The baseline covariates are more predictive of mortality during the early days of COVID-19 hospitalization. Models trained at healthcare systems with larger cohort size largely retain good transportability performance when porting to different sites. The combination of routine laboratory test values at admission along with basic demographic features can predict mortality in patients hospitalized with COVID-19. Importantly, this potentially deployable model differs from prior work by demonstrating not only consistent performance but also reliable transportability across healthcare systems in the US and Europe, highlighting the generalizability of this model and the overall approach.

Abstract Background We investigated whether we could use influenza data to develop prediction models for COVID-19 to increase the speed at which prediction models can reliably be developed and validated early in a pandemic. We developed COVID-19 Estimated Risk (COVER) scores that quantify a patient’s risk of hospital admission with pneumonia (COVER-H), hospitalization with pneumonia requiring intensive services or death (COVER-I), or fatality (COVER-F) in the 30-days following COVID-19 diagnosis using historical data from patients with influenza or flu-like symptoms and tested this in COVID-19 patients. Methods We analyzed a federated network of electronic medical records and administrative claims data from 14 data sources and 6 countries containing data collected on or before 4/27/2020. We used a 2-step process to develop 3 scores using historical data from patients with influenza or flu-like symptoms any time prior to 2020. The first step was to create a data-driven model using LASSO regularized logistic regression, the covariates of which were used to develop aggregate covariates for the second step where the COVER scores were developed using a smaller set of features. These 3 COVER scores were then externally validated on patients with 1) influenza or flu-like symptoms and 2) confirmed or suspected COVID-19 diagnosis across 5 databases from South Korea, Spain, and the United States. Outcomes included i) hospitalization with pneumonia, ii) hospitalization with pneumonia requiring intensive services or death, and iii) death in the 30 days after index date. Results Overall, 44,507 COVID-19 patients were included for model validation. We identified 7 predictors (history of cancer, chronic obstructive pulmonary disease, diabetes, heart disease, hypertension, hyperlipidemia, kidney disease) which combined with age and sex discriminated which patients would experience any of our three outcomes. The models achieved good performance in influenza and COVID-19 cohorts. For COVID-19 the AUC ranges were, COVER-H: 0.69–0.81, COVER-I: 0.73–0.91, and COVER-F: 0.72–0.90. Calibration varied across the validations with some of the COVID-19 validations being less well calibrated than the influenza validations. Conclusions This research demonstrated the utility of using a proxy disease to develop a prediction model. The 3 COVER models with 9-predictors that were developed using influenza data perform well for COVID-19 patients for predicting hospitalization, intensive services, and fatality. The scores showed good discriminatory performance which transferred well to the COVID-19 population. There was some miscalibration in the COVID-19 validations, which is potentially due to the difference in symptom severity between the two diseases. A possible solution for this is to recalibrate the models in each location before use.

Background and Aims: Gastrointestinal (GI) symptoms are well-recognized manifestations of coronavirus disease 2019 (COVID-19). Our primary objective was to evaluate the association between GI symptoms and COVID-19 severity. Methods: In this nationwide cohort of US veterans, we evaluated GI symptoms (nausea/vomiting/diarrhea) reported 30 days before and including the date of positive SARS-CoV-2 testing (March 1, 2020, to February 20, 2021). All patients had ≥1 year of prior baseline data and ≥60 days follow-up relative to the test date. We used propensity score (PS)-weighting to balance covariates in patients with vs without GI symptoms. The primary composite outcome was severe COVID-19, defined as hospital admission, intensive care unit admission, mechanical ventilation, or death within 60 days of positive testing. Results: Of 218,045 SARS-CoV-2 positive patients, 29,257 (13.4%) had GI symptoms. After PS weighting, all covariates were balanced. In the PS-weighted cohort, patients with vs without GI symptoms had severe COVID-19 more often (29.0% vs 17.1%; P < .001). When restricted to hospitalized patients (14.9%; n=32,430), patients with GI symptoms had similar frequencies of intensive care unit admission and mechanical ventilation compared with patients without symptoms. There was a significant age interaction; among hospitalized patients aged ≥70 years, lower COVID-19–associated mortality was observed in patients with vs without GI symptoms, even after accounting for COVID-19–specific medical treatments. Conclusion: In the largest integrated US health care system, SARS-CoV-2–positive patients with GI symptoms experienced severe COVID-19 outcomes more often than those without symptoms. Additional research on COVID-19–associated GI symptoms may inform preventive efforts and interventions to reduce severe COVID-19.

Abstract Many patients with bipolar disorder (BD) are initially misdiagnosed with major depressive disorder (MDD) and are treated with antidepressants, whose potential iatrogenic effects are widely discussed. It is unknown whether MDD is a comorbidity of BD or its earlier stage, and no consensus exists on individual conversion predictors, delaying BD’s timely recognition and treatment. We aimed to build a predictive model of MDD to BD conversion and to validate it across a multi-national network of patient databases using the standardization afforded by the Observational Medical Outcomes Partnership (OMOP) common data model. Five “training” US databases were retrospectively analyzed: IBM MarketScan CCAE, MDCR, MDCD, Optum EHR, and Optum Claims. Cyclops regularized logistic regression models were developed on one-year MDD-BD conversion with all standard covariates from the HADES PatientLevelPrediction package. Time-to-conversion Kaplan-Meier analysis was performed up to a decade after MDD, stratified by model-estimated risk. External validation of the final prediction model was performed across 9 patient record databases within the Observational Health Data Sciences and Informatics (OHDSI) network internationally. The model’s area under the curve (AUC) varied 0.633–0.745 (µ = 0.689) across the five US training databases. Nine variables predicted one-year MDD-BD transition. Factors that increased risk were: younger age, severe depression, psychosis, anxiety, substance misuse, self-harm thoughts/actions, and prior mental disorder. AUCs of the validation datasets ranged 0.570–0.785 (µ = 0.664). An assessment algorithm was built for MDD to BD conversion that allows distinguishing as much as 100-fold risk differences among patients and validates well across multiple international data sources.

Abstract The Sentinel System is a major component of the United States Food and Drug Administration’s (FDA) approach to active medical product safety surveillance. While Sentinel has historically relied on large quantities of health insurance claims data, leveraging longitudinal electronic health records (EHRs) that contain more detailed clinical information, as structured and unstructured features, may address some of the current gaps in capabilities. We identify key challenges when using EHR data to investigate medical product safety in a scalable and accelerated way, outline potential solutions, and describe the Sentinel Innovation Center’s initiatives to put solutions into practice by expanding and strengthening the existing system with a query-ready, large-scale data infrastructure of linked EHR and claims data. We describe our initiatives in four strategic priority areas: (1) data infrastructure, (2) feature engineering, (3) causal inference, and (4) detection analytics, with the goal of incorporating emerging data science innovations to maximize the utility of EHR data for medical product safety surveillance.

Purpose: Alpha-1 blockers, often used to treat benign prostatic hyperplasia (BPH), have been hypothesized to prevent COVID-19 complications by minimising cytokine storm release. The proposed treatment based on this hypothesis currently lacks support from reliable real-world evidence, however. We leverage an international network of large-scale healthcare databases to generate comprehensive evidence in a transparent and reproducible manner.Methods: In this international cohort study, we deployed electronic health records from Spain (SIDIAP) and the United States (Department of Veterans Affairs, Columbia University Irving Medical Center, IQVIA OpenClaims, Optum DOD, Optum EHR). We assessed association between alpha-1 blocker use and risks of three COVID-19 outcomes—diagnosis, hospitalization, and hospitalization requiring intensive services—using a prevalent-user active-comparator design. We estimated hazard ratios using state-of-the-art techniques to minimize potential confounding, including large-scale propensity score matching/stratification and negative control calibration. We pooled database-specific estimates through random effects meta-analysis.Results: Our study overall included 2.6 and 0.46 million users of alpha-1 blockers and of alternative BPH medications. We observed no significant difference in their risks for any of the COVID-19 outcomes, with our meta-analytic HR estimates being 1.02 (95% CI: 0.92–1.13) for diagnosis, 1.00 (95% CI: 0.89–1.13) for hospitalization, and 1.15 (95% CI: 0.71–1.88) for hospitalization requiring intensive services.Conclusion: We found no evidence of the hypothesized reduction in risks of the COVID-19 outcomes from the prevalent-use of alpha-1 blockers—further research is needed to identify effective therapies for this novel disease.

As the implementation of artificial intelligence (AI)-enabled tools is realized across diverse clinical environments, there is a growing understanding of the need for ongoing monitoring and updating of prediction models. Dataset shift—temporal changes in clinical practice, patient populations, and information systems—is now well-documented as a source of deteriorating model accuracy and a challenge to the sustainability of AI-enabled tools in clinical care. While best practices are well-established for training and validating new models, there has been limited work developing best practices for prospective validation and model maintenance. In this paper, we highlight the need for updating clinical prediction models and discuss open questions regarding this critical aspect of the AI modeling lifecycle in three focus areas: model maintenance policies, performance monitoring perspectives, and model updating strategies. With the increasing adoption of AI-enabled tools, the need for such best practices must be addressed and incorporated into new and existing implementations. This commentary aims to encourage conversation and motivate additional research across clinical and data science stakeholders.

Artificial intelligence (AI) has demonstrated promise in predicting acutekidney injury (AKI), however, clinical adoption of these models requires interpretability and transportability across sites. Here, the authors develop an AKI prediction model and a measure for model transportability across six independent health systems.

Detailed knowledge of the characteristics of COVID-19 patients helps with public health planning. Here, the authors use routinely-collected data from seven databases in three countries to describe the characteristics of >30,000 patients admitted with COVID-19 and compare them with those admitted for influenza in previous years.

Background Social risk factors influence rehospitalization rates yet are challenging to incorporate into prediction models. Integration of social risk factors using natural language processing (NLP) and machine learning could improve risk prediction of 30‐day readmission following an acute myocardial infarction. Methods and Results Patients were enrolled into derivation and validation cohorts. The derivation cohort included inpatient discharges from Vanderbilt University Medical Center between January 1, 2007, and December 31, 2016, with a primary diagnosis of acute myocardial infarction, who were discharged alive, and not transferred from another facility. The validation cohort included patients from Dartmouth‐Hitchcock Health Center between April 2, 2011, and December 31, 2016, meeting the same eligibility criteria described above. Data from both sites were linked to Centers for Medicare & Medicaid Services administrative data to supplement 30‐day hospital readmissions. Clinical notes from each cohort were extracted, and an NLP model was deployed, counting mentions of 7 social risk factors. Five machine learning models were run using clinical and NLP‐derived variables. Model discrimination and calibration were assessed, and receiver operating characteristic comparison analyses were performed. The 30‐day rehospitalization rates among the derivation (n=6165) and validation (n=4024) cohorts were 15.1% (n=934) and 10.2% (n=412), respectively. The derivation models demonstrated no statistical improvement in model performance with the addition of the selected NLP‐derived social risk factors. Conclusions Social risk factors extracted using NLP did not significantly improve 30‐day readmission prediction among hospitalized patients with acute myocardial infarction. Alternative methods are needed to capture social risk factors.

Objective: To determine whether natural language processing (NLP) of unstructured medical text can improve identification of ASCVD patients not using high-intensity statin therapy (HIST) due to statin-associated side effects (SASEs) and other reasons. Methods: Reviewers annotated reasons for not prescribing HIST in notes of 1152 randomly selected patients from across the VA healthcare system treated for ASCVD but not receiving HIST. Developers used reviewer annotations to train the Canary NLP tool to detect and extract notes containing one or more of these reasons. Negative predictive value (NPV), sensitivity, specificity and Area Under the Curve (AUC) were used to assess accuracy at detecting documents containing reasons when using structured data, NLP-extracted unstructured data, or both data sources combined. Results: At least one documented reason for not prescribing HIST occurred in 47% of notes. The most frequent reasons were SASEs (41%) and general intolerance (20%). When identifying notes containing any documented reason for not using HIST, adding NLP-extracted, unstructured data significantly (p

OBJECTIVES/GOALS: Using the covariate-rich Veteran Health Administration data, estimate the association between Proton Pump Inhibitor (PPI) use and severe COVID-19, rigorously adjusting for confounding using propensity score (PS)-weighting. METHODS/STUDY POPULATION: We assembled a national retrospective cohort of United States veterans who tested positive for SARS-CoV-2, with information on 33 covariates including comorbidity diagnoses, lab values, and medications. Current outpatient PPI use was compared to non-use (two or more fills and pills on hand at admission vs no PPI prescription fill in prior year). The primary composite outcome was mechanical ventilation use or death within 60 days; the secondary composite outcome included ICU admission. PS-weighting mimicked a 1:1 matching cohort, allowing inclusion of all patients while achieving good covariate balance. The weighted cohort was analyzed using logistic regression. RESULTS/ANTICIPATED RESULTS: Our analytic cohort included 97,674 veterans with SARS-CoV-2 testing, of whom 14,958 (15.3%) tested positive (6,262 [41.9%] current PPI-users, 8,696 [58.1%] non-users). After weighting, all covariates were well-balanced with standardized mean differences less than a threshold of 0.1. Prior to PS-weighting (no covariate adjustment), we observed higher odds of the primary (9.3% vs 7.5%; OR 1.27, 95% CI 1.13-1.43) and secondary (25.8% vs 21.4%; OR 1.27, 95% CI 1.18-1.37) outcomes among PPI users vs non-users. After PS-weighting, PPI use vs non-use was not associated with the primary (8.2% vs 8.0%; OR 1.03, 95% CI 0.91-1.16) or secondary (23.4% vs 22.9%;OR 1.03, 95% CI 0.95-1.12) outcomes. DISCUSSION/SIGNIFICANCE: The associations between PPI use and severe COVID-19 outcomes that have been previously reported may be due to limitations in the covariates available for adjustment. With respect to COVID-19, our robust PS-weighted analysis provides patients and providers with further evidence for PPI safety.

Abstract Background Estimated glomerular filtration rate (eGFR) is the clinical standard for assessing kidney function and staging chronic kidney disease. Automated reporting of eGFR using the Modification of Diet in Renal Disease (MDRD) study equation was first implemented within the Department of Veterans Affairs (VA) in 2007 with staggered adoption across laboratories. When automated eGFR are not used or unavailable, values are retrospectively calculated using clinical and demographic data that are currently available in the electronic health record (EHR). Due to the dynamic nature of EHRs, current data may not always match past data. Whether and to what extent the practice of re-calculating eGFR on retrospective data differs from using the automated values is unknown. Methods We assessed clinical data for patients enrolled in VA who had their first automated eGFR lab in 2013.We extracted the eGFR value, the corresponding serum creatinine value, and patient race, gender, and date of birth from the EHR. The MDRD equation was applied to retrospectively calculate eGFR. Stage of chronic kidney disease (CKD) was defined using both eGFR values. We used Bland–Altman plots and percent agreement to assess the difference between the automated and calculated values. We developed an algorithm to select the most parsimonious parameter set to explain the difference in values and used chart review on a small subsample of patients to determine if one approach more accurately describes the patient at the time of eGFR measurement. Results We evaluated eGFR data pairs from 266,084 patients. Approximately 33.0% (n = 86,747) of eGFR values differed between automated and retrospectively calculated methods. The majority of discordant pairs were classified as the same CKD stage (n = 74,542, 85.93%). The Bland–Altman plot showed differences in the data pairs were centered near zero (mean difference: 0.8 mL/min/1.73m2) with 95% limits of agreement between − 6.4 and 8.0. A change in recorded age explained 95.6% (n = 78,903) of discordant values and 85.02% (n = 9371) of the discordant stages. Conclusions Values of retrospectively calculated eGFR can differ from automated values, but do not always result in a significant classification change. In very large datasets these small differences could become significant.

Abstract Background To realize potential public health benefits from genetic and genomic innovations, understanding how best to implement the innovations into clinical care is important. The objective of this study was to synthesize data on challenges identified by six diverse projects that are part of a National Human Genome Research Institute (NHGRI)-funded network focused on implementing genomics into practice and strategies to overcome these challenges. Methods We used a multiple-case study approach with each project considered as a case and qualitative methods to elicit and describe themes related to implementation challenges and strategies. We describe challenges and strategies in an implementation framework and typology to enable consistent definitions and cross-case comparisons. Strategies were linked to challenges based on expert review and shared themes. Results Three challenges were identified by all six projects, and strategies to address these challenges varied across the projects. One common challenge was to increase the relative priority of integrating genomics within the health system electronic health record (EHR). Four projects used data warehousing techniques to accomplish the integration. The second common challenge was to strengthen clinicians’ knowledge and beliefs about genomic medicine. To overcome this challenge, all projects developed educational materials and conducted meetings and outreach focused on genomic education for clinicians. The third challenge was engaging patients in the genomic medicine projects. Strategies to overcome this challenge included use of mass media to spread the word, actively involving patients in implementation (e.g., a patient advisory board), and preparing patients to be active participants in their healthcare decisions. Conclusions This is the first collaborative evaluation focusing on the description of genomic medicine innovations implemented in multiple real-world clinical settings. Findings suggest that strategies to facilitate integration of genomic data within existing EHRs and educate stakeholders about the value of genomic services are considered important for effective implementation. Future work could build on these findings to evaluate which strategies are optimal under what conditions. This information will be useful for guiding translation of discoveries to clinical care, which, in turn, can provide data to inform continual improvement of genomic innovations and their applications.

Objectives. This research describes the prevalence and covariates associated with opioid-induced constipation (OIC) in an observational cohort study utilizing a national veteran cohort and integrated data from the Center for Medicare and Medicaid Services (CMS). Methods. A cohort of 152,904 veterans with encounters between 1 January 2008 and 30 November 2010, an exposure to opioids of 30 days or more, and no exposure in the prior year was developed to establish existing conditions and medications at the start of the opioid exposure and determining outcomes through the end of exposure. OIC was identified through additions/changes in laxative prescriptions, all-cause constipation identification through diagnosis, or constipation related procedures in the presence of opioid exposure. The association of time to constipation with opioid use was analyzed using Cox proportional hazard regression adjusted for patient characteristics, concomitant medications, laboratory tests, and comorbidities. Results. The prevalence of OIC was 12.6%. Twelve positively associated covariates were identified with the largest associations for prior constipation and prevalent laxative (any laxative that continued into the first day of opioid exposure). Among the 17 negatively associated covariates, the largest associations were for erythromycins, androgens/anabolics, and unknown race. Conclusions. There were several novel covariates found that are seen in the all-cause chronic constipation literature but have not been reported for opioid-induced constipation. Some are modifiable covariates, particularly medication coadministration, which may assist clinicians and researchers in risk stratification efforts when initiating opioid medications. The integration of CMS data supports the robustness of the analysis and may be of interest in the elderly population warranting future examination.

BackgroundStudies of kidney disease associated with cardiac catheterization typically rely on billing records rather than laboratory data. We examined the associations between percutaneous coronary interventions, acute kidney injury, and chronic kidney disease progression using comprehensive Veterans Affairs clinical and laboratory databases. Methods and ResultsPatients undergoing percutaneous coronary interventions between 2005 and 2010 (N=24 405) were identified in the Veterans Affairs Clinical Assessment, Reporting, and Tracking registry and examined for associated acute kidney injury and chronic kidney disease development or progression relative to 24 405 matched population controls. Secondary outcomes analyzed included dialysis, acute myocardial infarction, and mortality. The incidence of chronic kidney disease progression following percutaneous coronary interventions complicated by acute kidney injury, following uncomplicated coronary interventions, and in matched controls were 28.66, 11.15, and 6.81 per 100 person‐years, respectively. Percutaneous coronary intervention also increased the likelihood of chronic kidney disease progression in both the presence and absence of acute injury relative to controls in adjusted analyses (hazard ratio [HR], 5.02 [95% CI, 4.68–5.39]; and HR, 1.76 [95% CI, 1.70–1.86]). Among patients with estimated glomerular filtration rate

BackgroundAcute kidney injury (AKI) and dialysis‐requiring AKI (AKI‐D) are common, serious complications of cardiac procedures. Methods and ResultsWe evaluated 3 633 762 (17 765 214 weighted population) cardiac catheterization or percutaneous coronary intervention (PCI) hospital discharges from the nationally representative National Inpatient Sample to determine annual population incidence rates for AKI and AKI‐D in the United States from 2001 to 2011. Odds ratios for both conditions and associated in‐hospital mortality were calculated for each year in the study period using multiple logistic regression. The number of cardiac catheterization or PCI cases resulting in AKI rose almost 3‐fold from 2001 to 2011. The adjusted odds of AKI and AKI‐D per year among cardiac catheterization and PCI patients were 1.11 (95% CI: 1.10–1.12) and 1.01 (95% CI: 0.99–1.02), respectively. Most importantly, in‐hospital mortality significantly decreased from 2001 to 2011 for AKI (19.6–9.2%) and AKI‐D (28.3–19.9%), whereas odds of associated in‐hospital mortality were 0.50 (95% CI: 0.45–0.56) and 0.70 (95% CI: 0.55–0.93) in 2011 versus 2001, respectively. The population‐attributable risk of mortality for AKI and AKI‐D was 25.8% and 3.8% in 2001 and 41.1% and 6.5% in 2011, respectively. Males and females had similar patterns of AKI increase, although males outpaced females. ConclusionsThe Incidence of AKI among cardiac catheterization and PCI patients has increased sharply in the United States, and this should be addressed by implementing prevention strategies. However, mortality has significantly declined, suggesting that efforts to manage AKI and AKI‐D after cardiac catheterization and PCI have reduced mortality.

Background Acute kidney injury (AKI) occurs frequently after cardiac catheterization and percutaneous coronary intervention. Although a clinical risk model exists for percutaneous coronary intervention, no models exist for both procedures, nor do existing models account for risk factors prior to the index admission. We aimed to develop such a model for use in prospective automated surveillance programs in the Veterans Health Administration. Methods and Results We collected data on all patients undergoing cardiac catheterization or percutaneous coronary intervention in the Veterans Health Administration from January 01, 2009 to September 30, 2013, excluding patients with chronic dialysis, end‐stage renal disease, renal transplant, and missing pre‐ and postprocedural creatinine measurement. We used 4 AKI definitions in model development and included risk factors from up to 1 year prior to the procedure and at presentation. We developed our prediction models for postprocedural AKI using the least absolute shrinkage and selection operator (LASSO) and internally validated using bootstrapping. We developed models using 115 633 angiogram procedures and externally validated using 27 905 procedures from a New England cohort. Models had cross‐validated C‐statistics of 0.74 (95% CI: 0.74–0.75) for AKI, 0.83 (95% CI: 0.82–0.84) for AKIN2, 0.74 (95% CI: 0.74–0.75) for contrast‐induced nephropathy, and 0.89 (95% CI: 0.87–0.90) for dialysis. Conclusions We developed a robust, externally validated clinical prediction model for AKI following cardiac catheterization or percutaneous coronary intervention to automatically identify high‐risk patients before and immediately after a procedure in the Veterans Health Administration. Work is ongoing to incorporate these models into routine clinical practice.