Pragmatic Trial of Hospitalization Rate in Chronic Kidney Disease.

BACKGROUND: Despite the availability of effective therapies for patients with chronic kidney disease, type 2 diabetes, and hypertension (the kidney-dysfunction triad), the results of large-scale trials examining the implementation of guideline-directed therapy to reduce the risk of death and complications in this population are lacking. METHODS: In this open-label, cluster-randomized trial, we assigned 11,182 patients with the kidney-dysfunction triad who were being treated at 141 primary care clinics either to receive an intervention that used a personalized algorithm (based on the patient's electronic health record [EHR]) to identify patients and practice facilitators to assist providers in delivering guideline-based interventions or to receive usual care. The primary outcome was hospitalization for any cause at 1 year. Secondary outcomes included emergency department visits, readmissions, cardiovascular events, dialysis, and death. RESULTS: We assigned 71 practices (enrolling 5690 patients) to the intervention group and 70 practices (enrolling 5492 patients) to the usual-care group. The hospitalization rate at 1 year was 20.7% (95% confidence interval [CI], 19.7 to 21.8) in the intervention group and 21.1% (95% CI, 20.1 to 22.2) in the usual-care group (between-group difference, 0.4 percentage points; P = 0.58). The risks of emergency department visits, readmissions, cardiovascular events, dialysis, or death from any cause were similar in the two groups. The risk of adverse events was also similar in the trial groups, except for acute kidney injury, which was observed in more patients in the intervention group (12.7% vs. 11.3%). CONCLUSIONS: In this pragmatic trial involving patients with the triad of chronic kidney disease, type 2 diabetes, and hypertension, the use of an EHR-based algorithm and practice facilitators embedded in primary care clinics did not translate into reduced hospitalization at 1 year. (Funded by the National Institutes of Health and others; ICD-Pieces ClinicalTrials.gov number, NCT02587936.).

Validation of a predictive model for hospital-acquired acute kidney injury with emergence of SARS-CoV-2 variants.

We previously developed and validated a model to predict acute kidney injury (AKI) in hospitalized coronavirus disease 2019 (COVID-19) patients and found that the variables with the highest importance included a history of chronic kidney disease and markers of inflammation. Here, we assessed model performance during periods when COVID-19 cases were attributable almost exclusively to individual variants. Electronic Health Record data were obtained from patients admitted to 19 hospitals. The outcome was hospital-acquired AKI. The model, previously built in an Inception Cohort, was evaluated in Delta and Omicron cohorts using model discrimination and calibration methods. A total of 9104 patients were included, with 5676 in the Inception Cohort, 2461 in the Delta cohort, and 967 in the Omicron cohort. The Delta Cohort was younger with fewer comorbidities, while Omicron patients had lower rates of intensive care compared with the other cohorts. AKI occurred in 13.7% of the Inception Cohort, compared with 13.8% of Delta and 14.4% of Omicron (Omnibus p = 0.84). Compared with the Inception Cohort (area under the curve (AUC): 0.78, 95% confidence interval (CI): 0.76-0.80), the model showed stable discrimination in the Delta (AUC: 0.78, 95% CI: 0.75-0.80, p = 0.89) and Omicron (AUC: 0.74, 95% CI: 0.70-0.79, p = 0.37) cohorts. Estimated calibration index values were 0.02 (95% CI: 0.01-0.07) for Inception, 0.08 (95% CI: 0.05-0.17) for Delta, and 0.12 (95% CI: 0.04-0.47) for Omicron cohorts, p = 0.10 for both Delta and Omicron vs Inception. Our model for predicting hospital-acquired AKI remained accurate in different COVID-19 variants, suggesting that risk factors for AKI have not substantially evolved across variants.

The Texas Health Resources Clinical Scholars Program: Learning healthcare system workforce development through embedded translational research.

Introduction: Texas Health Resources (THR), a large, nonprofit health care system based in the Dallas-Fort Worth area, has collaborated with the University of Texas Southwestern Medical Center (UTSW) to develop and operate a unique, integrated approach for Learning Health System (LHS) workforce development. This training model centers on academic health system faculty members conducting later-stage translational research within a partnering regional care delivery organization. Methods: The THR Clinical Scholars Program engages early career UTSW faculty members to conduct studies that are likely to have an impact on care delivery at the health system level. Interested candidates submit formal applications to the program. A joint committee comprised of senior research faculty from UTSW and THR clinical leadership reviews proposals with a focus on the shared LHS needs of both institutions-developing high quality research output that can be applied to enhance care delivery. A key prioritization criterion for funding is the degree to which the research addresses a question relevant to THR as a high-volume network with multiple channels for consumers to access care. The program emphasis is on supporting embedded research initiatives using health system data to generate knowledge that will improve the quality and efficiency of care for the patient populations served by the participant organizations. Results: We discuss specific strategic and tactical components of the THR Clinical Scholars Program including an overview of the academic affiliation agreement between the collaborating organizations, criteria for successful program applications, data sharing, and funding. We also share project summaries from selected clinical scholars as examples of the LHS research done in the program to date. Conclusion: This experience report provides an implementation framework for other academic health systems interested in adopting similar LHS workforce training models with community partners.

Risk Prediction for Acute Kidney Injury in Patients Hospitalized With COVID-19.

Rationale & Objective: Acute kidney injury (AKI) is common in patients hospitalized with COVID-19, but validated, predictive models for AKI are lacking. We aimed to develop the best predictive model for AKI in hospitalized patients with coronavirus disease 2019 and assess its performance over time with the emergence of vaccines and the Delta variant. Study Design: Longitudinal cohort study. Setting & Participants: Hospitalized patients with a positive severe acute respiratory syndrome coronavirus 2 polymerase chain reaction result between March 1, 2020, and August 20, 2021 at 19 hospitals in Texas. Exposures: Comorbid conditions, baseline laboratory data, inflammatory biomarkers. Outcomes: AKI defined by KDIGO (Kidney Disease: Improving Global Outcomes) creatinine criteria. Analytical Approach: Three nested models for AKI were built in a development cohort and validated in 2 out-of-time cohorts. Model discrimination and calibration measures were compared among cohorts to assess performance over time. Results: Of 10,034 patients, 5,676, 2,917, and 1,441 were in the development, validation 1, and validation 2 cohorts, respectively, of whom 776 (13.7%), 368 (12.6%), and 179 (12.4%) developed AKI, respectively (P = 0.26). Patients in the validation cohort 2 had fewer comorbid conditions and were younger than those in the development cohort or validation cohort 1 (mean age, 54 ± 16.8 years vs 61.4 ± 17.5 and 61.7 ± 17.3 years, respectively, P < 0.001). The validation cohort 2 had higher median high-sensitivity C-reactive protein level (81.7 mg/L) versus the development cohort (74.5 mg/L; P < 0.01) and higher median ferritin level (696 ng/mL) versus both the development cohort (444 ng/mL) and validation cohort 1 (496 ng/mL; P < 0.001). The final model, which added high-sensitivity C-reactive protein, ferritin, and D-dimer levels, had an area under the curve of 0.781 (95% CI, 0.763-0.799). Compared with the development cohort, discrimination by area under the curve (validation 1: 0.785 [0.760-0.810], P = 0.79, and validation 2: 0.754 [0.716-0.795], P = 0.53) and calibration by estimated calibration index (validation 1: 0.116 [0.041-0.281], P = 0.11, and validation 2: 0.081 [0.045-0.295], P = 0.11) showed stable performance over time. Limitations: Potential billing and coding bias. Conclusions: We developed and externally validated a model to accurately predict AKI in patients with coronavirus disease 2019. The performance of the model withstood changes in practice patterns and virus variants.

Using dipstick urinalysis to predict development of acute kidney injury in patients with COVID-19.

BACKGROUND: Acute kidney injury (AKI) is a common complication in patients hospitalized with COVID-19 and may require renal replacement therapy (RRT). Dipstick urinalysis is frequently obtained, but data regarding the prognostic value of hematuria and proteinuria for kidney outcomes is scarce. METHODS: Patients with positive severe acute respiratory syndrome-coronavirus 2 (SARS-CoV2) PCR, who had a urinalysis obtained on admission to one of 20 hospitals, were included. Nested models with degree of hematuria and proteinuria were used to predict AKI and RRT during admission. Presence of Chronic Kidney Disease (CKD) and baseline serum creatinine were added to test improvement in model fit. RESULTS: Of 5,980 individuals, 829 (13.9%) developed an AKI during admission, and 149 (18.0%) of those with AKI received RRT. Proteinuria and hematuria degrees significantly increased with AKI severity (P < 0.001 for both). Any degree of proteinuria and hematuria was associated with an increased risk of AKI and RRT. In predictive models for AKI, presence of CKD improved the area under the curve (AUC) (95% confidence interval) to 0.73 (0.71, 0.75), P < 0.001, and adding baseline creatinine improved the AUC to 0.85 (0.83, 0.86), P < 0.001, when compared to the base model AUC using only proteinuria and hematuria, AUC = 0.64 (0.62, 0.67). In RRT models, CKD status improved the AUC to 0.78 (0.75, 0.82), P < 0.001, and baseline creatinine improved the AUC to 0.84 (0.80, 0.88), P < 0.001, compared to the base model, AUC = 0.72 (0.68, 0.76). There was no significant improvement in model discrimination when both CKD and baseline serum creatinine were included. CONCLUSIONS: Proteinuria and hematuria values on dipstick urinalysis can be utilized to predict AKI and RRT in hospitalized patients with COVID-19. We derived formulas using these two readily available values to help prognosticate kidney outcomes in these patients. Furthermore, the incorporation of CKD or baseline creatinine increases the accuracy of these formulas.

Association of Healthcare Access With Intensive Care Unit Utilization and Mortality in Patients of Hispanic Ethnicity Hospitalized With COVID-19.

BACKGROUND: Racial and ethnic minority groups in the United States experience a disproportionate burden of COVID-19 deaths. OBJECTIVE: To evaluate whether outcome differences between Hispanic and non-Hispanic COVID-19 hospitalized patients exist and, if so, to identify the main malleable contributing factors. DESIGN, SETTING, PARTICIPANTS: Retrospective, cross-sectional, observational study of 6097 adult COVID-19 patients hospitalized within a single large healthcare system from March to November 2020. EXPOSURES: Self-reported ethnicity and primary language. MAIN OUTCOMES AND MEASURES: Clinical outcomes included intensive care unit (ICU) utilization and in-hospital death. We used age-adjusted odds ratios (OR) and multivariable analysis to evaluate the associations between ethnicity/language groups and outcomes. RESULTS: 32.1% of patients were Hispanic, 38.6% of whom reported a non-English primary language. Hispanic patients were less likely to be insured, have a primary care provider, and have accessed the healthcare system prior to the COVID-19 admission. After adjusting for age, Hispanic inpatients experienced higher ICU utilization (non-English-speaking: OR, 1.75; 95% CI, 1.47-2.08; English-speaking: OR, 1.13; 95% CI, 0.95-1.33) and higher mortality (non-English-speaking: OR, 1.43; 95% CI, 1.10-1.86; English-speaking: OR, 1.53; 95% CI, 1.19-1.98) compared to non-Hispanic inpatients. There were no observed treatment disparities among ethnic groups. After adjusting for age, Hispanic inpatients had elevated disease severity at admission (non-English-speaking: OR, 2.27; 95% CI, 1.89-2.72; English-speaking: OR, 1.33; 95% CI, 1.10- 1.61). In multivariable analysis, the associations between ethnicity/language and clinical outcomes decreased after considering baseline disease severity (P < .001). CONCLUSION: The associations between ethnicity and clinical outcomes can be explained by elevated disease severity at admission and limited access to healthcare for Hispanic patients, especially non-English-speaking Hispanics.

COVID-19 Mass Vaccination Resource Calculator.

BACKGROUND: Despite the recent emergency use authorization of two vaccines for the prevention of the 2019 novel coronavirus (COVID-19) disease, vaccination rates are lower than expected. Vaccination efforts may be hampered by supply, delivery, storage, patient prioritization, administration infrastructure or logistics problems. To address the last issue, our institution is sharing publically a calculator to optimize the management of staffing and facility resources in an outpatient mass vaccination effort. OBJECTIVE: By sharing our calculator locally and through this paper, we aim to help health organizations administering vaccines optimize resource allocation while maximizing efficiency. METHODS: Our calculator determines the maximum number of vaccinations that can be administered per hour, the number of check-in staff (clerks) needed, the number of vaccination staff (nurses) needed, and the required room capacity needed for the vaccination and the mandatory 15-minute observation period after inoculation. RESULTS: We provide a functional version of the calculator, allowing users to replicate the calculation for their own vaccine events. CONCLUSION: An efficient and organized vaccination program is critical to halting the spread of COVID-19. By sharing this calculator, it is our hope that other organizations may use it to facilitate rapid and efficient vaccination.

Rapid-Cycle Implementation of a Multi-Organization Registry for Heart Failure with Preserved Ejection Fraction Using Health Information Exchange Standards.

Constructing multi-site specialty registries typically proves time-consuming. Electronic health record (EHR) data collected during clinical care affords a pragmatic approach to accelerating registry implementation. Heart failure with preserved ejection fraction (HFpEF) is an increasingly common and morbid condition. Building a multi-site registry for HFpEF proved feasible using EHR data coded in standard terminologies (SNOMED CT, LOINC) and shared via Health Information Exchanges.

SNOMED CT Concept Hierarchies for Sharing Definitions of Clinical Conditions Using Electronic Health Record Data.

BACKGROUND: Defining clinical conditions from electronic health record (EHR) data underpins population health activities, clinical decision support, and analytics. In an EHR, defining a condition commonly employs a diagnosis value set or "grouper." For constructing value sets, Systematized Nomenclature of Medicine-Clinical Terms (SNOMED CT) offers high clinical fidelity, a hierarchical ontology, and wide implementation in EHRs as the standard interoperability vocabulary for problems. OBJECTIVE: This article demonstrates a practical approach to defining conditions with combinations of SNOMED CT concept hierarchies, and evaluates sharing of definitions for clinical and analytic uses. METHODS: We constructed diagnosis value sets for EHR patient registries using SNOMED CT concept hierarchies combined with Boolean logic, and shared them for clinical decision support, reporting, and analytic purposes. RESULTS: A total of 125 condition-defining "standard" SNOMED CT diagnosis value sets were created within our EHR. The median number of SNOMED CT concept hierarchies needed was only 2 (25th-75th percentiles: 1-5). Each value set, when compiled as an EHR diagnosis grouper, was associated with a median of 22 International Classification of Diseases (ICD)-9 and ICD-10 codes (25th-75th percentiles: 8-85) and yielded a median of 155 clinical terms available for selection by clinicians in the EHR (25th-75th percentiles: 63-976). Sharing of standard groupers for population health, clinical decision support, and analytic uses was high, including 57 patient registries (with 362 uses of standard groupers), 132 clinical decision support records, 190 rules, 124 EHR reports, 125 diagnosis dimension slicers for self-service analytics, and 111 clinical quality measure calculations. Identical SNOMED CT definitions were created in an EHR-agnostic tool enabling application across disparate organizations and EHRs. CONCLUSION: SNOMED CT-based diagnosis value sets are simple to develop, concise, understandable to clinicians, useful in the EHR and for analytics, and shareable. Developing curated SNOMED CT hierarchy-based condition definitions for public use could accelerate cross-organizational population health efforts, "smarter" EHR feature configuration, and clinical-translational research employing EHR-derived data.

Vital Signs Are Still Vital: Instability on Discharge and the Risk of Post-Discharge Adverse Outcomes.

BACKGROUND: Vital sign instability on discharge could be a clinically objective means of assessing readiness and safety for discharge; however, the association between vital sign instability on discharge and post-hospital outcomes is unclear. OBJECTIVE: To assess the association between vital sign instability at hospital discharge and post-discharge adverse outcomes. DESIGN: Multi-center observational cohort study using electronic health record data. Abnormalities in temperature, heart rate, blood pressure, respiratory rate, and oxygen saturation were assessed within 24 hours of discharge. We used logistic regression adjusted for predictors of 30-day death and readmission. PARTICIPANTS: Adults (≥18 years) with a hospitalization to any medicine service in 2009-2010 at six hospitals (safety-net, community, teaching, and non-teaching) in north Texas. MAIN MEASURES: Death or non-elective readmission within 30 days after discharge. KEY RESULTS: Of 32,835 individuals, 18.7 % were discharged with one or more vital sign instabilities. Overall, 12.8 % of individuals with no instabilities on discharge died or were readmitted, compared to 16.9 % with one instability, 21.2 % with two instabilities, and 26.0 % with three or more instabilities (p < 0.001). The presence of any (≥1) instability was associated with higher risk-adjusted odds of either death or readmission (AOR 1.36, 95 % CI 1.26-1.48), and was more strongly associated with death (AOR 2.31, 95 % CI 1.91-2.79). Individuals with three or more instabilities had nearly fourfold increased odds of death (AOR 3.91, 95 % CI 1.69-9.06) and increased odds of 30-day readmission (AOR 1.36, 95 % 0.81-2.30) compared to individuals with no instabilities. Having two or more vital sign instabilities at discharge had a positive predictive value of 22 % and positive likelihood ratio of 1.8 for 30-day death or readmission. CONCLUSIONS: Vital sign instability on discharge is associated with increased risk-adjusted rates of 30-day mortality and readmission. These simple vital sign criteria could be used to assess safety for discharge, and to reduce 30-day mortality and readmissions.

Predicting all-cause readmissions using electronic health record data from the entire hospitalization: Model development and comparison.

BACKGROUND: Incorporating clinical information from the full hospital course may improve prediction of 30-day readmissions. OBJECTIVE: To develop an all-cause readmissions risk-prediction model incorporating electronic health record (EHR) data from the full hospital stay, and to compare "full-stay" model performance to a "first day" and 2 other validated models, LACE (includes Length of stay, Acute [nonelective] admission status, Charlson Comorbidity Index, and Emergency department visits in the past year), and HOSPITAL (includes Hemoglobin at discharge, discharge from Oncology service, Sodium level at discharge, Procedure during index hospitalization, Index hospitalization Type [nonelective], number of Admissions in the past year, and Length of stay). DESIGN: Observational cohort study. SUBJECTS: All medicine discharges between November 2009 and October 2010 from 6 hospitals in North Texas, including safety net, teaching, and nonteaching sites. MEASURES: Thirty-day nonelective readmissions were ascertained from 75 regional hospitals. RESULTS: Among 32,922 admissions (validation = 16,430), 12.7% were readmitted. In addition to many first-day factors, we identified hospital-acquired Clostridium difficile infection (adjusted odds ratio [AOR]: 2.03, 95% confidence interval [CI]: 1.18-3.48), vital sign instability on discharge (AOR: 1.25, 95% CI: 1.15-1.36), hyponatremia on discharge (AOR: 1.34, 95% CI: 1.18-1.51), and length of stay (AOR: 1.06, 95% CI: 1.04-1.07) as significant predictors. The full-stay model had better discrimination than other models though the improvement was modest (C statistic 0.69 vs 0.64-0.67). It was also modestly better in identifying patients at highest risk for readmission (likelihood ratio +2.4 vs. 1.8-2.1) and in reclassifying individuals (net reclassification index 0.02-0.06). CONCLUSIONS: Incorporating clinically granular EHR data from the full hospital stay modestly improves prediction of 30-day readmissions. Given limited improvement in prediction despite incorporation of data on hospital complications, clinical instabilities, and trajectory, our findings suggest that many factors influencing readmissions remain unaccounted for. Further improvements in readmission models will likely require accounting for psychosocial and behavioral factors not currently captured by EHRs. Journal of Hospital Medicine 2016;11:473-480. © 2016 Society of Hospital Medicine.

Electronic medical record-based multicondition models to predict the risk of 30 day readmission or death among adult medicine patients: validation and comparison to existing models.

BACKGROUND: There is increasing interest in using prediction models to identify patients at risk of readmission or death after hospital discharge, but existing models have significant limitations. Electronic medical record (EMR) based models that can be used to predict risk on multiple disease conditions among a wide range of patient demographics early in the hospitalization are needed. The objective of this study was to evaluate the degree to which EMR-based risk models for 30-day readmission or mortality accurately identify high risk patients and to compare these models with published claims-based models. METHODS: Data were analyzed from all consecutive adult patients admitted to internal medicine services at 7 large hospitals belonging to 3 health systems in Dallas/Fort Worth between November 2009 and October 2010 and split randomly into derivation and validation cohorts. Performance of the model was evaluated against the Canadian LACE mortality or readmission model and the Centers for Medicare and Medicaid Services (CMS) Hospital Wide Readmission model. RESULTS: Among the 39,604 adults hospitalized for a broad range of medical reasons, 2.8% of patients died, 12.7% were readmitted, and 14.7% were readmitted or died within 30 days after discharge. The electronic multicondition models for the composite outcome of 30-day mortality or readmission had good discrimination using data available within 24 h of admission (C statistic 0.69; 95% CI, 0.68-0.70), or at discharge (0.71; 95% CI, 0.70-0.72), and were significantly better than the LACE model (0.65; 95% CI, 0.64-0.66; P =0.02) with significant NRI (0.16) and IDI (0.039, 95% CI, 0.035-0.044). The electronic multicondition model for 30-day readmission alone had good discrimination using data available within 24 h of admission (C statistic 0.66; 95% CI, 0.65-0.67) or at discharge (0.68; 95% CI, 0.67-0.69), and performed significantly better than the CMS model (0.61; 95% CI, 0.59-0.62; P < 0.01) with significant NRI (0.20) and IDI (0.037, 95% CI, 0.033-0.041). CONCLUSIONS: A new electronic multicondition model based on information derived from the EMR predicted mortality and readmission at 30 days, and was superior to previously published claims-based models.

Enabling cross-platform clinical decision support through Web-based decision support in commercial electronic health record systems: proposal and evaluation of initial prototype implementations.

Enabling clinical decision support (CDS) across multiple electronic health record (EHR) systems has been a desired but largely unattained aim of clinical informatics, especially in commercial EHR systems. A potential opportunity for enabling such scalable CDS is to leverage vendor-supported, Web-based CDS development platforms along with vendor-supported application programming interfaces (APIs). Here, we propose a potential staged approach for enabling such scalable CDS, starting with the use of custom EHR APIs and moving towards standardized EHR APIs to facilitate interoperability. We analyzed three commercial EHR systems for their capabilities to support the proposed approach, and we implemented prototypes in all three systems. Based on these analyses and prototype implementations, we conclude that the approach proposed is feasible, already supported by several major commercial EHR vendors, and potentially capable of enabling cross-platform CDS at scale.

Reducing clinical costs with an EHR.

Steps that hospitals should take to ensure they are gaining optimal value from their electronic health record (EHR) systems include: Creating a value framework for EHR implementation a value framework or EHR implementation. Creating and build executive understanding of the framework. Quantifying each of the expected benefits of EHR implementation. Creating a cross-functional executive team to lead investments in performance management related to the EHR system. Aligning incentives through a formal physician engagement strategy.

Implementation pearls from a new guidebook on improving medication use and outcomes with clinical decision support. Effective CDS is essential for addressing healthcare performance improvement imperatives.

Effective clinical decision support (CDS) is essential for addressing healthcare performance improvement imperatives, but care delivery organizations (CDO) typically struggle with CDS deployment. Ensuring safe and effective medication delivery to patients is a central focus of CDO performance improvement efforts, and this article provides an overview of best-practice strategies for applying CDS to these goals. The strategies discussed are drawn from a new guidebook, co-published and co-sponsored by more than a dozen leading organizations. Developed by scores of CDS implementers and experts, the guidebook outlines key steps and success factors for applying CDS to medication management. A central thesis is that improving outcomes with CDS interventions requires that the CDS five rights be addressed successfully. That is, the interventions must deliver the right information, to the right person, in the right format, through the right channel, at the right point in workflow. This paper provides further details about these CDS five rights, and highlights other important strategies for successful CDS programs.

Impact of a computerized alert during physician order entry on medication dosing in patients with renal impairment.

Computerized assistance to clinicians during physician order entry can provide protection against medical errors. However, computer systems that provide too much assistance may adversely affect training of medical students and residents. Trainees may rely on the computer to automatically perform complex calculations and create appropriate orders and are thereby deprived of an important educational exercise. An alternative strategy is to provide a critique at the completion of an order, requiring the trainee to enter the entire order but displaying an alert if an error is made. While this approach preserves the educational components of order-writing, the potential for errors exists if the computerized critique does not induce clinicians to correct the order. The goal of this study was to determine (a) the frequency with which errors are made by trainees in an environment in which renal dosing adjustment calculation for antimicrobials are done by the system after the user has entered an order, and (b) the frequency with which prompts to clinicians regarding these errors leads to correction of those orders.