Search

Introduction: Urinary incontinence (UI) affects an estimated 51% of US adult women. This is a comparative effectiveness study of practice-based interventions to improve UI care quality and reduce health disparities. Objectives: Compare the effectiveness of two nonsurgical UI interventions on care quality, shared decision making (SDM), patient-centered outcomes and knowledge. Determine if interventions reduce care disparities and knowledge gaps in underserved Spanish-speaking Latinas. Methods: Sixty primary care physicians (PCPs) from 3 health systems will be randomized into two arms. In Arm 1,patients are co-managed by urology advanced practice provider (APP) and PCP. APP provides UI care, education, and self-management by telemedicine. In Arm 2, patients are co-managed by PCP and urologist. Urologist electronically reviews referral for appropriate primary UI care and provide recommendations if indicated. In both arms, PCPs receive academic detailing and electronic clinical decision support. Shared decision making, patient-reported UI outcomes and knowledge will be assessed using validated questionnaires. Will compare the care quality by site, provider characteristics (sex and years in practice), and racial/ethnic patient groups. Results: Study funding began in October 2022. 181 primary care clinics are eligible for participation. Recruitment began April 2023. Preliminary analysis found 21.1% of women who screened positive for UI discussed UI with PCP. EHR clinical decision support tools are implemented to prompt PCPs to discuss UI patients who screen positive. Conclusions: Successful intervention(s) may lead to wide-scale implementation of effective, cost-saving, quality improvement methods to improve patient satisfaction and streamline UI care.

ObjectiveWe aimed to develop a distributed, immutable, and highly available cross-cloud blockchain system to facilitate federated data analysis activities among multiple institutions.Materials and methodsWe preprocessed 9166 COVID-19 Structured Query Language (SQL) code, summary statistics, and user activity logs, from the GitHub repository of the Reliable Response Data Discovery for COVID-19 (R2D2) Consortium. The repository collected local summary statistics from participating institutions and aggregated the global result to a COVID-19-related clinical query, previously posted by clinicians on a website. We developed both on-chain and off-chain components to store/query these activity logs and their associated queries/results on a blockchain for immutability, transparency, and high availability of research communication. We measured run-time efficiency of contract deployment, network transactions, and confirmed the accuracy of recorded logs compared to a centralized baseline solution.ResultsThe smart contract deployment took 4.5 s on an average. The time to record an activity log on blockchain was slightly over 2 s, versus 5-9 s for baseline. For querying, each query took on an average less than 0.4 s on blockchain, versus around 2.1 s for baseline.DiscussionThe low deployment, recording, and querying times confirm the feasibility of our cross-cloud, blockchain-based federated data analysis system. We have yet to evaluate the system on a larger network with multiple nodes per cloud, to consider how to accommodate a surge in activities, and to investigate methods to lower querying time as the blockchain grows.ConclusionBlockchain technology can be used to support federated data analysis among multiple institutions.

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

ObjectiveTo utilize, in an individual and institutional privacy-preserving manner, electronic health record (EHR) data from 202 hospitals by analyzing answers to COVID-19-related questions and posting these answers online.Materials and methodsWe developed a distributed, federated network of 12 health systems that harmonized their EHRs and submitted aggregate answers to consortia questions posted at https://www.covid19questions.org. Our consortium developed processes and implemented distributed algorithms to produce answers to a variety of questions. We were able to generate counts, descriptive statistics, and build a multivariate, iterative regression model without centralizing individual-level data.ResultsOur public website contains answers to various clinical questions, a web form for users to ask questions in natural language, and a list of items that are currently pending responses. The results show, for example, that patients who were taking angiotensin-converting enzyme inhibitors and angiotensin II receptor blockers, within the year before admission, had lower unadjusted in-hospital mortality rates. We also showed that, when adjusted for, age, sex, and ethnicity were not significantly associated with mortality. We demonstrated that it is possible to answer questions about COVID-19 using EHR data from systems that have different policies and must follow various regulations, without moving data out of their health systems.Discussion and conclusionsWe present an alternative or a complement to centralized COVID-19 registries of EHR data. We can use multivariate distributed logistic regression on observations recorded in the process of care to generate results without transferring individual-level data outside the health systems.

Background & aimsWe investigated 30- and 90-day rates and causes of, risk factors for, and interventions to reduce hospital readmission in patients who received medical treatment for inflammatory bowel diseases (IBD).MethodsWe performed a systematic search of publications through July 1, 2018 for studies of rates of hospital readmission and associated causes and risk factors in patients who received medical treatments for IBD. Our final analysis included 17 cohort studies (6324 patients) of hospitalized adults with IBD who had received medical treatment, along with reported readmission rates with detailed chart review. We performed random effects meta-analysis to estimate 30- and 90-day rates of readmission and identified causes and risk factors associated with readmission. We also performed qualitative analyses of studies that focused on interventions to reduce readmission.ResultsOverall, the 30-day rate of readmission was 18.1% (95% CI, 14.4-22.4) and the 90-day rate was 26.0% (95% CI, 22.7-29.6). On meta-regression, studies with higher proportions of patients with ulcerative colitis than Crohn's disease reported higher risks for readmission. Most common reasons for readmission were IBD flare, infection, or complications from unplanned surgeries during hospitalizations. Consistent risk factors for 30-day readmission were admission for pain control (odds ratio [OR], 2.27; 95% CI, 1.69-3.03), need for total parenteral nutrition on discharge (OR, 2.13; 95% CI, 1.36-3.35), and prior or unplanned surgery during admission (OR, 3.11; 95% CI, 2.27-4.25). Only 1 study focused on interventions (specialized inpatient IBD service) to reduce risk of readmission.ConclusionsOverall 30- and 90-day rates of readmission for patients who received medical treatment for IBD are 18.1% and 26.0%, respectively. IBD flares and infections are common reasons for readmission, and inadequate pain control and need for parenteral nutrition were common risk factors. Interventional studies to reduce risk of readmission are needed.

BackgroundEarly hospital readmission for patients with cirrhosis continues to challenge the healthcare system. Risk stratification may help tailor resources, but existing models were designed using small, single-institution cohorts or had modest performance.AimsWe leveraged a large clinical database from the Department of Veterans Affairs (VA) to design a readmission risk model for patients hospitalized with cirrhosis. Additionally, we analyzed potentially modifiable or unexplored readmission risk factors.MethodsA national VA retrospective cohort of patients with a history of cirrhosis hospitalized for any reason from January 1, 2006, to November 30, 2013, was developed from 123 centers. Using 174 candidate variables within demographics, laboratory results, vital signs, medications, diagnoses and procedures, and healthcare utilization, we built a 47-variable penalized logistic regression model with the outcome of all-cause 30-day readmission. We excluded patients who left against medical advice, transferred to a non-VA facility, or if the hospital length of stay was greater than 30 days. We evaluated calibration and discrimination across variable volume and compared the performance to recalibrated preexisting risk models for readmission.ResultsWe analyzed 67,749 patients and 179,298 index hospitalizations. The 30-day readmission rate was 23%. Ascites was the most common cirrhosis-related cause of index hospitalization and readmission. The AUC of the model was 0.670 compared to existing models (0.649, 0.566, 0.577). The Brier score of 0.165 showed good calibration.ConclusionOur model achieved better discrimination and calibration compared to existing models, even after local recalibration. Assessment of calibration by variable parsimony revealed performance improvements for increasing variable inclusion well beyond those detectable for discrimination.

OBJECTIVE: Cirrhotic patients are at high hospitalisation risk with subsequent high mortality. Current risk prediction models have varied performances with methodological room for improvement. We used current analytical techniques using automatically extractable variables from the electronic health record (EHR) to develop and validate a posthospitalisation mortality risk score for cirrhotic patients and compared performance with the model for end-stage liver disease (MELD), model for end-stage liver disease with sodium (MELD-Na), and the CLIF Consortium Acute Decompensation (CLIF-C AD) models. DESIGN: We analysed a retrospective cohort of 73 976 patients comprising 247 650 hospitalisations between 2006 and 2013 at any of 123 Department of Veterans Affairs hospitals. Using 45 predictor variables, we built a time-dependent Cox proportional hazards model with all-cause mortality as the outcome. We compared performance to the three extant models and reported discrimination and calibration using bootstrapping. Furthermore, we analysed differential utility using the net reclassification index (NRI). RESULTS: The C-statistic for the final model was 0.863, representing a significant improvement over the MELD, MELD-Na, and the CLIF-C AD, which had C-statistics of 0.655, 0.675, and 0.679, respectively. Multiple risk factors were significant in our model, including variables reflecting disease severity and haemodynamic compromise. The NRI showed a 24% improvement in predicting survival of low-risk patients and a 30% improvement in predicting death of high-risk patients. CONCLUSION: We developed a more accurate mortality risk prediction score using variables automatically extractable from an EHR that may be used to risk stratify patients with cirrhosis for targeted postdischarge management.

OBJECTIVES:  Underserved populations can benefit from consumer health informatics (CHI) that promotes self-management at a lower cost. However, prior literature suggested that the digital divide and low motivation constituted barriers to CHI adoption. Despite increased Internet use, underserved populations continue to show slow CHI uptake. The aim of the paper is to revisit barriers and facilitators that may impact CHI adoption among underserved populations. METHODS:  We surveyed the past five years of literature. We searched PubMed for articles published between 2012 and 2017 that describe empirical evaluations involving CHI use by underserved populations. We abstracted and summarized data about facilitators and barriers impacting CHI adoption. RESULTS:  From 645 search results, after abstract and full-text screening, 13 publications met the inclusion criteria of identifying barriers to and facilitators of underserved populations CHI adoption. Contrary to earlier literature, the studies suggested that the motivation to improve health literacy and adopt technology was high among studied populations. Beyond the digital divide, barriers included: low health and computer literacy, challenges in accepting the presented information, poor usability, and unclear content. Factors associated with increased use were: user needs for information, user-access mediated by a proxy person, and early user engagement in system design. CONCLUSIONS:  While the digital divide remains a barrier, newer studies show that high motivation for CHI use exists. However, simply gaining access to technology is not sufficient to improve adoption unless CHI technology is tailored to address user needs. Future interventions should consider building larger empirical evidence on identifying CHI barriers and facilitators.

OBJECTIVE:Hepatorenal Syndrome (HRS) is a devastating form of acute kidney injury (AKI) in advanced liver disease patients with high morbidity and mortality, but phenotyping algorithms have not yet been developed using large electronic health record (EHR) databases. We evaluated and compared multiple phenotyping methods to achieve an accurate algorithm for HRS identification. MATERIALS AND METHODS:A national retrospective cohort of patients with cirrhosis and AKI admitted to 124 Veterans Affairs hospitals was assembled from electronic health record data collected from 2005 to 2013. AKI was defined by the Kidney Disease: Improving Global Outcomes criteria. Five hundred and four hospitalizations were selected for manual chart review and served as the gold standard. Electronic Health Record based predictors were identified using structured and free text clinical data, subjected through NLP from the clinical Text Analysis Knowledge Extraction System. We explored several dimension reduction techniques for the NLP data, including newer high-throughput phenotyping and word embedding methods, and ascertained their effectiveness in identifying the phenotype without structured predictor variables. With the combined structured and NLP variables, we analyzed five phenotyping algorithms: penalized logistic regression, naïve Bayes, support vector machines, random forest, and gradient boosting. Calibration and discrimination metrics were calculated using 100 bootstrap iterations. In the final model, we report odds ratios and 95% confidence intervals. RESULTS:The area under the receiver operating characteristic curve (AUC) for the different models ranged from 0.73 to 0.93; with penalized logistic regression having the best discriminatory performance. Calibration for logistic regression was modest, but gradient boosting and support vector machines were superior. NLP identified 6985 variables; a priori variable selection performed similarly to dimensionality reduction using high-throughput phenotyping and semantic similarity informed clustering (AUC of 0.81 - 0.82). CONCLUSION:This study demonstrated improved phenotyping of a challenging AKI etiology, HRS, over ICD-9 coding. We also compared performance among multiple approaches to EHR-derived phenotyping, and found similar results between methods. Lastly, we showed that automated NLP dimension reduction is viable for acute illness.