OBJECTIVE: We aimed to develop a distributed, immutable, and highly available cross-cloud blockchain system to facilitate federated data analysis activities among multiple institutions. MATERIALS AND METHODS: We 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. RESULTS: The 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. DISCUSSION: The 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. CONCLUSION: Blockchain technology can be used to support federated data analysis among multiple institutions.

OBJECTIVE: The study sought to determine availability and use of structured override reasons for drug-drug interaction (DDI) alerts in electronic health records. MATERIALS AND METHODS: We collected data on DDI alerts and override reasons from 10 clinical sites across the United States using a variety of electronic health records. We used a multistage iterative card sort method to categorize the override reasons from all sites and identified best practices. RESULTS: Our methodology established 177 unique override reasons across the 10 sites. The number of coded override reasons at each site ranged from 3 to 100. Many sites offered override reasons not relevant to DDIs. Twelve categories of override reasons were identified. Three categories accounted for 78% of all overrides: "will monitor or take precautions," "not clinically significant," and "benefit outweighs risk." DISCUSSION: We found wide variability in override reasons between sites and many opportunities to improve alerts. Some override reasons were irrelevant to DDIs. Many override reasons attested to a future action (eg, decreasing a dose or ordering monitoring tests), which requires an additional step after the alert is overridden, unless the alert is made actionable. Some override reasons deferred to another party, although override reasons often are not visible to other users. Many override reasons stated that the alert was inaccurate, suggesting that specificity of alerts could be improved. CONCLUSIONS: Organizations should improve the options available to providers who choose to override DDI alerts. DDI alerting systems should be actionable and alerts should be tailored to the patient and drug pairs.

BACKGROUND: Patients with kidney disease are at risk for adverse events due to improper medication prescribing. Few randomized controlled trials of clinical decision support (CDS) utilizing dynamic assessment of patients' kidney function to improve prescribing for patients with kidney disease have been published. METHODS: We developed a CDS tool for 20 medications within a commercial electronic health record. Our system detected scenarios in which drug discontinuation or dosage adjustment was recommended for adult patients with impaired renal function in the ambulatory and acute settings - both at the time of the initial prescription ("prospective" alerts) and by monitoring changes in renal function for patients already receiving one of the study medications ("look-back" alerts). We performed a prospective, cluster randomized controlled trial of physicians receiving clinical decision support for renal dosage adjustments versus those performing their usual workflow. The primary endpoint was the proportion of study prescriptions that were appropriately adjusted for patients' kidney function at the time that patients' conditions warranted a change according to the alert logic. We employed multivariable logistic regression modeling to adjust for glomerular filtration rate, gender, age, hospitalized status, length of stay, type of alert, time from start of study, and clustering within the prescribing physician on the primary endpoint. RESULTS: A total of 4068 triggering conditions occurred in 1278 unique patients; 1579 of these triggering conditions generated alerts seen by physicians in the intervention arm and 2489 of these triggering conditions were captured but suppressed, so as not to generate alerts for physicians in the control arm. Prescribing orders were appropriate adjusted in 17% of the time vs 5.7% of the time in the intervention and control arms, respectively (odds ratio: 1.89, 95% confidence interval, 1.45-2.47, P < .0001). Prospective alerts had a greater impact than look-back alerts (55.6% vs 10.3%, in the intervention arm). CONCLUSIONS: The rate of appropriate drug prescribing in kidney impairment is low and remains a patient safety concern. Our results suggest that CDS improves drug prescribing, particularly when providing guidance on new prescriptions.

BACKGROUND: Centralized and federated models for sharing data in research networks currently exist. To build multivariate data analysis for centralized networks, transfer of patient-level data to a central computation resource is necessary. The authors implemented distributed multivariate models for federated networks in which patient-level data is kept at each site and data exchange policies are managed in a study-centric manner. OBJECTIVE: The objective was to implement infrastructure that supports the functionality of some existing research networks (e.g., cohort discovery, workflow management, and estimation of multivariate analytic models on centralized data) while adding additional important new features, such as algorithms for distributed iterative multivariate models, a graphical interface for multivariate model specification, synchronous and asynchronous response to network queries, investigator-initiated studies, and study-based control of staff, protocols, and data sharing policies. MATERIALS AND METHODS: Based on the requirements gathered from statisticians, administrators, and investigators from multiple institutions, the authors developed infrastructure and tools to support multisite comparative effectiveness studies using web services for multivariate statistical estimation in the SCANNER federated network. RESULTS: The authors implemented massively parallel (map-reduce) computation methods and a new policy management system to enable each study initiated by network participants to define the ways in which data may be processed, managed, queried, and shared. The authors illustrated the use of these systems among institutions with highly different policies and operating under different state laws. DISCUSSION AND CONCLUSION: Federated research networks need not limit distributed query functionality to count queries, cohort discovery, or independently estimated analytic models. Multivariate analyses can be efficiently and securely conducted without patient-level data transport, allowing institutions with strict local data storage requirements to participate in sophisticated analyses based on federated research networks.

OBJECTIVE: Competing tools are available online to assess the risk of developing certain conditions of interest, such as cardiovascular disease. While predictive models have been developed and validated on data from cohort studies, little attention has been paid to ensure the reliability of such predictions for individuals, which is critical for care decisions. The goal was to develop a patient-driven adaptive prediction technique to improve personalized risk estimation for clinical decision support. MATERIAL AND METHODS: A data-driven approach was proposed that utilizes individualized confidence intervals (CIs) to select the most 'appropriate' model from a pool of candidates to assess the individual patient's clinical condition. The method does not require access to the training dataset. This approach was compared with other strategies: the BEST model (the ideal model, which can only be achieved by access to data or knowledge of which population is most similar to the individual), CROSS model, and RANDOM model selection. RESULTS: When evaluated on clinical datasets, the approach significantly outperformed the CROSS model selection strategy in terms of discrimination (p<1e-14) and calibration (p<0.006). The method outperformed the RANDOM model selection strategy in terms of discrimination (p<1e-12), but the improvement did not achieve significance for calibration (p=0.1375). LIMITATIONS: The CI may not always offer enough information to rank the reliability of predictions, and this evaluation was done using aggregation. If a particular individual is very different from those represented in a training set of existing models, the CI may be somewhat misleading. CONCLUSION: This approach has the potential to offer more reliable predictions than those offered by other heuristics for disease risk estimation of individual patients.

Actionable reminders (electronic reminders linked to computerized order entry) might improve care by facilitating direct ordering of recommended tests. The authors implemented four enhanced actionable reminders targeting performance of annual mammography, one-time bone-density screening, and diabetic testing. There was no difference in rates of appropriate testing between the four intervention and four matched, control primary care clinics for screening mammography (OR 0.81, 95% CI 0.64 to 1.02), bone-density exams (OR 1.29, 95% CI 0.82 to 2.02), HbA1c monitoring (OR 0.91, 95% CI 0.58 to 1.42) and LDL cholesterol monitoring (OR 1.40, 95% CI 0.76 to 2.59). Of the survey respondents, 79% almost never used the system or were unaware of the functionality. In the 9/228 (3.9%) cases with indirect evidence of mammography reminder use, there was a significantly lower proportion with test performance. Our actionable reminders did not improve receipt of overdue testing, potentially due to limitations of workflow integration.