Search

BackgroundThe Strategic Health IT Advanced Research Projects (SHARP) program seeks to conquer well-understood challenges in medical informatics through breakthrough research. Two SHARP centers have found alignment in their methodological needs: (1) members of the National Center for Cognitive Informatics and Decision-making (NCCD) have developed knowledge bases to support problem-oriented summarizations of patient data, and (2) Substitutable Medical Apps, Reusable Technologies (SMART), which is a platform for reusable medical apps that can run on participating platforms connected to various electronic health records (EHR). Combining the work of these two centers will ensure wide dissemination of new methods for synthesized views of patient data. Informatics for Integrating Biology and the Bedside (i2b2) is an NIH-funded clinical research data repository platform in use at over 100 sites worldwide. By also working with a co-occurring initiative to SMART-enabling i2b2, we can confidently write one app that can be used extremely broadly. ObjectiveOur goal was to facilitate development of intuitive, problem-oriented views of the patient record using NCCD knowledge bases that would run in any EHR. To do this, we developed a collaboration between the two SHARPs and an NIH center, i2b2. MethodsFirst, we implemented collaborative tools to connect researchers at three institutions. Next, we developed a patient summarization app using the SMART platform and a previously validated NCCD problem-medication linkage knowledge base derived from the National Drug File-Reference Terminology (NDF-RT). Finally, to SMART-enable i2b2, we implemented two new Web service “cells” that expose the SMART application programming interface (API), and we made changes to the Web interface of i2b2 to host a “carousel” of SMART apps. ResultsWe deployed our SMART-based, NDF-RT-derived patient summarization app in this SMART-i2b2 container. It displays a problem-oriented view of medications and presents a line-graph display of laboratory results. ConclusionsThis summarization app can be run in any EHR environment that either supports SMART or runs SMART-enabled i2b2. This i2b2 “clinical bridge” demonstrates a pathway for reusable app development that does not require EHR vendors to immediately adopt the SMART API. Apps can be developed in SMART and run by clinicians in the i2b2 repository, reusing clinical data extracted from EHRs. This may encourage the adoption of SMART by supporting SMART app development until EHRs adopt the platform. It also allows a new variety of clinical SMART apps, fueled by the broad aggregation of data types available in research repositories. The app (including its knowledge base) and SMART-i2b2 are open-source and freely available for download.

WormBase (www.wormbase.org) is the central repository for the genetics and genomics of the nematode Caenorhabditis elegans. We provide the research community with data and tools to facilitate the use of C. elegans and related nematodes as model organisms for studying human health, development, and many aspects of fundamental biology. Throughout our 22-year history, we have continued to evolve to reflect progress and innovation in the science and technologies involved in the study of C. elegans. We strive to incorporate new data types and richer data sets, and to provide integrated displays and services that avail the knowledge generated by the published nematode genetics literature. Here, we provide a broad overview of the current state of WormBase in terms of data type, curation workflows, analysis, and tools, including exciting new advances for analysis of single-cell data, text mining and visualization, and the new community collaboration forum. Concurrently, we continue the integration and harmonization of infrastructure, processes, and tools with the Alliance of Genome Resources, of which WormBase is a founding member.

OBJECTIVE: Clinical decision support (CDS) can contribute to quality and safety. Prior work has shown that errors in CDS systems are common and can lead to unintended consequences. Many CDS systems use Boolean logic, which can be difficult for CDS analysts to specify accurately. We set out to determine the prevalence of certain types of Boolean logic errors in CDS statements. METHODS: Nine health care organizations extracted Boolean logic statements from their Epic electronic health record (EHR). We developed an open-source software tool, which implemented the Espresso logic minimization algorithm, to identify three classes of logic errors. RESULTS: Participating organizations submitted 260,698 logic statements, of which 44,890 were minimized by Espresso. We found errors in 209 of them. Every participating organization had at least two errors, and all organizations reported that they would act on the feedback. DISCUSSION: An automated algorithm can readily detect specific categories of Boolean CDS logic errors. These errors represent a minority of CDS errors, but very likely require correction to avoid patient safety issues. This process found only a few errors at each site, but the problem appears to be widespread, affecting all participating organizations. CONCLUSION: Both CDS implementers and EHR vendors should consider implementing similar algorithms as part of the CDS authoring process to reduce the number of errors in their CDS interventions.

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.

Objective This study aims to investigate the feasibility of using Large Language Models (LLMs) to engage with patients at the time they are drafting a question to their healthcare providers, and generate pertinent follow-up questions that the patient can answer before sending their message, with the goal of ensuring that their healthcare provider receives all the information they need to safely and accurately answer the patient's question, eliminating back-and-forth messaging, and the associated delays and frustrations. Methods We collected a dataset of patient messages sent between January 1, 2022 to March 7, 2023 at Vanderbilt University Medical Center. Two internal medicine physicians identified 7 common scenarios. We used 3 LLMs to generate follow-up questions: (1) Comprehensive LLM Artificial Intelligence Responder (CLAIR): a locally fine-tuned LLM, (2) GPT4 with a simple prompt, and (3) GPT4 with a complex prompt. Five physicians rated them with the actual follow-ups written by healthcare providers on clarity, completeness, conciseness, and utility. Results For five scenarios, our CLAIR model had the best performance. The GPT4 model received higher scores for utility and completeness but lower scores for clarity and conciseness. CLAIR generated follow-up questions with similar clarity and conciseness as the actual follow-ups written by healthcare providers, with higher utility than healthcare providers and GPT4, and lower completeness than GPT4, but better than healthcare providers. Conclusion LLMs can generate follow-up patient messages designed to clarify a medical question that compares favorably to those generated by healthcare providers. [ABSTRACT FROM AUTHOR]

Objective To use workflow execution models to highlight new considerations for patient-centered clinical decision support policies (PC CDS), processes, procedures, technology, and expertise required to support new workflows. Methods To generate and refine models, we used (1) targeted literature reviews; (2) key informant interviews with 6 external PC CDS experts; (3) model refinement based on authors' experience; and (4) validation of the models by a 26-member steering committee. Results and Discussion We identified 7 major issues that provide significant challenges and opportunities for healthcare systems, researchers, administrators, and health IT and app developers. Overcoming these challenges presents opportunities for new or modified policies, processes, procedures, technology, and expertise to: (1) Ensure patient-generated health data (PGHD), including patient-reported outcomes (PROs), are documented, reviewed, and managed by appropriately trained clinicians, between visits and after regular working hours. (2) Educate patients to use connected medical devices and handle technical issues. (3) Facilitate collection and incorporation of PGHD, PROs, patient preferences, and social determinants of health into existing electronic health records. (4) Troubleshoot erroneous data received from devices. (5) Develop dashboards to display longitudinal patient-reported data. (6) Provide reimbursement to support new models of care. (7) Support patient engagement with remote devices. Conclusion Several new policies, processes, technologies, and expertise are required to ensure safe and effective implementation and use of PC CDS. As we gain more experience implementing and working with PC CDS, we should be able to begin realizing the long-term positive impact on patient health that the patient-centered movement in healthcare promises. [ABSTRACT FROM AUTHOR]

Bipolar disorder (BD) is a common, highly heritable neuropsychiatric disease characterized by recurrent episodes of mania and depression. Lithium is the best-established long-term treatment for BD, even though individual response is highly variable. Evidence suggests that some of this variability has a genetic basis. This is supported by the largest genome-wide association study (GWAS) of lithium response to date conducted by the International Consortium on Lithium Genetics (ConLiGen). Recently, we performed the first genome-wide analysis of the involvement of miRNAs in BD and identified nine BD-associated miRNAs. However, it is unknown whether these miRNAs are also associated with lithium response in BD. In the present study, we therefore tested whether common variants at these nine candidate miRNAs contribute to the variance in lithium response in BD. Furthermore, we systematically analyzed whether any other miRNA in the genome is implicated in the response to lithium. For this purpose, we performed gene-based tests for all known miRNA coding genes in the ConLiGen GWAS dataset (n = 2,563 patients) using a set-based testing approach adapted from the versatile gene-based test for GWAS (VEGAS2). In the candidate approach, miR-499a showed a nominally significant association with lithium response, providing some evidence for involvement in both development and treatment of BD. In the genome-wide miRNA analysis, 71 miRNAs showed nominally significant associations with the dichotomous phenotype and 106 with the continuous trait for treatment response. A total of 15 miRNAs revealed nominal significance in both phenotypes with miR-633 showing the strongest association with the continuous trait (p = 9.80E-04) and miR-607 with the dichotomous phenotype (p = 5.79E-04). No association between miRNAs and treatment response to lithium in BD in either of the tested conditions withstood multiple testing correction. Given the limited power of our study, the investigation of miRNAs in larger GWAS samples of BD and lithium response is warranted.

Objective Conduct a scoping review of research studies that describe rule-based clinical decision support (CDS) malfunctions. Materials and Methods In April 2022, we searched three bibliographic databases (MEDLINE, CINAHL, and Embase) for literature referencing CDS malfunctions. We coded the identified malfunctions according to an existing CDS malfunction taxonomy and added new categories for factors not already captured. We also extracted and summarized information related to the CDS system, such as architecture, data source, and data format. Results Twenty-eight articles met inclusion criteria, capturing 130 malfunctions. Architectures used included stand-alone systems (eg, web-based calculator), integrated systems (eg, best practices alerts), and service-oriented architectures (eg, distributed systems like SMART or CDS Hooks). No standards-based CDS malfunctions were identified. The "Cause" category of the original taxonomy includes three new types (organizational policy, hardware error, and data source) and two existing causes were expanded to include additional layers. Only 29 malfunctions (22%) described the potential impact of the malfunction on patient care. Discussion While a substantial amount of research on CDS exists, our review indicates there is a limited focus on CDS malfunctions, with even less attention on malfunctions associated with modern delivery architectures such as SMART and CDS Hooks. Conclusion CDS malfunctions can and do occur across several different care delivery architectures. To account for advances in health information technology, existing taxonomies of CDS malfunctions must be continually updated. This will be especially important for service-oriented architectures, which connect several disparate systems, and are increasing in use. [ABSTRACT FROM AUTHOR]

Although numerous studies have examined if students of color benefit from having a teacher of the same race/ethnicity, all attention has been paid to students without disabilities. We examine whether the same benefits hold for students with disabilities (SWDs). Using a nationally representative data set of kindergartners, we explored whether SWDs of color had different academic and social-emotional outcomes when with a teacher of the same race/ethnicity. We compared students of color with and without disabilities in the same classroom with regard to a same-race teacher match. Unlike students without disabilities, we do not find evidence in the data set that SWDs of color benefit from a same-race teacher match in terms of achievement and social-emotional development. Implications with regard to educational equity are discussed.

Objectives To evaluate the capability of using generative artificial intelligence (AI) in summarizing alert comments and to determine if the AI-generated summary could be used to improve clinical decision support (CDS) alerts. Materials and Methods We extracted user comments to alerts generated from September 1, 2022 to September 1, 2023 at Vanderbilt University Medical Center. For a subset of 8 alerts, comment summaries were generated independently by 2 physicians and then separately by GPT-4. We surveyed 5 CDS experts to rate the human-generated and AI-generated summaries on a scale from 1 (strongly disagree) to 5 (strongly agree) for the 4 metrics: clarity, completeness, accuracy, and usefulness. Results Five CDS experts participated in the survey. A total of 16 human-generated summaries and 8 AI-generated summaries were assessed. Among the top 8 rated summaries, five were generated by GPT-4. AI-generated summaries demonstrated high levels of clarity, accuracy, and usefulness, similar to the human-generated summaries. Moreover, AI-generated summaries exhibited significantly higher completeness and usefulness compared to the human-generated summaries (AI: 3.4 ± 1.2, human: 2.7 ± 1.2, P  = .001). Conclusion End-user comments provide clinicians' immediate feedback to CDS alerts and can serve as a direct and valuable data resource for improving CDS delivery. Traditionally, these comments may not be considered in the CDS review process due to their unstructured nature, large volume, and the presence of redundant or irrelevant content. Our study demonstrates that GPT-4 is capable of distilling these comments into summaries characterized by high clarity, accuracy, and completeness. AI-generated summaries are equivalent and potentially better than human-generated summaries. These AI-generated summaries could provide CDS experts with a novel means of reviewing user comments to rapidly optimize CDS alerts both online and offline. [ABSTRACT FROM AUTHOR]

Ontology is essential for achieving health information and information technology application interoperability in the biomedical fields and beyond. Traditionally, ontology construction is carried out manually by human domain experts (HDE). Here, we explore an active learning approach to automatically identify candidate terms from publications, with manual verification later as a part of a deep learning model training and learning process. We introduce the overall architecture of the active learning pipeline and present some preliminary results. This work is a critical and complementary component in addition to manually building the ontology, especially during the long-term maintenance stage. [ABSTRACT FROM AUTHOR]