Showing papers in "Journal of the American Medical Informatics Association in 2014"
••
TL;DR: The Patient-Centered Outcomes Research Institute has launched PCORnet, a major initiative to support an effective, sustainable national research infrastructure that will advance the use of electronic health data in comparative effectiveness research (CER) and other types of research.
486 citations
••
TL;DR: There are a variety of approaches for classifying patients into a particular phenotype, and good performance is reported on datasets at respective institutions, however, no system makes comprehensive use of electronic medical records addressing all of their known weaknesses.
430 citations
••
TL;DR: Stress may rise for physicians with a moderate number of EMR functions, primary care work conditions, and physician satisfaction, stress and burnout as well as time pressure during visits.
310 citations
••
TL;DR: The BD2K initiative seeks to better define how to extract value from the data, both for the individual investigator and the overall research community, and create the analytic tools needed to enhance utility of the data.
262 citations
••
TL;DR: Through machine learning-based integration of drug phenotypic, therapeutic, structural, and genomic similarities, it is demonstrated that HNAI is promising for uncovering DDIs in drug development and postmarketing surveillance.
255 citations
••
TL;DR: Examination of the current literature shows there are considerable gaps in knowledge regarding patient engagement in the hospital setting and inconsistent use of terminology regarding patientagement overall.
217 citations
••
TL;DR: Hierarchy-based classification yields better ICD9 coding than flat classification for MIMIC patients and is an example of a task for which data and tools can be shared and for which the research community can work together to build on shared models and advance the state of the art.
188 citations
••
TL;DR: The override rates for medication-related CDS alerts in the outpatient setting, the reasons cited for overrides at the time of prescribing, and the appropriateness of overrides were characterized to improve the relevance of alerts and reduce alert fatigue.
182 citations
••
TL;DR: The development, implementation, and evaluation of active CDS for multiple pharmacogenetic test results reported preemptively illustrated the feasibility of developing computational systems that provide clinicians with actionable alerts for gene-based drug prescribing at the point of care.
179 citations
••
TL;DR: Because EHR-related safety concerns have complex sociotechnical origins, institutions with long-standing as well as recent EHR implementations should build a robust infrastructure to monitor and learn from them.
169 citations
••
Leonard Davis Institute of Health Economics1, Children's Hospital of Philadelphia2, Cincinnati Children's Hospital Medical Center3, University of Washington4, Seattle Children's5, Harvard University6, Boston Children's Hospital7, University of Central Florida8, The Research Institute at Nationwide Children's Hospital9, Washington University in St. Louis10, University of Colorado Boulder11
TL;DR: PEDSnet is implementing a flexible dual data architecture that incorporates two widely used data models and national terminology standards to support multi-institutional data integration, cohort discovery, and advanced analytics that enable rapid learning.
••
TL;DR: This study introduces a new scheme for the prediction of lactate levels and mortality risk from patient vital signs and WBC that can drive the appropriate response by clinical staff and thus may have important implications for patient health and treatment outcome.
••
TL;DR: The nature, methodological, and theoretical foundations of handoff tool evaluations varied significantly in terms of their quality and rigor, thereby limiting their ability to inform strategic standardization initiatives.
••
TL;DR: Many modern physician specialists like to think of their work as grounded in strong science, yet 5 years ago, a group of cardiologists published their findings on the science underlying over 2700 practice recommendations issued by their specialty societies, finding that only 314 of the recommendations were based on ‘level A’ evidence.
••
TL;DR: It is feasible to identify DDI signals and estimate the rate of adverse events among patients on drug combinations, directly from clinical text, and this could have utility in prioritizing drug interaction surveillance as well as in clinical decision support.
••
TL;DR: The authors' evaluation on the independent test set showed that most types of feature were beneficial to Chinese NER systems, although the improvements were limited, and the system achieved the highest performance by combining word segmentation and section information, indicating that these two types offeature complement each other.
••
TL;DR: The need for enhanced measures to secure patients' PHI to avoid undermining their trust is underscored, as most respondents expressed concerns about data breach when their PHI was being transferred between healthcare professionals by fax or electronically.
••
TL;DR: Predictive models developed from off-the-shelf and EMR data using machine learning (ML) algorithms exceeded the treatment sensitivity and treatment specificity of clinicians.
••
TL;DR: It appears that as a complement to existing health services, patient portals can lead to improvements in clinical outcomes, patient behavior, and experiences and these networks provide more fertile contexts for patient portals to be effective.
••
Virginia Commonwealth University1, University of Wisconsin-Madison2, Mathematica Policy Research3, American Academy of Family Physicians4, University of Michigan5, Vanderbilt University6, University at Buffalo7, University of Oklahoma Health Sciences Center8, University of Colorado Denver9, University of Minnesota10, American Board of Family Medicine11, MetroHealth12
TL;DR: A consensus statement is presented about gaps in current EHR functionality and needed enhancements to support primary care, including EHR modifications, expanded use of patient portals, seamless integration with external applications, and advancement of national infrastructure and policies.
••
Roy J. and Lucille A. Carver College of Medicine1, Boston University2, Edith Nourse Rogers Memorial Veterans Hospital3, University of Massachusetts Medical School4, Portland VA Medical Center5, Oregon Health & Science University6, Brigham and Women's Hospital7, Veterans Health Administration8, University of Iowa9, Stanford University10, University of Missouri11
TL;DR: Veterans' self-rated computer ability was the strongest factor contributing to both Blue Button use and to sharing information with non-VA providers, and barriers to adoption were low awareness of the feature and difficulty using the Blue Button.
••
TL;DR: The majority of studies focused on 'theoretical' and 'pre-development/design'.
••
TL;DR: Although few positive findings generally favored patient access, the literature is unclear on whether providing patients access to their medical records improves quality, and outcomes were equivocal with respect to several aspects of effectiveness and patient-centeredness.
••
TL;DR: Substantial variability exists in the methods used to identify adverse drug events in administrative data and this work may serve as a point of reference for future research and consensus building in this area.
••
TL;DR: Evidence is provided that applying human factors design principles to medication alerts can improve usability and prescribing outcomes and design modifications that likely contributed to better prescribing.
••
TL;DR: Using the dataset from a popular OHC, the research demonstrated that the proposed metric is highly effective in identifying influential users and combining the metric with other traditional measures further improves the identification of influential users.
••
Columbia University1, University of Wisconsin-Madison2, Mayo Clinic3, National Institutes of Health4, University of Virginia5, AcademyHealth6, Ohio State University7, Durham University8, University of Illinois at Chicago9, AstraZeneca10, Partners HealthCare11, Harvard University12, University of Minnesota13
TL;DR: It is asserted that the use of health data should be viewed as a public good and that achieving the broad benefits of this use will require understanding and support from patients.
••
TL;DR: EHR data can generate clinically plausible mortality predictive models with excellent discrimination and models that incorporate laboratory and AHRQ's CCS and CS variables have utility for risk adjustment in retrospective outcome studies.
••
TL;DR: In this paper, the authors investigated three approaches to learn hospital-specific predictions about the risk of hospitalassociated infection with Clostridium difficile, and performed a comparative analysis of the value of different ways of using external data to enhance hospital-specifi credictions.
••
TL;DR: The consumer-facing part of the PCEHR, designed around the needs of consumers, has the potential to transform the ability of patients to actively engage in their own healthcare, and to enable the emerging partnership model of health and healthcare in medicine.