Entity

Time filter

Source Type

North Bethesda, MD, United States

Del Fiol G.,University of Utah | Workman T.E.,Lister Hill Center | Gorman P.N.,Oregon Health And Science University
JAMA Internal Medicine | Year: 2014

IMPORTANCE In making decisions about patient care, clinicians raise questions and are unable to pursue or find answers to most of them. Unanswered questions may lead to suboptimal patient care decisions. OBJECTIVE To systematically review studies that examined the questions clinicians raise in the context of patient care decision making. DATA SOURCES MEDLINE (from 1966), CINAHL (from 1982), and Scopus (from 1947), all through May 26, 2011. STUDY SELECTION Studies that examined questions raised and observed by clinicians (physicians, medical residents, physician assistants, nurse practitioners, nurses, dentists, and care managers) in the context of patient care were independently screened and abstracted by 2 investigators. Of 21 710 citations, 72 met the selection criteria. DATA EXTRACTION AND SYNTHESIS Question frequencywas estimated by pooling data from studies with similar methods. MAIN OUTCOMES AND MEASURES Frequency of questions raised, pursued, and answered and questions by type according to a taxonomy of clinical questions. Thematic analysis of barriers to information seeking and the effects of information seeking on decision making. RESULTS In 11 studies, 7012 questions were elicited through short interviews with clinicians after each patient visit. The mean frequency of questions raised was 0.57 (95%CI, 0.38-0.77) per patient seen, and clinicians pursued 51%(36%-66%) of questions and found answers to 78%(67%-88%) of those they pursued. Overall, 34%of questions concerned drug treatment, and 24%concerned potential causes of a symptom, physical finding, or diagnostic test finding. Clinicians' lack of time and doubt that a useful answer exists were the main barriers to information seeking. CONCLUSIONS AND RELEVANCE Clinicians frequently raise questions about patient care in their practice. Although they are effective at finding answers to questions they pursue, roughly half of the questions are never pursued. This picture has been fairly stable over time despite the broad availability of online evidence resources that can answer these questions. Technology-based solutions should enable clinicians to track their questions and provide just-in-time access to high-quality evidence in the context of patient care decision making. Opportunities for improvement include the recent adoption of electronic health record systems and maintenance of certification requirements. © 2014 American Medical Association. All rights reserved. Source


Morid M.A.,University of Utah | Fiszman M.,Lister Hill Center | Raja K.,Northwestern University | Jonnalagadda S.R.,Northwestern University | Del Fiol G.,University of Utah
Journal of Biomedical Informatics | Year: 2016

Most patient care questions raised by clinicians can be answered by online clinical knowledge resources. However, important barriers still challenge the use of these resources at the point of care. Objective: To design and assess a method for extracting clinically useful sentences from synthesized online clinical resources that represent the most clinically useful information for directly answering clinicians' information needs. Materials and methods: We developed a Kernel-based Bayesian Network classification model based on different domain-specific feature types extracted from sentences in a gold standard composed of 18 UpToDate documents. These features included UMLS concepts and their semantic groups, semantic predications extracted by SemRep, patient population identified by a pattern-based natural language processing (NLP) algorithm, and cue words extracted by a feature selection technique. Algorithm performance was measured in terms of precision, recall, and F-measure. Results: The feature-rich approach yielded an F-measure of 74% versus 37% for a feature co-occurrence method (p < 0.001). Excluding predication, population, semantic concept or text-based features reduced the F-measure to 62%, 66%, 58% and 69% respectively (p < 0.01). The classifier applied to Medline sentences reached an F-measure of 73%, which is equivalent to the performance of the classifier on UpToDate sentences (p = 0.62). Conclusions: The feature-rich approach significantly outperformed general baseline methods. This approach significantly outperformed classifiers based on a single type of feature. Different types of semantic features provided a unique contribution to overall classification performance. The classifier's model and features used for UpToDate generalized well to Medline abstracts. © 2016 Elsevier Inc. Source


Hanauer D.A.,University of Michigan | Saeed M.,University of Michigan | Zheng K.,University of Michigan | Mei Q.,University of Michigan | And 3 more authors.
Journal of the American Medical Informatics Association | Year: 2014

Objective: We describe experiments designed to determine the feasibility of distinguishing known from novel associations based on a clinical dataset comprised of International Classification of Disease, V.9 (ICD-9) codes from 1.6 million patients by comparing them to associations of ICD-9 codes derived from 20.5 million Medline citations processed using MetaMap. Associations appearing only in the clinical dataset, but not in Medline citations, are potentially novel. Methods: Pairwise associations of ICD-9 codes were independently identified in both the clinical and Medline datasets, which were then compared to quantify their degree of overlap. We also performed a manual review of a subset of the associations to validate how well MetaMap performed in identifying diagnoses mentioned in Medline citations that formed the basis of the Medline associations. Results: The overlap of associations based on ICD-9 codes in the clinical and Medline datasets was low: only 6.6% of the 3.1 million associations found in the clinical dataset were also present in the Medline dataset. Further, a manual review of a subset of the associations that appeared in both datasets revealed that cooccurring diagnoses from Medline citations do not always represent clinically meaningful associations. Discussion: Identifying novel associations derived from large clinical datasets remains challenging. Medline as a sole data source for existing knowledge may not be adequate to filter out widely known associations. Conclusions: In this study, novel associations were not readily identified. Further improvements in accuracy and relevance for tools such as MetaMap are needed to realize their expected utility. Source


Fiol G.D.,University of Utah | Medlin R.,University of North Carolina | Weir C.,University of Utah | Fiszman M.,Lister Hill Center | Mostafa J.,University of North Carolina
Proceedings - 2012 IEEE 2nd Conference on Healthcare Informatics, Imaging and Systems Biology, HISB 2012 | Year: 2012

Online health knowledge resources contain answers to most of the information needs raised by clinicians in the course of care. However, significant barriers limit the use of these resources for decision-making, especially clinicians' lack of time. Existing solutions are less optimal when information needs cannot be met without substantial cognitive effort and time. Objectives: In this study, we assessed the feasibility of automatically generating knowledge summaries for a particular clinical topic composed of relevant sentences extracted from Medline citations. Methods: The proposed approach combines information retrieval and semantic information extraction techniques to identify relevant sentences from Medline abstracts. We assessed this approach in two case studies on the treatment alternatives for depression and Alzheimer's disease. Results: A total of 515 out of 564 (91.3%) sentences retrieved in the two case studies were relevant to the topic of interest. About one third of the relevant sentences described factual knowledge or a study conclusion that can be used for supporting information needs at the point of care. Conclusions: Our proposed technical approach to helping clinicians meet their information needs is promising. The approach can be extended for other knowledge resources and information need types. © 2012 IEEE. Source


Jonnalagadda S.R.,Mayo Medical School | Del Fiol G.,University of Utah | Medlin R.,University of North Carolina at Chapel Hill | Weir C.,University of Utah | And 4 more authors.
Journal of the American Medical Informatics Association | Year: 2013

Objective: Online health knowledge resources contain answers to most of the information needs raised by clinicians in the course of care. However, significant barriers limit the use of these resources for decisionmaking, especially clinicians' lack of time. In this study we assessed the feasibility of automatically generating knowledge summaries for a particular clinical topic composed of relevant sentences extracted from Medline citations. Methods: The proposed approach combines information retrieval and semantic information extraction techniques to identify relevant sentences from Medline abstracts. We assessed this approach in two case studies on the treatment alternatives for depression and Alzheimer's disease. Results: A total of 515 of 564 (91.3%) sentences retrieved in the two case studies were relevant to the topic of interest. About one-third of the relevant sentences described factual knowledge or a study conclusion that can be used for supporting information needs at the point of care. Conclusions: The high rate of relevant sentences is desirable, given that clinicians' lack of time is one of the main barriers to using knowledge resources at the point of care. Sentence rank was not significantly associated with relevancy, possibly due to most sentences being highly relevant. Sentences located closer to the end of the abstract and sentences with treatment and comparative predications were likely to be conclusive sentences. Our proposed technical approach to helping clinicians meet their information needs is promising. The approach can be extended for other knowledge resources and information need types. Source

Discover hidden collaborations