We review existing query answering systems for sensor data. We then propose an extended query answering approach termed smart query, specifically for marine sensor data. The smart query answering system integrates pattern queries and continuous queries. The proposed smart query system considers both streaming data and historical data from marine sensor networks. The smart query also uses query relaxation technique and semantics from domain knowledge as a recommender system. The proposed smart query benefits in building data and information systems for marine sensor networks.
marine sensor network; sensor data; smart query
Objective To develop a model based upon factors able to predict the time spent answering drug-related queries to Norwegian drug information centres (DICs). Setting and method Drug-related queries received at 5 DICs in Norway from March to May 2007 were randomly assigned to 20 employees until each of them had answered a minimum of five queries. The employees reported the number of drugs involved, the type of literature search performed, and whether the queries were considered judgmental or not, using a specifically developed scoring system. Main outcome measures The scores of these three factors were added together to define a workload score for each query. Workload and its individual factors were subsequently related to the measured time spent answering the queries by simple or multiple linear regression analyses. Results Ninety-six query/answer pairs were analyzed. Workload significantly predicted the time spent answering the queries (adjusted R2 = 0.22, P < 0.001). Literature search was the individual factor best predicting the time spent answering the queries (adjusted R2 = 0.17, P < 0.001), and this variable also contributed the most in the multiple regression analyses. Conclusion The most important workload factor predicting the time spent handling the queries in this study was the type of literature search that had to be performed. The categorisation of queries as judgmental or not, also affected the time spent answering the queries. The number of drugs involved did not significantly influence the time spent answering drug information queries.
Drug information; Drug Information Centres; Norway; Queries; Time; Workload
To assess the intra‐reader and inter‐reader reliabilities of interpreting ultrasonography by several experts using video clips.
99 video clips of healthy and rheumatic joints were recorded and delivered to 17 physician sonographers in two rounds. The intra‐reader and inter‐reader reliabilities of interpreting the ultrasound results were calculated using a dichotomous system (normal/abnormal) and a graded semiquantitative scoring system.
The video reading method worked well. 70% of the readers could classify at least 70% of the cases correctly as normal or abnormal. The distribution of readers answering correctly was wide. The most difficult joints to assess were the elbow, wrist, metacarpophalangeal (MCP) and knee joints. The intra‐reader and inter‐reader agreements on interpreting dynamic ultrasound images as normal or abnormal, as well as detecting and scoring a Doppler signal were moderate to good (κ = 0.52–0.82).
Dynamic image assessment (video clips) can be used as an alternative method in ultrasonography reliability studies. The intra‐reader and inter‐reader reliabilities of ultrasonography in dynamic image reading are acceptable, but more definitions and training are needed to improve sonographic reproducibility.
Six factual queries were unobtrusively telephoned to fifty-one U.S. academic health sciences and hospital libraries. The majority of the queries (63.4%) were answered accurately. Referrals to another library or information source were made for 25.2% of the queries. Eleven answers (3.6%) were inaccurate, and no answer was provided for 7.8% of the queries. There was a correlation between the number of accurate answers provided and the presence of at least one staff member with a master's degree in library and information science. The correlation between employing a librarian certified by the Medical Library Association (MLA) and providing accurate answers was significant. The majority of referrals were to specific sources. If these "helpful referrals" are counted with accurate answers as correct responses, they total 76.8% of the answers. In a follow-up survey, five libraries stated that they did not provide accurate answers because they did not own an appropriate source. Staff-related problems were given as reasons for other than accurate answers by two of the libraries, while eight indicated that library policy prevented them from providing answers to the public.
Query networks are specializations of Belief networks used in information retrieval. We hypothesize that query networks can be incorporated into medical information systems in at least two ways: First, the relative values of nodes in the query networks can be used to initiate searches based on query term-weights. Second, query models can incorporate reader feedback and can become simple task-specific user models. If large query networks are to be useful, one must find means to assign reasonable “default” values to those nodes and edges which are not explicitly defined by some other means. This paper presents preliminary data assessing the suitability of various default heuristic query network edge assignment functions. Early evidence suggests that query networks using default assignment functions exhibit behavior consistent with that expected from an information retrieval aid.
Maze tasks have appealing properties as progress-monitoring tools, but there is a need for a thorough examination of the psychometric properties of Maze tasks among middle school students. We evaluated form effects, reliability, validity, and practice effects of Maze among students in Grades 6 through 8. We administered the same (familiar) and novel Maze passages for progress monitoring of a reading intervention among typical readers (n = 588), struggling readers receiving researcher-provided intervention (n = 471), and struggling readers not receiving intervention (n = 284). Form effects accounted for significant variance in Maze performance. Familiar passages had greater test–retest reliability than novel passages. Both administrative conditions had similar, moderate correlations (validity coefficients) with other measures of reading fluency and comprehension. There were also significant practice effects. Students who read the same passage showed steeper slopes in Maze performance than students who read different passages over time. Practice effects were influenced by beginning levels of reading comprehension and by intervention status.
Maze; reading comprehension; measurement; middle school; progress monitoring
We analyzed query logs from use of MEDLINEplus to answer the questions: Are consumers’ health information needs stable over time? and To what extent do users’ queries change over time? To determine log stability, we assessed an Overlap Rate (OR) defined as the number of unique queries common to two adjacent months divided by the total number of unique queries in those months. All exactly matching queries were considered as one unique query. We measured ORs for the top 10 and 100 unique queries of a month and compared these to ORs for the following month.
Over ten months, users submitted 12,234,737 queries; only 2,179,571 (17.8%) were unique and these had a mean word count of 2.73 (S.D., 0.24); 121 of 137 (88.3%) unique queries each comprised of exactly matching search term(s) used at least 5000 times were of only one word. We could predict with 95% confidence that the monthly OR for the top 100 unique queries would lie between 67% – 87% when compared with the top 100 from the previous month. The mean month-to-month OR for top 10 queries was 62% (S.D., 20%) indicating significant variability; the lowest OR of 33% between the top 10 in Mar. compared to Apr. was likely due to “new” interest in information about SARS pneumonia in Apr. 2003.
Consumers’ health information needs are relatively stable and the 100 most common unique queries are about 77% the same from month to month. Website sponsors should provide a broad range of information about a relatively stable number of topics. Analyses of log similarity may identify media-induced, cyclical, or seasonal changes in areas of consumer interest.
MEDLINEplus; Consumer Informatics
Evaluate KNAVE-II, a knowledge-based framework for visualization, interpretation, and exploration of longitudinal clinical data, clinical concepts and patterns. KNAVE-II mediates queries to a distributed temporal-abstraction architecture (IDAN), which uses a knowledge-based problem-solving method specializing in on-the-fly computation of clinical queries.
A two-phase, balanced cross-over study to compare efficiency and satisfaction of a group of clinicians when answering queries of variable complexity about time-oriented clinical data, typical for oncology protocols, using KNAVE-II, versus standard methods: Both paper charts and a popular electronic spreadsheet (ESS) in Phase I; an ESS in Phase II. The measurements included the time required to answer and the correctness of answer for each query and each complexity category, and for all queries, assessed versus a predetermined gold standard set by a domain expert. User satisfaction was assessed by the Standard Usability Score (SUS) tool-specific questionnaire and by a “Usability of Tool Comparison” comparative questionnaire developed for this study.
In both evaluations, subjects answered higher-complexity queries significantly faster using KNAVE-II than when using paper charts or an ESS up to a mean of 255 seconds difference per query versus the ESS for hard queries (p=0.0003) in the second evaluation. Average correctness scores when using KNAVE-II versus paper charts, in the first phase, and the ESS, in the second phase, were significantly higher over all queries. In the second evaluation, 91.6% (110/120) of all of the questions asked within queries of all levels produced correct answers using KNAVE-II, opposed to only 57.5% (69/120) using the ESS (p<0.0001). User satisfaction with KNAVE-II was significantly superior compared to using either a paper chart or the ESS (p=0.006). Clinicians ranked KNAVE-II superior to both paper and the ESS.
An evaluation of the functionality and usability of KNAVE-II and its supporting knowledge-based temporal-mediation architecture has produced highly encouraging results regarding saving of physician time, enhancement of accuracy of clinical assessment, and user satisfaction.
Medical Informatics; Clinical Decision-Support Systems; Human-Computer Interface; Information Visualization; Knowledge-Based Systems; Temporal Reasoning; Intelligent User Interfaces
Medical data are characterized by complex taxonomies and evolving terminology. Questions that clinicians, medical administrators, and researchers may wish to answer using medical databases are not easily formulated as SQL queries. In this paper we describe a graphical tool that facilitates formulation of ad hoc questions as SQL queries. This tool manages multiple attribute hierarchies and creates SQL query strings by navigating through the hierarchies. This interactive tool has been optimized using indexing to improve the overall speed of the query building and the data retrieval process. Indexed queries performed 5 to 100 times faster than query strings. However, query string generation time depends on the size of the taxonomies describing the hierarchies, while the index generation time depends on the size of the data warehouse.
Translating a question into a query using patient characteristics, type of intervention, control, and outcome (PICO) should help answer therapeutic questions in PubMed searches. The authors performed a randomized crossover trial to determine whether the PICO format was useful for quick searches of PubMed.
Twenty-two residents and specialists working at the Radboud University Nijmegen Medical Centre were trained in formulating PICO queries and then presented with a randomized set of questions derived from Cochrane reviews. They were asked to use the best query possible in a five-minute search, using standard and PICO queries. Recall and precision were calculated for both standard and PICO queries.
Twenty-two physicians created 434 queries using both techniques. Average precision was 4.02% for standard queries and 3.44% for PICO queries (difference nonsignificant, t(21) = −0.56, P = 0.58). Average recall was 12.27% for standard queries and 13.62% for PICO queries (difference nonsignificant, t(21) = −0.76, P = 0.46).
PICO queries do not result in better recall or precision in time-limited searches. Standard queries containing enough detail are sufficient for quick searches.
The use of PubMed to answer daily medical care questions is limited because it is challenging to retrieve a small set of relevant articles and time is restricted. Knowing what aspects of queries are likely to retrieve relevant articles can increase the effectiveness of PubMed searches. The objectives of our study were to identify queries that are likely to retrieve relevant articles by relating PubMed search techniques and tools to the number of articles retrieved and the selection of articles for further reading.
This was a prospective observational study of queries regarding patient-related problems sent to PubMed by residents and internists in internal medicine working in an Academic Medical Centre. We analyzed queries, search results, query tools (Mesh, Limits, wildcards, operators), selection of abstract and full-text for further reading, using a portal that mimics PubMed.
PubMed was used to solve 1121 patient-related problems, resulting in 3205 distinct queries. Abstracts were viewed in 999 (31%) of these queries, and in 126 (39%) of 321 queries using query tools. The average term count per query was 2.5. Abstracts were selected in more than 40% of queries using four or five terms, increasing to 63% if the use of four or five terms yielded 2–161 articles.
Queries sent to PubMed by physicians at our hospital during daily medical care contain fewer than three terms. Queries using four to five terms, retrieving less than 161 article titles, are most likely to result in abstract viewing. PubMed search tools are used infrequently by our population and are less effective than the use of four or five terms. Methods to facilitate the formulation of precise queries, using more relevant terms, should be the focus of education and research.
A model of clinical query management is described that supports the integration of various types of biomedical information and the delivery of that information through a common interface. The model extends the architecture of the World Wide Web to include a Common Gateway Interface (CGI) mediator, which takes in user queries, performs syntactic and semantic processing to transform the input to a canonical form, selects the appropriate information sources to answer the query, translates the canonical query statement into a query of each information resource, queries the chosen information sources in parallel, and controls the analysis and display of results. We describe WebMedline, a CGI mediator that implements portions of this model, and discuss the benefits and limitations of this approach.
Inexperienced users of online medical databases often do not know how to formulate their queries for effective searches. Previous attempts to help them have provided some standard procedures for query formulation, but depend on the user to enter the concepts of a query properly so that the correct search strategy will be formed. Intelligent assistance specific to a particular query often is not given. Several systems do refine the initial strategy based on relevance feedback, but usually do not make an effort to determine how well-formed a query is before actually performing the search. As part of the Interactive Query Workstation (IQW), we have developed an expert system, Questions and Answers (Q&A), that assists in formulating an initial strategy given concepts entered by the user and that determines if the strategy is well-formed, refining it when necessary.
Imaging plays an important role in characterizing tumors. Knowledge inferred from imaging data has the potential to improve disease management dramatically, but physicians lack a tool to easily interpret and manipulate the data. A probabilistic disease model, such as a Bayesian belief network, may be used to quantitatively model relationships found in the data. In this paper, a framework is presented that enables visual querying of an underlying disease model via a query-by-example paradigm. Users draw graphical metaphors to visually represent features in their query. The structure and parameters specified within the model guide the user through query formulation by determining when a user may draw a particular metaphor. Spatial and geometrical features are automatically extracted from the query diagram and used to instantiate the probabilistic model in order to answer the query. An implementation is described in the context of managing patients with brain tumors.
The National Medical Association (NMA) is accredited by the Accreditation Council for Continuing Medical Education to sponsor continuing medical education (CME) for physicians.
NMA certifies that when CME material is used as directed it meets the criteria for 2 hours of credit in Category I toward the NMA Physician Achievement Award (PAA) or American Medical Association Physician's Recognition Award (PRA).
Each physician should claim only those hours of credit that the physician actually spent in the educational activity. Estimated time for reading the text and taking the CME quiz is approximately 2 hours. The NMA will not maintain any records on individual performance.
Physician readers will receive 2 category I credits upon correctly answering a minimum of 70% of the CME questions at the end of this CME article. Physician readers must send the answers to JNMA/CME, 1012 Tenth St., NW, Washington, DC 20001. Answers to the CME questions accompanying this article must be marked by September 25, 2001.
The first or second author of articles published in the Journal of the National Medical Association may claim Category I credit for the NMA PAA or the American Medical Association PRA by including a reprint of the article's first page as part of the PRA or PAA application.
PAA application can be obtained by calling NMA's CME office at (202) 347-1895, ext. 241. PRA application can be found by visiting http://www.ama-assn.org/med-sci/pra/prahdr.htm.
We present a general model for data integration systems using a mediated schema to represent commonalities in the underlying sources. These sources are mapped to the mediated schema using source descriptions. Users can pose queries against the mediated schema, allowing the system to generate automatically a query plan that enumerates and ranks all possible ways in which the query could be answered. We apply this approach to the domain of online genetic databases, demonstrating the system s ability to answer relevant queries across multiple sources.
Objective: The authors' goal was to determine whether dynamic categorization, a new technique for organizing search results, is more useful than the two existing organizational techniques: relevance ranking and clustering. They define a useful tool as one that helps users learn about the kinds of information that pertain to their query, find answers to their questions efficiently and easily, and feel satisfied with their search experience.
Design: Fifteen patients with breast cancer and their family members completed query-related tasks using all three tools. The authors measured the time it took the subjects to accomplish their tasks, the number of answers to the query that the subjects found in four minutes, and the number of new answers that they could recall at the end of the study. Subjects also completed a user-satisfaction questionnaire.
Results: The results showed that patients with breast cancer and their family members could find significantly (P < 0.05) more answers in a fixed amount of time and were significantly (P < 0.05) more satisfied with their search experience when they used the dynamic categorization tool than when they used either the cluster tool or the ranking tool. Subjects indicated that the dynamic categorization tool provided an organization of search results that was more clear, easy to use, accurate, precise, and helpful than those of the other tools.
Conclusion: The experiments indicate that dynamic categorization is an effective and useful approach for organizing search results. Tools that use this technique will help patients and their families gain quick and easy access to important medical information.
The aim of this study was to evaluate the added utility of embedding images for findings described in radiology text reports to referring clinicians.
Thirty-five cases referred for abdominal CT scans in 2007 and 2008 were included. Referring physicians were asked to view text-only reports, followed by the same reports with pertinent images embedded. For each pair of reports, a questionnaire was administered. A 5-point, Likert-type scale was used to assess if the clinical query was satisfactorily answered by the text-only report. A “yes-or-no” question was used to assess whether the report with images answered the clinical query better; a positive answer to this question generated “yes-or-no” queries to examine whether the report with images helped in making a more confident decision on management, whether it reduced time spent in forming the plan, and whether it altered management. The questionnaire asked whether a radiologist would be contacted with queries on reading the text-only report and the report with images.
In 32 of 35 cases, the text-only reports satisfactorily answered the clinical queries. In these 32 cases, the reports with attached images helped in making more confident management decisions and reduced time in planning management. Attached images altered management in 2 cases. Radiologists would have been consulted for clarifications in 21 and 10 cases on reading the text-only reports and the reports with embedded images, respectively.
Providing relevant images with reports saves time, increases physicians' confidence in deciding treatment plans, and can alter management.
Radiology reporting; radiology practice; communication; digital images
The Indian Journal of Psychiatry receives many reports which, despite obvious academic worth, are too poorly written to be publishable. Such submissions tax manuscript reviewers and increase the editorial office workload without benefiting the authors with a publication.
We describe an authentic and previously unpublished case of idiopathic leucopenia and psychosis. Leucocyte levels in this patient dropped upon challenge with different atypical antipsychotic drugs. Lithium pretreatment, however, permitted the safe and successful use of trifluperazine. Readers are invited to use a roughly-prepared version of the case report to draft a submission-worthy manuscript.
Two versions of the manuscript are presented. The first version is generally satisfactory but will trigger several queries during peer review; these queries are indicated. The second version would be considered acceptable by most reviewers.
Readers who work through the exercise provided in this article will better understand how authors should prepare their report and how reviewers may scrutinize their manuscript.
Case report preparation; idiopathic leucopenia; lithium; surviving peer review; trifluperazine; writing skills
Many abbreviations are used in the literature especially in the life sciences, and polysemous abbreviations appear frequently, making it difficult to read and understand scientific papers that are outside of a reader’s expertise. Thus, we have developed Allie, a database and a search service of abbreviations and their long forms (a.k.a. full forms or definitions). Allie searches for abbreviations and their corresponding long forms in a database that we have generated based on all titles and abstracts in MEDLINE. When a user query matches an abbreviation, Allie returns all potential long forms of the query along with their bibliographic data (i.e. title and publication year). In addition, for each candidate, co-occurring abbreviations and a research field in which it frequently appears in the MEDLINE data are displayed. This function helps users learn about the context in which an abbreviation appears. To deal with synonymous long forms, we use a dictionary called GENA that contains domain-specific terms such as gene, protein or disease names along with their synonymic information. Conceptually identical domain-specific terms are regarded as one term, and then conceptually identical abbreviation-long form pairs are grouped taking into account their appearance in MEDLINE. To keep up with new abbreviations that are continuously introduced, Allie has an automatic update system. In addition, the database of abbreviations and their long forms with their corresponding PubMed IDs is constructed and updated weekly.
Database URL: The Allie service is available at http://allie.dbcls.jp/.
Transcriptomic biomarkers of psychiatric diseases obtained from a query of peripheral tissues that are clinically accessible (e.g., blood cells instead of post-mortem brain tissue) have substantial practical appeal to discern the molecular subtypes of common complex diseases such as major psychosis. To this end, spliceome-profiling is a new methodological approach that has considerable conceptual relevance for discovery and clinical translation of novel biomarkers for psychiatric illnesses. Advances in microarray technology now allow for improved sensitivity in measuring the transcriptome while simultaneously querying the “exome” (all exons) and “spliceome” (all alternatively spliced variants). The present study aimed to evaluate the feasibility of spliceome-profiling to discern transcriptomic biomarkers of psychosis.
We measured exome and spliceome expression in peripheral blood mononuclear cells from 13 schizophrenia patients, nine bipolar disorder patients, and eight healthy control subjects. Each diagnostic group was compared to each other, and the combined group of bipolar disorder and schizophrenia patients was also compared to the control group. Furthermore, we compared subjects with a history of psychosis to subjects without such history.
After applying Bonferroni corrections for the 21,866 full-length gene transcripts analyzed, we found significant interactions between diagnostic group and exon identity, consistent with group differences in rates or types of alternative splicing. Relative to the control group, 18 genes in the bipolar disorder group, eight genes in the schizophrenia group, and 15 genes in the combined bipolar disorder and schizophrenia group appeared differentially spliced. Importantly, thirty-three genes showed differential splicing patterns between the bipolar disorder and schizophrenia groups. More frequent exon inclusion and/or over-expression was observed in psychosis. Finally, these observations are reconciled with an analysis of the ontologies, the pathways and the protein domains significantly over-represented among the alternatively spliced genes, several of which support prior discoveries.
To our knowledge, this is the first blood-based spliceome-profiling study of schizophrenia and bipolar disorder to be reported. The battery of alternatively spliced genes and exons identified in this discovery-oriented exploratory study, if replicated, may have potential utility to discern the molecular subtypes of psychosis. Spliceome-profiling, as a new methodological approach in transcriptomics, warrants further work to evaluate its utility in personalized medicine. Potentially, this approach could also permit the future development of tissue-sampling methodologies in a form that is more acceptable to patients and thereby allow monitoring of dynamic and time-dependent plasticity in disease severity and response to therapeutic interventions in clinical psychiatry.
Gene expression; spliceome-profiling; blood-based biomarkers; psychosis; CNS disease diagnostics
To compare PubMed Clinical Queries and UpToDate regarding the amount and speed of information retrieval and users' satisfaction.
A cross-over randomized trial was conducted in February 2009 in Tehran University of Medical Sciences that included 44 year-one or two residents who participated in an information mastery workshop. A one-hour lecture on the principles of information mastery was organized followed by self learning slide shows before using each database. Subsequently, participants were randomly assigned to answer 2 clinical scenarios using either UpToDate or PubMed Clinical Queries then crossed to use the other database to answer 2 different clinical scenarios. The proportion of relevantly answered clinical scenarios, time to answer retrieval, and users' satisfaction were measured in each database.
Based on intention-to-treat analysis, participants retrieved the answer of 67 (76%) questions using UpToDate and 38 (43%) questions using PubMed Clinical Queries (P<0.001). The median time to answer retrieval was 17 min (95% CI: 16 to 18) using UpToDate compared to 29 min (95% CI: 26 to 32) using PubMed Clinical Queries (P<0.001). The satisfaction with the accuracy of retrieved answers, interaction with UpToDate and also overall satisfaction were higher among UpToDate users compared to PubMed Clinical Queries users (P<0.001).
For first time users, using UpToDate compared to Pubmed Clinical Querries can lead to not only a higher proportion of relevant answer retrieval within a shorter time, but also a higher users' satisfaction. So, addition of tutoring pre-appraised sources such as UpToDate to the information mastery curricula seems to be highly efficient.
OWL, the Web Ontology Language, provides syntax and semantics for representing knowledge for the semantic web. Many of the constructs of OWL have a basis in the field of description logics. While the formal underpinnings of description logics have lead to a highly computable language, it has come at a cognitive cost. OWL ontologies are often unintuitive to readers lacking a strong logic background.
In this work we describe GLEEN, a regular path expression library, which extends the RDF query language SparQL to support complex path expressions over OWL and other RDF-based ontologies. We illustrate the utility of GLEEN by showing how it can be used in a query-based approach to defining simpler, more intuitive views of OWL ontologies. In particular we show how relatively simple GLEEN-enhanced SparQL queries can create views of the OWL version of the NCI Thesaurus that match the views generated by the web-based NCI browser.
In this issue of the Journal, Thall et al. present the results of a clinical trial that makes use of sequential randomization, a novel trial design that allows the investigator to study adaptive treatment strategies. Our aim is to complement this groundbreaking work by reviewing the current state of the art of statistical methods available for such analyses. Using the data collected by Thall et al. as an example, we focus on two different approaches for estimating the success rates of different adaptive treatment strategies of interest. By emphasizing the intuitive appeal and straightforward implementation of these methods and illustrating the striking findings to which these methods can lead, we hope to convince the reader that this novel trial design provides a rich source of information that is made readily accessible through current analytical approaches.
Independent evaluation of clinical evidence is advocated in evidence-based medicine (EBM). However, authors' conclusions are often appealing for readers who look for quick messages. We assessed how well a group of Malaysian hospital practitioners and medical students derived their own conclusions from systematic reviews (SRs) and to what extent these were influenced by their prior beliefs and the direction of the study results.
We conducted two cross-sectional studies: one with hospital practitioners (n = 150) attending an EBM course in June 2008 in a tertiary hospital and one with final-year medical students (n = 35) in November 2008. We showed our participants four Cochrane SR abstracts without the authors' conclusions. For each article, the participants chose a conclusion from among six options comprising different combinations of the direction of effect and the strength of the evidence. We predetermined the single option that best reflected the actual authors' conclusions and labelled this as our best conclusion. We compared the participants' choices with our predetermined best conclusions. Two chosen reviews demonstrated that the intervention was beneficial ("positive"), and two others did not ("negative"). We also asked the participants their prior beliefs about the intervention.
Overall, 60.3% correctly identified the direction of effect, and 30.1% chose the best conclusions, having identified both the direction of effect and the strength of evidence. More students (48.2%) than practitioners (22.2%) chose the best conclusions (P < 0.001). Fewer than one-half (47%) correctly identified the direction of effect against their prior beliefs. "Positive" SRs were more likely than "negative" SRs to change the participants' beliefs about the effect of the intervention (relative risk (RR) 1.8, 95% confidence interval 1.3 to 2.6) and "convert" those who were previously unsure by making them choose the appropriate direction of effect (RR 1.9, 95% confidence interval 1.3 to 2.8).
The majority of our participants could not generate appropriate conclusions from SRs independently. Judicious direction from the authors' conclusions still appears crucial to guiding our health care practitioners in identifying appropriate messages from research. Authors, editors and reviewers should ensure that the conclusions of a paper accurately reflect the results. Similar studies should be conducted in other settings where awareness and application of EBM are different.
Please see Commentary: http://www.biomedcentral.com/1741-7015/9/31/.