PMCC PMCC

Search tips
Search criteria

Advanced
Results 26-50 (980)
 

Clipboard (0)
None

Select a Filter Below

Journals
Year of Publication
more »
26.  ODM2CDA and CDA2ODM: Tools to convert documentation forms between EDC and EHR systems 
Background
Clinical trials apply standards approved by regulatory agencies for Electronic Data Capture (EDC). Operational Data Model (ODM) from Clinical Data Interchange Standards Consortium (CDISC) is commonly used. Electronic Health Record (EHR) systems for patient care predominantly apply HL7 standards, specifically Clinical Document Architecture (CDA). In recent years more and more patient data is processed in electronic form.
Results
An open source reference implementation was designed and implemented to convert forms between ODM and CDA format. There are limitations of this conversion method due to different scope and design of ODM and CDA. Specifically, CDA has a multi-level hierarchical structure and CDA nodes can contain both XML values and XML attributes.
Conclusions
Automated transformation of ODM files to CDA and vice versa is technically feasible in principle.
doi:10.1186/s12911-015-0163-5
PMCID: PMC4494189  PMID: 26004011
EHR; EDC; CDA; ODM; Documentation form; Data model
27.  Electronic medical record-based multicondition models to predict the risk of 30 day readmission or death among adult medicine patients: validation and comparison to existing models 
Background
There is increasing interest in using prediction models to identify patients at risk of readmission or death after hospital discharge, but existing models have significant limitations. Electronic medical record (EMR) based models that can be used to predict risk on multiple disease conditions among a wide range of patient demographics early in the hospitalization are needed. The objective of this study was to evaluate the degree to which EMR-based risk models for 30-day readmission or mortality accurately identify high risk patients and to compare these models with published claims-based models.
Methods
Data were analyzed from all consecutive adult patients admitted to internal medicine services at 7 large hospitals belonging to 3 health systems in Dallas/Fort Worth between November 2009 and October 2010 and split randomly into derivation and validation cohorts. Performance of the model was evaluated against the Canadian LACE mortality or readmission model and the Centers for Medicare and Medicaid Services (CMS) Hospital Wide Readmission model.
Results
Among the 39,604 adults hospitalized for a broad range of medical reasons, 2.8 % of patients died, 12.7 % were readmitted, and 14.7 % were readmitted or died within 30 days after discharge. The electronic multicondition models for the composite outcome of 30-day mortality or readmission had good discrimination using data available within 24 h of admission (C statistic 0.69; 95 % CI, 0.68-0.70), or at discharge (0.71; 95 % CI, 0.70-0.72), and were significantly better than the LACE model (0.65; 95 % CI, 0.64-0.66; P =0.02) with significant NRI (0.16) and IDI (0.039, 95 % CI, 0.035-0.044). The electronic multicondition model for 30-day readmission alone had good discrimination using data available within 24 h of admission (C statistic 0.66; 95 % CI, 0.65-0.67) or at discharge (0.68; 95 % CI, 0.67-0.69), and performed significantly better than the CMS model (0.61; 95 % CI, 0.59-0.62; P < 0.01) with significant NRI (0.20) and IDI (0.037, 95 % CI, 0.033-0.041).
Conclusions
A new electronic multicondition model based on information derived from the EMR predicted mortality and readmission at 30 days, and was superior to previously published claims-based models.
Electronic supplementary material
The online version of this article (doi:10.1186/s12911-015-0162-6) contains supplementary material, which is available to authorized users.
doi:10.1186/s12911-015-0162-6
PMCID: PMC4474456  PMID: 25991003
Readmission; Predictive model; All-cause readmission; Electronic medical record
28.  Developing a hybrid dictionary-based bio-entity recognition technique 
Background
Bio-entity extraction is a pivotal component for information extraction from biomedical literature. The dictionary-based bio-entity extraction is the first generation of Named Entity Recognition (NER) techniques.
Methods
This paper presents a hybrid dictionary-based bio-entity extraction technique. The approach expands the bio-entity dictionary by combining different data sources and improves the recall rate through the shortest path edit distance algorithm. In addition, the proposed technique adopts text mining techniques in the merging stage of similar entities such as Part of Speech (POS) expansion, stemming, and the exploitation of the contextual cues to further improve the performance.
Results
The experimental results show that the proposed technique achieves the best or at least equivalent performance among compared techniques, GENIA, MESH, UMLS, and combinations of these three resources in F-measure.
Conclusions
The results imply that the performance of dictionary-based extraction techniques is largely influenced by information resources used to build the dictionary. In addition, the edit distance algorithm shows steady performance with three different dictionaries in precision whereas the context-only technique achieves a high-end performance with three difference dictionaries in recall.
doi:10.1186/1472-6947-15-S1-S9
PMCID: PMC4460617  PMID: 26043907
29.  A formal concept analysis and semantic query expansion cooperation to refine health outcomes of interest 
Background
Electronic Health Records (EHRs) are frequently used by clinicians and researchers to search for, extract, and analyze groups of patients by defining Health Outcome of Interests (HOI). The definition of an HOI is generally considered a complex and time consuming task for health care professionals.
Methods
In our clinical note-based pharmacovigilance research, we often operate upon potentially hundreds of ontologies at once, expand query inputs, and we also increase the search space over clinical text as well as structured data. Such a method implies to specify an initial set of seed concepts, which are based on concept unique identifiers. This paper presents a novel method based on Formal Concept Analysis (FCA) and Semantic Query Expansion (SQE) to assist the end-user in defining their seed queries and in refining the expanded search space that it encompasses.
Results
We evaluate our method over a gold-standard corpus from the 2008 i2b2 Obesity Challenge. This experimentation emphasizes positive results for sensitivity and specificity measures. Our new approach provides better recall with high precision of the obtained results. The most promising aspect of this approach consists in the discovery of positive results not present our Obesity NLP reference set.
Conclusions
Together with a Web graphical user interface, our FCA and SQE cooperation end up being an efficient approach for refining health outcome of interest using plain terms. We consider that this approach can be extended to support other domains such as cohort building tools.
doi:10.1186/1472-6947-15-S1-S8
PMCID: PMC4460622  PMID: 26043839
Health outcome of interest; Ontology; Semantic Query Expansion; Formal Concept Analysis
30.  Injury narrative text classification using factorization model 
Narrative text is a useful way of identifying injury circumstances from the routine emergency department data collections. Automatically classifying narratives based on machine learning techniques is a promising technique, which can consequently reduce the tedious manual classification process. Existing works focus on using Naive Bayes which does not always offer the best performance. This paper proposes the Matrix Factorization approaches along with a learning enhancement process for this task. The results are compared with the performance of various other classification approaches. The impact on the classification results from the parameters setting during the classification of a medical text dataset is discussed. With the selection of right dimension k, Non Negative Matrix Factorization-model method achieves 10 CV accuracy of 0.93.
doi:10.1186/1472-6947-15-S1-S5
PMCID: PMC4460654  PMID: 26043671
Narrative Text; Classification; Pre-processing; Matrix Factorization; Learning Enhancement
31.  Entity linking for biomedical literature 
Background
The Entity Linking (EL) task links entity mentions from an unstructured document to entities in a knowledge base. Although this problem is well-studied in news and social media, this problem has not received much attention in the life science domain. One outcome of tackling the EL problem in the life sciences domain is to enable scientists to build computational models of biological processes with more efficiency. However, simply applying a news-trained entity linker produces inadequate results.
Methods
Since existing supervised approaches require a large amount of manually-labeled training data, which is currently unavailable for the life science domain, we propose a novel unsupervised collective inference approach to link entities from unstructured full texts of biomedical literature to 300 ontologies. The approach leverages the rich semantic information and structures in ontologies for similarity computation and entity ranking.
Results
Without using any manual annotation, our approach significantly outperforms state-of-the-art supervised EL method (9% absolute gain in linking accuracy). Furthermore, the state-of-the-art supervised EL method requires 15,000 manually annotated entity mentions for training. These promising results establish a benchmark for the EL task in the life science domain. We also provide in depth analysis and discussion on both challenges and opportunities on automatic knowledge enrichment for scientific literature.
Conclusions
In this paper, we propose a novel unsupervised collective inference approach to address the EL problem in a new domain. We show that our unsupervised approach is able to outperform a current state-of-the-art supervised approach that has been trained with a large amount of manually labeled data. Life science presents an underrepresented domain for applying EL techniques. By providing a small benchmark data set and identifying opportunities, we hope to stimulate discussions across natural language processing and bioinformatics and motivate others to develop techniques for this largely untapped domain.
doi:10.1186/1472-6947-15-S1-S4
PMCID: PMC4460707  PMID: 26045232
semantic web; biological ontologies; text mining; signal transduction; wikification; entity linking; biomedical literature
32.  Identification of genomic features in the classification of loss- and gain-of-function mutation 
Background
Alterations of a genome can lead to changes in protein functions. Through these genetic mutations, a protein can lose its native function (loss-of-function, LoF), or it can confer a new function (gain-of-function, GoF). However, when a mutation occurs, it is difficult to determine whether it will result in a LoF or a GoF. Therefore, in this paper, we propose a study that analyzes the genomic features of LoF and GoF instances to find features that can be used to classify LoF and GoF mutations.
Methods
In order to collect experimentally verified LoF and GoF mutational information, we obtained 816 LoF mutations and 474 GoF mutations from a literature text-mining process. Next, with data-preprocessing steps, 258 LoF and 129 GoF mutations remained for a further analysis. We analyzed the properties of these LoF and GoF mutations. Among the properties, we selected features which show different tendencies between the two groups and implemented classifications using support vector machine, random forest, and linear logistic regression methods to confirm whether or not these features can identify LoF and GoF mutations.
Results
We analyzed the properties of the LoF and GoF mutations and identified six features which have discriminative power between LoF and GoF conditions: the reference allele, the substituted allele, mutation type, mutation impact, subcellular location, and protein domain. When using the six selected features with the random forest, support vector machine, and linear logistic regression classifiers, the result showed accuracy levels of 72.23%, 71.28%, and 70.19%, respectively.
Conclusions
We analyzed LoF and GoF mutations and selected several properties which were different between the two classes. By implementing classifications with the selected features, it is demonstrated that the selected features have good discriminative power.
doi:10.1186/1472-6947-15-S1-S6
PMCID: PMC4460711  PMID: 26043747
33.  Parsing clinical text: how good are the state-of-the-art parsers? 
Background
Parsing, which generates a syntactic structure of a sentence (a parse tree), is a critical component of natural language processing (NLP) research in any domain including medicine. Although parsers developed in the general English domain, such as the Stanford parser, have been applied to clinical text, there are no formal evaluations and comparisons of their performance in the medical domain.
Methods
In this study, we investigated the performance of three state-of-the-art parsers: the Stanford parser, the Bikel parser, and the Charniak parser, using following two datasets: (1) A Treebank containing 1,100 sentences that were randomly selected from progress notes used in the 2010 i2b2 NLP challenge and manually annotated according to a Penn Treebank based guideline; and (2) the MiPACQ Treebank, which is developed based on pathology notes and clinical notes, containing 13,091 sentences. We conducted three experiments on both datasets. First, we measured the performance of the three state-of-the-art parsers on the clinical Treebanks with their default settings. Then we re-trained the parsers using the clinical Treebanks and evaluated their performance using the 10-fold cross validation method. Finally we re-trained the parsers by combining the clinical Treebanks with the Penn Treebank.
Results
Our results showed that the original parsers achieved lower performance in clinical text (Bracketing F-measure in the range of 66.6%-70.3%) compared to general English text. After retraining on the clinical Treebank, all parsers achieved better performance, with the best performance from the Stanford parser that reached the highest Bracketing F-measure of 73.68% on progress notes and 83.72% on the MiPACQ corpus using 10-fold cross validation. When the combined clinical Treebanks and Penn Treebank was used, of the three parsers, the Charniak parser achieved the highest Bracketing F-measure of 73.53% on progress notes and the Stanford parser reached the highest F-measure of 84.15% on the MiPACQ corpus.
Conclusions
Our study demonstrates that re-training using clinical Treebanks is critical for improving general English parsers' performance on clinical text, and combining clinical and open domain corpora might achieve optimal performance for parsing clinical text.
doi:10.1186/1472-6947-15-S1-S2
PMCID: PMC4460747  PMID: 26045009
Medical language processing; natural language processing; parsing; clinical text; NLP
34.  Discovering transnosological molecular basis of human brain diseases using biclustering analysis of integrated gene expression data 
Background
It has been reported that several brain diseases can be treated as transnosological manner implicating possible common molecular basis under those diseases. However, molecular level commonality among those brain diseases has been largely unexplored. Gene expression analyses of human brain have been used to find genes associated with brain diseases but most of those studies were restricted either to an individual disease or to a couple of diseases. In addition, identifying significant genes in such brain diseases mostly failed when it used typical methods depending on differentially expressed genes.
Results
In this study, we used a correlation-based biclustering approach to find coexpressed gene sets in five neurodegenerative diseases and three psychiatric disorders. By using biclustering analysis, we could efficiently and fairly identified various gene sets expressed specifically in both single and multiple brain diseases. We could find 4,307 gene sets correlatively expressed in multiple brain diseases and 3,409 gene sets exclusively specified in individual brain diseases. The function enrichment analysis of those gene sets showed many new possible functional bases as well as neurological processes that are common or specific for those eight diseases.
Conclusions
This study introduces possible common molecular bases for several brain diseases, which open the opportunity to clarify the transnosological perspective assumed in brain diseases. It also showed the advantages of correlation-based biclustering analysis and accompanying function enrichment analysis for gene expression data in this type of investigation.
doi:10.1186/1472-6947-15-S1-S7
PMCID: PMC4460778  PMID: 26043779
35.  Inference of brain pathway activities for Alzheimer's disease classification 
Background
Alzheimer's disease (AD) is a neurodegenerative and progressive disorder that results in brain malfunctions. Resting-state (RS) functional magnetic resonance imaging (fMRI) techniques have been successfully applied for quantifying brain activities of both Alzheimer's disease (AD) and amnestic mild cognitive impairment (aMCI) patients. Region-based approaches are widely utilized to classify patients from cognitively normal subjects (CN). Nevertheless, region-based approaches have a few limitations, reproducibility owing to selection of disease-specific brain regions, and heterogeneity of brain activities during disease progression. For coping with these issues, network-based approaches have been suggested in the field of molecular bioinformatics. In comparison with individual gene-based approaches, they acquired more accurate results in diverse disease classification, and reproducibility was confirmed by replication studies. In our work, we applied a similar methodology integrating brain pathway information into pathway activity inference, and permitting classification of both aMCI and AD patients based on pathway activities rather than single region activities.
Results
After aggregating the 59 brain pathways from literature, we estimated brain pathway activities by using exhaustive search algorithms between patients and cognitively normal subjects, and identified discriminatory pathways according to disease progression. We used three different data sets and each data set consists of two different groups. Our results show that the pathway-based approach (AUC = 0.89, 0.9, 0.75) outperformed the region-based approach (AUC = 0.69, 0.8, 0.68). Also, our approach provided enhanced diagnostic power achieving higher accuracy, sensitivity, and specificity (pathway-based approach: accuracy = 83%; sensitivity = 86%; specificity = 78%, region-based approach: accuracy = 74%; sensitivity = 78%; specificity = 76%).
Conclusions
We proposed a novel method inferring brain pathway activities for disease classification. Our approach shows better classification performance than region-based approach in four classification models. We expect that brain pathway-based approach would be helpful for precise classification of brain disorders, and provide new opportunities for uncovering disrupted brain pathways caused by disease. Moreover, discriminatory pathways between patients and cognitively normal subjects may facilitate the interpretation of functional alterations during disease progression.
doi:10.1186/1472-6947-15-S1-S1
PMCID: PMC4460780  PMID: 26044913
36.  Context-based resolution of semantic conflicts in biological pathways 
Background
Interactions between biological entities such as genes, proteins and metabolites, so called pathways, are key features to understand molecular mechanisms of life. As pathway information is being accumulated rapidly through various knowledge resources, there are growing interests in maintaining the integrity of the heterogeneous databases.
Methods
Here, we defined conflict as a status where two contradictory pieces of evidence (i.e. 'A increases B' and 'A decreases B') coexist in a same pathway. This conflict damages unity so that inference of simulation on the integrated pathway network might be unreliable. We defined rule and rule group. A rule consists of interaction of two entities, meta-relation (increase or decrease), and contexts terms about tissue specificity or environmental conditions. The rules, which have the same interaction, are grouped into a rule group. If the rules don't have a unanimous meta-relation, the rule group and the rules are judged as being conflicting.
Results
This analysis revealed that almost 20% of known interactions suffer from conflicting information and conflicting information occurred much more frequently in the literature than the public database.
With consideration for dual functions depending on context, we thought it might resolve conflict to consider context. We grouped rules, which have the same context terms as well as interaction. It's revealed that up to 86% of the conflicts could be resolved by considering context.
Subsequent analysis also showed that those contradictory records generally compete each other closely, but some information might be suspicious when their evidence levels are seriously imbalanced.
Conclusions
By identifying and resolving the conflicts, we expect that pathway databases can be cleaned and used for better secondary analyses such as gene/protein annotation, network dynamics and qualitative/quantitative simulation.
doi:10.1186/1472-6947-15-S1-S3
PMCID: PMC4461014  PMID: 26045143
37.  Optimization and planning of operating theatre activities: an original definition of pathways and process modeling 
Background
The Operating Room (OR) is a key resource of all major hospitals, but it also accounts for up 40 % of resource costs. Improving cost effectiveness, while maintaining a quality of care, is a universal objective. These goals imply an optimization of planning and a scheduling of the activities involved. This is highly challenging due to the inherent variable and unpredictable nature of surgery.
Methods
A Business Process Modeling Notation (BPMN 2.0) was used for the representation of the “OR Process” (being defined as the sequence of all of the elementary steps between “patient ready for surgery” to “patient operated upon”) as a general pathway (“path”). The path was then both further standardized as much as possible and, at the same time, keeping all of the key-elements that would allow one to address or define the other steps of planning, and the inherent and wide variability in terms of patient specificity. The path was used to schedule OR activity, room-by-room, and day-by-day, feeding the process from a “waiting list database” and using a mathematical optimization model with the objective of ending up in an optimized planning.
Results
The OR process was defined with special attention paid to flows, timing and resource involvement. Standardization involved a dynamics operation and defined an expected operating time for each operation. The optimization model has been implemented and tested on real clinical data. The comparison of the results reported with the real data, shows that by using the optimization model, allows for the scheduling of about 30 % more patients than in actual practice, as well as to better exploit the OR efficiency, increasing the average operating room utilization rate up to 20 %.
Conclusions
The optimization of OR activity planning is essential in order to manage the hospital’s waiting list. Optimal planning is facilitated by defining the operation as a standard pathway where all variables are taken into account. By allowing a precise scheduling, it feeds the process of planning and, further up-stream, the management of a waiting list in an interactive and bi-directional dynamic process.
doi:10.1186/s12911-015-0161-7
PMCID: PMC4436841  PMID: 25982033
Clinical pathways; Business Process Modeling; Operating room planning and scheduling
38.  An end-to-end hybrid algorithm for automated medication discrepancy detection 
Background
In this study we implemented and developed state-of-the-art machine learning (ML) and natural language processing (NLP) technologies and built a computerized algorithm for medication reconciliation. Our specific aims are: (1) to develop a computerized algorithm for medication discrepancy detection between patients’ discharge prescriptions (structured data) and medications documented in free-text clinical notes (unstructured data); and (2) to assess the performance of the algorithm on real-world medication reconciliation data.
Methods
We collected clinical notes and discharge prescription lists for all 271 patients enrolled in the Complex Care Medical Home Program at Cincinnati Children’s Hospital Medical Center between 1/1/2010 and 12/31/2013. A double-annotated, gold-standard set of medication reconciliation data was created for this collection. We then developed a hybrid algorithm consisting of three processes: (1) a ML algorithm to identify medication entities from clinical notes, (2) a rule-based method to link medication names with their attributes, and (3) a NLP-based, hybrid approach to match medications with structured prescriptions in order to detect medication discrepancies. The performance was validated on the gold-standard medication reconciliation data, where precision (P), recall (R), F-value (F) and workload were assessed.
Results
The hybrid algorithm achieved 95.0%/91.6%/93.3% of P/R/F on medication entity detection and 98.7%/99.4%/99.1% of P/R/F on attribute linkage. The medication matching achieved 92.4%/90.7%/91.5% (P/R/F) on identifying matched medications in the gold-standard and 88.6%/82.5%/85.5% (P/R/F) on discrepant medications. By combining all processes, the algorithm achieved 92.4%/90.7%/91.5% (P/R/F) and 71.5%/65.2%/68.2% (P/R/F) on identifying the matched and the discrepant medications, respectively. The error analysis on algorithm outputs identified challenges to be addressed in order to improve medication discrepancy detection.
Conclusion
By leveraging ML and NLP technologies, an end-to-end, computerized algorithm achieves promising outcome in reconciling medications between clinical notes and discharge prescriptions.
Electronic supplementary material
The online version of this article (doi:10.1186/s12911-015-0160-8) contains supplementary material, which is available to authorized users.
doi:10.1186/s12911-015-0160-8
PMCID: PMC4427951  PMID: 25943550
Automated medication reconciliation; Medication discrepancy detection; Machine learning; Natural language processing
39.  Engineering a mobile health tool for resource-poor settings to assess and manage cardiovascular disease risk: SMARThealth study 
Background
The incidence of chronic diseases in low- and middle-income countries is rapidly increasing both in urban and rural regions. A major challenge for health systems globally is to develop innovative solutions for the prevention and control of these diseases. This paper discusses the development and pilot testing of SMARTHealth, a mobile-based, point-of-care Clinical Decision Support (CDS) tool to assess and manage cardiovascular disease (CVD) risk in resource-constrained settings. Through pilot testing, the preliminary acceptability, utility, and efficiency of the CDS tool was obtained.
Methods
The CDS tool was part of an mHealth system comprising a mobile application that consisted of an evidence-based risk prediction and management algorithm, and a server-side electronic medical record system. Through an agile development process and user-centred design approach, key features of the mobile application that fitted the requirements of the end users and environment were obtained. A comprehensive analytics framework facilitated a data-driven approach to investigate four areas, namely, system efficiency, end-user variability, manual data entry errors, and usefulness of point-of-care management recommendations to the healthcare worker. A four-point Likert scale was used at the end of every risk assessment to gauge ease-of-use of the system.
Results
The system was field-tested with eleven village healthcare workers and three Primary Health Centre doctors, who screened a total of 292 adults aged 40 years and above. 34% of participants screened by health workers were identified by the CDS tool to be high CVD risk and referred to a doctor. In-depth analysis of user interactions found the CDS tool feasible for use and easily integrable into the workflow of healthcare workers. Following completion of the pilot, further technical enhancements were implemented to improve uptake of the mHealth platform. It will then be evaluated for effectiveness and cost-effectiveness in a cluster randomized controlled trial involving 54 southern Indian villages and over 16000 individuals at high CVD risk.
Conclusions
An evidence-based CVD risk prediction and management tool was used to develop an mHealth platform in rural India for CVD screening and management with proper engagement of health care providers and local communities. With over a third of screened participants being high risk, there is a need to demonstrate the clinical impact of the mHealth platform so that it could contribute to improved CVD detection in high risk low resource settings.
doi:10.1186/s12911-015-0148-4
PMCID: PMC4430914  PMID: 25924825
Mobile health; Cardiovascular disease risk; Clinical decision support tool; Primary care; Chronic disease; LMIC; India
40.  Multiple perspectives on clinical decision support: a qualitative study of fifteen clinical and vendor organizations 
Background
Computerized clinical decision support (CDS) can help hospitals to improve healthcare. However, CDS can be problematic. The purpose of this study was to discover how the views of clinical stakeholders, CDS content vendors, and EHR vendors are alike or different with respect to challenges in the development, management, and use of CDS.
Methods
We conducted ethnographic fieldwork using a Rapid Assessment Process within ten clinical and five health information technology (HIT) vendor organizations. Using an inductive analytical approach, we generated themes from the clinical, content vendor, and electronic health record vendor perspectives and compared them.
Results
The groups share views on the importance of appropriate manpower, careful knowledge management, CDS that fits user workflow, the need for communication among the groups, and for mutual strategizing about the future of CDS. However, views of usability, training, metrics, interoperability, product use, and legal issues differed. Recommendations for improvement include increased collaboration to address legal, manpower, and CDS sharing issues.
Conclusions
The three groups share thinking about many aspects of CDS, but views differ in a number of important respects as well. Until these three groups can reach a mutual understanding of the views of the other stakeholders, and work together, CDS will not reach its potential.
doi:10.1186/s12911-015-0156-4
PMCID: PMC4447027  PMID: 25903564
Clinical decision support; Knowledge management; Governance; Rapid assessment process
41.  A cross-sectional study assessing determinants of the attitude to the introduction of eHealth services among patients suffering from chronic conditions 
Background
Provision of care to patients with chronic diseases remains a great challenge for modern health care systems. eHealth is indicated as one of the strategies which could improve care delivery to this group of patients. The main objective of this study was to assess determinants of the acceptance of the Internet use for provision of chosen health care services remaining in the scope of current nationwide eHealth initiative in Poland.
Methods
The survey was carried out among patients with diagnosed chronic conditions who were treated in three health care facilities in Krakow, Poland. Survey data was used to develop univariate and multivariate logistic regression models for six outcome variables originating from the items assessing the acceptance of specific types of eHealth applications. The variables used as predictors were related to the sociodemographic characteristics of respondents, burden related to chronic disease, and the use of the Internet and its perceived usefulness in making personal health-related decisions.
Results
Among 395 respondents, there were 60.3% of Internet users. Univariate logistic regression models developed for six types of eHealth solutions demonstrated their higher acceptance among younger respondents, living in urban areas, who have attained a higher level of education, used the Internet on their own, and were more confident about its usefulness in making health-related decisions. Furthermore, the duration of chronic disease and hospitalization due to chronic disease predicted the acceptance of some of eHealth applications. However, when combined in multivariate models, only the belief in the usefulness of the Internet (five of six models), level of education (four of six models), and previous hospitalization due to chronic disease (three of six models) maintained the effect on the independent variables.
Conclusions
The perception of the usefulness of the Internet in making health-related decision is a key determinant of the acceptance of provision of health care services online among patients with chronic diseases. Among sociodemographic factors, only the level of education demonstrates a consistent impact on the level of acceptance. Interestingly, a greater burden of chronic disease related to previous hospitalizations leads to lower acceptance of eHealth solutions.
Electronic supplementary material
The online version of this article (doi:10.1186/s12911-015-0157-3) contains supplementary material, which is available to authorized users.
doi:10.1186/s12911-015-0157-3
PMCID: PMC4409745  PMID: 25927312
eHealth; Health care; Chronic disease; Internet use; Computer literacy
42.  Usefulness scale for patient information material (USE) - development and psychometric properties 
Background
One economical way to inform patients about their illness and medical procedures is to provide written health information material. So far, a generic and psychometrically sound scale to evaluate cognitive, emotional, and behavioral aspects of the subjectively experienced usefulness of patient information material from the patient’s perspective is lacking. The aim of our study was to develop and psychometrically test such a scale.
Methods
The Usefulness Scale for Patient Information Material (USE) was developed using a multistep approach. Ultimately, three items for each subscale (cognitive, emotional, and behavioral) were selected under consideration of face validity, discrimination, difficulty, and item content.
The final version of the USE was subjected to reliability analysis. Structural validity was tested using confirmatory factor analysis, and convergent and divergent validity were tested using correlation analysis. The criterion validity of the USE was tested in an experimental design. To this aim, patients were randomly allocated to one of two groups. One group received a full version of an information brochure on depression or chronic low back pain depending on the respective primary diagnosis. Patients in the second group received a reduced version with a lower design quality, smaller font size and less information.
Patients were recruited in six hospitals in Germany. After reading the brochure, they were asked to fill in a questionnaire.
Results
Analyzable data were obtained from 120 questionnaires. The confirmatory factor analysis supported the structural validity of the scale. Reliability analysis of the total scale and its subscales showed Cronbach’s α values between .84 and .94. Convergent and divergent validity were supported. Criterion validity was confirmed in the experimental condition. Significant differences between the groups receiving full and reduced information were found for the total score (p<.001) and its three subscales (cognitive p<.001, emotional p=.001, and behavioral p<.001), supporting criterion validity.
Conclusions
We developed a generic scale to measure the subjective usefulness of written patient information material from a patient perspective. Our construct is defined in line with current theoretical models for the evaluation of written patient information material. The USE was shown to be a short, reliable and valid psychometric scale.
Electronic supplementary material
The online version of this article (doi:10.1186/s12911-015-0153-7) contains supplementary material, which is available to authorized users.
doi:10.1186/s12911-015-0153-7
PMCID: PMC4456699  PMID: 25927192
Usefulness; Psychometrics; Patient empowerment; Medical education; Patient information; Pamphlet
43.  Conditions potentially sensitive to a Personal Health Record (PHR) intervention, a systematic review 
Background
Personal Health Records (PHRs) are electronic health records controlled, shared or maintained by patients to support patient centered care. The potential for PHRs to transform health care is significant; however, PHRs do not always achieve their potential. One reason for this may be that not all health conditions are sensitive to the PHR as an intervention. The goal of this review was to discover which conditions were potentially sensitive to the PHR as an intervention, that is, what conditions have empirical evidence of benefit from PHR-enabled management.
Methods
A systematic review of Medline and CINAHL was completed to find articles assessing PHR use and benefit from 2008 to 2014 in specific health conditions. Two researchers independently screened and coded articles. Health conditions with evidence of benefit from PHR use were identified from the included studies.
Results
23 papers were included. Seven papers were RCTs. Ten health conditions were identified, seven of which had documented benefit associated with PHR use: asthma, diabetes, fertility, glaucoma, HIV, hyperlipidemia, and hypertension. Reported benefits were seen in terms of care quality, access, and productivity, although many benefits were measured by self-report through quasi-experimental studies. No study examined morbidity/mortality. No study reported harm from the PHR.
Conclusion
There is a small body of condition specific evidence that has been published. Conditions with evidence of benefit when using PHRs tended to be chronic conditions with a feedback loop between monitoring in the PHR and direct behaviours that could be self-managed. These findings can point to other potentially PHR sensitive health conditions and guide PHR designers, implementers, and researchers. More research is needed to link PHR design, features, adoption and health outcomes to better understand how and if PHRs are making a difference to health outcomes.
doi:10.1186/s12911-015-0159-1
PMCID: PMC4411701  PMID: 25927384
Personal health records; Patient portals; Self-management; Systematic review; Chronic disease management
44.  Methods for identifying 30 chronic conditions: application to administrative data 
Background
Multimorbidity is common and associated with poor clinical outcomes and high health care costs. Administrative data are a promising tool for studying the epidemiology of multimorbidity. Our goal was to derive and apply a new scheme for using administrative data to identify the presence of chronic conditions and multimorbidity.
Methods
We identified validated algorithms that use ICD-9 CM/ICD-10 data to ascertain the presence or absence of 40 morbidities. Algorithms with both positive predictive value and sensitivity ≥70% were graded as “high validity”; those with positive predictive value ≥70% and sensitivity <70% were graded as “moderate validity”. To show proof of concept, we applied identified algorithms with high to moderate validity to inpatient and outpatient claims and utilization data from 574,409 people residing in Edmonton, Canada during the 2008/2009 fiscal year.
Results
Of the 40 morbidities, we identified 30 that could be identified with high to moderate validity. Approximately one quarter of participants had identified multimorbidity (2 or more conditions), one quarter had a single identified morbidity and the remaining participants were not identified as having any of the 30 morbidities.
Conclusions
We identified a panel of 30 chronic conditions that can be identified from administrative data using validated algorithms, facilitating the study and surveillance of multimorbidity. We encourage other groups to use this scheme, to facilitate comparisons between settings and jurisdictions.
Electronic supplementary material
The online version of this article (doi:10.1186/s12911-015-0155-5) contains supplementary material, which is available to authorized users.
doi:10.1186/s12911-015-0155-5
PMCID: PMC4415341  PMID: 25886580
Multimorbidity; Administrative data
45.  A qualitative evaluation of the crucial attributes of contextual Information necessary in EHR design to support patient-centered medical home care 
Background
Effective implementation of a Primary Care Medical Home model of care (PCMH) requires integration of patients’ contextual information (physical, mental, social and financial status) into an easily retrievable information source for the healthcare team and clinical decision-making.
This project explored clinicians’ perceptions about important attributes of contextual information for clinical decision-making, how contextual information is expressed in CPRS clinical documentation as well as how clinicians in a highly computerized environment manage information flow related to these areas.
Methods
A qualitative design using Cognitive Task Analyses and a modified Critical Incident Technique were used. The study was conducted in a large VA with a fully implemented EHR located in the western United States. Seventeen providers working in a PCMH model of care in Primary Care, Home Based Care and Geriatrics reported on a recent difficult transition requiring contextual information for decision-making. The transcribed interviews were qualitatively analyzed for thematic development related to contextual information using an iterative process and multiple reviewers with ATLAS@ti software.
Results
Six overarching themes emerged as attributes of contextual information: Informativeness, goal language, temporality, source attribution, retrieval effort, and information quality.
Conclusions
These results indicate that specific attributes are needed to in order for contextual information to fully support clinical decision-making in a Medical Home care delivery environment. Improved EHR designs are needed for ease of contextual information access, displaying linkages across time and settings, and explicit linkages to both clinician and patient goals. Implications relevant to providers’ information needs, team functioning and EHR design are discussed.
doi:10.1186/s12911-015-0150-x
PMCID: PMC4416274  PMID: 25881181
Patient medical home; Cognitive task analysis; Contextual information; Electronic health record; Patient preferences; Information access
46.  Non-redundant association rules between diseases and medications: an automated method for knowledge base construction 
Background
The widespread use of electronic health records (EHRs) has generated massive clinical data storage. Association rules mining is a feasible technique to convert this large amount of data into usable knowledge for clinical decision making, research or billing. We present a data driven method to create a knowledge base linking medications to pathological conditions through their therapeutic indications from elements within the EHRs.
Methods
Association rules were created from the data of patients hospitalised between May 2012 and May 2013 in the department of Cardiology at the University Hospital of Strasbourg. Medications were extracted from the medication list, and the pathological conditions were extracted from the discharge summaries using a natural language processing tool. Association rules were generated along with different interestingness measures: chi square, lift, conviction, dependency, novelty and satisfaction. All medication-disease pairs were compared to the Summary of Product Characteristics, which is the gold standard. A score based on the other interestingness measures was created to filter the best rules, and the indices were calculated for the different interestingness measures.
Results
After the evaluation against the gold standard, a list of accurate association rules was successfully retrieved. Dependency represents the best recall (0.76). Our score exhibited higher exactness (0.84) and precision (0.27) than all of the others interestingness measures. Further reductions in noise produced by this method must be performed to improve the classification precision.
Conclusions
Association rules mining using the unstructured elements of the EHR is a feasible technique to identify clinically accurate associations between medications and pathological conditions.
doi:10.1186/s12911-015-0151-9
PMCID: PMC4415340  PMID: 25888890
Data mining; Association rules mining; Natural language processing; Knowledge base
47.  Improving performance in medical practices through the extended use of electronic medical record systems: a survey of Canadian family physicians 
Background
Numerous calls have been made for greater assimilation of information technology in healthcare organizations in general, and in primary care settings in particular. Considering the levels of IT investment and adoption in primary care medical practices, a deeper understanding is needed of the factors leading to greater performance outcomes from EMR systems in primary care. To address this issue, we developed and tested a research model centered on the concept of Extended EMR Use.
Methods
An online survey was conducted of 331 family physicians in Canadian private medical practices to empirically test seven research hypotheses using a component-based structural equation modeling approach.
Results
Five hypotheses were partially or fully supported by our data. Family physicians in our sample used 67% of the clinical and 41% of the communicational functionalities available in their EMR systems, compared to 90% of the administrative features. As expected, extended use was associated with significant improvements in perceived performance benefits. Interestingly, the benefits derived from system use were mainly tied to the clinical support provided by an EMR system. The extent to which physicians were using their EMR systems was influenced by two system design characteristics: functional coverage and ease of use. The more functionalities that are available in an EMR system and the easier they are to use, the greater the potential for exploration, assimilation and appropriation by family physicians.
Conclusions
Our study has contributed to the extant literature by proposing a new concept: Extended EMR Use. In terms of its practical implications, our study reveals that family physicians must use as many of the capabilities supported by their EMR system as possible, especially those which support clinical tasks, if they are to maximize its performance benefits. To ensure extended use of their software, vendors must develop EMR systems that satisfy two important design characteristics: functional coverage and system ease of use.
doi:10.1186/s12911-015-0152-8
PMCID: PMC4397686  PMID: 25888991
Electronic medical records; Primary care; Family physicians; Extended use; User satisfaction; Ease of use; Functional coverage; Survey research; Structural equation modeling
48.  Increasing the efficiency of trial-patient matching: automated clinical trial eligibility Pre-screening for pediatric oncology patients 
Background
Manual eligibility screening (ES) for a clinical trial typically requires a labor-intensive review of patient records that utilizes many resources. Leveraging state-of-the-art natural language processing (NLP) and information extraction (IE) technologies, we sought to improve the efficiency of physician decision-making in clinical trial enrollment. In order to markedly reduce the pool of potential candidates for staff screening, we developed an automated ES algorithm to identify patients who meet core eligibility characteristics of an oncology clinical trial.
Methods
We collected narrative eligibility criteria from ClinicalTrials.gov for 55 clinical trials actively enrolling oncology patients in our institution between 12/01/2009 and 10/31/2011. In parallel, our ES algorithm extracted clinical and demographic information from the Electronic Health Record (EHR) data fields to represent profiles of all 215 oncology patients admitted to cancer treatment during the same period. The automated ES algorithm then matched the trial criteria with the patient profiles to identify potential trial-patient matches. Matching performance was validated on a reference set of 169 historical trial-patient enrollment decisions, and workload, precision, recall, negative predictive value (NPV) and specificity were calculated.
Results
Without automation, an oncologist would need to review 163 patients per trial on average to replicate the historical patient enrollment for each trial. This workload is reduced by 85% to 24 patients when using automated ES (precision/recall/NPV/specificity: 12.6%/100.0%/100.0%/89.9%). Without automation, an oncologist would need to review 42 trials per patient on average to replicate the patient-trial matches that occur in the retrospective data set. With automated ES this workload is reduced by 90% to four trials (precision/recall/NPV/specificity: 35.7%/100.0%/100.0%/95.5%).
Conclusion
By leveraging NLP and IE technologies, automated ES could dramatically increase the trial screening efficiency of oncologists and enable participation of small practices, which are often left out from trial enrollment. The algorithm has the potential to significantly reduce the effort to execute clinical research at a point in time when new initiatives of the cancer care community intend to greatly expand both the access to trials and the number of available trials.
Electronic supplementary material
The online version of this article (doi:10.1186/s12911-015-0149-3) contains supplementary material, which is available to authorized users.
doi:10.1186/s12911-015-0149-3
PMCID: PMC4407835  PMID: 25881112
Automated clinical trial eligibility screening; Patient-trial matching; Natural language processing; Information extraction
49.  A mixed methods study of how clinician ‘super users’ influence others during the implementation of electronic health records 
Background
Despite the potential for electronic health records (EHRs) to improve patient safety and quality of care, the intended benefits of EHRs are not always realized because of implementation-related challenges. Enlisting clinician super users to provide frontline support to employees has been recommended to foster EHR implementation success. In some instances, their enlistment has been associated with implementation success; in other cases, it has not. Little is known about why some super users are more effective than others. The purpose of this study was to identify super users’ mechanisms of influence and examine their effects on EHR implementation outcomes.
Methods
We conducted a longitudinal (October 2012 – June 2013), comparative case study of super users’ behaviors on two medical units of a large, academic hospital implementing a new EHR system. We assessed super users’ behaviors by observing 29 clinicians and conducting 24 in-depth interviews. The implementation outcome, clinicians’ information systems (IS) proficiency, was assessed using longitudinal survey data collected from 43 clinicians before and after the EHR start-date. We used multivariable linear regression to estimate the relationship between clinicians’ IS proficiency and the clinical unit in which they worked.
Results
Super users on both units employed behaviors that supported and hindered implementation. Four super user behaviors differed between the two units: proactivity, depth of explanation, framing, and information-sharing. The unit in which super users were more proactive, provided more comprehensive explanations for their actions, used positive framing, and shared information more freely experienced significantly greater improvement in clinicians’ IS proficiency (p =0.03). Use of the four behaviors varied as a function of super users’ role engagement, which was influenced by how the two units’ managers selected super users and shaped the implementation climate.
Conclusions
Super users’ behaviors in implementing EHRs vary substantively and can have important influence on implementation success.
doi:10.1186/s12911-015-0154-6
PMCID: PMC4407776  PMID: 25889076
Electronic health record (EHR); Super users; Implementation; Social influence
50.  A randomised controlled trial of personalised decision support delivered via the internet for bowel cancer screening with a faecal occult blood test: the effects of tailoring of messages according to social cognitive variables on participation 
Background
In Australia, bowel cancer screening participation using faecal occult blood testing (FOBT) is low. Decision support tailored to psychological predictors of participation may increase screening. The study compared tailored computerised decision support to non-tailored computer or paper information. The primary outcome was FOBT return within 12 weeks. Additional analyses were conducted on movement in decision to screen and change on psychological variables.
Methods
A parallel, randomised controlled, trial invited 25,511 people aged 50–74 years to complete an eligibility questionnaire. Eligible respondents (n = 3,408) were assigned to Tailored Personalised Decision Support (TPDS), Non-Tailored PDS (NTPDS), or Control (CG) (intention-to-treat, ITT sample). TPDS and NTPDS groups completed an on-line baseline survey (BS) and accessed generic information. The TPDS group additionally received a tailored intervention. CG participants completed a paper BS only. Those completing the BS (n = 2270) were mailed an FOBT and requested to complete an endpoint survey (ES) that re-measured BS variables (per-protocol, PP sample).
Results
FOBT return: In the ITT sample, there was no significant difference between any group (χ2(2) = 2.57, p = .26; TPDS, 32.5%; NTPDS, 33%; and CG, 34.5%). In the PP sample, FOBT return in the internet groups was significantly higher than the paper group (χ2(2) = 17.01, p < .001; TPDS, 80%; NTPDS, 83%; and CG, 74%). FOBT completion by TPDS and NTPDS did not differ (χ2(1) = 2.23, p = .13). Age was positively associated with kit return.
Decision to screen: 2227/2270 of the PP sample provided complete BS data. Participants not wanting to screen at baseline (1083/2227) and allocated to TPDS and NTPDS were significantly more likely to decide to screen and return an FOBT than those assigned to the CG. FOBT return by TPDS and NTPDS did not differ from one another (OR = 1.16, p = .42).
Change on psychosocial predictors: Analysis of change indicated that salience and coherence of screening and self-efficacy were improved and faecal aversion decreased by tailored messaging.
Conclusions
Online information resources may have a role in encouraging internet-enabled people who are uncommitted to screening to change their attitudes, perceptions and behaviour.
Trial registration
Australian New Zealand Clinical Trials Registry ACTRN12610000095066
doi:10.1186/s12911-015-0147-5
PMCID: PMC4403749  PMID: 25886492
Randomised controlled trial; Decision support; Bowel cancer; Faecal occult blood test; Cancer screening; Tailored messages

Results 26-50 (980)