Clinical Informatics

Applied Clinical Informatics for Nurses, Second Edition utilizes a relevantly based training way to deal with advance clinical dynamic, moral lead, and critical thinking. The content is intended to help teachers in making noteworthy and commonsense learning encounters for nursing understudies in clinical informatics. Its true methodology makes it a handy handbook for both workforce and understudies. The Second Edition highlights refreshed and extended substance on an assortment of significant subjects that have been recognized as key needs by the National Institute for Nursing Research and the Agency for Healthcare Research and Quality. Another significant spotlight is on the association among patients and PCs and how such communications can influence the nature of information gathered by informatics applications. Key Features: Real-world application, for example, fall counteraction Explores bar coding and drug store the executives Chapter destinations and section synopses Navigate 2 Advantage Access Instructor Resources: Instructor's Manual HTML: Test Bank PowerPoint Slides.

a b s t r a c t HPV vaccines available in the market are not effective against different strains of papillomavirus, therefore, there is a need to develop a new prophylactic DNA vaccine which can work against different strains of HPVs and may lead to protection of cervical cancer against new pandemic viruses. We designed a potential prophylactic DNA vaccine by using all the consensus epitopic sequences of HPVs L2 capsid protein and performed in silico cloning of multiepitopic antigenic DNA sequence in pVAX-1 vector. Immunogenicity of vaccine has been enhanced by techniques like codon optimization, engineering CpG motifs, introducing promoters and co-injection with plasmids expressing immune-stimulatory molecules.

To support federated computerized phenotyping, we studied the suitability of LOINC to represent clinical document types in an outpatient integrated data repository (IDR). Our results indicate that 35 document types accounts for 80% of all documents. Only 69% of those have a corresponding LOINC concept.

Introduction

With recent advances in clinical research informatics and the existence of federated repositories such as SHRINE, it is important to have reference ontologies for all common EHR data sources. There are well established reference ontologies for several data feeds such as diagnoses, procedures, medications and lab (core set). Type of textual document filed in an EHR (e.g., spirometry report) can contain information which may complement the current core data set.
Our goal was to evaluate the suitability of Clinical Document Ontology (CDO) within Clinical LOINC (=Logical Observation Identifiers Names and Codes) to capture document types. Our work complements prior work done by Hyun [1] with results from a predominantly outpatient healthcare system.
This work was conducted as part of our effort to support inclusion of EHR events with coded type of clinical report into our framework for computerized high-throughput phenotyping (see http://healthcareworkflow.wordpress.com).

Methods

We used a sample of lifetime data of 250 thousand patients from Marshfield Clinic (MC) IDR. We computed descriptive statistics and mapped a subset of document types to LOINC (v2.27) using RELMA and other search tools.
Preliminary results
Marshfield Clinic document types are described by two internal codes: document class (e.g., pathology report or radiology interpretation) and document subclass (e.g., GYN cytopathology report or chest radiograph). For lifetime EHR data spanning from 1985 to 2009, 35 document types accounted for 80% of all reports and 311 document types accounted for 99% of all reports (retired document types were included). Within the subset of 35 most frequent document types, CDO’s fully corresponding terms were indentified for 24 (69%) of them. For 7 types (20%), only a higher-granularity term was identified, and for 4 types (11%), there was no CDO’s concept found.
For example, the CDO had a code for “Prescription for durable medical equipment” (52063-5), but lacked a code for MC’s subclass of “Prescription note”. Or, CDO had three codes for consent for abortion, sterilization and hysterectomy (52027-0,52029-6,52028-8), but lacked a less granular code for MC’s document subclass “Consent Form (Outpatient Administrative Doc)”. In another example, MC’s document subclass “Psychiatric Telephone Note” had to be mapped to a generic telephone encounter note despite existence of psychiatry specific concepts for counseling note, consultation note, evaluation and management note and group counseling note). MC data contained 1323 distinct document subclasses, while CDO has 528 concepts. Within the subset of 35 most frequent types, 8 subclasses mapped to a set of three CDO codes (51852-2 Letter, 34748-4 Telephone encounter note, 47045-0 Study report).

Conclusion and Discussion

Our result of 69% full-correspondence coverage of LOINC is lower then Hyun’s results [1]. The review of non-covered terms indicates that CDO seems to be more complete for inpatient documents. For example, we did not find adequately granular concept for “Well Child Visit” document type. This preliminary data is limited since mapping was done by a single expert. We plan to validate this mapping by using one more expert and calculate inter-rater reliability) and further study granularity issues.

Se revisan diversos aspectos de las políticas de salud y la calidad asistencial, así como el aporte de las TIC en distintos ámbitos de ésta. En particular, se alude al manejo de la información en salud y a la aplicación de las TIC en la mejora de la calidad asistencial. Finalmente, se aboca al tema de los estándares y la interoperabilidad en los sistemas de información en salud, explorando los distintos tipos y niveles de interoperabilidad, las áreas de aplicación de estándares y estándares específicos requeridos para determinadas necesidades de interoperabilidad. El caso de Brasil se expone mostrando los pasos dados para generar una propuesta de un conjunto de estándares y el marco legal necesario para ello, constituyendo un ejemplo para otros países que recién comienzan a transitar por este camino.

Abstract
A detailed electronic record of delivered clinical care is important for providing clinical decision support and for conducting research using existing clinical data. Knowing the type of document filed within an EHR (e.g., bronchoscopy report), helps to derive important procedural or phenotypic information that may not be obtainable from other sources. A comprehensive document ontology can also greatly facilitate review of clinical documents integrated from multiple sources within a health information exchange platform. The Clinical LOINC (Logical Observation Identifiers Names and Codes) terminology includes a Document Ontology (DO) that is intended to provide a standardized set of document types. We analyzed the frequency of clinical document types from the National Institute of Health’s (NIH) Clinical Center as mapped to LOINC DO. Our work complements prior work with results from a research-oriented healthcare institution, and has implications for LOINC developers as well as EHR system administrators.
Methods
We used clinical documents data from the NIH Biomedical Translational Research Information System (BTRIS), which contains documents from several systems. Using the RELMA mapping tool, two experts mapped the most frequent document types to LOINC DO (v2.36, containing 661 document types). A consensus process was used to resolve any mapping differences and produce a single mapping for each document type.
Preliminary Results
The current BTRIS repository has a total of 174 different document types, with 18 document types accounting for 80% of all documents and 67 document types accounting for 99% of all documents. The two mappers agreed eight times that there is no corresponding term within LOINC DO and agreed on the mapped term in 6 cases; they agreed on LOINC mapping for the four remaining document types after subsequent discussion. Therefore, the mappers identified a corresponding LOINC code for 56 % of NIH document types (10 out of 18 types).
Discussion and Conclusion
Our result of 56% LOINC DO coverage of documents types is comparable to findings by Chen1. The mapping revealed a possibility to use LOINC DO as a way of linking retired, view-only, legacy document types (e.g., legacy code C114110, respiratory observations) to the current active types at the integrated data repository (IDR) level. In order to improve DO coverage, we are in the process of submitting a request for new terms to the clinical LOINC committee as we have done in the past2. To expand our initial mapping and improve our analysis of LOINC DO, we have also created a draft mapping of all 174 NIH document types (single mapper only).
    To fully utilize LOINC DO as a reference ontology, mapping of standardized document types would ideally occur during introduction of new document types within the EHR rather than during import to the IDR. Unfortunately, most EHR vendors do not support mapping of internal document types to a common reference terminology. Moreover, the current hierarchy within LOINC DO is undergoing revisions and it was not originally developed to support a clinician picking the most relevant document type to view or author within an EHR system. Our future work includes creating a subset of commonly used document types from LOINC DO which would be similar to the “best of” Lab LOINC subset to facilitate adoption of LOINC DO and mapping efforts at other institutions. We also want to explore the use and possible roles for LOINC parts concepts within LOINC DO.
References
1. Chen ES, Melton GB, Engelstad ME, Sarkar IN. Standardizing Clinical Document Names Using the HL7/LOINC Document Ontology and LOINC Codes, AMIA Annual Symposium Proceedings, 2010: 101-5
2. Huser V, Evaluation of LOINC as a reference terminology for clinical document types: A case report of an outpatient EHR, AMIA NOW conference, 2010

El uso de sistemas informáticos en el área clínica
permite que los profesionales de la salud manejen mayor
cantidad y variedad de información de forma efectiva y
eficiente, aumentando su capacidad de resolución de
problemas de salud y la calidad asistencial de los pacientes.
Estos son sistemas complejos, difíciles de mantener a largo
plazo, y de costos elevados en su construcción y
mantenimiento, tanto en tiempo como en recursos humanos y
económicos. La falta de aplicación de estándares y buenas
prácticas en su diseño y construcción repercute negativamente en la calidad global del producto final. Esta situación pone en riesgo la viabilidad de los proyectos de informatización del área clínica, a gran escala y largo plazo. En este trabajo planteamos un enfoque distinto en la construcción de sistemas de información en salud, que busca sortear los problemas mencionados, en pos de viabilizar los proyectos de informatización del área clínica en contextos de recursos limitados (económicos y humanos), apuntando a la creación de sistemas informáticos de calidad, basados en estándares, mantenibles a largo plazo y a costos controlados.
Se propone la creación de una herramienta de software para la automatización de tareas en el desarrollo informáticos y un
proceso de desarrollo drásticamente diferente al proceso
actual, donde el profesional de la salud pasa a jugar el rol de
mayor importancia en el proceso, donde el foco está en la
gestión del conocimiento clínico, dejando la tecnología en un
segundo plano. Con el enfoque propuesto se podrían crear
sistemas de registro clínico de gran calidad, en menos tiempo, y con un menor consumo de recursos. Estos sistemas estarían basados en estándares, creados para ser modificados y capaces de evolucionar a largo plazo sin necesidad de modificar el código fuente del software.

"The clinical bacteria of multi-drug resistant to some antibiotics are
considered a common problem in the world wide. Alternative
antibacterial strategies are urgently needed, and thus this situation
has led to a re-evaluation of the therapeutic use of ancient
remedies, such as plants and plant-based products, including
Nigella sativa (N. sativa). This study aimed to evaluate the
antibacterial activity of Yemeni N. sativa oil against some Clinical
Bacterial Isolates (CBI) and Control Strains of Bacteria (CSB) in
comparison with Augmentin® (Amoxicillin and Clavulanic Acid).
This study was carried out in Sana’a city during the period of one
year from May 2012 to April 2013. The antibacterial activity of oil
with different concentrations was determined by using disc agar
diffusion technique against CBI (Staphylococcus aureus and
Pseudomonas aeruginosa) and CSB (Staphylococcus aureus
ATCC25619, Pseudomonas aeruginosa ATCC29737), also the
Minimum Inhibition Concentration (MIC) of oil extract was
determined. The results indicated that, the highest significant
antibacterial activity was at the maximum concentration of the oil
against Staphylococcus aureus and Pseudomonas aeruginosa in
comparison with Augmentin ® discs (p < 0.05) respectively. This
study observed that, there was strong positive correlation between
the diameter zone (DZ-mm) and oil concentrations (%). In
addition, the DZ (mm) of the oil for CSB was higher than CBI.
Also the oil activity was found to be more effective against
Staphylococcus aureus than Pseudomonas aeruginosa. On the
other hand, the MIC of the oil against CBI were ranged between ≥
0.5% and 4%. Whereas, the CSB particularly Staphylococcus
aureus were sensitive to low concentrations of oil. It could be
concluded that, the oil had high antibacterial effect against CSB
and CBI with high concentration and more effective than
Augmentin® discs."

BackgroundWorkflow engine technology represents a new class of software with the ability to graphically model step-based knowledge. We present application of this novel technology to the domain of clinical decision support. Successful implementation of decision support within an electronic health record (EHR) remains an unsolved research challenge. Previous research efforts were mostly based on healthcare-specific representation standards and execution engines and did not reach wide adoption. We focus on two challenges in decision support systems: the ability to test decision logic on retrospective data prior prospective deployment and the challenge of user-friendly representation of clinical logic.ResultsWe present our implementation of a workflow engine technology that addresses the two above-described challenges in delivering clinical decision support. Our system is based on a cross-industry standard of XML (extensible markup language) process definition language (XPDL). The core components of the system are a workflow editor for modeling clinical scenarios and a workflow engine for execution of those scenarios. We demonstrate, with an open-source and publicly available workflow suite, that clinical decision support logic can be executed on retrospective data. The same flowchart-based representation can also function in a prospective mode where the system can be integrated with an EHR system and respond to real-time clinical events. We limit the scope of our implementation to decision support content generation (which can be EHR system vendor independent). We do not focus on supporting complex decision support content delivery mechanisms due to lack of standardization of EHR systems in this area. We present results of our evaluation of the flowchart-based graphical notation as well as architectural evaluation of our implementation using an established evaluation framework for clinical decision support architecture.ConclusionsWe describe an implementation of a free workflow technology software suite (available at http://code.google.com/p/healthflow) and its application in the domain of clinical decision support. Our implementation seamlessly supports clinical logic testing on retrospective data and offers a user-friendly knowledge representation paradigm. With the presented software implementation, we demonstrate that workflow engine technology can provide a decision support platform which evaluates well against an established clinical decision support architecture evaluation framework. Due to cross-industry usage of workflow engine technology, we can expect significant future functionality enhancements that will further improve the technology's capacity to serve as a clinical decision support platform.

Abstract
Process mining can be a useful visualization approach for analyzing EHR data. We present our experiments with data preparation techniques to improve process mining results on a large cohort of chronic kidney disease patients.
Introduction
Healthcare processes are notoriously complex and difficult to model. Process mining (PM) is one approach for analyzing large volumes of event data which can convert them into visual process definitions. Previous reports1 on use of PM with healthcare data were limited in terms of origin of logs (simulated data), size of datasets (hundreds of patients) and scope (data about a single medical episode originating from a single medical department). We address some of these limitations with our analysis of lifetime data of a large cohort of chronic kidney disease patients and specifically focus on necessary pre-processing of raw EHR data. This poster will also provide general introduction to PM and demonstrate its application to studying progression of chronic kidney disease.
Method
Lifetime EHR data of chronic kidney disease patients were extracted from data warehouse of Marshfield Clinic. A complete set of coded EHR data (such as visit data, laboratory results, diagnoses and procedures) was processed with our previously developed analytical package called RetroGuide2 with the goal to test a range of healthcare-specific data abstraction and data filtering transformations which are not available directly in PM tools. This filtered dataset was then converted into a standard MXML process log format and loaded into an open-source PM tool called ProM2  where a number of data mining, analytical and conversion algorithms were applied. The resulting graphical process models or other visualizations were evaluated for displaying clinically meaningful content and their ability to support side-by side comparison of different sub-populations of CKD patients (e.g., different locations, insurance coverage, or co-morbidities).
Preliminary results
We have extracted 2.1 GB (15 million events) of coded EHR data on a cohort of 2445 CKD patients. Within RetroGuide, we created a set of CKD-specific data pre-processing abstractions. For example, identification of disease onset dates or key treatment procedures, and determination of disease stages or level of control using coded laboratory, clinical, or aggregate data (e.g., eGFR, BP, HbA1c, specialty specific visit frequencies, or dialysis frequency). The following ProM mining algorithms were used: heuristic miner (example shown in Figure 1), alpha algorithm, association rules mining and grouping log conversion. Additional details about our methodology and results can be found on our project website (http://healthcareworkflow.wordpress.com).
Discussion
Existing process mining tools and techniques do not produce clinically meaningful visualizations when applied to raw EHR data. We tested several data pre-processing transformations and demonstrate their usefulness for analysis of EHR data. PM can be a valid alternative to authoring process definitions within a workflow editor. This work on PM is part of our larger project focusing on use of a Workflow Management System within an EHR system.

Provision of query systems which are intuitive for non-experts has been recognized as an important informatics challenge. We developed a prototype of a flowchart-based analytical framework called RetroGuide that enables non-experts to formulate query tasks using a step-based, patient-centered paradigm inspired by workflow technology. We present results of the evaluation of RetroGuide in comparison to Structured Query Language (SQL) in laboratory settings using a mixed method design. We asked 18 human subjects with limited database experience to solve query tasks in RetroGuide and SQL, and quantitatively compared their test scores. A follow-up questionnaire was designed to compare both technologies qualitatively and investigate RetroGuide technology acceptance. The quantitative comparison of test scores showed that the study subjects achieved significantly higher scores using the RetroGuide technology. Qualitative study results indicated that 94% of subjects preferred RetroGuide to SQL because RetroGuide was easier to learn, it better supported temporal tasks, and it seemed to be a more logical modeling paradigm. Additional qualitative evaluation results, based on a technology acceptance model, suggested that a fully developed RetroGuide-like technology would be well accepted by users. Our study is an example of a structure validation study of a prototype query system, results of which provided significant guidance in further development of a novel query paradigm for EHR data. We discuss the strengths and weakness of our study design and results, and their implication for future evaluations of query systems in general.

The Purpose of this paper is to shed the light on the history of AHRQ (Agency for Healthcare Research and Quality), and how the leadership at the time dealt with the controversy and challenges to the organizational structure and helped it overcome rough times and made it one of the most valuable agencies in HHS.

IJCI conference Proceedings is an open access peer reviewed Computer Science Conference Proceedings (CSCP) series that welcomes conferences to publish their proceedings / post conference proceedings. This series intends to focus on publishing high quality papers to help the scientific community furthering our goal to preserve and disseminate scientific knowledge. Conference proceedings are accepted for publication in IJCI conference proceedings based on peer-reviewed full papers and revised short papers that target international scientific community and latest IT trends. Our mission is to provide the most valuable publication service.

The value of clinical guidelines and decision support tools are yet to be realized, due to a roadblock in its implementation that arises from both lack of understanding user needs, as well as a discrepancy of trust and transparency in its development process. With greater insight to understanding the organizational behaviors that are involved at each step of the process, from development to implementation, adoption to execution, heightened use and benefit from standardized care through guidelines can be evaluated. Beginning to enforce a more rigorous regulation and monitoring of guidelines development will attract more clinical utility. Standardized use of clinical guidelines will enhance care quality, eliminate discrepancies in treatment, and reduce variability across the health care system.

"BACKGROUND: High-alert medications are frequently responsible for adverse drug events and present significant hazards to inpatients, despite technical improvements in the way they are ordered, dispensed, and administered.
METHODS: A real-time surveillance application was designed and implemented to enable pharmacy review of high-alert medication orders to complement existing computerized provider order entry and integrated clinical decision support systems in a tertiary care hospital. The surveillance tool integrated real-time data from multiple clinical systems and applied logical criteria to highlight potentially high-risk scenarios. Use of the surveillance system for adult inpatients was analyzed for warfarin, heparin and enoxaparin, and aminoglycoside antibiotics.
RESULTS: Among 28,929 hospitalizations during the study period, patients eligible to appear on a dashboard included 2224 exposed to warfarin, 8383 to heparin or enoxaparin, and 893 to aminoglycosides. Clinical pharmacists reviewed the warfarin and aminoglycoside dashboards during 100% of the days in the study period-and the heparinlenoxaparin dashboard during 71% of the days. Displayed alert conditions ranged from common events, such as 55% of patients receiving aminoglycosides were missing a baseline creatinine, to rare events, such as 0.1% of patients exposed to heparin were given a bolus greater than 10,000 units. On the basis of interpharmacist communication and electronic medical record notes recorded within the dashboards, interventions to prevent further patient harm were frequent.
CONCLUSIONS: Even in an environment with sophisticated computerized provider order entry and clinical decision support systems, real-time pharmacy surveillance of high-alert medications provides an important platform for intercepting medication errors and optimizing therapy."

OBJECTIVE: Clinical summarization, the process by which relevant patient information is electronically summarized and presented at the point of care, is of increasing importance given the increasing volume of clinical data in electronic health record systems (EHRs). There is a paucity of research on electronic clinical summarization, including the capabilities of currently available EHR systems.
METHODS: We compared different aspects of general clinical summary screens used in twelve different EHR systems using a previously described conceptual model: AORTIS (Aggregation, Organization, Reduction, Interpretation and Synthesis).
RESULTS: We found a wide variation in the EHRs' summarization capabilities: all systems were capable of simple aggregation and organization of limited clinical content, but only one demonstrated an ability to synthesize information from the data.
CONCLUSION: Improvement of the clinical summary screen functionality for currently available EHRs is necessary. Further research should identify strategies and methods for creating easy to use, well-designed clinical summary screens that aggregate, organize and reduce all pertinent patient information as well as provide clinical interpretations and synthesis as required.

Objective: Alerting systems, a type of clinical decision support (CDS), are increasingly prevalent in healthcare, yet few studies have concurrently measured the appropriateness of alerts with provider responses to alerts. Recent reports of suboptimal alert system design and implementation highlight the need for better evaluation to inform future designs. The authors present a comprehensive framework for evaluating the clinical appropriateness of synchronous, interruptive medication safety alerts.
Methods: Through literature review and iterative testing, we developed metrics that describe successes, justifiable overrides, provider non-adherence, and unintended adverse consequences of CDS alerts. We validated the framework by applying it to a medication alerting system for patients with acute kidney injury (AKI).
Results: Through expert review, the framework assesses each alert episode for appropriateness of the alert display and the necessity and urgency of a clinical response. Primary outcomes of the framework include the false positive alert rate, alert override rate, provider non-adherence rate, and rate of provider response appropriateness. Application of the framework to evaluate an existing AKI medication alerting system provided a more complete understanding of the process outcomes measured in the AKI medication alerting system. We confirmed that previous alerts and provider responses were most often appropriate.
Conclusion: The new evaluation model offers a potentially effective method to assess the clinical appropriateness of synchronous interruptive medication alerts prior to evaluating patient outcomes in a comparative trial. More work can determine the generalizability of the framework for use in other settings and other alert types.

Outcomes assessment for intervention studies requires blinding of reviewers to prevent bias. We used Mozilla Firefox and the Greasemonkey Add-on to remove notes generated for intervention patients during a randomized controlled trial to ensure blinding during electronic chart review. Similar methods could be employed with other web-based electronic medical records.

In response to mounting evidence that use of electronic medical record systems may cause unintended consequences, and even patient harm, the AMIA Board of Directors convened a Task Force on Usability to examine evidence from the literature and make recommendations. This task force was composed of representatives from both academic settings and vendors of electronic health record (EHR) systems. After a careful review of the literature and of vendor experiences with EHR design and implementation, the task force developed 10 recommendations in four areas: (1) human factors health information technology (IT) research, (2) health IT policy, (3) industry recommendations, and (4) recommendations for the clinician end-user of EHR software. These AMIA recommendations are intended to stimulate informed debate, provide a plan to increase understanding of the impact of usability on the effective use of health IT, and lead to safer and higher quality care with the adoption of useful and usable EHR systems.

The problem list is a critical component of the electronic medical record, with implications for clinical care, provider communication, clinical decision support, quality measurement and research. However, many of its benefits depend on the use of coded terminologies. Two standard terminologies (ICD-9 and SNOMED-CT) are available for problem documentation, and two SNOMED-CT subsets (VA/KP and CORE) are available for SNOMED-CT users. We set out to examine these subsets, characterize their overlap and measure their coverage. We applied the subsets to a random sample of 100,000 records from Brigham and Women&#39;s Hospital to determine the proportion of problems covered. Though CORE is smaller (5,814 terms vs. 17,761 terms for VA/KP), 94.8% of coded problem entries from BWH were in the CORE subset, while only 84.0% of entries had matches in VA/KP (p&lt;0.001). Though both subsets had reasonable coverage, CORE was superior in our sample, and had fewer clinically significant gaps.

Type I disorders of glycosylation (CDG), themost frequent of which is phosphomannomutase
2 (PMM2-CDG), are a group of diseases causing the incomplete N-glycosylation of proteins.
PMM2-CDG is an autosomal recessive disease with a large phenotypic spectrum, and is associated
with mutations in the PMM2 gene. The biochemical analysis of mutants does not allow a precise
genotype–phenotype correlation for PMM2-CDG. PMM2 is very tolerant to missense and loss of
function mutations, suggesting that a partial deficiency of activity might be beneficial under certain
circumstances. The patient phenotype might be influenced by variants in other genes associated with
the type I disorders of glycosylation in the general population.

Extracting concepts (such as drugs, symptoms, and diagnoses) from clinical narratives constitutes a basic enabling technology to unlock the knowledge within and support more advanced reasoning applications such as diagnosis explanation, disease progression modeling, and intelligent analysis of the effectiveness of treatment. The recent release of annotated training sets of de-identified clinical narratives has contributed to the development and refinement of concept extraction methods. However, as the annotation process is labor-intensive, training data are necessarily limited in the concepts and concept patterns covered, which impacts the performance of supervised machine learning applications trained with these data. This paper proposes an approach to minimize this limitation by combining supervised machine learning with empirical learning of semantic relatedness from the distribution of the relevant words in additional unannotated text.

As utilization of clinical decision support (CDS) increases, it is important to continue the development and refinement of methods to accurately translate the intention of clinical practice guidelines (CPG) into a computable form. In this study, we validate and extend the 13 steps that Shiffman et al. 5 identified for translating CPG knowledge for use in CDS. During an implementation project of ATHENA-CDS, we encoded complex CPG recommendations for five common chronic conditions for integration into an existing clinical dashboard. Major decisions made during the implementation process were recorded and categorized according to the 13 steps. During the implementation period, we categorized 119 decisions and identified 8 new categories required to complete the project. We provide details on an updated model that outlines all of the steps used to translate CPG knowledge into a CDS integrated with existing health information technology.

Abstract This CHI 2011 SIG provides a workshop for collective problem finding and community identification. The goal is to initiate a working group to coordinate systemic design research issues across practitioner communities. This SIG addresses the insufficiency of user-centered design and informatics research to design for system and service-level innovations in healthcare. The SIG seeks to coordinate communications and participation across design practice, research disciplines, and areas of health practice for ...

Inflammatory Bowel Disease (IBD) is a group of chronic gastrointestinal disorders that
are difficult to treat. Having no known cure, treatment courses can be long-term and expensive. IBD flare-ups can happen without warning and there exists no objective criteria to
measure the disease’s activity. Recently, Recurrent Neural Networks (RNN) have emerged as
a state-of-the-art method in clinical time series analysis; building on recent work that apply
RNNs to temporal patient data, this thesis explores methodologies for processing temporal
clinical data, the feasibility of a deep RNN classifier to forecast the future healthcare utilization, and techniques to curb overfitting while training on a small dataset. This work
shows that multitask learning is helpful to train stable models, and deep networks can be
engineered to process small noisy datasets in the clinical domain.

EJISE has an open invitation for Industry practitioners to submit opinion and commentary papers. In this section we publish viewpoints of Industry experts on current or emerging industry-based Information Systems management practice, or on current or emerging technologies. The objective of this section of the issue is to stimulate discussion and debate on topical Information Systems issues from an industry perspective, thereby feeding into the academic research cycle.

Objective A method for the automatic resolution of coreference between medical concepts in clinical records. Materials and methods A multiple pass sieve approach utilizing support vector machines (SVMs) at each pass was used to resolve coreference. Information such as lexical similarity, recency of a concept mention, synonymy based on Wikipedia redirects, and local lexical context were used to inform the method. Results were evaluated using an unweighted average of MUC, CEAF, and B 3 coreference evaluation metrics. The datasets used in these research experiments were made available through the 2011 i2b2/VA Shared Task on Coreference.

Objective To provide a natural language processing method for the automatic recognition of events, temporal expressions, and temporal relations in clinical records. Materials and Methods A combination of supervised, unsupervised, and rule-based methods were used. Supervised methods include conditional random fields and support vector machines. A flexible automated feature selection technique was used to select the best subset of features for each supervised task. Unsupervised methods include Brown clustering on several corpora, which result in our method being considered semisupervised. Results On the 2012 Informatics for Integrating Biology and the Bedside (i2b2) shared task data, we achieved an overall event F1-measure of 0.8045, an overall temporal expression F1-measure of 0.6154, an overall temporal link detection F1-measure of 0.5594, and an end-to-end temporal link detection F1-measure of 0.5258. The most competitive system was our event recognition method, which ranked third out of the 14 participants in the event task. Discussion Analysis reveals the event recognition method has difficulty determining which modifiers to include/exclude in the event span. The temporal expression recognition method requires significantly more normalization rules, although many of these rules apply only to a small number of cases. Finally, the temporal relation recognition method requires more advanced medical knowledge and could be improved by separating the single discourse relation classifier into multiple, more targeted component classifiers. Conclusions Recognizing events and temporal expressions can be achieved accurately by combining supervised and unsupervised methods, even when only minimal medical knowledge is available. Temporal normalization and temporal relation recognition, however, are far more dependent on the modeling of medical knowledge.

Objective: We describe a novel, crowdsourcing method for generating a knowledge base of problem-medication pairs that takes advantage of manually asserted links between medications and problems.

Methods:Through iterative review, we developed metrics to estimate the appropriateness of manually entered problem-medication links for inclusion in a knowledge base that can be used to infer previously unasserted links between problems and medications.

Results: Clinicians manually linked 231 223 medications (55.30% of prescribed medications) to problems within the electronic health record, generating 41 203 distinct problem-medication pairs, although not all were accurate. We developed methods to evaluate the accuracy of the pairs, and after limiting the pairs to those meeting an estimated 95% appropriateness threshold, 11 166 pairs remained. The pairs in the knowledge base accounted for 183 127 total links asserted (76.47% of all links). Retrospective application of the knowledge base linked 68 316 medications not previously linked by a clinician to an indicated problem (36.53% of unlinked medications). Expert review of the combined knowledge base, including inferred and manually linked problem-medication pairs, found a sensitivity of 65.8% and a specificity of 97.9%.

Conclusion: Crowdsourcing is an effective, inexpensive method for generating a knowledge base of problem-medication pairs that is automatically mapped to local terminologies, up-to-date, and reflective of local prescribing practices and trends.

The purpose of this research was to identify, name and define a set of concepts to describe specific times and time intervals relevant to patient transport by helicopter. A list of 206 potential terms was identified from 96 patient records. A purposive sample of experts representing nurses, physicians, paramedics, pilots and communication specialists involved in air transport was selected to participate in a five-round Delphi study conducted by email. A set of 19 concepts were identified and defined. Fifteen of the terms were specific times, such as Time of Call, Depart Base and Arrive Location. Four of the terms were intervals, such as Ground Time or Transport Time.

Purpose: To assess progress made in hospital information systems (HIS) since 1979, when the forerunner of the International Medical Informatics Association Working Group on HIS first met. Methods: A review of the recommendations made in 1979 identified core concerns, which were analyzed in light of the state of the art in 2002. Results: Despite significant changes over the years, the underlying concerns identified in 1979 are still valid today. In 2002 as in 1979, HIS must be integrated into the hospital's organizational structure; financial and economic benefits depend upon using technology as an enabler of improved clinical outcomes; and education and training remain critical to the successful use of technology solutions. The tools available for addressing these concerns have changed enormously. Where there were dumb terminals, there are the World Wide Web and handheld devices. As a result, we are raising our expectations and changing the terms of our discussions. Today the focus is shifting to patient safety, decision support, and evidence-based practice; the concerns voiced in 1979 have become medical informatics cornerstones. New tools and new approaches now available can improve the quality of care. Using them appropriately requires careful planning and education for patients as well as healthcare professionals.

A personal look at some of the developments in practical clinical informatics over the past two decades, with discussion of several successful projects, including the National Center for Emergency Medicine Informatics, the Azyxxi system, Federal Project ER One, the Institutes for Innovation in Medicine, the Medical MediaLab, Project Sentinel, and others. Lessons learned, and hints and suggestions for future developers and informaticists.

An important barrier to the widespread dissemination of clinical decision support (CDS) is the heterogeneity of information models and terminologies used across healthcare institutions, health information systems, and CDS resources such as knowledge bases. To address this problem, the Health Level 7 (HL7) Virtual Medical Record project (an open, international standards development effort) is developing community consensus on the clinical information exchanged between CDS engines and clinical information systems. As a part of this effort, the HL7 CDS Work Group embarked on a multinational, collaborative effort to identify a representative set of clinical data elements required for CDS. Based on an analysis of CDS systems from 20 institutions representing 4 nations, 131 data elements were identified as being currently utilized for CDS. These findings will inform the development of the emerging HL7 Virtual Medical Record standard and will facilitate the achievement of scalable, standards-based CDS.

Objective Health information exchange (HIE) systems are being developed across the nation. Understanding approaches taken by existing successful exchanges can help new exchange efforts determine goals and plan implementations. The goal of this study was to explore characteristics of use and users of a successful regional HIE. Design We used a mixed-method analysis, consisting of cross-sectional audit log data, semi-structured interviews, and direct observation in a sample of emergency departments and ambulatory safety net clinics actively using HIE. For each site, we measured overall usage trends, user logon statistics, and data types accessed by users. We also assessed reasons for use and outcomes of use. Results Overall, users accessed HIE for 6.8% of all encounters, with higher rates of access for repeat visits, for patients with comorbidities, for patients known to have data in the exchange, and at sites providing HIE access to both nurses and physicians. Discharge summaries and test reports were the most frequently accessed data in the exchange. Providers consistently noted retrieving additional history, preventing repeat tests, comparing new results to retrieved results, and avoiding hospitalizations as a consequence of HIE access. Conclusion HIE use in emergency departments and ambulatory clinics was focused on patients where missing information was believed to be present in the exchange and was related to factors including the roles of people with access, the setting, and other sitespecific issues that impacted the overall breadth of routine system use. These data should form an important foundation as other sites embark upon HIE implementation.

Experience in applying semantic web technology to clinical health care research has revealed the need for a more consistent approach to RDF data production.

Data originating in diverse clinical systems, formats and data models typically must be transformed to hub ontologies, merged, inferenced, selected and finally transformed to consuming applications' ontologies and data formats for productive use. The process is quite repetitive: similar transformations are often performed each day, week or month with only slight variations to the data windows and queries. Ad hoc data production scripts can be created to help automate this process, but they tend to be fragile, inefficient, difficult to maintain and hard to visualize.

This presentation describes a simple framework and ontology for cached RDF data production pipelines, based on RESTful HTTP and SPARQL. These pipelines are easily visualized, and incremental data changes automatically propagate through to consuming applications.

The proliferation of smartphones and sensors, the continuous monitoring of physiology and environment (personal health signals), notifications from public health sources (public health signals), and more digital access to clinical data, are resulting in massive multisensory and multimodal observational data.  The technology has significant potential to improve health and well-being, through early detection, better diagnosis, effective prevention and treatment of a disease; and improved the quality of life. However, to make this personalized digital medicine a reality, it is crucial to derive actionable insights from data including heterogeneous and fine-grained observations.

At Kno.e.sis, we have collaborations with clinicians in growing number of specializations (Cardiovascular, Pulmonology, Gastroenterology)  to study personalized health decision making that involve the use of real-world patient data, deep background knowledge and well targeted clinical applications. For example:

For a patient discharged from hospital with Acute Decompensated Heart Failure, can  we compute post hospital discharge risk factor to reduce 30-day readmissions?
For children with Asthma,  can we predict an impending attack to enable actions that prevent an attack reducing the need for post-attack symptomatic relief?
For Parkinson’s Disease,  can we characterize the progression to adjust medication and therapeutic changes?

The above provides the context for a research agenda around what I call Smart Data, which (a) provides value from harnessing the challenges posed by volume, velocity, variety and veracity  of Big Data, in-turn providing actionable information and improve decision making, and/or (b) is focused on the actionable value achieved by human involvement in data creation, processing and consumption phases for improving the Human experience.  In describing Smart Data approach to above heath applications, I will cover the following technical capabilities that adds semantics to enhance or complement traditional NLP and ML centric solutions:

* Semantic Sensor Web- including semantic computation infrastructure, ability to semi-automatically create domain specific background knowledge (ontology) from unstructured data (e.g., EMR), and automatically do semantic annotation of multimodal and multisensory data

* Semantic perception – convert low level signals into higher level abstractions using IntellegO framework that utilizes domain knowledge and hybrid abductive/deductive reasoning

* Intelligence at Edge - perform scalable and efficient semantic computation on resource constrained devices

Background
With the existence of research over federated repositories, it is desirable to utilize high quality integrated data repositories (IDRs). IDR can be defined as a data warehouse optimized for research purposes rather than clinical care, which contains clinical, administrative, trial, and -omics data [1]. In this work, we focus on the quality of clinical and administrative components of IDRs. There is no standardized methodology which could quantitatively evaluate the quality of an IDR (e.g., “Does a given IDR have at least 2000 adult diabetic patients (type 1) with complete pediatric history?”). With the increased interest in research of existing data (such as comparative effectiveness research) and increasing number of institutions with an comprehensive IDRs, it is important to have a mechanism for quickly selecting quality IDRs.

Methods
Our poster will present a set of IDR quality measures which can compare IDRs in size and completeness. We considered the following criteria for a good measure: the measure is intuitive to interpreted (such as count of patients);  facilitates monitoring improvement; and does not place any arbitrary value on individual measure components (e.g., value of 10 years of medication history vs. 10 years of weight/height history).
Our methodology proposes a hierarchy of definitions of minimum EHR elements (see Table 1 for examples) and uses a simple count of each level to quantitatively evaluate an IDR.

Results
We have applied our methodology to an IDR at Marshfield Clinic (see Table 1). To facilitate evaluations at other institutions, we have created an ANSI-SQL script which can compute all current measures in a single execution.

Conclusion
Our evaluation methodology provides a quick way to compare IDRs at different institutions. It can be applied to institutions contributing to a virtual warehouse. Our goal was to arrive at a pragmatic set of measures operating on an easy-to-implement event schema. The limitations are: focus on general research idea and event types and criteria included in some level definitions. We plan to conduct a Delphi study involving informatics experts to arrive at an improved consensus set of measures.