Decision support from local data: creating adaptive order menus from past clinician behavior.

OBJECTIVE: Reducing care variability through guidelines has significantly benefited patients. Nonetheless, guideline-based Clinical Decision Support (CDS) systems are not widely implemented or used, are frequently out-of-date, and cannot address complex care for which guidelines do not exist. Here, we develop and evaluate a complementary approach - using Bayesian Network (BN) learning to generate adaptive, context-specific treatment menus based on local order-entry data. These menus can be used as a draft for expert review, in order to minimize development time for local decision support content. This is in keeping with the vision outlined in the US Health Information Technology Strategic Plan, which describes a healthcare system that learns from itself. MATERIALS AND METHODS: We used the Greedy Equivalence Search algorithm to learn four 50-node domain-specific BNs from 11,344 encounters: abdominal pain in the emergency department, inpatient pregnancy, hypertension in the Urgent Visit Clinic, and altered mental state in the intensive care unit. We developed a system to produce situation-specific, rank-ordered treatment menus from these networks. We evaluated this system with a hospital-simulation methodology and computed Area Under the Receiver-Operator Curve (AUC) and average menu position at time of selection. We also compared this system with a similar association-rule-mining approach. RESULTS: A short order menu on average contained the next order (weighted average length 3.91-5.83 items). Overall predictive ability was good: average AUC above 0.9 for 25% of order types and overall average AUC .714-.844 (depending on domain). However, AUC had high variance (.50-.99). Higher AUC correlated with tighter clusters and more connections in the graphs, indicating importance of appropriate contextual data. Comparison with an Association Rule Mining approach showed similar performance for only the most common orders with dramatic divergence as orders are less frequent. DISCUSSION AND CONCLUSION: This study demonstrates that local clinical knowledge can be extracted from treatment data for decision support. This approach is appealing because: it reflects local standards; it uses data already being captured; and it produces human-readable treatment-diagnosis networks that could be curated by a human expert to reduce workload in developing localized CDS content. The BN methodology captured transitive associations and co-varying relationships, which existing approaches do not. It also performs better as orders become less frequent and require more context. This system is a step forward in harnessing local, empirical data to enhance decision support.

Statistical design and analysis of label-free LC-MS proteomic experiments: a case study of coronary artery disease.

This chapter presents a case study, which applies statistical design and analysis to an LC-MS-based -investigation of subjects with coronary artery disease. First, we discuss the principles of statistical -experimental design, and the specification of an Analysis of Variance (ANOVA) model that describes the major sources of variation in the data. Second, we discuss procedures for detecting differentially abundant proteins, estimating protein abundance in individual samples, testing predefined groups of proteins for enrichment in differential abundance, and calculating sample size for a future experiment. The discussion is accompanied by examples of computer code implemented in the open-source statistical software R, which can be followed for an independent implementation of a similar investigation.

An outline for a vocabulary of nominal properties and examinations--basic and general concepts and associated terms.

Scientists of disciplines in clinical laboratory sciences have long recognized the need for a common language for efficient and safe request of investigations, reporting of results, and communication of experience and scientific achievements. Widening the scope, most scientific disciplines, not only clinical laboratory sciences, rely to some extent on various nominal examinations, in addition to measurements. The 'International vocabulary of metrology--Basic and general concepts and associated terms' (VIM) is designed for metrology, science of measurement. The aim of the proposed vocabulary is to suggest definitions and explanations of concepts and terms related to nominal properties, i.e., properties that can be compared for identity with other properties of the same kind-of-property, but that have no magnitude.

Querying the National Drug File Reference Terminology (NDFRT) to assign drugs to decision support categories.

INTRODUCTION: The accurate categorization of drugs is a prerequisite for decision support rules. The manual process of creating drug classes can be laborious and error-prone. METHODS: All 142 drug classes currently used at Regenstrief Institute for drug interaction alerts were extracted. These drug classes were replicated as fully-defined concepts in our local instance of the NDFRT knowledge base. The performance of these two strategies (manual classification vs. NDFRT-based queries) was compared, and the sensitivity and specificity of each was calculated. RESULTS: Compared to existing manual classifications, NDFRT-based queries made a greater number of correct class-drug assignments: 1528 vs. 1266. NDFRT queries have greater sensitivity (74.9% vs. 62.1%) to classify drugs. However, they have less specificity (85.6% vs. 99.8%). CONCLUSION: The NDFRT knowledge base shows promise for use in an automated strategy to improve the creation and update of drug classes. The chief disadvantage of our NDFRT-based approach was a greater number of false positive assignments due to the inclusion of non-systemic doseforms.

A method to compute treatment suggestions from local order entry data.

Although clinical decision support systems can reduce costs and improve care, the challenges associated with manually maintaining content has led to low utilization. Here we pilot an alternative, more automatic approach to decision support content generation. We use local order entry data and Bayesian networks to automatically find multivariate associations and suggest treatments. We evaluated this on 5044 hospitalizations of pregnant women, choosing 70 frequent order and treatment variables comprising 20 treatable conditions. The method produced treatment suggestion lists for 15 of these conditions. The lists captured accurate and non-trivial clinical knowledge, and all contained the key treatment for the condition, often as the first suggestion (71% overall, 90% non-labor-related). Additionally, when run on a test set of patient data, it very accurately predicted treatments (average AUC .873) and predicted pregnancy-specific treatments with even higher accuracy (AUC above .9). This method is a starting point for harnessing the wisdom-of-the-crowd for decision support.

Protein quantification in label-free LC-MS experiments.

The goal of many LC-MS proteomic investigations is to quantify and compare the abundance of proteins in complex biological mixtures. However, the output of an LC-MS experiment is not a list of proteins, but a list of quantified spectral features. To make protein-level conclusions, researchers typically apply ad hoc rules, or take an average of feature abundance to obtain a single protein-level quantity for each sample. We argue that these two approaches are inadequate. We discuss two statistical models, namely, fixed and mixed effects Analysis of Variance (ANOVA), which views individual features as replicate measurements of a protein's abundance, and explicitly account for this redundancy. We demonstrate, using a spike-in and a clinical data set, that the proposed models improve the sensitivity and specificity of testing, improve the accuracy of patient-specific protein quantifications, and are more robust in the presence of missing data.

Clinical laboratory sciences data transmission: the NPU coding system.

In health care services, technology requires that correct information be duly available to professionals, citizens and authorities, worldwide. Thus, clinical laboratory sciences require standardized electronic exchanges for results of laboratory examinations. The NPU (Nomenclature, Properties and Units) coding system provides a terminology for identification of result values (property values). It is structured according to BIPM, ISO, IUPAC and IFCC recommendations. It uses standard terms for established concepts and structured definitions describing: which part of the universe is examined, which component of relevance in that part, which kind-of-property is relevant. Unit and specifications can be added where relevant [System(spec)-Component(spec); kind-of-property(spec) = ? unit]. The English version of this terminology is freely accessible at http://dior.imt.liu.se/cnpu/ and http://www.labterm.dk, directly or through the IFCC and IUPAC websites. It has been nationally used for more than 10 years in Denmark and Sweden and has been translated into 6 other languages. The NPU coding system provides a terminology for dedicated kinds-of-property following the international recommendations. It fits well in the health network and is freely accessible. Clinical laboratory professionals worldwide will find many advantages in using the NPU coding system, notably with regards to an accreditation process.

Structured product labeling improves detection of drug-intolerance issues.

OBJECTIVES: This study sought to assess the value of the Health Level 7/U.S. Food and Drug Administration Structured Product Labeling (SPL) drug knowledge representation standard and its associated terminology sources for drug-intolerance (allergy) decision support in computerized provider order entry (CPOE) systems. DESIGN: The Regenstrief Institute CPOE drug-intolerance issue detection system and its knowledge base was compared with a method based on existing SPL label content enriched with knowledge sources used with SPL (NDF-RT/MeSH). Both methods were applied to a large set of drug-intolerance (allergy) records, drug orders, and medication dispensing records covering >50,000 patients over 30 years. MEASUREMENTS: The number of drug-intolerance issues detected by both methods was counted, as well as the number of patients with issues, number of distinct drugs, and number of distinct intolerances. The difference between drug-intolerance issues detected or missed by either method was qualitatively analyzed. RESULTS: Although <70% of terms were mapped to SPL, the new approach detected four times as many drug-intolerance issues on twice as many patients. CONCLUSION: The SPL-based approach is more sensitive and suggests that mapping local dictionaries to SPL, and enhancing the depth and breadth of coverage of SPL content are worth accelerating. The study also highlights specificity problems known to trouble drug-intolerance decision support and suggests how terminology and methods of recording drug intolerances could be improved.

A recommendation algorithm for automating corollary order generation.

Manual development and maintenance of decision support content is time-consuming and expensive. We explore recommendation algorithms, e-commerce data-mining tools that use collective order history to suggest purchases, to assist with this. In particular, previous work shows corollary order suggestions are amenable to automated data-mining techniques. Here, an item-based collaborative filtering algorithm augmented with association rule interestingness measures mined suggestions from 866,445 orders made in an inpatient hospital in 2007, generating 584 potential corollary orders. Our expert physician panel evaluated the top 92 and agreed 75.3% were clinically meaningful. Also, at least one felt 47.9% would be directly relevant in guideline development. This automated generation of a rough-cut of corollary orders confirms prior indications about automated tools in building decision support content. It is an important step toward computerized augmentation to decision support development, which could increase development efficiency and content quality while automatically capturing local standards.

Medication and indication linkage: A practical therapy for the problem list?

BACKGROUND: Establishing a relationship between medications and diagnoses within a functioning electronic medical record system (EMR) has many valuable applications,such as improving the quality and utility of the problem list to support better decisions. METHODS: We evaluated over 1.6 million de-identified patient records from the Regenstrief Medical Record System (RMRS) with over 90 million diagnoses and 20 million medications. Using RxNorm, the VA National Drug File Reference Terminology, and SNOMED-CT (SCT)standard terminologies and mappings we evaluated the linkage for local concept terms for medications and problems (diagnoses & complaints). RESULTS: We were able to map 24,398 candidates as medication and indication pairs. The overall sensitivity and specificity for term pairs was 67.5% and 86% respectively and 39.5% and 97.4 when adjusted for term pair occurrence within single patient records. CONCLUSIONS: Medications can be mapped by machine to a disease/ disorder using established terminology standards.This mapping may inform many knowledge management and decision support features in an EMR.

A system for sharing routine surgical pathology specimens across institutions: the Shared Pathology Informatics Network.

This report presents an overview for pathologists of the development and potential applications of a novel Web enabled system allowing indexing and retrieval of pathology specimens across multiple institutions. The system was developed through the National Cancer Institute's Shared Pathology Informatics Network program with the goal of creating a prototype system to find existing pathology specimens derived from routine surgical and autopsy procedures ("paraffin blocks") that may be relevant to cancer research. To reach this goal, a number of challenges needed to be met. A central aspect was the development of an informatics system that supported Web-based searching while retaining local control of data. Additional aspects included the development of an eXtensible Markup Language schema, representation of tissue specimen annotation, methods for deidentifying pathology reports, tools for autocoding critical data from these reports using the Unified Medical Language System, and hierarchies of confidentiality and consent that met or exceeded federal requirements. The prototype system supported Web-based querying of millions of pathology reports from 6 participating institutions across the country in a matter of seconds to minutes and the ability of bona fide researchers to identify and potentially to request specific paraffin blocks from the participating institutions. With the addition of associated clinical and outcome information, this system could vastly expand the pool of annotated tissues available for cancer research as well as other diseases.

Assessing the impact of HL7/FDA Structured Product Label (SPL) content for medication knowledge management.

The amount and quality of the SPL drug knowledge which has been released so far is assessed. All published labels were loaded into a relational database and classified to create vendor-independent descriptions. While SPL labels cover only 23% of RxNorm clinical drugs, they still describe 78% of actual community pharmacy dispenses records. SPL descriptions agree well with RxNorm. SPL can be used as the primary source of drug information for e-prescribing systems once the upcoming FDA listing rule takes effect. In the interim, existing gaps can be temporarily closed with RxNorm or other sources.

Enabling joint commission medication reconciliation objectives with the HL7 / ASTM Continuity of Care Document standard.

We sought to determine how well the HL7/ASTM Continuity of Care Document (CCD) standard supports the requirements underlying the Joint Commission medication reconciliation recommendations. In particular, the Joint Commission emphasizes that transition points in the continuum of care are vulnerable to communication breakdowns, and that these breakdowns are a common source of medication errors. These transition points are the focus of communication standards, suggesting that CCD can support and enable medication related patient safety initiatives. Data elements needed to support the Joint Commission recommendations were identified and mapped to CCD, and a detailed clinical scenario was constructed. The mapping identified minor gaps, and identified fields present in CCD not specifically identified by Joint Commission, but useful nonetheless when managing medications across transitions of care, suggesting that a closer collaboration between the Joint Commission and standards organizations will be mutually beneficial. The nationally recognized CCD specification provides a standards-based solution for enabling Joint Commission medication reconciliation objectives.

Evaluation of the VA/KP problem list subset of SNOMED as a clinical terminology for electronic prescription clinical decision support.

A standardized terminology for medical indications is essential for building e-prescription applications with decision support. The FDA has adopted the Veteran Administration and Kaiser Permanente (VA/KP) Problem List Subset of SNOMED as the terminology to represent indications in electronic labels. In this paper, we evaluate the ability of this subset to represent the text phrases extracted from a medication decision support system and the indications section of existing drug labels. We compiled a test set of 1265 distinct indication phrases and mapped them to (1) UMLS, (2) Entire SNOMED, (3) All Precoordinated concepts from the "Clinical Finding" hierarchy of SNOMED, and (4) VA/KP Subset. 95% of the phrases mapped to concepts in UMLS, 90.3% to SNOMED, 79.5% to SNOMED Precordinated and 71.1% mapped completely or partially to concepts in the VA/KP subset. Our study suggests that the VA/KP Subset has significant limitations for coding drug indications; however, when focusing on indications as medical conditions only, the coverage seems more adequate.

The HL7 reference information model under scrutiny.

The Health Level 7 (HL7) Reference Information Model (RIM) was once incepted as an object oriented information model to harmonize the definition of HL7 messages across different application domains. On the heels of the hugely successful HL7 version 2, version 3 and the RIM has received significant attention and credit and in turn is increasingly subjected to criticism. In this paper the authors, who are among the chief designers of the RIM, respond to the major points that have been raised against the RIM in the published literature. We find that much of the criticism is based on misunderstandings and differences in point of view. We wish to advance the dialogue in the hope that when we account for those differences, effective critique may lead to real improvements of the standard.

Integrative specimen information service - a campus-wide resource for tissue banking, experimental data annotation, and analysis services.

We present the architecture and approach of an evolving campus-wide information service for tissues with clinical and data annotations to be used and contributed to by clinical researchers across the campus. The services provided include specimen tracking, long term data storage, and computational analysis services. The project is conceived and sustained by collaboration among researchers on the campus as well as participation in standards organizations and national collaboratives.

The Indiana network for patient care: a working local health information infrastructure. An example of a working infrastructure collaboration that links data from five health systems and hundreds of millions of entries.

The Indiana Network for Patient Care (INPC) is a local health information infrastructure (LHII) that includes information from the five major hospital systems (fifteen separate hospitals), the county and state public health departments, and Indiana Medicaid and RxHub and that carries 660 million separate results. It provides cross-institutional access to physicians in emergency rooms and hospitals based on patient-physician proximity or on hospital credentialing. The network includes and delivers laboratory, radiology, dictation, and other documents to a majority of Indianapolis office practices. The INPC began operation seven years ago and is one of the first and best examples of an LHII.

A pilot study of usefulness of clinician-patient videoconferencing for making routine medical decisions in the nursing home.

OBJECTIVES: To pilot and assess the role of videoconferencing in clinicians' medical decision-making and their interactions with nursing home residents (NHRs). DESIGN: Paired virtual and bedside examinations. Face-to-face (FTF) examination of NHRs by off-site clinicians immediately followed videoconferencing between the same clinician-NHR pair. SETTING: A 240-bed, county-managed, urban nursing home. PARTICIPANTS: NHRs (n=35) and clinicians (n=3) receiving or providing routine care between 2002 and 2003. MEASUREMENTS: Orders generated by clinicians, clinicians' ratings of videoconferencing, and coded review of video encounters. After both examinations, clinicians rated the encounters and generated orders necessary for NHRs. Orders were categorized and counted according to timing (before or after the FTF visit). Clinician-NHR interactions were assessed using coding videos with a 31-item instrument. RESULTS: For 71% of the encounters, clinicians stated that videoconferencing facilitated their assessment. Difficulties included sound quality (19%) and participants' familiarity with videoconferencing (7%). Although NHRs were alert in 50% of encounters, 62% of alert NHRs did not indicate understanding of the recommended treatment. CONCLUSION: FTF examination was superior for most assessments, but videoconferencing was judged to be valuable, especially for wound care. Even when NHRs were alert, informed medical decision-making by NHRs with their clinicians was limited. Enhancing videoconferencing quality and providing more training about informed decision-making using videoconferencing might improve the effectiveness of the technology.

SPIN query tools for de-identified research on a humongous database.

The Shared Pathology Informatics Network (SPIN), a research initiative of the National Cancer Institute, will allow for the retrieval of more than 4 million pathology reports and specimens. In this paper, we describe the special query tool as developed for the Indianapolis/Regenstrief SPIN node, integrated into the ever-expanding Indiana Network for Patient care (INPC). This query tool allows for the retrieval of de-identified data sets using complex logic, auto-coded final diagnoses, and intrinsically supports multiple types of statistical analyses. The new SPIN/INPC database represents a new generation of the Regenstrief Medical Record system - a centralized, but federated system of repositories.