Proceedings. AMIA Symposium最新文献

The Connecticut Hospital Association has developed a data resource for inpatient pharmacy information. The RxData project collects drug dispensing information from member hospitals and joins it to administrative discharge data in the Chime database. The resulting dataset is useful for descriptive epidemiology of drug use patterns as well as surveillance, quality improvement, and some hypothesis testing. The drug identity is derived from the National Drug Code submitted by hospital pharmacies. A drug reference file is used together with these codes for hierarchical analysis. Data are accepted from participating facilities in a variety of formats and mapped to a common schema. The program uses locally developed roll-up logic to overcome the lack of consistent standards for recording inpatient drug order and dispense information. Dispensing records at different levels of aggregation are collected from source pharmacy information systems and converted to a standard "regimen" based on continuous dispensing of the same drug. The resulting record structure allows direct comparison of data from dissimilar systems. Data are currently available for eleven acute care hospitals and most of their associated emergency and outpatient surgery facilities. The program is expected to expand to cover most if not all Connecticut hospitals over the next two to three years.

Abstract As the home becomes an increasingly important site for health care, an increasing number of technology applications or devices are being introduced to support health at home. However, introducing new technology into a household raises a number of issues that must be considered prior to, during, and after the technology is implemented. This paper reviews the experiences of the UW-Madison Advanced Technologies for Health@Home Project, summarizing our assessment of household requirements that should be analyzed prior to introducing new technology. The overall goal of the Health@Home project is to improve the functionality and content of information technology innovations for the home. Using Venkatesh and Mazumdar's framework this article will summarize the relevant social, behavioral, technological, and physical dimensions of households that must be carefully assessed and understood to help ensure that the technology fits the needs of home residents.

Prediction of microscopic spread of tumor cells is becoming critically important in the decision making process in planning radiation therapy for cancer. Until recently, radiation treatment of head and neck cancer has been conservative, treating large regions to insure eradication of disease. However, if it is known that regional spread is confined, a more focused treatment can be considered, with the payoff of reducing or eliminating morbidity due to irradiating healthy tissue in the vicinity of node groups. Knowledge about the occurrence of micrometastases comes mainly from pathology reports in connection with surgery. As the data accrue, it will be possible and necessary to represent this knowledge in a symbolic computational model. Our work reports on the feasibility of modeling this knowledge using published data.

Several clinical terminologies now utilize description logic to model the logical definitions of concepts. Recent editions of the Systematized Nomenclature of Medicine (SNOMED) have been developed using the description logic Ontylog. A significant design criterion for SNOMED is to keep concept expressions simple enough to be broadly usable by clinicians, while maintaining faithful representation of concept meaning. Motivated by this criterion, "role grouping" has been developed as an extension to the description logic Ontylog. This paper describes the problems that motivated the creation of role grouping, outlines the semantics of role grouping, illustrates the benefits of this construct with examples from SNOMED Clinical Terms, and provides an algorithm for determining normal forms for expressions involving role groups.

At Columbia-Presbyterian Medical Center, free-text "Signout" notes are typed into the electronic record by clinicians for the purpose of cross-coverage. We plan to "unlock" information about adverse events contained in these notes in a subsequent project using Natural Language Processing (NLP). To better understand the requirements for parsing, Signout notes were compared to other common medical notes (ambulatory clinic notes and discharge summaries) on a series of quantitative metrics. They are shorter (mean length 59.25 words vs. 144.11 and 340.85 for ambulatory and discharge notes respectively) and use more abbreviations (26.88% vs. 20.07% and 3.57%). Despite being terser, Signout notes use less ambiguous abbreviations (8.34% vs. 9.09% and 18.02%). Differences were found using Relative Entropy and Squared Chi-square Distance in a novel fashion to compare these medical corpora. Signout notes appear to constitute a unique sublanguage of medicine. The implications for parsing free-text cross-coverage notes into coded medical data are discussed.

The American Board of Family Practice is developing a patient simulation program to evaluate diagnostic and management skills. The simulator must give temporally and physiologically reasonable answers to symptom questions such as "Have you been tired?" A three-step process generates symptom histories. In the first step, the simulator determines points in time where it should calculate instantaneous symptom status. In the second step, a Bayesian network implementing a roughly physiologic model of the symptom generates a value on a severity scale at each sampling time. Positive, zero, and negative values represent increased, normal, and decreased status, as applicable. The simulator plots these values over time. In the third step, another Bayesian network inspects this plot and reports how the symptom changed over time. This mechanism handles major trends, multiple and concurrent symptom causes, and gradually effective treatments. Other temporal insights, such as observations about short-term symptom relief, require complimentary mechanisms.

Clinical guidelines aim to eliminate clinician errors, reduce practice variation, and promote best medical practices. Computer-interpretable guidelines (CIGs) can deliver patient-specific advice during clinical encounters, which makes them more likely to affect clinician behavior than narrative guidelines. To reduce the number of errors that are introduced while developing narrative guidelines and CIGs, we studied the process used by the ACP-ASIM to develop clinical algorithms from narrative guidelines. We analyzed how changes progressed between subsequent versions of an algorithm and between a narrative guideline and its derived clinical algorithm. We recommend procedures that could limit the number of errors produced when generating clinical algorithms. In addition, we developed a tool for authoring CIGs in GLIF3 format and validating their syntax, data type matches, cardinality constraints, and structural integrity constraints. We used this tool to author guidelines and to check them for errors.

As the amount of data in public genomic databases grows, interoperability among them is becoming an increasingly critical feature. The ability for automated systems to mine and integrate data will be crucial to extracting knowledge from sources of data whose volume far exceeds the capabilities of human researchers. The currently dominant paradigm of presenting information as Web pages and using hyperlinks to describe relationships between pieces of information favors usability, but makes interoperability and automated data exchange more difficult. In this paper we describe how SNPper, a web-based system for the retrieval and analysis of Single Nucleotide Polymorphisms (SNPs), was augmented with a Remote Procedure Call interface, allowing client applications to query our program for SNP data and to receive the response as an XML document. Data represented in this form can be easily parsed by the requesting program, and thus reused for other applications. In this paper we describe the implementation of the interface and we show examples of its usage in a number of existing applications.

Bridging levels of scale and context are key problems for integrating Bio- and Health Informatics. Formal, logic-based ontologies using expressive formalisms are naturally "fractal" and provide new methods to support these aims. The basic notion of composition can be used to bridge scales; axioms can be used to carry implicit information; specific context markers can be included in definitions; and a hierarchy of semantic links can be used to represent subtle differences in point of view. Experience with OpenGALEN, the UK Drug Ontology and new experiments with the Gene Ontology and Foundational Model of Anatomy suggest that these are powerful tools provide practical solutions.

We have analyzed a publicly available dataset consisting of gene-expression measurements from 105 lung carcinomas joined with clinical parameters describing the age, smoking history, and survival statistics for the patients that the tumors originated in. Our aim was to demonstrate how the unsupervised analysis technique embodied in PathlinX allows researchers to quickly gain an intuition for the most significant relationships between heterogeneous data elements. A variety of metrics were evaluated empirically by their ability to distinguish biological signal in the data from random noise; this was accomplished by random permutation of the data rows followed by comprehensive pair-wise comparison of all experimental elements. Thresholds of significance were established based on the metric scores for the permuted data. Sub-threshold associations were then removed. The remaining associations were then grouped by a transitive closure process to generate undirected graphs of associations called PathlinX networks. We discuss the various features of each generated PathlinX network and demonstrate the ability of the technique to highlight biological features in large heterogeneous datasets.