Biomedical subjects

Daniel Rappaport

Publications and source records attributed to Daniel Rappaport.

3 recordsLinked to original sources

PubMed2006

PhenoGO: assigning phenotypic context to gene ontology annotations with natural language processing.

Natural language processing (NLP) is a high throughput technology because it can process vast quantities of text within a reasonable time period. It has the potential to substantially facilitate biomedical research by extracting, linking, and organizing massive amounts of information that occur in biomedical journal articles as well as in textual fields of biological databases. Until recently, much of the work in biological NLP and text mining has revolved around recognizing the occurrence of biomolecular entities in articles, and in extracting particular relationships among the entities. Now, researchers have recognized a need to link the extracted information to ontologies or knowledge bases, which is a more difficult task. One such knowledge base is Gene Ontology annotations (GOA), which significantly increases semantic computations over the function, cellular components and processes of genes. For multicellular organisms, these annotations can be refined with phenotypic context, such as the cell type, tissue, and organ because establishing phenotypic contexts in which a gene is expressed is a crucial step for understanding the development and the molecular underpinning of the pathophysiology of diseases. In this paper, we propose a system, PhenoGO, which automatically augments annotations in GOA with additional context. PhenoGO utilizes an existing NLP system, called BioMedLEE, an existing knowledge-based phenotype organizer system (PhenOS) in conjunction with MeSH indexing and established biomedical ontologies. More specifically, PhenoGO adds phenotypic contextual information to existing associations between gene products and GO terms as specified in GOA. The system also maps the context to identifiers that are associated with different biomedical ontologies, including the UMLS, Cell Ontology, Mouse Anatomy, NCBI taxonomy, GO, and Mammalian Phenotype Ontology. In addition, PhenoGO was evaluated for coding of anatomical and cellular information and assigning the coded phenotypes to the correct GOA; results obtained show that PhenoGO has a precision of 91% and recall of 92%, demonstrating that the PhenoGO NLP system can accurately encode a large number of anatomical and cellular ontologies to GO annotations. The PhenoGO Database may be accessed at the following URL: http://www.phenoGO.org

Computational Biology↗

PubMed2005

Electronic discharge summaries.

Timely completion of Discharge Summaries is a requirement of high quality care. We developed a system for writing electronic Discharge Summaries. DSUM Writer has generated 2464 of 7349 total summaries (34%) and has paid for itself during its first 8 weeks in production. DSUM Writer is a component of a suite of tools (eNote) for electronic physician documentation used to support clinical care, billing and narrative analysis research.

Cost Savings↗

PubMed2002

Frequency of visualization and thickness of normal appendix at nonenhanced helical CT.

PURPOSE: To evaluate the frequency of visualization, thickness, and features of the normal appendix at nonenhanced helical computed tomography (CT). MATERIALS AND METHODS: Three radiologists blinded to patient surgical history retrospectively reviewed CT scans obtained for renal colic assessment in 187 consecutive patients. No contrast material was administered. The frequency of visualization and the two-wall thickness of normal appendices were recorded. Interobserver agreement and effect of adequacy of intraperitoneal fat on identification of the appendix were assessed. RESULTS: The prevalence of appendectomy was 10.7% (20 of 187 patients). The means for the three reviewers' sensitivity, specificity, positive and negative predictive values, and accuracy of visualization of normal appendix were 79% (CI: 73%, 84%), 90% (CI: 78%, 96%), 98% (CI: 97%, 99%), 34% (CI: 22%, 47%), and 80% (CI: 74%, 86%), respectively. There was no significant difference among the three reviewers (P >.05) according to conditional logistic regression and exact McNemar test results. For all reviewers, the frequency of appendix visualization was significantly lower in patients with less intraperitoneal fat (P =.01-.001, chi(2) test). The mean thickness of normal appendix if no intraluminal content was visualized was 6.6 mm +/- 1.0 (SD), and the mean thickness, excluding visualized intraluminal content, was 3.6 mm +/- 0.8. The nonweighted kappa value for interobserver agreement for normal appendix visualization was 0.69-0.75 among the three reviewers, which indicated good to excellent agreement. CONCLUSION: Most normal appendices are seen at nonenhanced helical CT. The thickness of normal appendix, when the content is not recognizable, overlaps the values currently used to diagnose appendicitis at CT.

Adolescent↗