Faculty Bibliography

Natural Language Processing (NLP) offers an approach for capturing data from narratives and creating structured reports for further computer processing. We explored the ability of a NLP system, Medical Language Extraction and Encoding (MedLEE), on nursing narratives. MedLEE extracted 490 concepts from narrative text in a sample of 553 oncology nursing process notes. The most frequently monitored and recorded signs and symptoms were related to chemotherapy care, such as adverse reactions, shortness of breath, nausea, pain, and bleeding. In terms of nursing interventions, chemotherapy, blood culture, medication, and blood transfusion were commonly recorded in free text. NLP may provide a feasible approach to extract data related to patient safety/quality measures and nursing outcomes by capturing nursing concepts that are not recorded through structured data entry. For better NLP performance in the domain of nursing, additional nursing terms and abbreviations must be added to MedLEE's lexicon.

OBJECTIVE:To identify some of the challenges that medical residents face in addressing their information needs in an inpatient setting, by examining how voice capture in natural language of clinical questions fits into workflow, and by characterizing the focus, format, and semantic content and complexity of their questions. DESIGN/METHODS:Internal medicine residents captured information needs on a digital recorder while on a hospital inpatient service and then participated in semi-structured interviews. MEASUREMENTS/METHODS:Interviews were analyzed to identify emergent themes. Recorded questions were analyzed for focus (diagnosis, treatment, or epidemiology) and format, either foreground (specific knowledge relating to an individual patient) or background (general knowledge about a condition). Semantic concepts and types were identified using MetaMap (UMLS - Unified Medical Language System) and manually. RESULTS:Voice recording of questions appeared to unmask residents' latent information needs. Although residents were able to record questions during workflow, there was a delay from the time questions materialized to when they were recorded. Question focus was distributed among diagnosis (32%), treatment (40%), and epidemiology (28%), and the majority of questions were background (69%). Questions were semantically complex; foreground and background questions averaged 12.6 (SD 6.0) and 9.1 (SD 6.0) UMLS concepts, respectively. MetaMap failed to recognize concepts when residents used acronyms or abbreviations or omitted key terms. CONCLUSIONS:We found that it is feasible for residents to capture their clinical questions in natural language during workflow and that recording questions may prompt awareness of previously unrecognized information needs. However, the semantic complexity of typical questions and mapping failures due to residents' use of acronyms and abbreviations present challenges to machine-based extraction of semantic content.

The authors summarize their experience in iteratively testing the adequacy of three versions of the Health Level Seven (HL7) Logical Observation Identifiers Names and Codes (LOINC) Clinical Document Ontology (CDO) to represent document names at Columbia University Medical Center. The percentage of documents fully represented increased from 23.4% (Version 1) to 98.5% (Version 3). The proportion of unique representations increased from 7.9% (Analysis 1) to 39.4% (Analysis 4); the proportion reflects the level of specificity in the document names as well as the completeness and level of granularity of the CDO. The authors shared the findings of each analysis with the Clinical LOINC committee and participated in the decision-making regarding changes to the CDO on the basis of those analyses and those conducted by the Department of Veterans Affairs. The authors encourage other institutions to actively engage in testing healthcare standards and participating in standards development activities to increase the likelihood that the evolving standards will meet institutional needs.

OBJECTIVE: Human adiposity is highly heritable, but few of the genes that predispose to obesity in most humans are known. We tested candidate genes in pathways related to food intake and energy expenditure for association with measures of adiposity. METHODS: We studied 355 genetic variants in 30 candidate genes in 7 molecular pathways related to obesity in two groups of adult subjects: 1,982 unrelated European Americans living in the New York metropolitan area drawn from the extremes of their body mass index (BMI) distribution and 593 related Yup'ik Eskimos living in rural Alaska characterized for BMI, body composition, waist circumference, and skin fold thicknesses. Data were analyzed by using a mixed model in conjunction with a false discovery rate (FDR) procedure to correct for multiple testing. RESULTS: After correcting for multiple testing, two single nucleotide polymorphisms (SNPs) in Ghrelin (GHRL) (rs35682 and rs35683) were associated with BMI in the New York European Americans. This association was not replicated in the Yup'ik participants. There was no evidence for gene x gene interactions among genes within the same molecular pathway after adjusting for multiple testing via FDR control procedure. CONCLUSION: Genetic variation in GHRL may have a modest impact on BMI in European Americans

Providing knowledge at the point of care offers the possibility for reducing error and improving patient outcomes. However, the vast majority of the physician's information needs are not met in a timely fashion. The research presented in this paper characterizes an expert librarian's search strategies as it pertains to the selection and use of various electronic information resources. The 10 searches conducted by the librarian to address the physician's information needs varied in terms of complexity and question type. The librarian employed a total of 10 resources and used as many as 7 in a single search. The longer term objective is to model the sequential process in sufficient detail as to be able to contribute to the development of intelligent automated search agents.

This work has the objective to implement a search strategy model for high precision retrieval of documents in reply to a clinical query. To achieve this goal we designed a series of search filters on a staged configuration that allow documents to be retrieved from the most precise to the less specific. We found that for most questions the most relevant articles are retrieved at early stages of the search.

Transdisciplinary research accelerates scientific progress. Despite the value of social network analysis to characterize interdepartmental collaboration, institutions have been slow to adopt the approach. We use the approach to characterize collaboration among obesity researchers at our institution, identifying cores of researchers engaged in frequent collaborations. Providing an objective view of research across an institution, social network analysis is a baseline for efforts to facilitate transdisciplinary collaboration.

In this paper we examine frequently performed clinical research activities with the objective of identifying aspects of workflow that could be amenable to informatics-based re-engineering. This paper is part of a series of studies under the NIH Roadmap initiative, which examines workflow of clinical research in community practices. We describe three common work activities, detailing the main actors involved, the tools used and the challenges faced. These activities illustrate inefficiencies in the clinical research workflow which include: a) lack of supporting tools to perform routine work activities, b) redundancy, low reuse of data and poor interoperability between systems and c) the fragmented and distributed nature of the workflow. We identify opportunities for re-engineering at both a micro (activity) and macro level (organization).

In the interest of designing an automated high-level, longitudinal clinical summary of a patient record, we analyze traditional ways in which medical problems pertaining to the patient are summarized in the electronic health record. The patient problem list has become a commonly used proxy for a summary of patient history and automated methods have been proposed to generate it. However, little research has been conducted on how to structure the problem list in a manner most effective for supporting clinical care. This study analyzes the structure and content of the Past Medical History (PMH) sections of a large corpus of clinical notes, as a proxy for problem lists. Findings show that when listing patients history, physicians convey several semantic types of information, not only problems. Furthermore, they often group related concepts in a single line of the PMH. In contrast, traditional problem lists allow only a simple enumeration of coded terms. Content analysis goes on to reiterate the value of more complex representations as well as provide valuable data and guidelines for automated generation of a clinical summary.

BACKGROUND:The National Institutes of Health (NIH) Roadmap for Medical Research aims to increase the efficiency and speed of clinical research. We report results and lessons learned from a key component of the Roadmap, the Clinical Research Networks initiative. METHODS:Twelve diverse, experienced, large, clinical research networks were funded for 3 years to develop strategies for integrating, expanding, and increasing the interoperability of clinical research networks in support of the Roadmap goals. Network leaders met periodically in person and by teleconference to describe common challenges encountered and solutions used for expansion and increased interoperability. RESULTS:These networks developed innovative solutions to technical challenges, including strategies for interoperability of information systems and management of complex information system technologies (eg, "brokering" to address data system incompatibility, data transfer, and security requirements), and solutions to human factor challenges at the individual, group, intraorganizational, and interorganizational levels (eg, applying collaborative organizing and decision-making processes based on key principles). CONCLUSIONS:These solutions can provide guidance to existing and future clinical research networks, particularly those forming as part of the NIH Clinical Translation Science Award program. Remaining technical and human factor challenges, however, as well as the largely unmet need for consistent funding for network infrastructure and maintenance, stand in the way of fulfilling the vision of a robust future role for clinical research networks.