Henry J. Lowe, MD

Abstract

The implementation of health information technology (HIT) is accelerating, driven in part by a growing interest in computerized physician order entry (CPOE) as a tool for improving the quality and safety of patient care. Computerized physician order entry could have a substantial impact on patients in intensive care, where the potential for medical error is high, and the clinical workflow is complex. In 2009, only 17% of hospitals had functional CPOE systems in place. In intensive care unit (ICU) settings, CPOE has been shown to reduce the occurrence of some medication errors, but evidence of a beneficial effect on clinical outcomes remains limited. In some cases, new error types have arisen with the use of CPOE. Intensive care unit workflow and staff relationships have been affected by CPOE, often in unanticipated ways. The design of CPOE software has a strong impact on user acceptance. Intensive care unit-specific order sets lessen the cognitive workload associated with the use of CPOE and improve user acceptance. The diffusion of new technological innovations in the ICU can have unintended consequences, including changes in workflow, staff roles, and patient outcomes. When implementing CPOE in critical care areas, both organizational and technical factors should be considered. Further research is needed to inform the design and management of CPOE systems in the ICU and to better assess their impact on clinical end points, cost-effectiveness, and user satisfaction.

View details for DOI 10.1177/0885066610387984

View details for PubMedID 21257633

Abstract

Use of terminology standards facilitates aggregating data from multiple sources for information retrieval, exchange and analysis. However, medical vocabularies are continuously updated and incorporating those changes consistently into clinical data warehouses requires rigorous methodology. To integrate pharmacy data from two hospital pharmacy information systems the Stanford Translational Research Integrated Database Environment (STRIDE) project mapped medication orders to RxNorm content using the RxNorm drug model. In order to keep the data relevant and up-to-date, we developed a strategy for updating to RxNorm, while preserving the original meaning and mapping of the legacy data. This case study discusses managing the vocabulary update by following the RxNorm content maintenance strategy and supplementing it with operations to retain access to its drug model information.

View details for PubMedID 21347024

Abstract

To address the problem of extracting structured information from pathology reports for research purposes in the STRIDE Clinical Data Warehouse, we adapted the ChartIndex Medical Language Processing system to automatically identify and map anatomic and diagnostic noun phrases found in full-text pathology reports to SNOMED CT concept descriptors. An evaluation of the system's performance showed a positive predictive value for anatomic concepts of 92.3% and positive predictive value for diagnostic concepts of 84.4%. The experiment also suggested strategies for improving ChartIndex's performance coding pathology reports.

View details for PubMedID 20351885

Abstract

STRIDE (Stanford Translational Research Integrated Database Environment) is a research and development project at Stanford University to create a standards-based informatics platform supporting clinical and translational research. STRIDE consists of three integrated components: a clinical data warehouse, based on the HL7 Reference Information Model (RIM), containing clinical information on over 1.3 million pediatric and adult patients cared for at Stanford University Medical Center since 1995; an application development framework for building research data management applications on the STRIDE platform and a biospecimen data management system. STRIDE's semantic model uses standardized terminologies, such as SNOMED, RxNorm, ICD and CPT, to represent important biomedical concepts and their relationships. The system is in daily use at Stanford and is an important component of Stanford University's CTSA (Clinical and Translational Science Award) Informatics Program.

View details for PubMedID 20351886

Abstract

The Stanford Translational Research Integrated Database Environment (STRIDE) clinical data warehouse integrates medication information from two Stanford hospitals that use different drug representation systems. To merge this pharmacy data into a single, standards-based model supporting research we developed an algorithm to map HL7 pharmacy orders to RxNorm concepts. A formal evaluation of this algorithm on 1.5 million pharmacy orders showed that the system could accurately assign pharmacy orders in over 96% of cases. This paper describes the algorithm and discusses some of the causes of failures in mapping to RxNorm.

View details for PubMedID 20351858

Abstract

Traditionally, the elucidation of genes involved in maturation and aging has been studied in a temporal fashion by examining gene expression at different time points in an organism's life as well as by knocking out, knocking in, and mutating genes thought to be involved. Here, we propose an in silico method to combine clinical electronic medical record (EMR) data and gene expression measurements in the context of disease to identify genes that may be involved in the process of human maturation and aging. First we show that absolute lymphocyte count may serve as a biomarker for maturation by using statistical methods to compare trends among different clinical laboratory tests in response to an increase in age. We then propose using the rate of decay for absolute lymphocyte count across 12 diseases as a proxy for differences in aging. We correlate the differing rates with gene expression across the same diseases to find maturation/aging related genes. Among the 53 genes with strongest correlations between expression profile and change in rate of decay, we found genes previously implicated in the process of aging, including MGMT (DNA repair), TERF2 (telomere stability), POLD1 (DNA replication and repair), and POLG (mtDNA replication).

View details for PubMedID 18229690

Abstract

Negation is common in clinical documents and is an important source of poor precision in automated indexing systems. Previous research has shown that negated terms may be difficult to identify if the words implying negations (negation signals) are more than a few words away from them. We describe a novel hybrid approach, combining regular expression matching with grammatical parsing, to address the above limitation in automatically detecting negations in clinical radiology reports.Negations are classified based upon the syntactical categories of negation signals, and negation patterns, using regular expression matching. Negated terms are then located in parse trees using corresponding negation grammar.A classification of negations and their corresponding syntactical and lexical patterns were developed through manual inspection of 30 radiology reports and validated on a set of 470 radiology reports. Another 120 radiology reports were randomly selected as the test set on which a modified Delphi design was used by four physicians to construct the gold standard.In the test set of 120 reports, there were a total of 2,976 noun phrases, of which 287 were correctly identified as negated (true positives), along with 23 undetected true negations (false negatives) and 4 mistaken negations (false positives). The hybrid approach identified negated phrases with sensitivity of 92.6% (95% CI 90.9-93.4%), positive predictive value of 98.6% (95% CI 96.9-99.4%), and specificity of 99.87% (95% CI 99.7-99.9%).This novel hybrid approach can accurately locate negated concepts in clinical radiology reports not only when in close proximity to, but also at a distance from, negation signals.

View details for DOI 10.1197/jamia.M2284

View details for Web of Science ID 000246670800007

View details for PubMedID 17329723

Abstract

The severity of diseases has often been assigned by direct observation of a patient and by pathological examination after symptoms have appeared. As we move into the genomic era, the ability to predict disease severity prior to manifestation has improved dramatically due to genomic sequencing and analysis of gene expression microarrays. However, as the severity of diseases can be exacerbated by non genetic factors, the ability to predict disease severity by examining gene expression alone may be inadequate. We propose the creation of a "clinarray" to examine phenotypic expression in the form of clinical laboratory measurements. We demonstrate that the clinarray can be used to distinguish between the severities of patients with cystic fibrosis and those with Crohn's disease by applying unsupervised clustering methods that have been previously applied to microarrays.

View details for PubMedID 18693809

Abstract

The aim of this study was to develop and evaluate a method of extracting noun phrases with full phrase structures from a set of clinical radiology reports using natural language processing (NLP) and to investigate the effects of using the UMLS(R) Specialist Lexicon to improve noun phrase identification within clinical radiology documents.The noun phrase identification (NPI) module is composed of a sentence boundary detector, a statistical natural language parser trained on a nonmedical domain, and a noun phrase (NP) tagger. The NPI module processed a set of 100 XML-represented clinical radiology reports in Health Level 7 (HL7)(R) Clinical Document Architecture (CDA)-compatible format. Computed output was compared with manual markups made by four physicians and one author for maximal (longest) NP and those made by one author for base (simple) NP, respectively. An extended lexicon of biomedical terms was created from the UMLS Specialist Lexicon and used to improve NPI performance.The test set was 50 randomly selected reports. The sentence boundary detector achieved 99.0% precision and 98.6% recall. The overall maximal NPI precision and recall were 78.9% and 81.5% before using the UMLS Specialist Lexicon and 82.1% and 84.6% after. The overall base NPI precision and recall were 88.2% and 86.8% before using the UMLS Specialist Lexicon and 93.1% and 92.6% after, reducing false-positives by 31.1% and false-negatives by 34.3%.The sentence boundary detector performs excellently. After the adaptation using the UMLS Specialist Lexicon, the statistical parser's NPI performance on radiology reports increased to levels comparable to the parser's native performance in its newswire training domain and to that reported by other researchers in the general nonmedical domain.

View details for DOI 10.1197/jamia.M1695

View details for Web of Science ID 000229384600005

View details for PubMedID 15684131

Abstract

Despite the advantages of structured data entry, much of the patient record is still stored as unstructured or semistructured narrative text. The issue of representing clinical document content remains problematic. The authors' prior work using an automated UMLS document indexing system has been encouraging but has been affected by the generally low indexing precision of such systems. In an effort to improve precision, the authors have developed a context-sensitive document indexing model to calculate the optimal subset of UMLS source vocabularies used to index each document section. This pilot study was performed to evaluate the utility of this indexing approach on a set of clinical radiology reports.A set of clinical radiology reports that had been indexed manually using UMLS concept descriptors was indexed automatically by the SAPHIRE indexing engine. Using the data generated by this process the authors developed a system that simulated indexing, at the document section level, of the same document set using many permutations of a subset of the UMLS constituent vocabularies.The precision and recall scores generated by simulated indexing for each permutation of two or three UMLS constituent vocabularies were determined.While there was considerable variation in precision and recall values across the different subtypes of radiology reports, the overall effect of this indexing strategy using the best combination of two or three UMLS constituent vocabularies was an improvement in precision without significant impact of recall.In this pilot study a contextual indexing strategy improved overall precision in a set of clinical radiology reports.

View details for DOI 10.1197/jamia.M1369

View details for Web of Science ID 000186529200009

View details for PubMedID 12925544

View details for PubMedID 12853225

Abstract

To examine whether feedback and treatment advice for depression presented to primary care physicians (PCPs) via an electronic medical record (EMR) system can potentially improve clinical outcomes and care processes for patients with major depression.Randomized controlled trial.Academically affiliated primary care practice in Pittsburgh, PA.Two hundred primary care patients with major depression on the Primary Care Evaluation of Mental Disorders (PRIME-MD) and who met all protocol-eligibility criteria.PCPs were randomly assigned to 1 of 3 levels of exposure to EMR feedback of guideline-based treatment advice for depression: "active care" (AC), "passive care" (PC), or "usual care" (UC).Patients' 3- and 6-month Hamilton Rating Scale for Depression (HRS-D) score and chart review of PCP reports of depression care in the 6 months following the depression diagnosis. Only 22% of patients recovered from their depressive episode at 6 months (HRS-D /=3 contacts with usual PCP at 6 months: 31% AC, 31% PC, 18% UC; P =.09 and antidepressant medication suggested/prescribed or baseline regimen modified at 6 months: 59% AC, 57% PC, 52% UC; P =.3).Screening for major depression, electronically informing PCPs of the diagnosis, and then exposing them to evidence-based treatment recommendations for depression via EMR has little differential impact on patients' 3- or 6-month clinical outcomes or on process measures consistent with high-quality depression care.

View details for Web of Science ID 000176923700001

View details for PubMedID 12133139

Abstract

Access to clinical data is of increasing importance to biomedical research. The pending HIPAA privacy regulations provide specific requirements for the release of protected health information. Under the regulations, biomedical researchers may utilize anonymized data, or adhere to HIPAA requirements regarding protected health information. In order to provide researchers with anonymized data from a clinical research database, we reviewed several published strategies for de-identification of protected health information. Critical analysis with respect to this project suggests that de-identification alone is problematic when applied to clinical research databases. We propose a hybrid system; utilizing secure key escrow, de-identification, and role-based access for IRB approved researchers.

View details for Web of Science ID 000189418100050

View details for PubMedID 12463824

Abstract

Academic cancer centers will be hit, simultaneously, by all three of the technology tidal waves outlined above within the next five years. In preparing for this impact one should note the central role that Internet technologies will play in providing solutions in all three areas. In addition, as the volume and size of data objects increases dramatically, having an adequate networking infrastructure in place will be crucial. So what do we do now to prepare for the future? The following five steps are suggested: (1) Establish an oncology informatics group within the cancer center to provide the necessary expertise and begin the planning process. (2) Begin implementing a secure intranet based on standard Internet technologies. (3) Work with the host medical center and external agencies to determine who will pay for and implement a high-bandwidth networking infrastructure. (4) Recruit a bioinformatician who can help implement technologies to take advantage of the genomics data wave when it hits. (5) Ensure that the cancer center's EMR system can support cancer protocol data and facilitate the retrieval and delivery of the complex digital imaging data that are in our future.

View details for PubMedID 10439599

Abstract

A wide range of imaging technologies are becoming increasingly important to the practice of medicine. In addition, many medical specialties are highly visual, independent of their use of new imaging modalities. Because today's medical record contains text, images, and physiologic signals, it is inherently multimedia in nature. However, most electronic medical record systems handle only the textual portion of the patient record, resulting in a fragmentation of the database that physicians need to make timely, effective clinical decisions. Advances in database-, storage-, data-compression, and networking technologies will facilitate the development of multimedia electronic medical record systems for the 21st century. These systems will become widely used over the next decade, and in addition to enhancing patient care, will also present new opportunities for using clinical imaging data for biomedical research and education.

View details for Web of Science ID 000078705800016

View details for PubMedID 10065056

Abstract

Using the Agency for Health Care Policy and Research Depression Guideline Panel's recommendations as its focus, this article describes a step-by-step approach for disseminating a paper-based depression guideline to primary care physicians via a commercially available electronic medical record (EMR) system.Description of the author's approach to disseminate an evidence-based depression treatment guideline to a group of primary care physicians using a commercially available EMR system and to evaluate the results.We review clinical considerations and practical barriers faced in this process with the expectation that our experiences can guide others attempting to disseminate psychiatric treatment guideline via EMR systems.The EMR offers critical efficiencies in disseminating state-of-the-art clinical practice guidelines and in directing the primary care physicians' use of them. Still, well-designed, randomized controlled trials are necessary to demonstrate their effectiveness at enhancing patient outcomes for major depression in primary care settings.

View details for Web of Science ID 000084640400002

View details for PubMedID 10642902

Abstract

Medicine is increasingly image-intensive. The central importance of imaging technologies such as computerized tomography and magnetic resonance imaging in clinical decision making, combined with the trend to store many "traditional" clinical images such as conventional radiographs, microscopic pathology and dermatology images in digital format present both challenges and an opportunities for the designers of clinical information systems. The emergence of Multimedia Electronic Medical Record Systems (MEMRS), architectures that integrate medical images with text-based clinical data, will further hasten this trend. The development of these systems, storing a large and diverse set of medical images, suggests that in the future MEMRS will become important digital libraries supporting patient care, research and education. The representation and retrieval of clinical images within these systems is problematic as conventional database architectures and information retrieval models have, until recently, focused largely on text-based data. Medical imaging data differs in many ways from text-based medical data but perhaps the most important difference is that the information contained within imaging data is fundamentally knowledge-based. New representational and retrieval models for clinical images will be required to address this issue. Within the Image Engine multimedia medical record system project at the University of Pittsburgh we are evolving an approach to representation and retrieval of medical images which combines semantic indexing using the UMLS Metathesuarus, image content-based representation and knowledge-based image analysis.

View details for Web of Science ID 000171768600172

View details for PubMedID 9929345

Abstract

The rapid adoption of Internet-accessible information resources by the clinical community, has resulted in an exponential growth in the variety and type of clinical information resources along with an increasing diversity of information technologies to deliver clinical information. To date, little formal work has been done to investigate the significance of new information technologies such as Internet-based digital libraries and multimedia record systems on clinical information need or information seeking behavior. In the work described in this paper, we highlight some results from our recent multimethod research design and investigation of the information-seeking behavior of Pittsburgh area medical oncologists to argue for the use of a multimethod research design as an essential component of any investigation of clinical information need and information-seeking behavior in the era of the digital medical library.

View details for Web of Science ID 000171768600128

View details for PubMedID 9929301

Abstract

The Internet is rapidly evolving from a resource used primarily by the research community to a true global information network offering a wide range of databases and services. This evolution presents many opportunities for improved access to biomedical information, but Internet-based resources have often been difficult for the non-expert to develop and use. The World Wide Web (WWW) supports an inexpensive, easy-to-use, cross-platform, graphic interface to the Internet that may radically alter the way we retrieve and disseminate medical data. This paper summarizes the Internet and hypertext origins of the WWW, reviews WWW-specific technologies, and describes current and future applications of this technology in medicine and medical informatics. The paper also includes an appendix of useful biomedical WWW servers.

View details for Web of Science ID A1996TN79200001

View details for PubMedID 8750386

Abstract

This paper describes WebReport, a World Wide Web (WWW) client for the Image Engine multimedia clinical information system under development at the University of Pittsburgh. WebReport uses advanced HTML features such as frames, forms, tables and inline JPEG image display to provide an easy to use system for retrieving and viewing diagnostic images and reports generated by clinical procedures such as gastrointestinal endoscopy, radiology and surgical pathology. WebReport implements a number of WWW client-side features, such as HTML forms data entry verification and makes extensive use of the JavaScript programming language. The WebReport system uses a number of approaches for ensuring the confidentiality and security of patient data transmitted over the InterNet.

View details for PubMedID 8947679

Abstract

Image Engine is multi-user, client-server database for the storage, retrieval and sharing of a wide range of digitized biomedical images under development at the University of Pittsburgh. This paper provides an overview of the system and describes the use of agent-based technology to integrate clinical information from the Image Engine database and the MARS clinical information system at the University of Pittsburgh Medical Center. Agent-mediated links provide a mechanism for combining clinical data from multiple databases to create a unified, multimedia view of the electronic medical record.

View details for PubMedID 8563320

Abstract

The rapid growth of diagnostic-imaging technologies over the past two decades has dramatically increased the amount of nontextual data generated in clinical medicine. The architecture of traditional, text-oriented, clinical information systems has made the integration of digitized clinical images with the patient record problematic. Systems for the classification, retrieval, and integration of clinical images are in their infancy. Recent advances in high-performance computing, imaging, and networking technology now make it technologically and economically feasible to develop an integrated, multimedia, electronic patient record. As part of The National Library of Medicine's Biomedical Applications of High-Performance Computing and Communications program, we plan to develop Image Engine, a prototype microcomputer-based system for the storage, retrieval, integration, and sharing of a wide range of clinically important digital images. Images stored in the Image Engine database will be indexed and organized using the Unified Medical Language System Metathesaurus and will be dynamically linked to data in a text-based, clinical information system. We will evaluate Image Engine by initially implementing it in three clinical domains (oncology, gastroenterology, and clinical pathology) at the University of Pittsburgh Medical Center.

View details for Web of Science ID A1995QC12200011

View details for PubMedID 7703940

Abstract

The United States National Library of Medicine's (NLM) MEDLINE database is the largest and most widely used medical bibliographic database. MEDLINE is manually indexed with NLM's Medical Subject Headings (MeSH) vocabulary. Using MeSH, a searcher can potentially create powerful and unambiguous MEDLINE queries. This article reviews the structure and use of MeSH, directed toward the nonexpert, and outlines how MeSH may help resolve a number of common difficulties encountered when searching MEDLINE. The increasing importance of the MEDLINE database as an information resource and the trend toward individuals performing their own bibliographic searches makes it crucial that health care professionals become familiar with MeSH.

View details for Web of Science ID A1994NE22800033

View details for PubMedID 8151853

Abstract

This paper describes Image Engine, an object-oriented, microcomputer-based, multimedia database designed to facilitate the storage and retrieval of digitized biomedical still images, video, and text using inexpensive desktop computers. The current prototype runs on Apple Macintosh computers and allows network database access via peer to peer file sharing protocols. Image Engine supports both free text and controlled vocabulary indexing of multimedia objects. The latter is implemented using the TView thesaurus model developed by the author. The current prototype of Image Engine uses the National Library of Medicine's Medical Subject Headings (MeSH) vocabulary (with UMLS Meta-1 extensions) as its indexing thesaurus.

View details for PubMedID 8130596