Clement J McDonald

National Library of Medicine, 베서스다, Maryland, United States

Are you Clement J McDonald?

Claim your profile

Publications (217)1100.86 Total impact

  • [Show abstract] [Hide abstract]
    ABSTRACT: Clinical documents made available for secondary use play an increasingly important role in discovery of clinical knowledge, development of research methods, and education. An important step in facilitating secondary use of clinical document collections is easy access to descriptions and samples that represent the content of the collections. This paper presents an approach to developing a collection of radiology examinations, including both the images and radiologist narrative reports, and making them publicly available in a searchable database. The authors collected 3996 radiology reports from the Indiana Network for Patient Care and 8121 associated images from the hospitals' picture archiving systems. The images and reports were de-identified automatically and then the automatic de-identification was manually verified. The authors coded the key findings of the reports and empirically assessed the benefits of manual coding on retrieval. The automatic de-identification of the narrative was aggressive and achieved 100% precision at the cost of rendering a few findings uninterpretable. Automatic de-identification of images was not quite as perfect. Images for two of 3996 patients (0.05%) showed protected health information. Manual encoding of findings improved retrieval precision.Conclusion Stringent de-identification methods can remove all identifiers from text radiology reports. DICOM de-identification of images does not remove all identifying information and needs special attention to images scanned from film. Adding manual coding to the radiologist narrative reports significantly improved relevancy of the retrieved clinical documents. The de-identified Indiana chest X-ray collection is available for searching and downloading from the National Library of Medicine ( Published by Oxford University Press on behalf of the American Medical Informatics Association 2015. This work is written by US Government employees and is in the public domain in the US.
    Journal of the American Medical Informatics Association 07/2015; DOI:10.1093/jamia/ocv080 · 3.93 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Electronic health records have the potential to improve the care of patients with chronic medical conditions. CKD provides a unique opportunity to show this potential: the disease is common in the United States, there is significant room to improve CKD detection and management, CKD and its related conditions are defined primarily by objective laboratory data, CKD care requires collaboration by a diverse team of health care professionals, and improved access to CKD-related data would enable identification of a group of patients at high risk for multiple adverse outcomes. However, to realize the potential for improvement in CKD-related care, electronic health records will need to provide optimal functionality for providers and patients and interoperability across multiple health care settings. The goal of the National Kidney Disease Education Program Health Information Technology Working Group is to enable and support the widespread interoperability of data related to kidney health among health care software applications to optimize CKD detection and management. Over the course of the last 2 years, group members met to identify general strategies for using electronic health records to improve care for patients with CKD. This paper discusses these strategies and provides general goals for appropriate incorporation of CKD-related data into electronic health records and corresponding design features that may facilitate (1) optimal care of individual patients with CKD through improved access to clinical information and decision support, (2) clinical quality improvement through enhanced population management capabilities, (3) CKD surveillance to improve public health through wider availability of population-level CKD data, and (4) research to improve CKD management practices through efficiencies in study recruitment and data collection. Although these strategies may be most effectively applied in the setting of CKD, because it is primarily defined by laboratory abnormalities and therefore, an ideal computable electronic health record phenotype, they may also apply to other chronic diseases. Copyright © 2015 by the American Society of Nephrology.
    Clinical Journal of the American Society of Nephrology 06/2015; DOI:10.2215/CJN.00940115 · 5.25 Impact Factor
  • Journal of the American Medical Informatics Association 05/2015; DOI:10.1093/jamia/ocv066 · 3.93 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Newborn screening (NBS) has high-stakes health implications and requires rapid and effective communication between many people and organizations. Multiple NBS stakeholders worked together to create national guidance for reporting NBS results with HL7 (Health Level 7) messages that contain LOINC (Logical Observation Identifiers Names and Codes) and SNOMED-CT (Systematized Nomenclature of Medicine-Clinical Terms) codes, report quantitative test results, and use standardized computer-readable UCUM units of measure. This guidance (a LOINC panel and an example annotated HL7 message) enables standard HL7 v2.5.1 laboratory messages to carry the information required for reporting NBS results. Other efforts include HL7 implementation guides for reporting point-of-care (POC) NBS results as well as standardizing follow-up of patients diagnosed with conditions identified through NBS. If the guidance is used nationally, regional and national registries can aggregate results from state programs to facilitate research and quality assurance and help ensure continuity of operations following a disaster situation. Published by Elsevier Inc.
    Seminars in perinatology 04/2015; 8(3). DOI:10.1053/j.semperi.2015.03.003 · 2.42 Impact Factor
  • Jamalynne Deckard · Clement J McDonald · Daniel J Vreeman
    [Show abstract] [Hide abstract]
    ABSTRACT: Electronic reporting of genetic testing results is increasing, but they are often represented in diverse formats and naming conventions. Logical Observation Identifiers Names and Codes (LOINC) is a vocabulary standard that provides universal identifiers for laboratory tests and clinical observations. In genetics, LOINC provides codes to improve interoperability in the midst of reporting style transition, including codes for cytogenetic or mutation analysis tests, specific chromosomal alteration or mutation testing, and fully structured discrete genetic test reporting. LOINC terms follow the recommendations and nomenclature of other standards such as the Human Genome Organization Gene Nomenclature Committee's terminology for gene names. In addition to the narrative text they report now, we recommend that laboratories always report as discrete variables chromosome analysis results, genetic variation(s) found, and genetic variation(s) tested for. By adopting and implementing data standards like LOINC, information systems can help care providers and researchers unlock the potential of genetic information for delivering more personalized care. © The Author 2015. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For Permissions, please email: For numbered affiliations see end of article.
  • JAMA Internal Medicine 09/2014; 174(11). DOI:10.1001/jamainternmed.2014.4506 · 13.25 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Recent research has suggested that high vitamin B12 levels may be associated with increased mortality after ICU admission. However, it is known that impaired liver function may lead to elevated B12 since B12 is metabolized through the liver, and therefore high B12 levels may serve as a proxy for poor liver function. The aim of this study is to assess the impact that liver function and liver disease have on the relationship between high vitamin B12 levels and mortality in the ICU. We performed an observational cohort study using ICU data that were collected from patients admitted to four ICU types (medical, surgical, cardiac care and cardiac surgery recovery) in one large urban hospital from 2001 to 2008. We analyzed the medical records of 1,684 adult patients (age ≥ 18 years) who had vitamin B12 and liver function measurements up to 14 days prior to ICU admission or within 24 hours after admission. While we found an association between high B12 and mortality when we did not control for any potential confounders, after we adjusted for liver function and liver disease, no significant association existed between B12 and mortality using multivariable logistic regression (30-day mortality: OR=1.18, 95% CI 0.81 to 1.72, p=0.3890; 90-day mortality: OR=1.20, 95% CI 0.84 to 1.71, p=0.3077). Elevated B12 levels are not a significant predictor of mortality after ICU admission when liver function is controlled for, and may instead be a proxy for poor liver function.
    e-SPEN Journal 04/2014; 9(2):e76-e83. DOI:10.1016/j.clnme.2014.01.003
  • [Show abstract] [Hide abstract]
    ABSTRACT: To develop a generalizable method for identifying patient cohorts from electronic health record (EHR) data-in this case, patients having dialysis-that uses simple information retrieval (IR) tools. We used the coded data and clinical notes from the 24 506 adult patients in the Multiparameter Intelligent Monitoring in Intensive Care database to identify patients who had dialysis. We used SQL queries to search the procedure, diagnosis, and coded nursing observations tables based on ICD-9 and local codes. We used a domain-specific search engine to find clinical notes containing terms related to dialysis. We manually validated the available records for a 10% random sample of patients who potentially had dialysis and a random sample of 200 patients who were not identified as having dialysis based on any of the sources. We identified 1844 patients that potentially had dialysis: 1481 from the three coded sources and 1624 from the clinical notes. Precision for identifying dialysis patients based on available data was estimated to be 78.4% (95% CI 71.9% to 84.2%) and recall was 100% (95% CI 86% to 100%). Combining structured EHR data with information from clinical notes using simple queries increases the utility of both types of data for cohort identification. Patients identified by more than one source are more likely to meet the inclusion criteria; however, including patients found in any of the sources increases recall. This method is attractive because it is available to researchers with access to EHR data and off-the-shelf IR tools.
    Journal of the American Medical Informatics Association 01/2014; 21(5). DOI:10.1136/amiajnl-2013-001915 · 3.93 Impact Factor
  • Selcuk Ozturk · Mehmet Kayaalp · Clement J McDonald
    [Show abstract] [Hide abstract]
    ABSTRACT: Interpreting patient's medication history from long textual data can be unwieldy especially in emergency care. We developed a real-time software application that converts one-year-long patient prescription history data into a visually appealing and information-rich timeline chart. The chart can be digested by healthcare providers quickly; hence, it could be an invaluable clinical tool when the rapid response time is crucial as in stroke or severe trauma cases. Furthermore, the visual clarity of the displayed information may help providers minimize medication errors. The tool has been deployed at the emergency department of a trauma center. Due to its popularity, we developed another version of this tool. It provides more granular drug dispensation information, which clinical pharmacists find very useful in their routine medication-reconciliation efforts.
    AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium 01/2014; 2014:963-8.
  • Mehmet Kayaalp · Allen C Browne · Zeyno A Dodd · Pamela Sagan · Clement J McDonald
    [Show abstract] [Hide abstract]
    ABSTRACT: The Privacy Rule of Health Insurance Portability and Accountability Act requires that clinical documents be stripped of personally identifying information before they can be released to researchers and others. We have been developing a software application, NLM Scrubber, to de-identify narrative clinical reports. We compared NLM Scrubber with MIT's and MITRE's de-identification systems on 3,093 clinical reports about 1,636 patients. The performance of each system was analyzed on address, date, and alphanumeric identifier recognition separately. Their overall performance on de-identification and on conservation of the remaining clinical text was analyzed as well. NLM Scrubber's sensitivity on de-identifying these identifiers was 99%. It's specificity on conserving the text with no personal identifiers was 99% as well. The current version of the system recognizes and redacts patient names, alphanumeric identifiers, addresses and dates. We plan to make the system available prior to the AMIA Annual Symposium in 2014.
    AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium 01/2014; 2014:767-76.
  • Allen C Browne · Mehmet Kayaalp · Zeyno A Dodd · Pamela Sagan · Clement J McDonald
    [Show abstract] [Hide abstract]
    ABSTRACT: We created a Gold Standard corpus comprised over 20,000 records of annotated narrative clinical reports for use in the training and evaluation of NLM Scrubber, a de-identification software system for medical records. Our experience with designing the corpus demonstrated the conceptual complexity of the task.
    AMIA ... Annual Symposium proceedings / AMIA Symposium. AMIA Symposium 01/2014; 2014:353-8.
  • Clement J McDonald
    JAMA Internal Medicine 10/2013; 173(18):1755-1756. DOI:10.1001/jamainternmed.2013.9332 · 13.25 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: To understand the factors that influence success in scrubbing personal names from narrative text. We developed a scrubber, the NLM Name Scrubber (NLM-NS), to redact personal names from narrative clinical reports, hand tagged words in a set of gold standard narrative reports as personal names or not, and measured the scrubbing success of NLM-NS and that of four other scrubbing/name recognition tools (MIST, MITdeid, LingPipe, and ANNIE/GATE) against the gold standard reports. We ran three comparisons which used increasingly larger name lists. The test reports contained more than 1 million words, of which 2388 were patient and 20 160 were provider name tokens. NLM-NS failed to scrub only 2 of the 2388 instances of patient name tokens. Its sensitivity was 0.999 on both patient and provider name tokens and missed fewer instances of patient name tokens in all comparisons with other scrubbers. MIST produced the best all token specificity and F-measure for name instances in our most relevant study (study 2), with values of 0.997 and 0.938, respectively. In that same comparison, NLM-NS was second best, with values of 0.986 and 0.748, respectively, and MITdeid was a close third, with values of 0.985 and 0.796 respectively. With the addition of the Clinical Center name list to their native name lists, Ling Pipe, MITdeid, MIST, and ANNIE/GATE all improved substantially. MITdeid and Ling Pipe gained the most-reaching patient name sensitivity of 0.995 (F-measure=0.705) and 0.989 (F-measure=0.386), respectively. The privacy risk due to two name tokens missed by NLM-NS was statistically negligible, since neither individual could be distinguished among more than 150 000 people listed in the US Social Security Registry. The nature and size of name lists have substantial influences on scrubbing success. The use of very large name lists with frequency statistics accounts for much of NLM-NS scrubbing success.
    Journal of the American Medical Informatics Association 09/2013; 21(3). DOI:10.1136/amiajnl-2013-001689 · 3.93 Impact Factor
  • Source
    Mehmet Kayaalp · Allen Browne · Zeyno A Dodd · Pamela Sagan · Clement J McDonald
  • Source
    Kin Wah Fung · Mehmet Kayaalp · Fiona Callaghan · Clement J McDonald
    [Show abstract] [Hide abstract]
    ABSTRACT: STUDY OBJECTIVE: Medication history is an essential part of patient assessment in emergency care. Patient-reported medication history can be incomplete. We study whether an electronic pharmacy-sourced prescription record can supplement the patient-reported history. METHODS: In a community hospital, we compared the patient-reported history obtained by triage nurses to a proprietary electronic pharmacy record in all emergency department (ED) patients during 3 months. RESULTS: Of 9,426 triaged patients, 5,001 (53%) had at least 1 (mean 7.7) prescription medication in the full-year electronic pharmacy record. Counting only recent prescription medications (supply lasting to at least 7 days before the ED visit), 3,688 patients (39%) had at least 1 (mean 4.0) recent medication. After adjustment for possible false-positive results, recent electronic prescription medication record enriched the patient-reported history by 28% (adding 1.1 drugs per patient). However, only 60% of patients with any active prescription medications from either source had any recent prescription medications in their electronic pharmacy record. CONCLUSION: The electronic pharmacy prescription record augments the manually collected history.
    Annals of emergency medicine 05/2013; 62(3). DOI:10.1016/j.annemergmed.2013.04.014 · 4.33 Impact Factor
  • Source
  • Swapna Abhyankar · Clement J McDonald
    JAMA The Journal of the American Medical Association 04/2013; 309(16):1680-1. DOI:10.1001/jama.2013.3092 · 30.39 Impact Factor
  • Clement J McDonald · Daniel J Vreeman · Swapna Abhyankar
    [Show abstract] [Hide abstract]
    ABSTRACT: The same code standards should be used in both research and clinical care to facilitate data integration across domains.
    Science translational medicine 04/2013; 5(179):179le1. DOI:10.1126/scitranslmed.3005700 · 14.41 Impact Factor
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Introduction Two thirds of United States adults are overweight or obese, which puts them at higher risk of developing chronic diseases and of death compared with normal-weight individuals. However, recent studies have found that overweight and obesity by themselves may be protective in some contexts, such as hospitalization in an intensive care unit (ICU). Our objective was to determine the relation between body mass index (BMI) and mortality at 30 days and 1 year after ICU admission. Methods We performed a cohort analysis of 16,812 adult patients from MIMIC-II, a large database of ICU patients at a tertiary care hospital in Boston, Massachusetts. The data were originally collected during the course of clinical care, and we subsequently extracted our dataset independent of the study outcome. Results Compared with normal-weight patients, obese patients had 26% and 43% lower mortality risk at 30 days and 1 year after ICU admission, respectively (odds ratio (OR), 0.74; 95% confidence interval (CI), 0.64 to 0.86) and 0.57 (95% CI, 0.49 to 0.67)); overweight patients had nearly 20% and 30% lower mortality risk (OR, 0.81; 95% CI, 0.70 to 0.93) and OR, 0.68 (95% CI, 0.59 to 0.79)). Severely obese patients (BMI ≥ 40 kg/m2) did not have a significant survival advantage at 30 days (OR, 0.94; 95% CI, 0.74 to 1.20), but did have 30% lower mortality risk at 1 year (OR, 0.70 (95% CI, 0.54 to 0.90)). No significant difference in admission acuity or ICU and hospital length of stay was found across BMI categories. Conclusion Our study supports the hypothesis that patients who are overweight or obese have improved survival both 30 days and 1 year after ICU admission.
    Critical care (London, England) 12/2012; 16(6):R235. DOI:10.1186/cc11903
  • Clement J McDonald · William M Tierney
    Health Affairs 06/2012; 31(6):1365; atuhor reply 1366. DOI:10.1377/hlthaff.2012.0471 · 4.64 Impact Factor

Publication Stats

8k Citations
1,100.86 Total Impact Points


  • 2010–2015
    • National Library of Medicine
      베서스다, Maryland, United States
    • University of Utah
      • Department of Biomedical Informatics
      Salt Lake City, UT, United States
    • Washington DC VA Medical Center
      Washington, Washington, D.C., United States
  • 2009–2015
    • National Institutes of Health
      • National Center for Biotechnology Information
      베서스다, Maryland, United States
  • 1977–2011
    • Indiana University-Purdue University Indianapolis
      • • Department of Medicine
      • • Division of General Internal Medicine and Geriatrics
      Indianapolis, Indiana, United States
  • 1975–2010
    • Regenstrief Institute, Inc.
      Indianapolis, Indiana, United States
  • 2003–2006
    • Indiana University-Purdue University School of Medicine
      • Department of Medicine
      Indianapolis, Indiana, United States
  • 2002
    • Indiana University Bloomington
      Bloomington, Indiana, United States
  • 1998
    • Moor Instruments
      Axminster, England, United Kingdom
  • 1996
    • Richard L. Roudebush VA Medical Center
      Indianapolis, Indiana, United States