Health Services Research & Development

Go to the ORD website
Go to the QUERI website

HIR 10-001 – HSR&D Study

New | Current | Completed | DRA | DRE | Portfolios/Projects | Centers | QUERI | Career Development Projects

HIR 10-001
Pro-WATCH: Epidemiology of Medically Unexplained Syndromes
Matthew H. Samore MD
VA Salt Lake City Health Care System, Salt Lake City, UT
Salt Lake City, UT
Funding Period: September 2010 - September 2015

The service-directed research proposal entitled "Protecting Warfighters using Algorithms for Test Processing to Capture Health Events (Pro - WATCH)" focused on the post-deployment health status of Iraq and Afghan veterans. We proposed to develop and implement informatics tools to monitor, detect, and prevent health problems in the OEF/OIF veteran population.

The objectives of this study are to: (a) use natural language processing (NLP) techniques to extract information about symptoms and related concepts from VA clinical notes; (b) develop algorithms to examine phenotypes of OEF/OIF Veterans with syndromic diagnoses (c) characterize the epidemiology of medically-unexplained syndromes in deployed Veterans.

An NLP pipeline (Sophia) was developed to perform high-throughput concept extraction. The system uses a novel look-up algorithm to identify Unified Medical Language System (UMLS) concepts in text documents. This pipeline makes it feasible to process extremely large datasets containing millions of documents.

Algorithms were developed to support a variety of key tasks. Machine learning algorithms to eliminate false-positive mentions of symptoms and to detect assertions of adverse childhood experiences. Rule-based algorithms were developed to classify medically unexplained syndromes on the basis of ICD9 codes. Algorithms were also developed to classify templates within clinic notes.

Annotations were performed by human reviewers to establish reference standards for training modules within the NLP pipeline. A total of 1000 documents were annotated for presence of symptom concepts.

Ontologies and vocabularies served as crucial methodological underpinnings for this project. We implemented a novel method to map symptoms into anatomically related categories. Starting from root concepts within the UMLS Metathesaurus, ancestor-descendent relationships were traversed to find symptoms and signs within a given organ system.

We extended an existing top level ontology to represent medically unexplained syndromes. The purpose was to provide a clear definition of medically unexplained syndromes and position medically unexplained syndromes within a hierarchy of diseases, diagnoses, and related terms.

Statistical models including logistic regression were used to characterize the relationship between adverse childhood experiences and a variety of types of diagnoses, including mental health disorders and medically unexplained syndromes. Poisson regression was used to examine healthcare utilization among deployed Veterans who carried a diagnosis of fibromyalgia.

In comparison to two other NLP pipelines, MetaMap and cTAKES, Sophia was demonstrated to be considerably faster in processing documents and similar (or better) in overall accuracy. A manuscript describing these results was accepted at the American Medical Informatics 2014 Annual Symposium.

The NLP module to extract psychosocial concepts from VA notes was validated in a study of 316,355 high yield documents. The module demonstrated excellent performance, with a precision of 80%. The results were published this year in the Journal of the American Medical Informatics Association.

Our method to map symptoms to organ systems was used to categorize a total of 115,000 concepts. Overall, 90% of 668 unique symptom and sign concepts in a 750 document corpus were correctly mapped to their organ systems. A manuscript describing this work is in revision for resubmission.

In the epidemiological analysis of Gulf War Veterans, adverse childhood experiences were found to be strongly associated with mental health disorders and weakly associated with medically unexplained syndromes. The manuscript describing the results of this analysis is under review. A paper describing an epidemiological analysis of medically unexplained syndromes in women OEF/OIF veterans is currently undergoing revision prior to resubmission. Fibromyalgia was the most common medically unexplained syndrome diagnosis in this population. The paper describing the analysis of healthcare utilization in Veterans with a diagnosis of fibromyalgia is currently under review.

Our work is intended to directly inform the efforts of clinical programs for OEF/OIF Veterans and to complement other studies of post-deployment health in Veterans, including the Millennium Cohort study.


Journal Articles

  1. Mohanty AF, Muthukutty A, Carter ME, Palmer MN, Judd J, Helmer D, McAndrew LM, Garvin JH, Samore MH, Gundlapalli AV. Chronic multisymptom illness among female Veterans deployed to Iraq and Afghanistan. Medical care. 2015 Apr 1; 53(4 Suppl 1):S143-8.
  2. Fortenberry KT, Berg CA, King PS, Stump T, Butler JM, Pham PK, Wiebe DJ. Longitudinal trajectories of illness perceptions among adolescents with type 1 diabetes. Journal of Pediatric Psychology. 2014 Aug 1; 39(7):687-96.
  3. Jones B, Gundlapalli AV, Jones JP, Brown SM, Dean NC. Admission decisions and outcomes of community-acquired pneumonia in the homeless population: a review of 172 patients in an urban setting. American journal of public health. 2013 Dec 1; 103 Suppl 2:S289-93.
  4. DeLisle S, Kim B, Deepak J, Siddiqui T, Gundlapalli A, Samore M, D'Avolio L. Using the electronic medical record to identify community-acquired pneumonia: toward a replicable automated strategy. PLoS ONE. 2013 Aug 13; 8(8):e70944.
  5. Toth DJ, Gundlapalli AV, Schell WA, Bulmahn K, Walton TE, Woods CW, Coghill C, Gallegos F, Samore MH, Adler FR. Quantitative models of the dose-response and time course of inhalational anthrax in humans. PLoS pathogens. 2013 Aug 1; 9(8):e1003555.
Conference Presentations

  1. Meystre S, Samore MH. Domain and Application Ontologies for Medically Unexplained Syndromes. Paper presented at: American Medical Informatics Association Annual Symposium; 2012 Nov 3; Chicago, IL.
  2. Gundlapalli AV, Samore MH, Palmer M, Tuteja AK, Carter M, Shen S, South B, Forbush T, Divita G. Annotation of Symptoms in VA Clinical Documents. Poster session presented at: Integrating Data for Analysis, Anonymization, and Sharing Annual Conference; 2012 Sep 29; La Jolla, California.
  3. Samore MH, Nelson R. Screening for Homelessness in the Free Text of VA Clinical Documents using Natural Language Processing. Poster session presented at: VA HSR&D / QUERI National Meeting; 2012 Jul 16; National Harbor, MD.
  4. Forbush T, Gundlapalli AV, Palmer M, Shen S, South B, Divita G, Carter M, Redd AM, Butler J, Samore MH. Sitting on Pins and Needles. Paper presented at: American Medical Informatics Association Spring Congress; 2012 Mar 20; San Francisco, CA.
  5. South B, Palmer M, Shen S, Divita G, DuVall SL, Samore MH, Gundlapalli AV. Using Clinician Mental Models to Guide Annotation of Medically Unexplained Symptoms and Syndromes found in VA Clinical Documents. Paper presented at: International Society for Disease Surveillance Annual Conference; 2011 Dec 7; Park City, UT.
  6. Zeng Q, Samore MH, Divita G. Finding Medically Unexplained Symptoms within VA Clinical Documents using v3NLP. Poster session presented at: International Society for Disease Surveillance Annual Conference; 2011 Dec 7; Park City , UT.
  7. Palmer M, South B, Shen S, Tuteja AK, Divita G, Samore MH, Gundlapalli AV. Identification and Classification of Medically Unexplained Symptoms in VA Clinical Documents. Poster session presented at: VA HSR&D National Meeting; 2011 Feb 16; National Harbor, MD.
  8. South B, Palmer M, Shen S, Divita G, DuVall SL, Samore MH. Using Clinician Mental Models to Guide Annotation of Medically Unexplained Symptoms and Syndromes found in VA Clinical Documents. Poster session presented at: VA HSR&D National Meeting; 2011 Feb 16; National Harbor, MD.

DRA: Autoimmunity, Allergy, and Immunology, Cardiovascular Disease, Military and Environmental Exposures
DRE: Epidemiology, Diagnosis, Research Infrastructure
Keywords: Clinical Diagnosis and Screening, Healthcare Algorithms, Information Management, Knowledge Integration, Natural Language Processing, Reintegration Post-Deployment, Risk Factors, Surveillance
MeSH Terms: none