A Proof of Concept for Assessing Emergency Room Use with Primary Care Data and Natural Language Processing

J. St-Maurice; M.-H. Kuo; P. Gooch

doi:10.3414/ME12-01-0012

Methods of Information in Medicine, Table of Contents

Methods Inf Med 2013; 52(01): 33-42
DOI: 10.3414/ME12-01-0012

Original Articles

Schattauer GmbH

A Proof of Concept for Assessing Emergency Room Use with Primary Care Data and Natural Language Processing^[*]

J. St-Maurice

¹School of Health and Life Sciences and Community Services, Conestoga College Institute of Technology and Advanced Learning, Kitchener, Ontario, Canada

²School of Health Information Science, University of Victoria, Victoria, British Columbia, Canada

,

M.-H. Kuo

²School of Health Information Science, University of Victoria, Victoria, British Columbia, Canada

,

P. Gooch

³Centre for Health Informatics, City University, London, UK

› Author Affiliations

Abstract

Summary

Objective: The objective of this study was to undertake a proof of concept that demonstrated the use of primary care data and natural language processing and term extraction to assess emergency room use. The study extracted biopsychosocial concepts from primary care free text and related them to inappropriate emergency room use through the use of odds ratios.

Methods: De-identified free text notes were extracted from a primary care clinic in Guelph, Ontario and analyzed with a software toolkit that incorporated General Architecture for Text Engineering (GATE) and MetaMap components for natural language processing and term extraction.

Results: Over 10 million concepts were extracted from 13,836 patient records. Codes found in at least 1% percent of the sample were regressed against inappropriate emergency room use. 77 codes fell within the realm of biopsychosocial, were very statistically significant (p < 0.001) and had an OR > 2.0. Thematically, these codes involved mental health and pain related concepts.

Conclusions: Analyzed thematically, mental health issues and pain are important themes; we have concluded that pain and mental health problems are primary drivers for inappropriate emergency room use. Age and sex were not significant. This proof of concept demonstrates the feasibly of combining natural language processing and primary care data to analyze a system use question. As a first work it supports further research and could be applied to investigate other, more complex problems.

Keywords

Primary care data - natural language processing - term extraction - emergency room inappropriate use - measurement methodology - service utilization

Full Text

References

References
1 Carret MLV, Fassa ACG, Domingues MR. Inappropriate use of emergency services: a systematic review of prevalence and associated factors. Cadernos de Saúde Pública 2009; 25 (01) 7-28.
2 Field S, Lantz A. Emergency department use by CTAS Levels IV and V patients. Canadian Journal of Emergency Medicine 2006; 8 (05) 317-322.
3 de Lusignan S. What is primary care informatics?. Journal of the American Medical Informatics Association 2003; 10 (04) 304-309.
4 St-Maurice J. Primary care data: gold or pyrite? A Literature Review. Journal of Health Information Management 2011; 25 (02) 27-31.
5 Davis J, Fujimoto R, Chan H, Juarez D. Identifying characteristics of patients with low urgency emergency department visits in a managed care setting. Managed Care 2010; 19 (10) 38
6 Carret MLV, Fassa AG, Kawachi I. Demand for emergency health service: factors associated with inappropriate use. BMC Health Services Research 2007; 7: 131
7 Béland F, Lemay A, Boucher M. Patterns of visits to hospital-based emergency rooms. Social science medicine 1998; 47 (02) 165-179.
8 De Vos P, Vanlerberghe V, Rodríguez A, García R, Bonet M, Van der Stuyft P. Uses of first line emergency services in Cuba. Health policy 2008; 85 (01) 94-104.
9 Lang T, Davido a, Diakité B, Agay E, Viel JF, Flicoteaux B. Non-urgent care in the hospital medical emergency department in France: how much and which health needs does it reflect?. Journal of Epidemiology and Community Health 1996; 50 (04) 456-462.
10 David M, Schwartau I, Anand Pant H, Borde T. Emergency outpatient services in the city of Berlin: Factors for appropriate use and predictors for hospital admission. European journal of emergency medicine: Official Journal of the European Society for Emergency Medicine 2006; 13 (06) 352-357.
11 Bianco A, Pileggi C, Angelillo IF. Non-urgent visits to a hospital emergency department in Italy. Public health 2003; 117 (04) 250-255.
12 Shah NM, Shah MA, Behbehani J. Predictors of non-urgent utilization of hospital emergency services in Kuwait. Social Science Medicine 1996; 42 (09) 1313-1323.
13 Selasawati HG, Naing L, Wan Aasim WA, Winn T, Rusli BN. Factors associated with inappropriate utilisation of emergency department services. Asia-Pacific Journal of Public Health 2007; 19 (02) 29-36.
14 Loria-Castellanos J, Flores-Maciel L, Márquez-Ávila G, Valladares-Aranda MA. Frequency and factors associated with misuse of hospital emergency services. Cir Cir 2010; 78 (06) 505-510.
15 Pereira S, Esilva A, Quintas M, Almeida J, Marujo C, Pizarro M. et al Appropriateness of emergency department visits in a Portuguese University hospital. Annals of Emergency Medicine 2001; 37 (06) 580-586.
16 Tsai JC-H, Liang Y-W. Pearson WS. Utilization of emergency department in patients with non-urgent medical problems: patient preference and emergency department convenience. Journal of the Formosan Medical Association 2010; 109 (07) 533-542.
17 Oktay C, Cete Y, Eray O, Pekdemir M, Gunerli A. Appropriateness of emergency department visits in a Turkish university hospital. Public Health 2003; 44 (05) 585-591.
18 Martin A, Martin C, Martin PB, Martin P a B, Green G, Eldridge S. “Inappropriate” attendance at an accident and emergency department by adults registered in local general practices: how is it related to their use of primary care?. Journal of Health Services Research Policy 2002; 7 (03) 160-165.
19 Liu T, Sayre MR, Carleton SC. Emergency medical care: types, trends, and factors related to nonurgent visits. Academic Emergency Medicine 1999; 6 (11) 1147-1152.
20 Selasawati HG, Naing L, Wan Aasim W a, Winn T, Rusli BN. Inappropriate utilization of emergency department services in Universiti Sains Malaysia hospital. The Medical Journal of Malaysia 2004; 59 (01) 26-33.
21 Afilalo J, Marinovich A, Afilalo M, Colacone A, Léger R, Unger B. et al Nonurgent emergency department patient characteristics and barriers to primary care. Academic Emergency Medicine 2004; 11 (12) 1302-1310.
22 Gill JM. Use of hospital emergency departments for nonurgent care: a persistent problem with no easy solutions. American Journal of Managed Care 1999; 5 (12) 1565-1568.
23 Northington WE, Brice JH, Zou B. Use of an emergency department by nonurgent patients. The American Journal of Emergency Medicine 2005; 23 (02) 131-137.
24 Abdallat A, Al-Smadi I, Abbadi M. Who uses the emergency room services?. Eastern Mediterranean Health Journal 2000; 6 (05) 1126-1129.
25 Sempere-Selva T, Peiró S, Sendra-Pina P, Martínez-Espín C, López-Aguilera I. Inappropriate use of an accident and emergency department: magnitude, associated factors, and reasons-an approach with explicit criteria. Annals of Emergency Medicine 2001; 37 (06) 568-579.
26 Siminski P, Bezzina AJ, Lago LP, Eagar K. Primary care presentations at emergency departments: rates and reasons by age and sex. Australian health review: a publication of the Australian Hospital Association 2008; 32 (04) 700-709.
27 Redstone P, Vancura JL, Barry D, Kutner JS. Nonurgent use of the emergency department. The Journal of Ambulatory Care Management 2008; 31 (04) 370-376.
28 Wilcox A, Bowes WA, Thornton SN, Narus SP, Narus S. Physician use of outpatient electronic health records to improve care. Annual Symposium proceedings of AMIA Symposium 2008; 809-813.
29 Nicholson A, Tate AR, Koeling R, Cassell JA. What does validation of cases in electronic record databases mean? The potential contribution of free text. Pharmacoepidemiology and Drug Safety 2011; 321-324.
30 Churches T, Christen P. Some methods for blindfolded record linkage. BMC Medical Informatics and Decision Making 2004; 4: 9
31 Aronson AR, Lang F-M. An overview of MetaMap: historical perspective and recent advances. Journal of the American Medical Informatics Association 2010; 17 (03) 229-236.
32 Kang N, van Mulligen EM, Kors JA. Comparing and combining chunkers of biomedical text. Journal of Biomedical Informatics 2011; 44 (02) 354-360.
33 Meystre S, Haug PJ. Natural language processing to extract medical problems from electronic clinical documents: performance evaluation. Journal of Biomedical Informatics 2006; 39 (06) 589-599.
34 Chapman WW, Fiszman M, Dowling JN, Chapman BE, Rindflesch TC. Identifying respiratory findings in emergency department reports for biosurveillance using MetaMap. Studies in Health Technology and Informatics 2004; 107 Pt 1 487-491.
35 Gooch P, Roudsari A. A tool for enhancing Meta-Map performance when annotating clinical guide-line documents with UMLS concepts. Proceedings of the IDAMAP Workshop at 13th Conference on Artificial Intelligence in Medicine (AIME’11). 2011.
36 Cunningham H, Gorrell G, Saggion H, Petrak J, Li Y, Maynard D. et al Text Processing with GATE (Version 6). 2011.
37 Cunningham H, Maynard D, Bontcheva K, Tablan V. GATE: A Framework and graphical development environment for robust NLP tools and applications. Proceedings of the 40th Anniversary Meeting of the Association for Computational Linguistics (ACL’02). 2002.
38 U.S. National Library of Medicine. MetaMap Portal [Internet]. 2011. Available from http://metamap.nlm.nih.gov/.
39 Bullard MJ, Unger B, Spence J, Grafstein E. Revisions to the Canadian emergency department triage and acuity scale (CTAS) adult guidelines. Canadian Journal of Emergency Medicine (Internet) 2008; (cited Aug 5, 2011) 10 (02) 136-142. Available from http://www.sphemerg.ca/files/RevisionCTASCJEMMar2008.pdf.
40 Kabacoff RI. R in Action. Shelter Island, NY: Manning Publications Inc; 2011.
41 Keene J, Rodriguez J. Are mental health problems associated with use of accident and emergency and health-related harm?. European Journal of Public Health 2007; 17 (04) 387-393.
42 Zou Q, Chu WW, Morioka C, Leazer GH, Kangarloo H. IndexFinder: a method of extracting key concepts from clinical texts for indexing. Proceedings of Annual AMIA Symposium. 2003: 763-767.
43 Savova GK, Masanz JJ, Ogren PV, Zheng J, Sohn S, Kipper-Schuler KC. et al Mayo clinical Text Analysis and Knowledge Extraction System (cTAKES): architecture, component evaluation and applications. Journal of the American Medical Informatics Association 2010; 17 (05) 507-513.
44 Kuo MH. Opportunities and Challenges of Cloud Computing to Improve Health Care Services. Journal of Medical Internet Research 2011; 13 (03) e67

Supplementary Material

Online Supplementary Material (PDF)

A Proof of Concept for Assessing Emergency Room Use with Primary Care Data and Natural Language Processing[*]

A Proof of Concept for Assessing Emergency Room Use with Primary Care Data and Natural Language Processing^[*]