Meta-generalis: A novel method for structuring information from radiology reports

Summary

Background

A structured report for imaging exams aims at increasing the precision in information retrieval and communication between physicians. However, it is more concise than free text and may limit specialists’ descriptions of important findings not covered by pre-defined structures. A computational ontological structure derived from free texts designed by specialists may be a solution for this problem. Therefore, the goal of our study was to develop a methodology for structuring information in radiology reports covering specifications required for the Brazilian Portuguese language, including the terminology to be used.

Methods

We gathered 1,701 radiological reports of magnetic resonance imaging (MRI) studies of the lumbosacral spine from three different institutions. Techniques of text mining and ontological conceptualization of lexical units extracted were used to structure information. Ten radiologists, specialists in lumbosacral MRI, evaluated the textual superstructure and terminology extracted using an electronic questionnaire.

Results

The established methodology consists of six steps: 1) collection of radiology reports of a specific MRI examination; 2) textual decomposition; 3) normalization of lexical units; 4) identification of textual superstructures; 5) conceptualization of candidate-terms; and 6) evaluation of superstructures and extracted terminology by experts using an electronic questionnaire. Three different textual superstructures were identified, with terminological variations in the names of their textual categories. The number of candidate-terms conceptualized was 4,183, yielding 727 concepts. There were a total of 13,963 relationships between candidate-terms and concepts and 789 relationships among concepts.

Conclusions

The proposed methodology allowed structuring information in a more intuitive and practical way. Indications of three textual superstructures, extraction of lexicon units and the normalization and ontologically conceptualization were achieved while maintaining references to their respective categories and free text radiology reports.

Citation: Barbosa F, Traina AJ, Muglia VF. Meta-generalis: A novel method for structuring information from radiology reports.

Keywords

Radiological report - free-text - structured report - ontology - terminology

• References

• 1 Brentari D. A prosodic model of sign language phonology. First edition. MIT Press, Cambridge; 1998
• 2 Reis AKO. The interfaces of lexicon disciplines. Dialogia 2010; 09: 173-179.
• 3 Pavel S, Nolet D. Terminology Manual. Public Works and Government Services. Translation Bureau. Government of Canada, 2002 https://linguisticadocumentaria.files.wordpress.com/2011/03/pavel-terminologia.pdf Accessed 11 Dec 2012.
• 4 Temmerman R. Towards new ways of Terminology description: the Sociocognitive approach. First edition. John Benjamins Publishing Company Amsterdam; 2000: 258.
• 5 Silva-Filho SC. Concept/Term: The variation of a relationship. Trama. 2010 06. 75-86 http://e-revis-ta.unioeste.br/index.php/trama/article/view/5121/4125 Accessed 12 Sep 2012.
• 6 Francelin MM, Kobashi NY. Conceptions about the concept in information and knowledge organizations. Cien Inf. 2011 40. 207-228 http://core.ac.uk/download/pdf/11889801.pdf Accessed 12 Sep 2012.
• 7 Spackman KA, Campbell KE, Côté RA. SNOMED RT: a reference terminology for health care. Proc AMIA Annu Fall Symp 1997; 640-644.
• 8 Vieira JML, Correa RF. Information visualization to user-friendly interface construction for information retrieval systems. R Eletr Bibliotecon Ci Inf 2012; 16: 73-93.
• 9 Maciel-Lima SM, Rasia JM. Images do not speak for themselves: a sociological study of a liver transplantation team. Saude Soc 2012; 01: 42-51.
• 10 Fenelon S. Ethical and legal aspects in imaging. Radiol Bras 2003; 36: 3-6.
• 11 Prestes-Jr LCL, Tourinho EK, Rangel M. Medico-legal analysis of imaging demands. Radiol Bras 2010; 45: 98-100.
• 12 American College of Radiology – ACR score. Available at http://www.acr.org/∼/media/ACR/Documents/ PDF/QualitySafety/Radpeer/ScoringWhitePaper.pdf Acessed on September 28th, 2015.
• 13 Langlotz CP. RadLex: a new method for indexing online educational materials. RadioGraphics 2006; 26 (06) 1595-1597.
• 14 ACR Breast Imaging and Radiological Data System – BIRADS. Fourth edition. American College of Radiology, Reston; 2003
• 15 Passman LJ, Farias AM, Tomazelli JG, de Abreu DM, de Assis M, de Almeida PF, da Silva RC, Santini LA. SISMAMA – Implementation of an information system for breast cancer early detection programs in Brazil. Breast 2011; 20 (Suppl. 02) S35-S39.
• 16 Colins SA, Bakken S, Vawdrey DK, Coiera E, Currie L. Clinician preferences for verbal communication compared to EHR documentation in the ICU. Applied Clinical Informatics 2011; 02: 190-201.
• 17 Andreisek G, Deyo RA, Jarvik JG, Porchet F, Winklhofer SF, Steurer J. Consensus conference on core radiological parameters to describe lumbar stenosis – an initiative for structured reporting. Eur Radiol 2014; 24: 3224-3232 doi: 10.1007/s00330–014–3346-z.
• 18 Rubin DL. Creating and curating a terminology for radiology: ontology modeling and analysis. J Digit Imaging 2008; 21 (04) 355-362.
• 19 Lavelli A, Califf ME, Ciravegna F, Freitag D, Giuliano C, Kushmerick N, Romano L, Ireson N. Evaluation of machine learning-based information extraction algorithms: criticisms and recommendations. Language Resources and Evaluation 2008; 42 (02) 361-393.
• 20 Roberto JA, Martí MA, Llorente MS. Analysis of lexical richness in the context of latent demographic user attributes classification. Procesamiento de Lenguaje Natural Journal 2012; 48: 97-104.
• 21 Friedman C, Alderson PO, Austin JHM, Cimino JJ, Johnson SB. 1994; A general natural-language text processor for clinical radiology. J Am Med Inform Assoc 1994; 01: 161-174.
• 22 DECS – Descritores em ciências da saúde – Health science descriptors [online]. Bireme. http://DECS.bvs.br Accessed 14 Jun 2012.
• 23 Michaelis Online Dictionary. http://michaelis.uol.com.br/escolar/ingles/index.php Accessed 06 Jun 2012.
• 24 Dorland’s. Ilustrated Medical Dictionary. Thirty-second edition. Saunders, Philadelphia: 2011
• 25 Unified Medical Language System (UMLS). https://uts.nlm.nih.gov/home.html Accessed 19 Jun 2013.
• 26 Netter FH. Human Anatomy Atlas. Sixth edition. Saunders, Philadelphia: 2014: 142-144.
• 27 Health Level Seven International – HL7. Available at www.hl7.org Acessed on september 12th, 2015
• 28 Hripsack G, Austin JH, Anderson PO, Friedman C. Use of natural language processing to translate clinical information from a database of 889,921 chest radiographic reports. Radiology 2002; 224: 157-163.
• 29 Hassanpour S, Langlots CP. Information extraction from multi-institutional radiology reports. Artificial Inteligence in Medicine 2016; 66: 29-39.
• 30 Fenoy AJ, Menezes AH, Fenoy KA. Craniocervical junction fusions in patients with hindbrain herniation and syringohydromyelia. J Neurosurg Spine 2008; 09: 1-9.
• 31 Gerstmair A, Daumke P, Simon K, Langer M, Kotter E. Intelligent image retrieval based on radiology reports. Eur Radiol 2012; 22 (12) 2750-2758.
• 32 Snomed Healthcare terminology. http://www.ihtsdo.org/snomed-ct Accessed 14 Jun 2012.
• 33 Protégé software. Available at protege.stanford.edu Accessed 12 Sep 2012.
• 34 Plazzotta F, Luna D, Quirós FGB. Health Information Systems: Integrating clinical data in different scenarios and users. Rev perú med exp salud publica 2015; 32: 343-351.