SemScribe: Automatic Generation of Medical Reports

  • Lukas C. Faulstich
  • Kristin Irsig
  • Malik Atalla
  • Sebastian Varges
  • Heike Bieler
  • Manfred Stede
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7058)


Images and videos resulting from diagnostic imaging procedures such as echocardiography need to be analyzed and interpreted by physicians in order to diagnose diseases of the patient. This process can be split into two steps: in a first step, various morphological features depicted in the images have to be interpreted and described. Then, a diagnostic conclusion has to be drawn from these observations. The first step can be facilitated by offering a structured entry form and some means to generate textual descriptions from the data entered in this form. While it is straight-forward to implement some basic text generation functionality using hard-wired text templates, the generation of fluent, well-readable text from structured data is much harder. In this collaboration we have combined advanced methods from computational linguistics and medical knowledge resources to solve this problem. We have built a prototype for the domain of echocardiography and evaluated it in a clinical setting.


Noun Phrase Medical Report Text Generation Text Block Natural Language Generation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Cawsey, A., Jones, R., Pearson, J.: The Evaluation of a Personalised Health Information System for Patients with Cancer. User Modeling and User-Adapted Interaction 10(1), 47–72 (2000)CrossRefGoogle Scholar
  2. 2.
    Dale, R., Reiter, E.: Computational Interpretations of the Gricean Maxims in the Generation of Referring Expressions. Cognitive Science 19, 233–263 (1995)CrossRefGoogle Scholar
  3. 3.
    Hüske-Kraus, D.: Suregen-2: A shell system for the generation of clinical documents. In: 10th Conference of the European Chapter of the Association for Computational Linguistics (EACL 2003), Budapest, Ungarn (2003)Google Scholar
  4. 4.
    Hüske-Kraus, D.: Text Generation in Clinical Medicine. Methods of Information in Medicine (Methods Inf. Med.) 42(1), 51–60 (2003)Google Scholar
  5. 5.
    Krahmer, E., Verleg, A., van Erk, S.: Graph-based Generation of Referring Expressions. Computational Linguistics 29(1), 53–72 (2003)CrossRefzbMATHGoogle Scholar
  6. 6.
    Langkilde, I., Knight, K.: Generation that Exploits Corpus-based Statistical Knowledge. In: Proceedings of COLING/ACL 1998, Montreal, Canada, pp. 704–710 (1998)Google Scholar
  7. 7.
    Mairesse, F., Walker, M.: Controlling User Perceptions of Linguistic Style: Trainable Generation of Personality Traits. Computational Linguistics 37(3) (2011)Google Scholar
  8. 8.
    Nicolov, N., Mellish, C.: PROTECTOR: Efficient Generation with Lexicalized Grammars. In: Recent Advances in Natural Language Processing (RANLP), vol. II, pp. 221–243. John Benjamins, Amsterdam (1999)Google Scholar
  9. 9.
    Paiva, D.S., Evans, R.: Empirically-based Control of Natural Language Generation. In: Proceedings of the 43rd Annual Meeting of the ACL, pp. 58–65 (2005)Google Scholar
  10. 10.
    Reiter, E., Robertson, R., Lennox, S., Osman, L.: Using a Randomised Controlled Clinical Trial to Evaluate an NLG System. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL) (2001)Google Scholar
  11. 11.
    Reiter, E.: Has a Consensus NL Generation Architecture Appeared, and is it Psycholinguistically Plausible? In: Proceedings of the Seventh International Workshop on Natural Language Generation (INLG 1994), Kennebunkport, Maine, USA, pp. 163–170 (1994)Google Scholar
  12. 12.
    Reiter, E., Dale, R.: Building Applied Natural Language Generation Systems. Cambridge University Press, Cambridge (2000)CrossRefGoogle Scholar
  13. 13.
    Sawitzky, D.R.: Generierung deutscher Sätze nach dem X-Bar-Schema: Entwurf und Implementierung, BA thesis, University of Potsdam (2011)Google Scholar
  14. 14.
    Stone, M., Doran, C.: Sentence Planning as Description Using Tree-Adjoining Grammar. In: Proceedings of ACL 1997, pp. 198–205 (1997)Google Scholar
  15. 15.
    Varges, S., van Deemter, K.: Generating referring expressions containing quantifiers. In: Proceedings of the 6th International Workshop on Computational Semantics (IWCS-6), Tilburg (2005)Google Scholar
  16. 16.
    Varges, S., Mellish, C.: Instance-based Natural Language Generation. Journal of Natural Language Engineering 16(3), 309–346 (2010)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Lukas C. Faulstich
    • 1
  • Kristin Irsig
    • 1
  • Malik Atalla
    • 1
  • Sebastian Varges
    • 2
  • Heike Bieler
    • 2
  • Manfred Stede
    • 2
  1. 1.ID GmbH & Co. KGaABerlinGermany
  2. 2.Applied Computational Linguistics LabUniversity of PotsdamGermany

Personalised recommendations