PDF herunterladen
CC BY-NC-ND 4.0 · Yearb Med Inform 2019; 28(01): 027-034
DOI: 10.1055/s-0039-1677899
Special Section: Artificial Intelligence in Health: New Opportunities, Challenges, and Practical Implications
Working Group Contributions
Georg Thieme Verlag KG Stuttgart

The Interplay of Knowledge Representation with Various Fields of Artificial Intelligence in Medicine

A Contribution from the IMIA Working Group on Language and Meaning in BioMedicine
Laszlo Balkanyi
1   Knowledge Manager, European Centre of Disease Prevention and Control (retired)
,
Ronald Cornet
2   Associate Professor, Department of Medical Informatics, Academic Medical Center - University of Amsterdam, Amsterdam Public Health research institute, Amsterdam, The Netherlands
› Institutsangaben
Weitere Informationen

Publikationsverlauf

Publikationsdatum:
25. April 2019 (online)

   Lizenzen und Reprints

Summary

Introduction: Artificial intelligence (AI) is widespread in many areas, including medicine. However, it is unclear what exactly AI encompasses. This paper aims to provide an improved understanding of medical AI and its constituent fields, and their interplay with knowledge representation (KR).

Methods: We followed a Wittgensteinian approach (“meaning by usage”) applied to content metadata labels, using the Medical Subject Headings (MeSH) thesaurus to classify the field. To understand and characterize medical AI and the role of KR, we analyzed: (1) the proportion of papers in MEDLINE related to KR and various AI fields; (2) the interplay among KR and AI fields and overlaps among the AI fields; (3) interconnectedness of fields; and (4) phrase frequency and collocation based on a corpus of abstracts.

Results: Data from over eighty thousand papers showed a steep, six-fold surge in the last 30 years. This growth happened in an escalating and cascading way. A corpus of 246,308 total words containing 21,842 unique words showed several hundred occurrences of notions such as robotics, fuzzy logic, neural networks, machine learning and expert systems in the phrase frequency analysis. Collocation analysis shows that fuzzy logic seems to be the most often collocated notion. Neural networks and machine learning are also used in the conceptual neighborhood of KR. Robotics is more isolated.

Conclusions: Authors note an escalation of published AI studies in medicine. Knowledge representation is one of the smaller areas, but also the most interconnected, and provides a common cognitive layer for other areas.

Keywords

Knowledge representation - Artificial Intelligence - natural language processing
 

  • References

  • 1 Jiang F, Jiang Y, Zhi H, Dong Y, Li H, Ma S. et al. Artificial intelligence in healthcare: past, present and future. Stroke Vasc Neurol 2017; 2: 230-43
    CrossrefPubMedGoogle Scholar
  • 2 Remenyi D. Second European Conference on Knowledge Management: Bled School of Management Bled, Slovenia, 8-9 November 2001. Academic Conferences Limited 2001
    PubMedGoogle Scholar
  • 3 Broughton V. Essential Classification. Facet Publishing 2015
    PubMedGoogle Scholar
  • 4 U.S. National Library of Medicine. Medical Subject Headings - Home Page 1999. https://www.nlm.nih.gov/mesh/ (accessed August 1, 2018)
    PubMedGoogle Scholar
  • 5 Sperr E. PubMed by Year n.d. https://esperr.github.io/pubmed-by-year/ (accessed February 2, 2019)
    PubMed
  • 6 Sperr E. Website. PubVenn n.d. https://pubvenn.appspot.com/ (accessed November 6, 2018)
    PubMed
  • 7 NodeXL Team. NodeXL n.d. https://archive.codeplex.com/?p=nodexl (accessed November 6, 2018)
    PubMed
  • 8 Speelman D. Mastering Corpus Linguistics Methods: A Practical Introduction with AntConc and R. John Wiley & Sons; 2016
    PubMedGoogle Scholar
  • 9 Horwich P. Meaning as Use. Meaning 1998; 43-102
    PubMedGoogle Scholar
  • 10 Schulz S, Balkanyi L, Cornet R, Bodenreider O. From concept representations to ontologies: a paradigm shift in health informatics?. Health Inform Res 2013; 19: 235-42
    PubMedGoogle Scholar
  • 11 Barros P, Jirak D, Weber C, Wermter S. Multimodal emotional state recognition using sequence-dependent deep hierarchical features. Neural Netw 2015; 72: 140-51
    CrossrefPubMedGoogle Scholar
  • 12 De La Cruz VM, Di Nuovo A, Di Nuovo S, Cangelosi A. Making fingers and words count in a cognitive robot. Front Behav Neurosci 2014; 8: 13
    PubMedGoogle Scholar
  • 13 Gonzalo de Diego B, Herrero Jaén S, Monsalvo San Macario E, Madariaga Casquero L, Jiménez Rodríguez ML, Santamaría García JM. et al. Robotic Implementation of the Necessary Mechanism for the Human Characteristics Simulation: Approach from Self-Care Conceptual Modeling. Stud Health Technol Inform 2018; 250: 115-20
    PubMedGoogle Scholar
  • 14 Bartels PH, Weber JE, Duckstein L. Machine learning in quantitative histopathology. Anal Quant Cytol Histol 1988; 10: 299-306
    PubMedGoogle Scholar
  • 15 Alshahrani M, Khan MA, Maddouri O, Kinjo AR, Queralt-Rosinach N, Hoehndorf R. Neuro-symbolic representation learning on biological knowledge graphs. Bioinformatics 2017; 33: 2723-30
    CrossrefPubMedGoogle Scholar
  • 16 Chiu P-H, Hripcsak G. EHR-based phenotyping: Bulk learning and evaluation. J Biomed Inform 2017; 70: 35-51
    CrossrefPubMedGoogle Scholar
  • 17 Coden A, Savova G, Sominsky I, Tanenblatt M, Masanz J, Schuler K. et al. Automatically extracting cancer disease characteristics from pathology reports into a Disease Knowledge Representation Model. J Biomed Inform 2009; 42: 937-49
    CrossrefPubMedGoogle Scholar
  • 18 Economou G-PK, Sourla E, Stamatopoulou K-M, Syrimpeis V, Sioutas S, Tsakalidis A. et al. Exploiting Expert Systems in Cardiology: A Comparative Study. In: Vlamos, P., Alexiou, A., editors. GeNeDis 2014, vol. 820. Cham: Springer International Publishing; 2015 p. 79-89
    PubMedGoogle Scholar
  • 19 d’Aquin M, Lieber J, Napoli A. Chapter 19 Towards a semantic portal for oncology using a description logic with fuzzy concrete domains. Capturing Intelligence 2006; p. 379-93
    PubMedGoogle Scholar
  • 20 Douali N, Csaba H, De Roo J, Papageorgiou EI, Jaulent M-C. Diagnosis support system based on clinical guidelines: comparison between case-based fuzzy cognitive maps and Bayesian networks. Comput Methods Programs Biomed 2014; 113: 133-43
    CrossrefPubMedGoogle Scholar
  • 21 Kwiatkowska M, Stella Atkins M, Ayas NT, Frank Ryan C. Knowledge-Based Data Analysis: First Step Toward the Creation of Clinical Prediction Rules Using a New Typicality Measure. IEEE Trans Inf Technol Biomed 2007; 11: 651-60
    CrossrefPubMedGoogle Scholar
  • 22 Bellamy JE. Medical diagnosis, diagnostic spaces, and fuzzy systems. J Am Vet Med Assoc 1997; 210: 390-6
    PubMedGoogle Scholar
  • 23 Boegl K, Adlassnig K-P, Hayashi Y, Rothenfluh TE, Leitich H. Knowledge acquisition in the fuzzy knowledge representation framework of a medical consultation system. Artif Intell Med 2004; 30: 1-26
    CrossrefPubMedGoogle Scholar
  • 24 Vineis P. Methodological insights: fuzzy sets in medicine. J Epidemiol Community Health 2008; 62: 273-8
    CrossrefPubMedGoogle Scholar
  • 25 di Bacco M, d’Amore G, Scalfari F. Applied Bayesian Statistical Studies in Biology and Medicine. Springer Science & Business Media 2013
    PubMedGoogle Scholar
  • 26 Grossi E. Artificial Neural Networks and Predictive Medicine: a Revolutionary Paradigm Shift. Artificial Neural Networks - Methodological Advances and Biomedical Applications 2011
    PubMedGoogle Scholar
  • 27 Malmgren H, Borga M, Niklasson L. Artificial Neural Networks in Medicine and Biology: Proceedings of the ANNIMAB-1 Conference, Göteborg, Sweden, 13-16 May 2000. Springer Science & Business Media 2012
    PubMedGoogle Scholar
  • 28 Hofstadter DR. Gödel, Escher, Bach: an Eternal Golden Braid. Basic Books 1979
    PubMedGoogle Scholar
  • 29 Dijkstra EW. Archive: the manuscripts of Edsger W. Dijkstra n.d. http://www.cs.utexas.edu/users/EWD/ewd08xx/EWD898.PDF (accessed August 1, 2018)
    PubMed