Extracting Propagation Patterns from Bacterial Culture Data in Medical Facility

  • Kazuki Nagayama
  • Kouichi HirataEmail author
  • Shigeki Yokoyama
  • Kimiko Matsuoka
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10091)


In this paper, we formulate propagation patterns as the pairs of records in the same bacterial culture occurring within a fixed span in bacterial culture data. Then, we design the exhaustive search algorithm to extract all of the propagation patterns from bacterial culture data based on the extended principle of the 2-dimensional career map to determine whether two records in bacterial culture data belong to the same bacterial culture or the different ones. In particular, we focus on infectious propagation patterns, in which two patients are not identical, and they are in the same room and/or treated by the same physician. Finally, we give the experimental results to extract all of the propagation patterns and analyze them.


Propagation Pattern Bacterial Culture Streptococcus Pneumoniae Enterococcus Faecium Candida Glabrata 
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.



The authors would like to thank anonymous referees of TSDAA 2015 for valuable comments to revise the previous version.


  1. 1.
    Allen, J.: Maintaining knowledge about temporal intervals. Commun. ACM 26, 832–843 (1983)CrossRefzbMATHGoogle Scholar
  2. 2.
    Fujimoto, S.: Control for hospital acquiared infection by automatic classification of antibiogram and 2 dimensional career map. IASR 32, 9–10 (2011). (in Japanese)Google Scholar
  3. 3.
    Hirata, K., Motoyama, K., Yokoyama, S., Matsuoka, K.: Temporal interrelations of bacteria based on the occurrence of time. In: Proceedings of CME 2010, pp. 188–192 (2010)Google Scholar
  4. 4.
    Katoh, T., Hirata, K., Arimura, H., Yokoyama, S., Matsuoka, K.: Extracting sequential episodes representing replacements of bacteria from bacterial culture data. In: Proceedings of CME 2009, 4 p. (2009)Google Scholar
  5. 5.
    Katoh, T., Hirata, K., Arimura, H., Yokoyama, S., Matsuoka, K.: Aligned bipartite episodes between the genera of bacteria. In: Proceedings of CME 2010, pp. 193–197 (2010)Google Scholar
  6. 6.
    Mannila, H., Toivonen, H., Verkamo, A.I.: Discovery of frequent episodes in event sequences. Data Min. Knowl. Discov. 1, 259–289 (1997)CrossRefGoogle Scholar
  7. 7.
    Nagayama, K., Eto, K., Haraguchi, N., Hirata, K.: Inferring bacterial culture from identification graph of bacteria for antibiogram. In: Proceedings of Hinokuni Symposium, IPSJ Kyushu (2014). (in Japanese)Google Scholar
  8. 8.
    Papapetrou, P., Kollios, G., Sclaroff, S., Gunopulos, D.: Mining frequent arrangements of temporal intervals. Knowl. Inf. Syst. 21, 133–171 (2009)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Kazuki Nagayama
    • 1
  • Kouichi Hirata
    • 4
    Email author
  • Shigeki Yokoyama
    • 2
  • Kimiko Matsuoka
    • 3
  1. 1.Department of Artificial Intelligence, Graduate School of Computer Science and Systems EngineeringKyushu Institute of TechnologyIizukaJapan
  2. 2.KD-ICONS Co. Ltd.OhtaJapan
  3. 3.Osaka Prefectural General Medical CenterOsakaJapan
  4. 4.Department of Artificial IntelligenceKyushu Institute of TechnologyIizukaJapan

Personalised recommendations