Abstract
Despite the vagueness and uncertainty that is intrinsic in any medical act, interpretation and decision (including acts of data reporting and representation of relevant medical conditions), still little research has focused on how to explicitly take this uncertainty into account. In this paper, we focus on a general and wide-spread HL7 terminology, which is grounded on a traditional and well-established convention, to represent severity of health conditions (e.g., pain, visible signs), ranging from absent to very severe (as a matter of fact, different versions of this standard present minor differences, like ‘minor’ instead of ‘mild’, or ‘fatal’ inst ead of ‘very severe’). Our aim is to provide a fuzzy version of this terminology. To this aim, we conducted a questionnaire-based qualitative research study involving a relatively large sample of clinicians to represent numerically the five different labels of the standard terminology: absent, mild, moderate, severe and very severe. Using the collected values we then present and discuss three different possible representations that address the vagueness of medical interpretation by taking into account the perceptions of domain experts. In perspective, our hope is to use the resulting fuzzifications to improve machine learning approaches to medicine.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
This latter design would have allowed to compute the inter-rater agreement for each severity coordinate, as each observer would have associated each coordinate to one and only one severity category. In our setup this is not feasible unless spurious labels for category overlaps are introduced, e.g. mild-and-moderate, besides the five regular ones, making the reliability assessment more laborious.
- 3.
Indeed, since many machine learning algorithms cannot operate on label data directly, usual feature engineering tasks consist in the transformation of ordinal (categorical) data into numbers (i.e., Integer Encoding), or in applying specific encoding schema to create dummy variables or binary features for each value of a specific nominal categorical attribute (One-Hot Encoding), like severity [7].
References
Atkinson, T.M., et al.: What do ‘none’, ‘mild’, ‘moderate’, ‘severe’, and ‘very severe’ mean to patients with cancer? Content validity of PRO-CTCAE response scales. J. Pain Symptom Manag. 55(3), e3–e6 (2018)
Black, N.: Patient reported outcome measures could help transform healthcare. BMJ: Brit. Med. J. 346, f167 (2013)
Bobillo, F., Straccia, U.: Fuzzy ontology representation using OWL 2. Int. J. Approx. Reason. 52(7), 1073–1094 (2011)
Bustince, H., Montero, J., Pagola, M., Barrenechea, E., Gomez, D.: A survey of interval valued fuzzy sets, Chap. 22, pp. 489–515. Wiley-Blackwell (2008)
Cabitza, F., Ciucci, D., Rasoini, R.: A giant with feet of clay: on the validity of the data that feed machine learning in medicine. In: Cabitza, F., Batini, C., Magni, M. (eds.) Organizing for the Digital World. LNISO, vol. 28, pp. 121–136. Springer, Cham (2019). https://doi.org/10.1007/978-3-319-90503-7_10
Cabitza, F., Locoro, A., Laderighi, C., Rasoini, R., Compagnone, D., Berjano, P.: The elephant in the record: on the multiplicity of data recording work. Health Inform. J. (2018, to be published)
Coates, A., Ng, A.Y.: The importance of encoding versus training with sparse coding and vector quantization. In: Proceedings of the 28th International Conference on Machine Learning, ICML 2011, pp. 921–928 (2011)
Crichton, N.: Visual analogue scale (VAS). J. Clin. Nurs. 10(5), 706–6 (2001)
Dijkman, J., van Haeringen, H., de Lange, S.: Fuzzy numbers. J. Math. Anal. Appl. 92(2), 301–341 (1983)
El-Sappagh, S., Elmogy, M.: A fuzzy ontology modeling for case base knowledge in diabetes mellitus domain. Eng. Sci. Technol. Int. J. 20(3), 1025–1040 (2017)
Forrest, M., Andersen, B.: Ordinal scale and statistics in medical research. Br. Med. J. (Clin. Res. Ed.) 292(6519), 537–538 (1986)
Garibaldi, J.M., John, R.I.: Choosing membership functions of linguistic terms. In: The 12th IEEE International Conference on Fuzzy Systems, FUZZ-IEEE 2003, St. Louis, Missouri, USA, 25–28 May 2003, pp. 578–583. IEEE (2003)
Godo, L., de Mántaras, R.L., Sierra, C., Verdaguer, A.: Milord the architecture and the management of linguistically expressed uncertainty. Int. J. Intell. Syst. 4, 471–501 (1989)
Guijun, W., Xiaoping, L.: The applications of interval-valued fuzzy numbers and interval-distribution numbers. Fuzzy Sets Syst. 98(3), 331–335 (1998)
Jakobsson, U.: Statistical presentation and analysis of ordinal data in nursing research. Scand. J. Caring Sci. 18(4), 437–440 (2004)
Kosara, R.: Joy plots, May 2017. https://eagereyes.org/blog/2017/joy-plots, http://archive.is/Ui0NN. Accessed 9 May 2018
Lee, C.S., Wang, M.H., Hsu, C.Y., Chen, Z.W.: Type-2 fuzzy set and fuzzy ontology for diet application. In: Sadeghian, A., Mendel, J., Tahayori, H. (eds.) Advances in Type-2 Fuzzy Sets and Systems. STUDFUZZ, vol. 301, pp. 237–256. Springer, New York (2013). https://doi.org/10.1007/978-1-4614-6666-6_15
Li, Q.: A novel Likert scale based on fuzzy sets theory. Expert Syst. Appl. 40(5), 1609–1618 (2013)
Salomon, J.A.: Reconsidering the use of rankings in the valuation of health states: a model for estimating cardinal values from ordinal data. Popul. Health Metr. 1(1), 12 (2003)
Sanchez, E.: Medical applications with fuzzy sets. In: Jones, A., Kaufmann, A., Zimmermann, H.J. (eds.) Fuzzy Sets Theory and Applications. ASIC, vol. 177, pp. 331–347. Springer, Dordrecht (1986). https://doi.org/10.1007/978-94-009-4682-8_16
Vetterlein, T., Mandl, H., Adlassnig, K.P.: Fuzzy Arden syntax: a fuzzy programming language for medicine. Artif. Intell. Med. 49(1), 1–10 (2010)
Vonglao, P.: Application of fuzzy logic to improve the Likert scale to measure latent variables. Kasetsart J. Soc. Sci. 38(3), 337–344 (2017)
Zadeh, L.: The concept of a linguistic variable and its application to approximate reasoning I. Inf. Sci. 8(3), 199–249 (1975)
Żywica, P.: Modelling medical uncertainties with use of fuzzy sets and their extensions. In: Medina, J., Ojeda-Aciego, M., Verdegay, J.L., Perfilieva, I., Bouchon-Meunier, B., Yager, R.R. (eds.) IPMU 2018. CCIS, vol. 855, pp. 369–380. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-91479-4_31
Acknowledgements
The authors would like to thank Giorgio Pilotti and Gabriele Caldara, two Master students of the Master Degree in Data Science, who have conceived and realised a preliminary version of the charts depicted in Figs. 5 and 6, respectively. Figure 3 was developed after an intuition of Pietro de Simoni, another student from the same master degree course. The authors are also grateful to Prof. Giuseppe Banfi for advocating the survey at IOG and to all of the anonymous clinicians who spontaneously participated in the research by playing the game of reporting severity categories on a traditional VAS.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Cabitza, F., Ciucci, D. (2018). Fuzzification of Ordinal Classes. The Case of the HL7 Severity Grading. In: Ciucci, D., Pasi, G., Vantaggi, B. (eds) Scalable Uncertainty Management. SUM 2018. Lecture Notes in Computer Science(), vol 11142. Springer, Cham. https://doi.org/10.1007/978-3-030-00461-3_5
Download citation
DOI: https://doi.org/10.1007/978-3-030-00461-3_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-00460-6
Online ISBN: 978-3-030-00461-3
eBook Packages: Computer ScienceComputer Science (R0)