Abstract
The use of activity monitoring sensors on users with some type of disease or dependence is very useful for health technicians, for family members or for the user himself. The knowledge of these values in real time allows alerting of a possible crisis or starting correcting actions to prevent a serious health problem. For this reason, many proposals have been made to summarize in words the huge amount of measures taken by these sensors in order to highlight only what is really important for the end user, family or medical staff. The emergence of new text generation tools based on Artificial Intelligence (AI), such as the latest GPT-4, is having a major impact in the healthcare field. In this article we analyze how the latest version of ChatGPT, allows the generation of linguistic summaries in natural language from glucose sensor measurements. We also learn how to ask the right questions to obtain the type of output adapted to the user, whether or not it is necessary to perform some kind of preprocessing on the data to be analyzed and what are the strengths and drawbacks of this technology.
This work has been partially supported by the Government of Spain through the projects RTI2018-098979-A-I00 MCIN/ AEI/10.13039/501100011033/, ERDF “A way to make Europe”, B-TIC-744-UGR20 ADIM: Accesibilidad de Datos para Investigación Médica of the Junta de Andalucía and the University of Jaén under Action 1 with reference EI_TIC1_2021.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Although GPT-4 allows the analysis of figures, this is still a beta feature and therefore has not been used in our experimentation.
References
Gpt-4 technical report (2023). https://arxiv.org/pdf/2303.08774.pdf
Ali, A., Aggarwal, J.: Segmentation and recognition of continuous human activity. In: Proceedings IEEE Workshop on Detection and Recognition of Events in Video, pp. 28–35 (2001). https://doi.org/10.1109/EVENT.2001.938863
Alkaissi, H., Mcfarlane, S.: Artificial hallucinations in chatGPT: implications in scientific writing. Cureus 15, e35179 (2023). https://doi.org/10.7759/cureus.3517
Alvarez-Alvarez, A., Triviño, G.: Linguistic description of the human gait quality. Eng. Appl. AI 26(1), 13–23 (2013). https://doi.org/10.1016/j.engappai.2012.01.022
Banaee, H., Ahmed, M.U., Loutfi, A.: A framework for automatic text generation of trends in physiological time series data. In: 2013 IEEE International Conference on Systems, Man, and Cybernetics, pp. 3876–3881 (2013). https://doi.org/10.1109/SMC.2013.661
Boran, F.E., Akay, D., Yager, R.R.: An overview of methods for linguistic summarization with fuzzy sets. Expert Syst. Appl. 61, 356–377 (2016)
Bubeck, S., et al.: Sparks of artificial general intelligence: early experiments with gpt-4 (2023)
Castillo-Ortega, R., Marín, N., Sánchez, D.: A fuzzy approach to the linguistic summarization of time series. J. Multiple-Valued Logic Soft Comput. 17, 157–182 (2011)
Castillo-Ortega, R., Marín, N., Sánchez, D.: Linguistic query answering on data cubes with time dimension. Int. J. Intell. Syst. (IJIS) 26(10), 1002–1021 (2011)
Conde-Clemente, P., Alonso, J.M., Trivino, G.: Toward automatic generation of linguistic advice for saving energy at home. Soft. Comput. 22(2), 345–359 (2016). https://doi.org/10.1007/s00500-016-2430-5
Douglas, D.H., Peucker, T.K.: Algorithms for the reduction of the number of points required to represent a digitized line or its caricature. Cartographica Int. J. Geogr. Inf. Geovisual. 10, 112–122 (1973). https://doi.org/10.3138/FM57-6770-U75U-7727
Etzioni, O.: Commentary: Openai’s gpt-4 has some limitations that are fixable - and some that are not (2023). https://www.geekwire.com/2023/commentary-openais-gpt-4-has-some-limitations-that-are-fixable-and-some-that-are-not/. Accessed 14 Mar 2023
Farsi, N., Mahjouri, N., Ghasemi, H.: Breakpoint detection in non-stationary runoff time series under uncertainty. J. Hydrol. 590, 125458 (2020). https://doi.org/10.1016/j.jhydrol.2020.125458
Fu, T.C.: A review on time series data mining. Eng. Appl. Artif. Intell. 24(1), 164–181 (2011)
Höppner, F.: Time series abstraction methods - a survey, pp. 777–786 (2002)
Ji, Z., et al.: Survey of hallucination in natural language generation. ACM Comput. Surv. 55(12), 1–38 (2023). https://doi.org/10.1145/3571730
Kacprzyk, J., Zadrozny, S.: Fuzzy logic based linguistic summaries of time series: a powerful tool for discovering knowledge on time varying processes and systems under imprecision. Wiley Interdisc. Rev. Data Mining Knowl. Disc. 6(1), 37–46 (2016). https://doi.org/10.1002/widm.1175
Marín, N., Sánchez, D.: On generating linguistic descriptions of time series. Fuzzy Sets Syst. 285, 6–30 (2016). Special Issue on Linguistic Description of Time Series
Martinez-Cruz, C., Rueda, A.J., Popescu, M., Keller, J.M.: New linguistic description approach for time series and its application to bed restlessness monitoring for eldercare. IEEE Trans. Fuzzy Syst. 30(4), 1048–1059 (2022). https://doi.org/10.1109/tfuzz.2021.3052107
OpenAI: Chatgpt - release notes (2023). https://help.openai.com/en/articles/6825453-chatgpt-release-notes
Ramos-Soto, A., Bugarín, A., Barro, S.: On the role of linguistic descriptions of data in the building of natural language generation systems. Fuzzy Sets Syst. 28, 31–51 (2016). https://doi.org/10.1016/j.fss.2015.06.019
Reiter, E., Sripada, S., Hunter, J., Davy, I.: Choosing words in computer-generated weather forecasts. Artif. Intell. 167, 137–169 (2005)
Sanchez-Valdes, D., Eciolaza, L., Triviño, G.: Linguistic description of human activity based on mobile phone’s accelerometers. In: Ambient Assisted Living and Home Care - 4th International Workshop, IWAAL 2012, Vitoria-Gasteiz, Spain, 3–5 December 2012, Proceedings, pp. 346–353 (2012)
Trivino, G., Sugeno, M.: Towards linguistic descriptions of phenomena. Int. J. Approx. Reas. 54(1), 22–34 (2013). https://doi.org/10.1016/j.ijar.2012.07.004. http://www.sciencedirect.com/science/article/pii/S0888613X12001375
Wang, F.Y., Miao, Q., Li, X., Wang, X., Lin, Y.: What does chatGPT say: the dao from algorithmic intelligence to linguistic intelligence. IEEE/CAA J. Automatica Sinica 10(3), 575–579 (2023). https://doi.org/10.1109/JAS.2023.123486
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Martinez-Cruz, C., Guerrero, J.F.G., Ruiz, J.L.L., Rueda, A.J., Espinilla, M. (2023). A First Approach to the Generation of Linguistic Summaries from Glucose Sensors Using GPT-4. In: Bravo, J., Urzáiz, G. (eds) Proceedings of the 15th International Conference on Ubiquitous Computing & Ambient Intelligence (UCAmI 2023). UCAmI 2023. Lecture Notes in Networks and Systems, vol 842. Springer, Cham. https://doi.org/10.1007/978-3-031-48642-5_4
Download citation
DOI: https://doi.org/10.1007/978-3-031-48642-5_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-48641-8
Online ISBN: 978-3-031-48642-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)