Abstract
This study developed a system that determines when to remove the pouch from the stoma to detect faecal leakage in non-contact stoma holders. Around January 2020, new coronary outbreaks occurred worldwide, making it difficult for hospitals and care homes to collect data from many stoma holders. Collecting data from many stoma holders in hospitals and care centers has generally been challenging. Therefore, sufficient training and correct data were obtained using artificial intelligence (AI) image generation containing more images. These training data were then used to determine the appropriate tame to change the pouch. Finally, the accuracy of the decisions was compared using two learning algorithms, the Microsoft lobe machine learning and the Google teachable machine learning modelling tools. The results showed that the percentage of correct decisions for the two learning algorithms was 100%, from the first day to approximately three days after the faceplate was fitted, but tended to be lower, ranging from 40% to 87.5%, from one to three days before the replacement date. The Google teachable machine learning modelling tool was also less accurate than the Microsoft lobe machine learning modelling tool.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Foundation for Promotion of Cancer Research. Cancer Statistics in Japan of 2022. https://ganjoho.jp/public/qa_links/report/statistics/pdf/cancer_statistics_2022.pdf. Published 12. Accessed 18 Dec 2022
Jeppesen, P.B., Vestergaard, M., Boisen, E.B., Ajslev, T.A.: Impact of stoma leakage in everyday life: data from the Ostomy Life Study 2019. Br. J. Nurs. 31(6), 48–58 (2022)
Jordan, M.I., Mitchell, T.M.: Machine learning: trends, perspectives, and prospects. Science 349(6245), 255–260 (2015)
Shahadat, U., Arif, K., Hossain, Md.E., Mohammad, A. M.: Comparing different supervised machine learning algorithms for disease prediction. BMC Med. Inform. Decis. Mak. 19(281) (2019)
Forchhammer, S., Abu-Ghazaleh, A., Metzler, G., Garbe, C., Eigentler, T.: Development of an image analysis-based prognosis score using Google’s teachable machine in melanoma. Cancers 14(2243), 1–12 (2022)
Wu, T., Wei, Y., Wu, J., Yi, B., Li, H.: Logistic regression technique is comparable to complex machine learning algorithms in predicting cognitive impairment related to post intensive care syndrome. Sci. Rep. 13(2485) (2023)
Lee, S.-K., Son, Y.-J., Kim, J., et al.: Prediction model for health-related quality of life of elderly with chronic diseases using machine learning techniques. Healthc. Inform. Res. 20(2), 125–134 (2014)
Yu, J.Y., Jeong, G.Y., Jeong, O.S., Chang, D.K., Cha, W.C.: Machine leaning and initial nursing assessment-based triage system for emergency department. Healthc. Inform. Res. 26(1), 13–19 (2020)
Geum, H.J.: Artificial intelligence, machine learning, and deep learning in women’s health nursing. Korean J. Women Health Nurse 26(1), 5–9 (2020)
Microsoft Lobe. https://lobe.ai/. Accessed 9 Jan 2023
Microsoft Lobe’s Image Classification Overview. https://learn.microsoft.com/ja-jp/ai-builder/lobe-overview. Accessed 9 Jan 2023
Google Machine Learning. https://teachablemachine.withgoogle.com/. Accessed 9 Jan2023
Github, Stable Diffusion Helper. https://github.com/fladdict/stable_diffusion/blob/main/Stable_Diffusion_Helper.ipynb. Accessed 22 Jan 2023
Hollister. https://www.hollister.com/en. Accessed 20 Feb 2023
Coloplast. https://www.coloplast.us/. Accessed 20 Feb 2023
Malahina, E.A.U., Hadjon, R.P., Bisilisin, F.Y.: Teachable machine. Real-time attendance of students based on open source system. Int. J. Inform. Comput. Sci. 6(3), 140–146 (2022)
Python deep learning library. https://keras.io/ja. Accessed 14 Jan 2023
Acknowledgment
This study was partly supported by the 2021 Specific Joint Research, Fundamental Mechatronics Research Institute, Osaka Electrocommunication University.
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
Mizoguchi, M., Watanabe, S., Nakahara, M., Noborio, H. (2023). Comparison of the Accuracy of Pouch Replacement Timing Decisions Using Image Generation Artificial Intelligence and Machine Learning. In: Kurosu, M., Hashizume, A. (eds) Human-Computer Interaction. HCII 2023. Lecture Notes in Computer Science, vol 14014. Springer, Cham. https://doi.org/10.1007/978-3-031-35572-1_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-35572-1_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-35571-4
Online ISBN: 978-3-031-35572-1
eBook Packages: Computer ScienceComputer Science (R0)