Advertisement

Learning from Human Behavior to Improve Preventative Health Information Systems

  • Remberto MartinezEmail author
  • Marcos Tong
  • Luis Diago
  • Jaana Lindstrom
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 876)

Abstract

Health services are often oriented to be ubiquitous for persons comfortable with mobile device and web technologies usage. In this environment, the main question is: can computer systems learn from human behavior to improve preventative health information systems? Current healthcare information systems focus on ensuring adherence to treatment through Just-In-Time Adaptive Interventions (JITAI). JITAI is used for preventative health and lifestyle behavior change interventions. The main problem for JITAI is lack of proper models of user’s behavior allowing effective interventions. Our novel approach adds contextual variables to the behavior learning system embedded in the message contents of lifestyle modifications interventions. The main result obtained from the proposal was a 33,8% perceived effective SMS intervention using behavior modeling with reduced specialized feedback. Chronic diseases like diabetes type 2 (DT2) are preventative when lifestyle behavior can be modified towards healthier habits. The research results open a new range of applications in context-aware computing and improve the effectiveness of JITAI for preventative chronic diseases.

Keywords

Lifestyle intervention Human behavior modelling Preventative health systems 

References

  1. 1.
    Manios, Y., et al.: Preliminary outcomes of the 1st year of an intervention aiming to promote healthy lifestyle in a large-scale European cohort: Feel4Diabetes study. In: Proceedings of 53rd Annual Meeting of the European Diabetes Epidemiology Group, p. 74 (2018)Google Scholar
  2. 2.
    Lindström, J., Tuomilehto, J.: The diabetes risk score: a practical tool to predict type 2 diabetes risk. Diabetes Care 26, 725–731 (2003).  https://doi.org/10.2337/diacare.26.3.725CrossRefGoogle Scholar
  3. 3.
    Saar-Tsechansky, M., Provost, F.: Handling missing values when applying classification models. J. Mach. Learn. Res. 8, 1217–1250 (2007)MathSciNetzbMATHGoogle Scholar
  4. 4.
    Brailsford, S.C.: Healthcare: human behavior in simulation models. In: Kunc, M., Malpass, J., White, L. (eds.) Behavioral Operational Research. Palgrave Macmillan, London (2016)CrossRefGoogle Scholar
  5. 5.
    op den Akker, H., et al.: Tailored motivational message generation: a model and practical framework for real-time physical activity coaching. J. Biomed. Inform. 55, 104–115 (2015)CrossRefGoogle Scholar
  6. 6.
    MacPhail, M., Mullan, B., Sharpe, L., MacCann, C., Todd, J.: Using the health action process approach to predict and improve health outcomes in individuals with type 2 diabetes mellitus. Diabetes Metab. Syndr. Obes. Targ. Ther. 7, 469–479 (2014)Google Scholar
  7. 7.
    Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.H.: The WEKA data mining software: an update. SIGKDD Explor. Newsl. 11, 10–18 (2009).  https://doi.org/10.1145/1656274.1656278CrossRefGoogle Scholar
  8. 8.
    Ramachandran, A., et al.: Effectiveness of mobile phone messaging in prevention of type 2 diabetes by lifestyle modification in men in India: a prospective, parallel-group, randomised controlled trial. Lancet Diabetes Endocrinol. 1(3), 191–198 (2013).  https://doi.org/10.1016/S2213-8587(13)70067-6. Epub 2013 Sep 11CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Remberto Martinez
    • 1
    Email author
  • Marcos Tong
    • 1
  • Luis Diago
    • 2
  • Jaana Lindstrom
    • 3
  1. 1.Extensive Life OyTampereFinland
  2. 2.Interlocus Inc.YokohamaJapan
  3. 3.National Institute for Health and WelfareHelsinkiFinland

Personalised recommendations