Abstract
Recent advances in technology and societal changes have increased the amount of patient data that is being collected remotely, outside of hospitals. As technology enables the ability to collect Ecological Momentary Assessments (EMAs) of patient symptoms remotely, personalised predictors have become especially relevant in the field of medicine. However, focusing a predictive model on a single patient’s data comes with sometimes extreme trade-offs on the amount of data available for training. While it is possible to mitigate this loss of data by including data from similar patients, the concept of similarity itself may be poorly defined in cases where patient data are available in two modalities - one that is fixed and relatively static (for e.g.: age, gender, etc.), and those that are more dynamic (instantaneous symptom severity). Including data from users with similar EMA data and disease characteristics has been explored with respect to building personalised predictors of the near future of a patient. We propose a method to build personalised predictors by discovering a neighbourhood for each user that decreases the prediction error of a model over that user’s data. This method is useful not just for building better personalised predictors, but may also serve as a starting point for future investigations into what properties are shared by patients whose EMA data predict each other. We test our method on two EMA datasets, and show that our proposed method achieves significantly better RMSE than a single non-personalised global model, and that our framework provides better predictions for 82%–89% of the users compared to the global model for two datasets.
This work has received funding from the European Union’s Horizon 2020 Research and Innovation Programme, Grant Agreement 848261 “Unification of treatments and Interventions for Tinnitus patients” (UNITI).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ahamed, F., Farid, F.: Applying internet of things and machine-learning for personalized healthcare: issues and challenges. In: 2018 International Conference on Machine Learning and Data Engineering (iCMLDE), pp. 19–21. IEEE (2018)
Hewamalage, H., Bergmeir, C., Bandara, K.: Global models for time series forecasting: a simulation study. Pattern Recognit. 124, 108441 (2022). https://doi.org/10.1016/j.patcog.2021.108441
Jamaludeen, N., Unnikrishnan, V., Pryss, R., Schobel, J., Schlee, W., Spiliopoulou, M.: Circadian conditional granger causalities on ecological momentary assessment data from an mhealth app. In: 2021 IEEE 34th International Symposium on Computer-Based Medical Systems (CBMS), pp. 354–359. IEEE (2021)
Makridakis, S., Spiliotis, E., Assimakopoulos, V.: The M5 competition: background, organization, and implementation. Int. J. Forecast. 38, 1325–1336 (2021)
Matheny, M.E., Whicher, D., Israni, S.T.: Artificial intelligence in health care: a report from the national academy of medicine. JAMA 323(6), 509–510 (2020)
Meir, R., El-Yaniv, R., Ben-David, S.: Localized boosting. In: COLT, pp. 190–199. Citeseer (2000)
Nwaokorie, A., Fey, D.: Personalised medicine for colorectal cancer using mechanism-based machine learning models. Int. J. Mol. Sci. 22(18), 9970 (2021)
Petropoulos, F., et al.: Forecasting: theory and practice. Int. J. Forecast. 38(3), 705–871 (2022). https://doi.org/10.1016/j.ijforecast.2021.11.001
Pryss, R., Reichert, M., Langguth, B., Schlee, W.: Mobile crowd sensing services for tinnitus assessment, therapy, and research. In: 2015 IEEE International Conference on Mobile Services, pp. 352–359. IEEE (2015)
Roorda, B., Heij, C.: Global total least squares modeling of multivariable time series. IEEE Trans. Autom. Control 40(1), 50–63 (1995)
Rožanec, J., Trajkova, E., Kenda, K., Fortuna, B., Mladenić, D.: Explaining bad forecasts in global time series models. Appl. Sci. 11(19), 9243 (2021)
Schlee, W., et al.: Towards a unification of treatments and interventions for tinnitus patients: the EU research and innovation action UNITI. In: Progress in Brain Research, pp. 441–451. Elsevier BV (2021)
Sedgwick, P.: What is recall bias? BMJ 344 (2012)
Unnikrishnan, V., et al.: Entity-level stream classification: exploiting entity similarity to label the future observations referring to an entity. Int. J. Data Sci. Anal. 9(1), 1–15 (2020)
Unnikrishnan, V., et al.: Love thy neighbours: a framework for error-driven discovery of useful neighbourhoods for one-step forecasts on EMA data. In: 2021 IEEE 34th International Symposium on Computer-Based Medical Systems (CBMS), pp. 295–300. IEEE (2021)
Vogel, C., Schobel, J., Schlee, W., Engelke, M., Pryss, R.: UNITI mobile-EMI-apps for a large-scale European study on tinnitus. In: 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), pp. 2358–2362. IEEE (2021)
Wilkinson, J., et al.: Time to reality check the promises of machine learning-powered precision medicine. Lancet Digit. Health 2, e677–e680 (2020)
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
Unnikrishnan, V. et al. (2023). A Similarity-Guided Framework for Error-Driven Discovery of Patient Neighbourhoods in EMA Data. In: Crémilleux, B., Hess, S., Nijssen, S. (eds) Advances in Intelligent Data Analysis XXI. IDA 2023. Lecture Notes in Computer Science, vol 13876. Springer, Cham. https://doi.org/10.1007/978-3-031-30047-9_36
Download citation
DOI: https://doi.org/10.1007/978-3-031-30047-9_36
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-30046-2
Online ISBN: 978-3-031-30047-9
eBook Packages: Computer ScienceComputer Science (R0)