Abstract
Vast amounts of data are collected about elderly patients diagnosed with chronic conditions and receiving care in telehealth services. The potential to discover hidden patterns in the collected data can be crucial in making effective decisions on dissemination of services and lead to improved quality of care for patients. In this research, we investigate a knowledge discovery method that applies a fusion of dimension reduction and classification algorithms to discover interesting patterns in patient data. The research premise is that discovery of such patterns could help explain unique features about patients who are likely or unlikely to have an adverse event. This is a unique and innovative technique that utilizes the best of probability, rules, random trees and association algorithms for; (a) feature selection, (b) predictive modelling and (c) frequent pattern mining. The proposed method has been applied in a case study context to discover interesting patterns and features in patients participating in telehealth services. The results of the models developed shows that identification of best feature set can lead to accurate predictors of adverse events as well as effective in generation of frequent patterns and discovery of interesting features in varying patient cohort.
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
Xiao, S., Hu, Y., Han, J., Zhou, R., Wen, J.: Bayesian networks-based association rules and knowledge reuse in maintenance decision-making of industrial product-service systems. Procedia CIRP 47, 198–203 (2016)
Liu, B., Hsu, W., Ma, Y.: Mining, integrating classification and association rule. In: KDD (1988)
Inibhunu, C., Schauer, A., Redwood, O., Clifford, P., McGregor, C.: The impact of gender, medical history and vital status on emergency visits and hospital admissions: a remote patient monitoring case study. In: IEEE LSC, Sidney, Australia (2017)
Weng, C.-H.: Discovering highly expected utility itemsets for revenue prediction. Knowl.-Based Syst. 104, 39–51 (2016)
D’Angelo, G., Rampone, S., Palmieri, F.: Developing a trust model for pervasive computing based on Apriori association rules learning and Bayesian classification. Soft Comput. 21, 6297–6315 (2017)
Gao, Y., Xua, A., Hua, P.J.-H., Cheng, T.-H.: Incorporating association rule networks in feature category-weighted naive Bayes model to support weaning decision making. Decis. Support Syst. 96, 27–38 (2017)
Fowkes, J., Sutton, C.: A Bayesian network model for interesting itemsets. In: Frasconi, P., Landwehr, N., Manco, G., Vreeken, J. (eds.) ECML PKDD 2016. LNCS (LNAI), vol. 9852, pp. 410–425. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46227-1_26
Yang, T., et al.: Improve the prediction accuracy of Naïve Bayes classifier with association rule mining. In: IEEE 2nd International Conference on Big Data Security on Cloud (2016)
Mai, T., Vo, B., Nguyen, L.T.: A lattice-based approach for mining high utility association rules. Inf. Sci. 399, 81–97 (2017)
Song, K., Lee, K.: Predictability-based collective class association rule mining. Expert Syst. Appl. 79, 1–7 (2017)
Inibhunu, C., Schauer, A., Redwood, O., Clifford, P., McGregor, C.: Predicting hospital admissions and emergency room visits using remote home monitoring data. In: IEEE LSC, Sidney, Australia (2017)
Frank, E., Hall, M.A., Witten, I.H.: Data Mining: Practical Machine Learning Tools and Techniques, 4edn. Morgan Kaufmann, Burlington (2016)
Vreeken, J., Tatti, N.: Interesting patterns. In: Aggarwal, C.C., Han, J. (eds.) Frequent Pattern Mining, pp. 105–134. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-07821-2_5
BPUK. http://www.bloodpressureuk.org/BloodPressureandyou/Thebasics/Bloodpressurechart
Acknowledgments
We would like to thank Alaya Care, We Care and Southlake Regional Hospital for their collaboration on the research grant from Ontario Centres of Excellence Advancing Health (MIS#23823) that generated data that was used as experimental data for this research.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Inibhunu, C., McGregor, C. (2018). Fusing Dimension Reduction and Classification for Mining Interesting Frequent Patterns in Patients Data. In: Perner, P. (eds) Machine Learning and Data Mining in Pattern Recognition. MLDM 2018. Lecture Notes in Computer Science(), vol 10935. Springer, Cham. https://doi.org/10.1007/978-3-319-96133-0_1
Download citation
DOI: https://doi.org/10.1007/978-3-319-96133-0_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-96132-3
Online ISBN: 978-3-319-96133-0
eBook Packages: Computer ScienceComputer Science (R0)