This presentation will expose attendees to a machine learning tool and analytical approach for the purpose of identifying patient subgroups within a healthcare dataset like one may obtain from their clinical site (e.g., insurance claims information or EHR). The value of this task is in understanding unique patient groups, their needs and improving patient-centered care. Attendees will learn when to apply the analytical approach, how it works, be led through an exercise demonstrating the process, interpretation of the results, and an open discussion period.
- Describe what a machine learning clustering algorithm can do with a large dataset such as the EHR.
- Identify applications for clustering at their own site.
- Determine next-steps in cluster analysis process at own site.
- Denaxas, S. C., Asselbergs, F. W., & Moore, J. H. (2016). The tip of the iceberg: challenges of accessing hospital electronic health record data for biological data mining.
- Miotto, R., Li, L., Kidd, B. A., & Dudley, J. T. (2016). Deep patient: an unsupervised representation to predict the future of patients from the electronic health records. Scientific reports, 6, 26094.
- Nelson, R., & Staggers, N. (2016). Health informatics: An interprofessional approach. Elsevier Health Sciences.
- Tomar, D., & Agarwal, S. (2013). A survey on Data Mining approaches for Healthcare. International Journal of Bio-Science and Bio-Technology, 5(5), 241-266.
- Vayena, E. & Blasimme, A. (2017). Bioethical Inquiry, 14, 501-513. https://doi.org/10.1007/s11673-017-9809-6