Hospitals routinely collect admitted patients’ data for administrative purposes and for reporting to the government and health insurers. These heterogeneous and mostly untapped data contain rich semantic information about patients’ health conditions in the form of standard disease codes. These traces of clinical information can be aggregated over patients to understand how their health progresses over time. When applied on particular chronic disease patients, this approach can potentially help in understanding chronic disease comorbidities as well as in the knowledge discovery on how the chronic disease progresses over time. In this paper, we propose a network-based approach to extract semantic information from hospital administrative data in order to develop a representation of chronic disease progression specifically – type 2 diabetes. We then propose measures for attribution adjustment that ranks the more prevalent comorbidities in chronic patients higher, compared to the non-chronic ones. We also have applied the framework on the administrative data of 2,760 sampled patients to understand how diabetes progresses over time through different comorbidities. This understanding can be effectively converted to actionable intelligence that can be useful in the formulation of better health policy and resource management.
Other information: Accepted in ACSW ’17, January 31-February 03, 2017, Geelong, Australia © 2017 ACM. ISBN 978-1-4503-4768-6/17/01…$15.00 DOI: