Ontario Regional Blood Coordinating Network Hamilton, ON, Canada
Background/Case Studies: Canada’s Immunoglobulin (Ig) product demand is rising despite high product costs and global shortages. Detection of groups with high utilization rates can help with resource planning for Ig products. This study aims to uncover subgroups among the Ig recipients using electronic health records (EHRs).
Study
Design/Methods: The study included all Ig recipients (intravenous or subcutaneous) in a Canadian city from 2014 to 2020 and analyzed their EHRs, including blood inventory, recipient demographics, and laboratory test results. Patient clusters were derived based on patient characteristics and laboratory test data using K-means clustering. Clusters were interpreted using descriptive analyses and visualization techniques.
Results/Findings: Among the 4,112 recipients, six clusters were identified. Cluster 1 consisted of 62 (1.5%) patients, with 77.3% infusions occurring in emergency departments. Cluster 2, comprising 1,034 (25.1%) patients, had a median age of 4 years, while clusters 2-6 were predominantly adult patients with median ages between 46 and 60 years. Cluster 3 included 1,253 (30.5%) patients, with 86.4% of infusions administered in an inpatient setting. Clusters 4 and 5 comprised 1,272 (30.9%) and 408 (9.9%) patients, respectively, contributing to 27.1% and 62.2% of total Ig utilization. Cluster 6 contained 83 (2.0%) patients, all of whom received subcutaneous Ig treatments. Conclusions: This study represents the first to utilize a data-driven clustering approach for Ig utilization patterns using EHR data. Through this study, we obtained valuable insights into trends and patterns of Ig utilization, identified the patient characteristics associated with high demand for Ig, and gained a deeper understanding of patient segmentations and their specific needs.
Importance of research: These findings hold the potential to inform the development of personalized care plans and enable more efficient resource allocation strategies tailored to the specific requirements of different patient groups.
