Key result
A claims-based algorithm incorporating patient characteristics and healthcare utilization predicted all-cause 30-day readmission in patients with type 2 diabetes (c-statistic = 0.82).
Why the study?
Can a claims-based algorithm predict all-cause 30-day readmission in hospitalized Medicare patients with type 2 diabetes?
Population
63,237 hospitalized Medicare Advantage patients with type 2 diabetes, aged 18-90, with ≥12 months'…
Design
Cohort
Follow-up
30 days
Authors
Loading...
May identify high-risk T2DM patients for readmission programs via claims data; leaves open prospective validation before use.
Cohort (n=63,237)
Can a claims-based algorithm predict all-cause 30-day readmission in hospitalized Medicare patients with type 2 diabetes?
Effect estimate: c-statistic 0.82
A claims-based algorithm using 14 variables demonstrated good discriminant ability (c-statistic = 0.82) for predicting 30-day readmission in Medicare patients with type 2 diabetes.
Collins et al. (2017) conducted a cohort in Type 2 diabetes (n=63,237). Patient characteristics and healthcare utilization was evaluated on All-cause 30 day readmission (c-statistic 0.82). A claims-based algorithm incorporating patient characteristics and healthcare utilization predicted all-cause 30-day readmission in patients with type 2 diabetes (c-statistic = 0.82).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: