Key result
An administrative claim-based algorithm predicted 30-day readmission with an AUC ≥0.75 for medical patients and ≥0.65 for chronic pancreatitis patients, performing similarly to clinical models.
Why the study?
Can an administrative claim-based algorithm using high-dimensional data accurately predict 30-day hospital readmissions in medical and chronic pancreatitis patients?
Population
46,209 hospital admissions, comprising medical patients and patients with chronic pancreatitis from two…
Design
Cohort
Follow-up
30 days
Authors
Loading...
May enable scalable readmission prediction from claims data alone; hypothesis-generating and should not yet change practice.
Observational (n=46,209)
Yes
Can an administrative claim-based algorithm using high-dimensional data accurately predict 30-day hospital readmissions in medical and chronic pancreatitis patients?
An administrative claim-based algorithm using high-dimensional data can predict 30-day hospital readmissions with performance comparable to models requiring clinical data.
He et al. (2013) conducted an observational in Medical patients and chronic pancreatitis (n=46,209). Administrative claim-based algorithm vs. State-of-the-art readmission models requiring clinical data was evaluated on 30-day readmission prediction performance (AUC). An administrative claim-based algorithm predicted 30-day readmission with an AUC ≥0.75 for medical patients and ≥0.65 for chronic pancreatitis patients, performing similarly to clinical models.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: