Key result
Adding admission laboratory data to administrative models modestly enhanced the prediction of 90-day postdischarge deaths without readmission, but provided negligible benefit for 90-day readmissions.
Why the study?
Does adding admission numerical laboratory data to administrative models improve the prediction accuracy for 90-day postdischarge deaths and readmissions in cardiac patients?
Observational
Yes
Does adding admission numerical laboratory data to administrative models improve the prediction accuracy for 90-day postdischarge deaths and readmissions in cardiac patients?
Adding admission laboratory data to administrative claims models provides modest improvement in predicting 90-day postdischarge mortality but negligible benefit for predicting 90-day readmissions in cardiac patients.
Answers are grounded in this paper and cite their sources.
Laboratory data may modestly aid mortality prediction in administrative models; leaves open whether integration refines cardiac risk stratification.
Predictive modeling for postdischarge outcomes of inpatient care has been suboptimal. This study evaluated whether admission numerical laboratory data added to administrative models from New York and Minnesota hospitals would enhance the prediction accuracy for 90-day postdischarge deaths without readmission (PD-90) and 90-day readmissions (RA-90) following inpatient care for cardiac patients. Risk-adjustment models for the prediction of PD-90 and RA-90 were designed for acute myocardial infarction, percutaneous cardiac intervention, coronary artery bypass grafting, and congestive heart failure. Models were derived from hospital claims data and were then enhanced with admission laboratory predictive results. Case-level discrimination, goodness of fit, and calibration were used to compare administrative models (ADM) and laboratory predictive models (LAB). LAB models for the prediction of PD-90 were modestly enhanced over ADM, but negligible benefit was seen for RA-90. A consistent predictor of PD-90 and RA-90 was prolonged length of stay outliers from the index hospitalization.
No takes yet. Share an insight, caveat, or question.
Pine et al. (2016) conducted an observational in Cardiac patients (AMI, PCI, CABG, CHF). Admission numerical laboratory data vs. Administrative models was evaluated on 90-day postdischarge deaths without readmission (PD-90) and 90-day readmissions (RA-90). Adding admission laboratory data to administrative models modestly enhanced the prediction of 90-day postdischarge deaths without readmission, but provided negligible benefit for 90-day readmissions.
Synapse has enriched 10 related papers. Consider them for comparative context: