Activity Measure for Postacute Care to Predict Discharge Destination After Surgery

Area of Science:

• Healthcare outcomes research
• Surgical quality improvement
• Predictive modeling in medicine

Background:

• Accurate prediction of discharge disposition is crucial for healthcare resource allocation.
• Existing risk calculators vary in their performance for predicting post-acute care needs.
• The Activity Measure for Post-Acute Care (AM-PAC) is a functional assessment tool with potential predictive capabilities.

Purpose of the Study:

• To compare the predictive performance of the AM-PAC model against the established American College of Surgeons National Surgical Quality Improvement Program (NSQIP) risk calculator.
• To evaluate the utility of the AM-PAC model in identifying patients likely to be discharged to post-acute care.
• To assess the area under the receiver operating characteristic curve (AUC) for both models.

Main Methods:

• Retrospective analysis of patient data.
• Calculation of the area under the receiver operating characteristic curve (AUC) for both the AM-PAC and NSQIP models.
• Statistical comparison of the predictive accuracy between the two models.

Main Results:

• The AM-PAC model demonstrated an AUC comparable to the NSQIP risk calculator for predicting discharge to post-acute care.
• Both models exhibited similar performance, suggesting the AM-PAC tool is a viable option for predicting post-acute care needs.
• Detailed AUC values indicate the discriminative ability of each model.

Conclusions:

• The AM-PAC model offers comparable predictive accuracy to the NSQIP risk calculator for post-acute care discharge.
• Healthcare providers can consider the AM-PAC tool as an effective measure for predicting patient disposition.
• Further research may explore integrating functional status data for enhanced predictive accuracy.