Back

Emergency Department Discharge Center Program Evaluation from a "Learning Organization" lens: Methods, Lessons Learned, and Future Directions

Razack, B. S.; Mahabir, N. B.; Iyeke, L.; Jordan, L.; Hope, R.; Diaz, E.; Barcia, L.; Fuzailov, D.; Willis, H.; Gizzi-Murphy, M.; Davis, F.; Berman, A.; Richman, M.; Kwon, N.

2024-08-01 emergency medicine
10.1101/2024.07.30.24310873 medRxiv
Show abstract

Our EDs Discharge Center (EDDC) facilitates appointments and paper-based social determinants of health (SDoH) screening. No criteria guide EDDC utilization. The EDs provider-administrator-run, patient-satisfying follow-up call program contacts only [~]25% of discharges. We describe Learning Organization-principle-guided evaluation of EDDC efficiency, aiming to create EDDC time to expand the follow-up program. We reviewed appointment-making, SDoH-screening, and follow-up program data. We surveyed patients to determine whether adopting SHOUT tool criteria (no home, no primary care physician, or insurance) might yield more-judicious EDDC utilization. EDDC staffs 20 minutes/patient yielded fewer ED returns and admissions. Most patients improved post-discharge and made appointments themselves; 6% met SHOUT criteria for EDDC assistance; 4.5% would benefit from SDoH screening. Adopting SHOUT criteria would create significant time for EDDC-staffed follow-up program expansion. QR-code-accessible SDoH surveys would screen thousands more patients, minimizing EDDC staff involvement, saving 95% of the effort while retaining 100% of the benefit.

Matching journals

The top 4 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.