To develop a predictive model using holistic EHR data and social determinants of health (SDOH) to accurately predict same-day cancellations (DOS) in elective urologic procedures, thereby improving surgical efficiency and patient outcomes.
Key Findings:
The DOS cancellation rate in the cohort was 17.5% (131 out of 778), indicating a significant area for improvement in surgical scheduling.
Hospital-related causes were the most common reasons for same-day cancellations, highlighting the need for operational changes.
Statistical prediction models show promise in predicting surgical cancellations, suggesting a pathway for enhanced resource allocation.
Interpretation:
The predictive model incorporating SDOH may facilitate early identification of patients at risk for DOS cancellations, enabling targeted interventions that could improve surgical efficiency and patient care.
Limitations:
Inconsistent reporting of SDOH in the EHR may affect data accuracy and introduce bias.
The study was conducted at a single institution, limiting generalizability and applicability to other settings.
Conclusion:
A predictive model using EHR data and SDOH can enhance the understanding of factors leading to DOS cancellations, potentially improving surgical efficiency in urology and informing future research on SDOH.
