Related Experiment Video
Updated: May 8, 2026
Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
Predictive Utility of Epic's Health Composite Score for Same-Day Cancellation in Cataract Surgery
Chi Phan1, Iden Amiri1, Marc Levi2
1Department of Ophthalmology, University of North Carolina, Chapel Hill, NC, USA.
Purpose:
To evaluate the predictive utility of the Epic Health Composite Score (HCS), an automated electronic health record (EHR)-derived risk stratification tool, for perioperative outcomes in cataract surgery.
Patients And Methods:
This retrospective cohort study included 1204 adult patients who underwent elective phacoemulsification with intraocular lens implantation at the UNC Hillsborough Hospital Campus between January 2024 and January 2025. Epic HCS was analyzed as a continuous variable (per 5-point increase) and categorically (low risk: 0-8, medium risk: 9-20, high risk: ≥21). Perioperative outcomes assessed included same-day cancellation, operative duration, and anesthesia type selection. Other outcomes included surgical complications, prolonged inflammation, and visual acuity at postoperative month 1. Multivariable regression models adjusted for cataract complexity, ocular comorbidities, prior ocular surgery, and surgeon training level.
Results:
The cohort included 268 (22.3%) low-risk, 641 (53.2%) medium-risk, and 295 (24.5%) high-risk patients. Same-day cancellation occurred in 53 cases (4.4%) and was 3.0%, 3.9%, and 6.8% for low-, medium-, and high-risk HCS categories, respectively (p = 0.060). Each 5-point increase in Epic HCS was independently associated with 23% higher odds of same-day cancellation (adjusted OR 1.23; 95% CI, 1.10-1.38; p<0.001). The model demonstrated moderate discriminative ability (AUC = 0.632). Epic HCS showed no association with operative duration, anesthesia selection, surgical complications, prolonged postoperative inflammation, or visual outcomes, which were instead predicted by ophthalmic-specific factors including cataract complexity, prior ocular surgery, and retinal or optic nerve pathology, as well as surgeon training level.
Conclusion:
The Epic HCS independently predicts same-day surgical cancellation in cataract surgery patients but does not predict surgical outcomes. These findings support the utility of automated EHR-based risk scores for preoperative triage and care coordination to reduce cancellations, while underscoring that cataract surgery outcomes remain primarily determined by ophthalmic rather than systemic factors.
