Integrating quantitative biometrics and automated risk stratification for ophthalmic surgical triage
Year: 2026
Type: article
Abstract: Ophthalmology generates extensive quantitative data from ocular biometry and imaging, yet these device-derived measurements are often separated from medical, social, and utilization data in the electronic health record (EHR). No validated ophthalmic tool currently integrates these streams for real-time, patient-specific perioperative decision support. This mini-review examines how automated EHR-based risk stratification and quantitative ocular biometrics could support perioperative decision-making. Across surgical specialties, cancellation models using demographic, comorbidity, socioeconomic, and appointment-related variables have achieved development areas under the curve (AUC) of 0.75–0.92 with a validation range of 0.70–0.74. When the bundle is paired with targeted care pathways, reduced same-day cancellations have been observed, although bundle designs prevent quantifying the independent contribution of the model. In cataract surgery, Epic's Health Composite Score independently predicts same-day cancellation but provides only limited discrimination, and does not predict operative or postoperative outcomes, which remain more closely associated with ocular complexity and surgeon-related factors. Cataract and glaucoma literature identifies additional candidate predictors of technical complexity, surgical outcomes, and access, including pupil and lens characteristics, axial length, anterior chamber anatomy, prior ocular surgery, angle dimensions, conjunctival imaging, frailty, and social vulnerability. We propose an EHR-integrated framework with endpoint- and procedure-specific models for surgical readiness, technical complexity, and adverse outcomes. Each output should be linked to a defined response, such as patient navigation, anesthesia review, case assignment, operative setting, equipment planning, or intensified postoperative follow-up. Prospective multicenter development should assess whether model-guided interventions improve access, efficiency, and outcomes.
Source: Frontiers in Medicine
Authors: Jacob Craft, David Fleischman
Institution: University of North Carolina at Chapel Hill
Language: English
Subfield: Emergency Medical Services
Field: Health Professions
Domain: Health Sciences
Open Access status: gold
Estimated APC paid: $3,801
OpenAlex ID: W7224965173