A Framework for Automating Psychiatric Distress Screening in Ophthalmology Clinics Using an EHR-Derived AI Algorithm

Abstract

Purpose In patients with ophthalmic disorders, psychosocial risk factors play an important role in morbidity and mortality. Proper and early psychiatric screening can result in prompt intervention and mitigate its impact. Because screening is resource intensive, we developed a framework for automating screening using an electronic health record (EHR)-derived artificial intelligence (AI) algorithm. Methods Subjects came from the Duke Ophthalmic Registry, a retrospective EHR database for the Duke Eye Center. Inclusion criteria included at least two encounters and a minimum of 1 year of follow-up. Presence of distress was defined at the encounter level using a computable phenotype. Risk factors included available EHR history. At each encounter, risk factors were used to discriminate psychiatric status. Model performance was evaluated using area under the receiver operating characteristic (ROC) curve and area under the precision–recall curve (PR AUC). Variable importance was presented using odds ratios (ORs). Results Our cohort included 358,135 encounters from 40,326 patients with an average of nine encounters per patient over 4 years. The ROC and PR AUC were 0.91 and 0.55, respectively. Of the top 25 predictors, the majority were related to existing distress, but some indicated stressful conditions, including chemotherapy (OR = 1.36), esophageal disorders (OR = 1.31), central pain syndrome (OR = 1.25), and headaches (OR = 1.24). Conclusions Psychiatric distress in ophthalmology patients can be monitored passively using an AI algorithm trained on existing EHR data. Translational Relevance When paired with an effective referral and treatment program, such algorithms may improve health outcomes in ophthalmology.

Lessons From The Glaucoma Foundation Think Tank 2023: A Patient-Centric Approach to Glaucoma

“…First, AI may facilitate patient selection and recruitment, identify suitable candidates' trials based on analysis of complex information from the EHR, and/or use predictive models to identify patients at high risk of progression, as shown in multiple studies. 14,[99][100][101] Second, AI may also help with data collection, analysis, and visualization. Furthermore, AI may automate and improve the quality of clinical data assessment by supplementing or replacing subjective human reading centers.…”

“…A novel solution for the myriad of challenges facing neuroprotection trials is the use of AI and deep-learning approaches. First, AI may facilitate patient selection and recruitment, identify suitable candidates' trials based on analysis of complex information from the EHR, and/or use predictive models to identify patients at high risk of progression, as shown in multiple studies [99][100][101][102]. Second, AI may also help with data collection, analysis, and visualization.…”