Feasibility of an Artificial Intelligence Phone Call After Cataract Surgery

Feasibility of an Artificial Intelligence Phone Call for Post-operative Care Following Cataract Surgery in a Diverse Population

To analyze the evidence for clinical safety, usability, acceptability, satisfaction, appropriateness, and cost-effectiveness of Dora for recognizing patients who require additional in-person evaluation post cataract surgery. To assess Dora's sensitivity and specificity in cataract surgery management To determine what can be learnt to enhance AI technology in the field of ophthalmology especially when working with culturally diverse patients such as Punjabi and Chinese speaking patients.

Background: Cataract is defined as the degradation of the optical quality of the crystalline lens that affects vision and is the current leading cause of blindness worldwide. AI is set to revolutionize post-cataract surgery management by enhancing automation, increasing effectiveness, decreasing burdens placed on patients and the health care system. Ultimately, using AI-enabled automation could enhance patient management during and post cataract surgery.Cataract post-operative contact will be delivered by Dora agent, a natural language AI assistant. Aim and objective: Dora is a clinically safe, usable, appropriate, satisfactory and cost-effective AI technology for recognizing patients who require additional evaluation post cataract surgery.

Dora will phone patients on the day of cataract surgery (2 to 4 hours after discharge home) and again at postoperative week three. Dora calls made on the day of surgery will evaluate if the patient has any acute post-operative concerns like pain, and will prompt a postoperative day 1 visit if necessary. Calls to Dora at postoperative week three will result in either a follow-up to check refractive difficulties and/or confirmation of second eye surgery.

Clinical safety will be assessed using the comparison between Dora's clinical decision and the OT team's clinical decision.

System usability scale will be used to assess usability of the technology. The scores are 0-100, a score above a 68 would be considered above average and anything below 68 is below average

System usability scale will be used to assess appropriateness of the technology. The scores are 0-100, a score above a 68 would be considered above average and anything below 68 is below average

Cost effectiveness will be assessed by comparing the cost of the system to the clinic specific costs (resources used and potential staff-hours) and patient specific costs (travel and time needed to be taken off from work)

To determine what can be learnt to enhance AI technology in the field of ophthalmology especially when working with culturally diverse patients such as Punjabi and Chinese speaking patients by holding interviews from a randomly selected pool of applicants selected for an in-depth interview to better understand their experience with Dora such as challenges regarding communication and comprehension of the technology.

Inclusion Criteria: Patients who are undergoing uncomplicated cataract surgery at a high volume surgical centre. Exclusion Criteria: clinically significant complications during surgery that require more than the standard postop treatment or follow-up