Accurate clinical documentation has become one of the most time-consuming aspects of modern ophthalmic practice, with multiple measurements, imaging findings, medications, and management decisions critical for patient care.

In response, many clinicians are exploring the use of ‘ambient’ artificial intelligence (AI) scribes – systems that transcribe clinician-patient conversations and generate structured medical notes.

Recognising the importance of rigorous evaluation, i-scribe, an AI documentation platform, has placed clinical research at the centre of its development strategy, conducting specialty-specific studies to assess the real-world performance of AI scribes in ophthalmology.

Unlike many technology solutions developed primarily outside clinical practice, i-scribe was founded by a team that includes practising ophthalmologists and clinicians. Their clinical experience helped shape the early development of the platform, with the goal of creating a documentation tool that reflects the practical realities of ophthalmology consultations.

In collaboration with i-scribe, and with the aim of refining AI documentation capabilities, researchers from Monash Health, Department of Otolaryngology, Head and Neck Surgery and Monash University Department of Surgery analysed recordings from 26 real-world ophthalmology consultations, conducted with patient consent. To ensure a fair comparison, three AI scribe systems, including i-scribe and two competing platforms, were tested under identical conditions.1

Each consultation recording was replayed via an external speaker to three identical laptops running the different systems. A large language model was used to generate a gold-standard through continuous real-world feedback, helping refine the system’s ability to capture ophthalmic terminology, measurements, and structured examination findings accurately.

While i-scribe demonstrated strong performance across all domains, insights from the study were used to further refine the system, with particular focus on minimising unsupported content and optimising performance in more complex consultations.

TAKE UP OF AI DOCUMENTATION

Practice management data presented at the Australasian Society of Cataract and Refractive Surgeons (AUSCRS) conference in 2025 suggest AI documentation platforms are already gaining traction within the profession, with more than one in five Australian ophthalmologists having engaged with i-scribe alone during its rollout.

Co-founder and practising ophthalmologist Dr Jamie Chew said the research driven development of iScribe reflects the company’s commitment to clinical validation.

“i-scribe is fine-tuned for ophthalmology, with specialty-specific templates and training that recognise terms like CCT, VA, and IOP (central corneal thickness, visual acuity, and intraocular pressure), while adapting language depending on whether notes are written for optometrists or GPs,” Dr Chew said.

“As AI tools increasingly enter clinical workflows, Dr Chew said studies such as this may play an important role in guiding their adoption, ensuring the enhancement of both clinical efficiency and patient care.

References available at mivision.com.au.