Development and Clinical Validation of an Artificial Intelligence-Based Automated Visual Acuity Testing System

TL;DR

This paper presents an AI-based system for automated visual acuity testing that was validated in a clinical setting and showed good agreement with manual testing.

Contribution

The novel contribution is an AI-driven automated visual acuity testing system with integrated speech and image recognition for self-administered assessments.

Findings

The fine-tuned model reduced word error rates for letters and numbers significantly.

Automated unaided VA showed good agreement with manual VA (ICC = 0.77).

User experience remained positive despite longer testing times.

Abstract

Background: To develop and validate an automated visual acuity (VA) testing system integrating artificial intelligence (AI)–driven speech and image recognition technologies, enabling self-administered, clinic-based VA assessment; Methods: The system incorporated a fine-tuned Whisper speech-recognition model with Silero voice activity detection and pose estimation through facial landmark and ArUco marker detection. A state-driven interface guided users through sequential testing with and without a pinhole. Speech recognition was enhanced using a local Singaporean English dataset. Laboratory validation assessed speech and pose recognition performance, while clinical validation compared automated and manual VA testing at a tertiary eye clinic; Results: The fine-tuned model reduced word error rates from 17.83% to 9.81% for letters and 2.76% to 1.97% for numbers. Pose detection accurately identified valid occluder states. Among 72 participants (144 eyes), automated unaided VA showed good agreement with manual VA (ICC = 0.77, 95% CI 0.62–0.85), while pinhole VA demonstrated moderate agreement (ICC = 0.63, 95% CI 0.25–0.83). Automated testing took longer (132.1 ± 47.5 s vs. 97.1 ± 47.8 s; p < 0.001), but user experience remained positive (mean Likert scale score 4.3 ± 0.8); Conclusions: The AI-based automated VA system delivered accurate, reliable, and user-friendly performance, supporting its feasibility for clinical implementation.

Figures