Unmasking Biases and Navigating Pitfalls in the Ophthalmic Artificial Intelligence Lifecycle: A Review

TL;DR

This review discusses the AI lifecycle in ophthalmology, highlighting biases and pitfalls at each stage, and proposes strategies to mitigate risks for safe and effective AI deployment in eye care.

Contribution

It provides a comprehensive analysis of potential biases and pitfalls in the ophthalmic AI lifecycle and suggests mitigation strategies for each stage.

Findings

Identifies key biases at each AI lifecycle stage.

Highlights risks of harm in ophthalmic AI applications.

Recommends strategies for bias mitigation and safety.

Abstract

Over the past two decades, exponential growth in data availability, computational power, and newly available modeling techniques has led to an expansion in interest, investment, and research in Artificial Intelligence (AI) applications. Ophthalmology is one of many fields that seek to benefit from AI given the advent of telemedicine screening programs and the use of ancillary imaging. However, before AI can be widely deployed, further work must be done to avoid the pitfalls within the AI lifecycle. This review article breaks down the AI lifecycle into seven steps: data collection; defining the model task; data pre-processing and labeling; model development; model evaluation and validation; deployment; and finally, post-deployment evaluation, monitoring, and system recalibration and delves into the risks for harm at each step and strategies for mitigating them.