Towards Realization of Augmented Intelligence in Dermatology: Advances and Future Directions

TL;DR

This paper reviews recent advances in AI for dermatology, emphasizing the need for clinical validation and integration of deep learning systems to achieve augmented intelligence that effectively supports dermatologists.

Contribution

It highlights the progress and challenges in translating dermatology AI from in silico models to clinically validated tools for real-world use.

Findings

AI algorithms excel in skin disease image classification but lack clinical validation.

Current models mainly perform binary classification, not reflecting dermatologists' diagnostic complexity.

Addressing validation, equity, and integration issues is crucial for clinical adoption.

Abstract

Artificial intelligence (AI) algorithms using deep learning have advanced the classification of skin disease images; however these algorithms have been mostly applied "in silico" and not validated clinically. Most dermatology AI algorithms perform binary classification tasks (e.g. malignancy versus benign lesions), but this task is not representative of dermatologists' diagnostic range. The American Academy of Dermatology Task Force on Augmented Intelligence published a position statement emphasizing the importance of clinical validation to create human-computer synergy, termed augmented intelligence (AuI). Liu et al's recent paper, "A deep learning system for differential diagnosis of skin diseases" represents a significant advancement of AI in dermatology, bringing it closer to clinical impact. However, significant issues must be addressed before this algorithm can be integrated into clinical workflow. These issues include accurate and equitable model development, defining and assessing appropriate clinical outcomes, and real-world integration.