AI Article Synopsis

  • Advances in deep learning systems show promise for improving clinical decision-making in medical diagnoses, but the effectiveness of combining physician expertise with machine learning is still uncertain, particularly when dealing with underrepresented populations.
  • A large-scale study involving nearly 850 physicians evaluated their diagnostic accuracy using a teledermatology simulation with 364 skin disease images, revealing that specialist dermatologists had an accuracy of 38% while primary-care physicians had only 19%.
  • Although the integration of fair deep learning assistance improved overall diagnostic accuracy by over 33%, it highlighted and worsened the existing diagnostic disparities between skin tones, showing that enhancing accuracy doesn't eliminate bias in the system.

Article Abstract

Although advances in deep learning systems for image-based medical diagnosis demonstrate their potential to augment clinical decision-making, the effectiveness of physician-machine partnerships remains an open question, in part because physicians and algorithms are both susceptible to systematic errors, especially for diagnosis of underrepresented populations. Here we present results from a large-scale digital experiment involving board-certified dermatologists (n = 389) and primary-care physicians (n = 459) from 39 countries to evaluate the accuracy of diagnoses submitted by physicians in a store-and-forward teledermatology simulation. In this experiment, physicians were presented with 364 images spanning 46 skin diseases and asked to submit up to four differential diagnoses. Specialists and generalists achieved diagnostic accuracies of 38% and 19%, respectively, but both specialists and generalists were four percentage points less accurate for the diagnosis of images of dark skin as compared to light skin. Fair deep learning system decision support improved the diagnostic accuracy of both specialists and generalists by more than 33%, but exacerbated the gap in the diagnostic accuracy of generalists across skin tones. These results demonstrate that well-designed physician-machine partnerships can enhance the diagnostic accuracy of physicians, illustrating that success in improving overall diagnostic accuracy does not necessarily address bias.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10878981PMC
http://dx.doi.org/10.1038/s41591-023-02728-3DOI Listing

Publication Analysis

Top Keywords

diagnostic accuracy
16
specialists generalists
12
decision support
8
skin tones
8
deep learning
8
physician-machine partnerships
8
skin
6
physicians
5
accuracy
5
diagnostic
5

Similar Publications

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!