Related Experiment Video
Updated: Jun 30, 2025

Determining the Likelihood of Variant Pathogenicity Using Amino Acid-level Signal-to-Noise Analysis of Genetic Variation
Published on: January 16, 2019
Recognition of Genetic Conditions After Learning With Images Created Using Generative Artificial Intelligence
Rebekah L Waikel1, Amna A Othman1, Tanviben Patel1
1Medical Genetics Branch, National Human Genome Research Institute, Bethesda, Maryland.
Real and AI-generated images improved pediatric residents' ability to recognize Kabuki syndrome (KS) and Noonan syndrome (NS). Real images were most effective, but AI images also showed promise for rare genetic conditions.
Area of Science:
- Medical Genetics
- Medical Education
- Artificial Intelligence in Medicine
Background:
- Pediatric residency programs face challenges in genetics education due to a lack of standardization and a shortage of medical geneticists.
- Innovative educational tools are needed to enhance residents' diagnostic skills for rare genetic syndromes.
Purpose of the Study:
- To compare the effectiveness of different educational interventions in improving pediatric residents' recognition of Kabuki syndrome (KS) and Noonan syndrome (NS).
- To evaluate the utility of generative artificial intelligence (AI) in creating educational images for rare genetic conditions.
Main Methods:
- A comparative effectiveness study involving US pediatric residents.
- Generative AI was used to create images of children with KS and NS.
- Residents were surveyed after viewing images from four interventions: text-only descriptions, real images, and two types of AI-generated images.
Main Results:
- Both real and AI-generated images significantly improved the recognition of KS and NS compared to text-only descriptions.
- Real images demonstrated the highest sensitivity for diagnosing KS and NS.
- AI-generated images were non-inferior to real images and significantly reduced resident uncertainty in diagnosing these conditions.
Conclusions:
- Visual aids, including both real and AI-generated images, are valuable tools for teaching rare genetic syndromes to pediatric residents.
- Generative AI offers a promising adjunctive educational resource, particularly for conditions with limited real-world image availability.
- Further integration of AI in medical education can help bridge gaps in specialized knowledge and improve diagnostic accuracy.
Related Concept Videos
What is Genetic Engineering?
Human Genetics
The complex relationship between genetics and psychology is observable through common biological components such...
Genetic Screens
Forward genetic screens
Forward or “classical” genetic screens involve creating random mutations in an organism’s DNA using radiation, mutagens, or insertion of additional bases, which...
Behavioral Genetics and Its Designs
The primary methodologies used in behavior genetics include family studies, twin studies, and adoption studies, each providing unique...
Genomic Imprinting and Inheritance
The expression of some genes depends on which parent passed the gene to the offspring, through a phenomenon known as...
Non-equilibrium in the Cell

