Evaluating ChatGPT-4omni in paediatric developmental screening: direct versus sequential prompts
Pathrada Traipidok1, Papichaya Srisombundit1, Nattaporn Tassanakijpanich1
1Prince of Songkla University Faculty of Medicine, Hat Yai, Songkhla, Thailand.
Insights
Large Language Models like ChatGPT-4o show promise for paediatric developmental screening. Direct Prompting was more sensitive, while Sequential Prompting was more specific in this study.
Area of Science:
- Pediatric Healthcare Technology
- Artificial Intelligence in Medicine
- Developmental Psychology
Background:
- Developmental screening is crucial for early intervention in children.
- Current screening methods can be time-consuming and resource-intensive.
- Large Language Models (LLMs) offer potential for innovative healthcare solutions.
Purpose of the Study:
- To evaluate the efficacy of ChatGPT-4o for paediatric developmental screening.
- To compare Direct and Sequential Prompting methods using ChatGPT-4o.
- To benchmark ChatGPT-4o's performance against the Bayley Scales of Infant Development, Third Edition.
Main Methods:
- 106 paediatric cases were analyzed.
- ChatGPT-4o was employed using Direct and Sequential Prompting techniques.
- Performance metrics included sensitivity, specificity, and overall accuracy.
Main Results:
- Direct Prompting achieved 73.42% sensitivity and 69.81% overall accuracy.
- Sequential Prompting demonstrated 62.96% specificity and 67.92% overall accuracy.
- Both LLM prompting methods showed potential in developmental screening.
Conclusions:
- ChatGPT-4o, via Direct and Sequential Prompting, can enhance paediatric developmental screening efficiency and accessibility.
- Direct Prompting exhibited higher sensitivity, whereas Sequential Prompting offered greater specificity.
- Further research is warranted to optimize LLM integration in clinical practice.
Abstract:
Integrating Large Language Models like ChatGPT-4omni (ChatGPT-4o) into paediatric healthcare could revolutionise developmental screening. This study evaluated ChatGPT-4o's efficacy in paediatric developmental screening using Direct and Sequential Prompting methods compared with the Bayley Scales of Infant Development, Third Edition. Among 106 paediatric cases, Direct Prompting showed a sensitivity of 73.42% and overall accuracy of 69.81%, while Sequential Prompting had a specificity of 62.96% and overall accuracy of 67.92%. Both methods demonstrate potential for improving the efficiency and accessibility of paediatric developmental screening, with Direct Prompts being more sensitive and Sequential Prompts more specific.
Related Concept Videos
Language Development
The critical period for language acquisition suggests that the ability to acquire language is at its peak early in life. As people age, this proficiency decreases. Language development begins very...
Introduction to Developmental Psychology
Three Developmental Domains
Physical Development
Physical processes, also known as maturation, encompass the biological changes that occur across an individual's life. These changes begin with genetic inheritance and continue through various stages, including growth in height and weight,...
Development of the Oral Microbiota


