Related Experiment Video
Updated: May 15, 2025

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
Published on: February 23, 2024
Artificial intelligence's contribution to biomedical literature search: revolutionizing or complicating?
Rui Yip1,2, Young Joo Sun1,2, Alexander G Bassuk3
1Molecular Surgery Laboratory, Stanford University, Palo Alto, California, United States of America.
Conversational AI like ChatGPT shows potential for scientific literature searches but has limitations in accuracy and relevance. User tools improve performance, yet rigorous comparative assessments are essential for reliable AI integration in research.
Area of Science:
- Biomedical Research
- Medical Informatics
- Artificial Intelligence
Background:
- Conversational AI, exemplified by ChatGPT, is increasingly used for scientific literature reviews and summaries.
- Widespread adoption by clinicians and researchers outpaces comparative evidence on its utility.
- There's a need to evaluate AI tools from an end-user perspective in scientific literature searching.
Purpose of the Study:
- To explore the utility of ChatGPT for literature search from the perspective of clinicians and biomedical researchers.
- To quantitatively compare basic ChatGPT against conventional search engines (Google, PubMed).
- To assess the impact of ChatGPT user-support tools on literature search performance across diverse scenarios.
Main Methods:
- Quantitative comparison of basic ChatGPT versus Google and PubMed for literature search.
- Testing ChatGPT with user-support tools (plugins, web-browsing, prompt-engineering, custom-GPTs).
- Evaluation across four scenarios: high-interest, niche, hypothesis generation, and emerging clinical topics.
Main Results:
- Basic ChatGPT exhibited limitations in consistency, accuracy, and relevancy.
- User-support tools enhanced ChatGPT's performance, but limitations remained.
- Different search scenarios presented unique challenges, including information overload and sparse literature.
Conclusions:
- Conversational AI tools like ChatGPT have potential but also pitfalls for scientific literature searches.
- User-support tools can mitigate some limitations but do not fully resolve them.
- Rigorous comparative assessments are crucial before widespread integration of AI in scientific research.
Related Concept Videos
Non-equilibrium in the Cell
Combination Therapies and Personalized Medicine
The combination of the drug acetazolamide and sulforaphane is a good example of combination therapy to treat cancer. The cells in the interior of a large tumor often die due to the hypoxic and...
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...
Genomics
Synthetic Biology
Golden rice
Golden rice is a genetically modified...
Imaging Biological Samples with Optical Microscopy
In optical microscopy, the specimen to be viewed is placed on a glass slide and clipped on the stage...

