AI Tool Demonstrates High Accuracy in Genetic Counseling Questions


  • Studies show that the AI tool ChatGPT can answer 83% of genetic counseling questions accurately, easing patient concerns.
  • Researchers at NYU Langone Health find ChatGPT performs best in genetic counseling queries and specific genetic disorders.
  • AI may aid patient education in gynecologic oncology but still needs input from human providers for optimal use.

In a groundbreaking study presented at the Society of Gynecologic Oncology’s Annual Meeting on Women’s Cancer, a team of researchers from NYU Langone Health and its Perlmutter Cancer Center unveiled the remarkable capabilities of a generative AI tool in answering common genetic counseling questions. 

Dr. Jharna M. Patel’s study showcased the potential of AI, particularly ChatGPT, in providing accurate and comprehensive responses related to genetic syndromes counseling in gynecologic oncology.

Study methodology and findings

The study involved consulting with gynecologic oncologists to select 40 frequently asked questions by patients, aligning with professional society guidelines. These questions were then inputted into ChatGPT version 3.4, prompting for answers. Subsequently, attending gynecologic oncologists evaluated the accuracy and comprehensiveness of the AI-generated responses.

The results were impressive, with ChatGPT providing correct and comprehensive answers to 82.5% of the questions, with the remaining responses either correct but not comprehensive or partially incorrect. Notably, none of the answers were deemed completely incorrect.

High accuracy in genetic counseling

Among the categories of questions, those on genetic counseling demonstrated the highest accuracy rates. For instance, all 20 questions in this category were answered with 100% accuracy by ChatGPT. Similarly, questions concerning specific genetic disorders, such as testing for differences in the BRCA1 or BRCA2 gene and Lynch syndrome, yielded high accuracy rates, further highlighting the AI tool’s proficiency in this domain.

Dr. Marina Stasenko, the senior study author, emphasized the potential for further enhancements in the AI tool’s performance through continued training on additional data and refining question sets. While the ultimate goal is to integrate this technology into clinical settings, it is envisioned as an assistant to human providers rather than a standalone solution.

The findings of this study underscore the promising role of generative AI, exemplified by ChatGPT, in addressing common genetic counseling queries in gynecologic oncology. With its high accuracy rates and potential for improvement, this AI tool stands poised to augment patient education and alleviate anxiety, ultimately contributing to more informed decision-making in cancer care.

The study’s authors, including Drs. Patel, Stasenko, Hermann, Growdon, and Aviki, hail from various departments within NYU Langone Health and NYU Grossman School of Medicine, collectively showcasing interdisciplinary collaboration in advancing healthcare through innovative AI solutions.

Disclaimer. The information provided is not trading advice. Cryptopolitan.com holds no liability for any investments made based on the information provided on this page. We strongly recommend independent research and/or consultation with a qualified professional before making any investment decisions.

Share link:

Benson Mawira

Benson is a blockchain reporter who has delved into industry news, on-chain analysis, non-fungible tokens (NFTs), Artificial Intelligence (AI), etc.His area of expertise is the cryptocurrency markets, fundamental and technical analysis.With his insightful coverage of everything in Financial Technologies, Benson has garnered a global readership.

Most read

Loading Most Read articles...

Stay on top of crypto news, get daily updates in your inbox

Related News

Subscribe to CryptoPolitan