2023 World Conference on Lung Cancer (Posters)-EP06.01. Concordance Between Generative AI GPT-4 and NCCN Guidelines: Biomarker-Driven Treatment Strategies in NSCLC

EP06.01. Concordance Between Generative AI GPT-4 and NCCN Guidelines: Biomarker-Driven Treatment Strategies in NSCLC - PDF(Abstract)

Back to course

Pdf Summary

This study evaluated the concordance between Generative Pretrained Transformer 4 (GPT-4), an advanced artificial intelligence (AI) system, and the 2023 National Comprehensive Cancer Network (NCCN) guidelines for biomarker-driven treatment strategies in non-small cell lung cancer (NSCLC). The researchers used 12 biomarker descriptors to query treatment options in GPT-4 and compared them to the NCCN guidelines. GPT-4 outputs were scored based on the proportion of NCCN-concordant recommendations.<br /><br />The results showed that all GPT-4 outputs included at least one NCCN-concordant recommendation, resulting in a 73% concordance rate for first- and second-line treatment options and a 100% concordance rate for the preferred option. None of the outputs were factually incorrect or irrelevant. The overall concordance rate was 77%, with non-concordance attributed to outdated information, omission, or alternative therapy.<br /><br />The study concluded that despite limitations in real-time knowledge and personalization, GPT-4 provided moderately accurate guidance for biomarker-driven treatment in NSCLC based on pre-September 2021 data. However, patients are advised to consult healthcare professionals for personalized and accurate medical recommendations.<br /><br />Keywords: Artificial intelligence, Biomarker, NCCN guidelines<br /><br />This abstract was presented at the WCLC 2023 conference in the Pathology and Biomarkers session.

Asset Subtitle

Hye Sung Kim

Meta Tag

Speaker Hye Sung Kim

Topic Pathology & Biomarkers: Artificial Intelligence in Pathology

Keywords

Generative Pretrained Transformer 4

GPT-4

artificial intelligence

NCCN guidelines

biomarker-driven treatment strategies

non-small cell lung cancer

NSCLC

treatment options

concordance rate

personalized medical recommendations