EUVIMEDEUVIMED entdecken
Crossref

AI for Oncology Drug Data Harmonization — Amazon versus OpenAI

Jay G Ronquillo iD, Brett R South iD, Timothy L Wiemken iD, Ajit Jadhav iD, Steve Watt iD, Magdia De Jesus iD, Aida Habtezion iD

NEJM AI · 24.10.2024 · 1 (11)

DOI: 10.1056/aics2400661 ↗

Kurz gefasst

Fachartikel in der Zeitschrift NEJM AI, erschienen am 24.10.2024. Verfasst von Jay G Ronquillo und 6 weiteren Autor:innen. Beteiligte Einrichtung: Worldwide Medical and Safety, Pfizer, Inc., New York. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 40 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

AbstractMedical-domain natural language processing (NLP) and general-domain large language models (LLMs) are powerful computational tools available to the drug development community. These tools have the potential ability to harmonize real-world oncology data, which could accelerate the standardization, integration, and analysis of scalable drug development informatics pipelines, albeit with differing associated costs. This potential use case was evaluated by extracting drugs indicated by the National Cancer Institute for single solid tumor sites from openFDA. Requests to map diagnosis codes to drug label indications were submitted to the Amazon Comprehend Medical NLP service and the OpenAI GPT-3.5 Turbo LLM using a general harmonization prompt (twice) and a cancer-optimized prompt (once). The LLM approach performed similarly to the NLP approach (74.4% vs. 67.9%, P=0.480) and to itself (74.4% vs. 74.4%, P=1.0) when harmonizing the 78 oncology drugs. The cancer-optimized LLM prompts showed greater harmonization accuracy than the NLP ones (89.7% vs. 67.9%, P=0.002), while LLM costs were approximately 3.7 times lower, showing that a general-domain LLM was capable of being more accurate, adaptable, and cost-effective than conventional medical-domain NLP. (Funded by Pfizer, Inc.).

Autor:innen und Institutionen

  • Worldwide Medical and Safety, Pfizer, Inc., New York.
  • Pfizer Research and Development, Pfizer, Inc., New York.
  • Real World Evidence Platform, Pfizer, Inc., New York.

ORCID-Profile: Jay G Ronquillo, Brett R South, Timothy L Wiemken, Ajit Jadhav, Steve Watt, Magdia De Jesus, Aida Habtezion

Zitieren

APA

Ronquillo, J. G., South, B. R., Wiemken, T. L., Jadhav, A., Watt, S., De Jesus, M., & Habtezion, A. (2024). AI for Oncology Drug Data Harmonization — Amazon versus OpenAI. NEJM AI, 1(11). https://doi.org/10.1056/aics2400661

Vancouver

Ronquillo JG, South BR, Wiemken TL, Jadhav A, Watt S, De Jesus M, et al. AI for Oncology Drug Data Harmonization — Amazon versus OpenAI. NEJM AI. 2024;1(11). doi:10.1056/aics2400661

BibTeX
@article{Ronquillo2024,
  author = {Ronquillo, Jay G and South, Brett R and Wiemken, Timothy L and Jadhav, Ajit and Watt, Steve and De Jesus, Magdia and Habtezion, Aida},
  title = {AI for Oncology Drug Data Harmonization — Amazon versus OpenAI},
  journal = {NEJM AI},
  year = {2024},
  volume = {1},
  number = {11},
  doi = {10.1056/aics2400661}
}
Kostenlos starten →