Credit score: Pixabay/CC0 Public Area
Analysis reveals that good diet can contribute to the general well being and effectively‐being of most cancers sufferers. Nevertheless, personalised dietary recommendation may be arduous to entry and isn’t typically lined by medical insurance.
A analysis workforce from Thomas Jefferson College questioned if synthetic intelligence (AI) bots would possibly be capable of shut this hole in supportive care.
In a paper showing within the journal Vitamins , they examined two extensively obtainable massive language fashions (LLMs)—ChatGPT and Gemini—with a wide range of prompts to generate meal plans and grocery lists for particular affected person traits akin to most cancers stage and different well being situations, in addition to budgets, geographic location, and cultural preferences.
The purpose, says senior creator and radiation oncologist at Sidney Kimmel Complete Most cancers Middle, Nicole Simone, MD, was to guage the LLMs’ capability to handle these various wants, and examine the recommendation generated to that of scientific dietitians.
Medical pupil and first creator, Julia Logan, examined the prompts for all of the variables throughout her summer season analysis stint within the division.
Co‐creator and computational physicist Wookjin Choi, Ph.D. says it will be almost unimaginable to construct a specialised mannequin from scratch. “The general LLMs provide a starting place, and then we develop it, score it, adjust it and create a new specialized model,” says Dr. Choi, who’s a member of Sidney Kimmel Medical Faculty.
The researchers have been pleasantly shocked by the extent of granularity the instruments achieved. Dr. Simone provides. “It was able to figure out cost and nearby grocery stores with available ingredients.”
“The ability of LLMs to generate meal plans tailored to socioeconomic and cultural considerations is one of the most promising aspects of this approach,” the authors write. Meaning the device may be useful for folks with monetary constraints and promotes adherence by integrating ethnic meals selections.
This research demonstrated the feasibility of making an AI device to generate and assist dietary recommendation tailor-made to most cancers sufferers. There’s extra work to be performed, akin to figuring out the bounds of an AI device’s reliability and when oversight by skilled dietitians is required.
Extra data:
Julia A. Logan et al, Bridging Gaps in Most cancers Care: Using Massive Language Fashions for Accessible Dietary Suggestions, Vitamins (2025). DOI: 10.3390/nu17071176
Offered by
Thomas Jefferson College
Quotation:
Designing an AI device for automated, custom-made diet recommendation for most cancers sufferers (2025, June 18)
retrieved 18 June 2025
from https://medicalxpress.com/information/2025-06-ai-tool-automated-customized-nutrition.html
This doc is topic to copyright. Other than any honest dealing for the aim of personal research or analysis, no
half could also be reproduced with out the written permission. The content material is offered for data functions solely.
