Bridging Gaps in Cancer Care: Utilizing Large Language Models for Accessible Dietary Recommendations

Abstract

Background/Objectives: Weight management is directly linked to cancer recurrence and survival, but unfortunately, nutritional oncology counseling is not typically covered by insurance, creating a disparity for patients without nutritional education and food access. Novel ways of imparting personalized nutrition advice are needed to address this issue. Large language models (LLMs) offer a promising path toward tailoring dietary advice to individual patients. This study aimed to assess the capacity of LLMs to offer personalized dietary advice to patients with breast cancer. Methods: Thirty-one prompt templates were designed to evaluate dietary recommendations generated by ChatGPT and Gemini with variations within eight categorical variables: cancer stage, comorbidity, location, culture, age, dietary guideline, budget, and store. Seven prompts were selected for four board-certified oncology dietitians to also respond to. Responses were evaluated based on nutritional content and qualitative observations. A quantitative comparison of the calories and macronutrients of the LLM- and dietitian-generated meal plans via the Acceptable Macronutrient Distribution Ranges and United States Department of Agriculture's estimated calorie needs was performed. Conclusions: The LLMs generated personalized grocery lists and meal plans adapting to location, culture, and budget but not age, disease stage, comorbidities, or dietary guidelines. Gemini provided more comprehensive responses, including visuals and specific prices. While the dietitian-generated diets offered more adherent total daily calorie contents to the United States Department of Agriculture's estimated calorie needs, ChatGPT and Gemini offered more adherent macronutrient ratios to the Acceptable Macronutrient Distribution Range. Overall, the meal plans were not significantly different between the LLMs and dietitians. LLMs can provide personalized dietary advice to cancer patients who may lack access to this care. Grocery lists and meal plans generated by LLMs are applicable to patients with variable food access, socioeconomic means, and cultural preferences and can be a tool to increase health equity.

Keywords: artificial intelligence; breast cancer; cancer; diet; weight management.

Figure 1

A schematic of LLM prompts designed to evaluate the dietary recommendations generated by ChatGPT and Gemini. A total of 31 zero-shot prompt templates with prompt variations within 8 categorical variables, including cancer stage, comorbidity, location, culture, age, dietary guideline, budget, and store, are shown. One variable was changed in each prompt. Seven of these prompts were selected (highlighted in gray) and four dietitians also responded to them.

Figure 2

Qualitative observations of ChatGPT’s and Gemini’s responses. (A) Gemini provided photos with linked recipes for some meal plans. Panel (A) is an example of a Gemini-generated image comparable to the one provided, for copyright purposes. ChatGPT did not provide any photos or recipe links. (B) A map from Gemini showing all nearby grocery stores to the zip code specified and another map giving directions to the nearest grocery store. (C) A comparison of breakfast suggestions for Latin American cuisine between the two LLMs. (D) The response of both LLMs to the request for a budget of USD 10 for a day. ChatGPT used language such as “tight budget”, suggesting “food assistance programs”, while Gemini simply stated that it is possible to achieve a healthy diet.