In a recent study published within the journal Nutrients, researchers evaluated the potential of chat generative pretrained transformer (ChatGPT) to supply dietary guidance.

Non-communicable diseases (NCDs) are the foremost reason behind mortality, accounting for 74% of deaths globally. The 2019 global burden of diseases study estimated there have been 43.8 million cases of type 2 diabetes (T2D), 1.2 billion cases of non-alcoholic fatty liver disease (NAFLD), and 18.5 million cases of hypertension. Obesity prevalence has almost tripled between 1975 and 2016.

Various studies have consistently underscored the impact of lifestyle and dietary aspects on NCD onset and progression. Of late, web searches for information on health-related queries have been increasing. ChatGPT is a widely used chatbot that generates responses to textual queries. It may well comprehend the context and supply coherent responses.

ChatGPT has emerged as an accessible and efficient resource for medical advice seekers. Chatbots can deliver real-time, interactive, personalized patient education and support, helping improve patient outcomes. Nevertheless, data on the utility of ChatGPT to enhance nutrition amongst NCD patients have been limited.

Study: Is ChatGPT an Effective Tool for Providing Dietary Advice?

The study and findings

In the current study, researchers compared the dietary advice provided by ChatGPT with recommendations from international guidelines within the context of NCDs. Analyses were performed using the default ChatGPT model (version 3.5). The team included medical conditions requiring specific dietary treatments, equivalent to arterial hypertension, T2D, dyslipidemia, obesity, NAFLD, sarcopenia, and chronic kidney disease (CKD).

A set of prompts for these conditions, formulated by doctors and dieticians, was used to acquire dietary advice from the chatbot. Separate chat sessions were conducted for every prompt conversation. ChatGPT’s responses were compared with recommendations from international clinical guidelines. Two dieticians independently assessed and categorized ChatGPT’s responses. Responses were deemed “appropriate” in the event that they aligned with the rules and “inappropriate” if contradictory.

Moreover, responses were classified as “unsupported” in the event that they weren’t confirmed in the rules, “not fully matched” in the event that they didn’t wholly fulfill guidelines, and “general advice” in the event that they were non-specific and promoted a healthy weight loss program overall. Besides, the team also assessed whether ChatGPT could substitute consultation with a dietician in managing complex cases and was presented with a scenario involving (a patient with) multiple coexisting conditions (CKD, obesity, and T2D).

Findings

Overall, the recommendation provided by ChatGPT was accurate. Appropriateness rates ranged between 55.5% for sarcopenia and 73.3% for NAFLD. One response each for NAFLD and obesity contradicted the rules. Regarding obesity, the chatbot suggested regular meals and snacks to stabilize blood sugar levels, whereas the rules emphasize avoiding snacks between meals.

Regarding NAFLD, it reported advantages from supplements like omega-3 fatty acids, antioxidants, and vitamin E under medical supervision. Nevertheless, existing guidelines don’t endorse antioxidants and omega-3 fatty acids for NAFLD treatment. One T2D-related suggestion was unsupported by the rules.

Specifically, ChatGPT suggested dividing meals into smaller, well-balanced portions as a substitute for three large meals. While this was in a roundabout way contradictory to the rules, existing T2D guidelines don’t address this. Further, quite a few responses were categorized as not fully matched with the rules.

For instance, ChatGPT emphasized incorporating foods with low glycemic index and monitoring portion sizes for hypertriglyceridemia, while guidelines recommend addressing excess body weight and reducing carbohydrates. As well as, ChatGPT offered generic health advice for several conditions. Examples include staying hydrated, avoiding processed foods, and incorporating lean proteins. The chatbot also repeatedly stressed overall well-being and appetite management.

The final advice comprised foods to be included within the weight loss program, which guidelines often don’t report. Regarding the scenario of a patient with obesity, CKD, and T2D, a number of suggestions by ChatGPT were inappropriate or conflicting. For example, it emphasized prioritizing lean proteins for muscle health and subsequently suggested limiting overall protein intake. Its responses were generally generic, repeatedly emphasizing consultation with a dietician.

Conclusions

The findings highlight several points of agreement and divergences in ChatGPT’s responses to dietary guidelines. Responses were clear and comprised practical examples of foods to be included or excluded from the weight loss program. Some recommendations by ChatGPT were partially complete. The chatbot failed to supply appropriate guidance within the case of multiple coexisting conditions. While ChatGPT was fairly accurate regarding dietary advice for NCDs, limitations were evident for more complex scenarios. Thus, while ChatGPT can have potential utility, it cannot replace the recommendation of experts.