In a recent study published in the journal Nutrientsresearchers evaluated the ability of pre-trained chat generation transformer (ChatGPT) to provide nutritional guidance.
Noncommunicable diseases (NCDs) are the leading cause of mortality, accounting for 74% of deaths worldwide. The 2019 Global Burden of Disease Study estimated that there were 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. The prevalence of obesity has nearly tripled between 1975 and 2016.
Various studies have consistently highlighted the influence of lifestyle and dietary factors on the onset and progression of MNC. In recent times, Internet searches for information on health-related questions have increased. ChatGPT is a widely used chatbot that generates responses to text queries. Can understand context and provide coherent responses.
ChatGPT has emerged as an accessible and effective resource for those seeking medical advice. Chatbots can provide real-time, interactive, personalized patient education and support, helping to improve patient outcomes. However, data on the utility of ChatGPT to improve nutrition in NCD patients were limited.
Study: Is ChatGPT an effective tool for nutritional counseling?
The study and findings
In the present study, researchers compared nutritional advice provided by ChatGPT with recommendations from international guidelines in the context of NCDs. Analyzes were performed using the default ChatGPT model (version 3.5). The group included medical conditions requiring specific nutritional treatments, such as arterial hypertension, T2D, dyslipidemia, obesity, NAFLD, sarcopenia, and chronic kidney disease (CKD).
A set of prompts for these conditions, formulated by doctors and dietitians, was used to get nutritional advice from the chatbot. Separate chat sessions were conducted for each instant chat. ChatGPT responses were compared with recommendations from international clinical guidelines. Two dietitians independently assessed and categorized the ChatGPT responses. Responses were considered “appropriate” if they aligned with the instructions and “inappropriate” if they were inconsistent.
In addition, responses were classified as “not supported” if they were not confirmed in the guidelines, “not fully matched” if they did not fully meet the guidelines, and “general advice” if they were nonspecific and promoted a healthy diet overall. In addition, the team also evaluated whether ChatGPT could replace consultation with a dietician in the management of complex cases and presented a scenario involving (a patient with) multiple co-existing conditions (CKD, obesity and T2DM).
Foundings
Overall, the advice provided by ChatGPT was accurate. Eligibility rates ranged between 55.5% for sarcopenia and 73.3% for NAFLD. Every answer about NAFLD and obesity contradicts the guidelines. Regarding obesity, the chatbot suggested regular meals and snacks to stabilize blood sugar levels, while the guidelines emphasize avoiding snacking between meals.
Regarding NAFLD, he reported benefits from supplements such as omega-3 fatty acids, antioxidants, and vitamin E under medical supervision. However, existing guidelines do not support antioxidants and omega-3 fatty acids for the treatment of NAFLD. One recommendation related to T2D is not supported by the guidelines.
Specifically, ChatGPT suggested breaking meals into smaller, well-balanced portions as an alternative to three large meals. Although this was not directly against the guidelines, existing T2D guidelines do not address it. In addition, many responses were categorized as not fully aligned with the guidelines.
For example, ChatGPT emphasized incorporating low-glycemic foods and monitoring portion sizes for hypertriglyceridemia, while the guidelines recommend addressing excess body weight and reducing carbohydrates. In addition, ChatGPT offered general health advice for various conditions. Examples include staying hydrated, avoiding processed foods, and incorporating lean protein. The chatbot also repeatedly emphasized overall wellness and appetite management.
The general advice included foods to include in the diet, which are often not mentioned in the guidelines. Regarding the scenario of a patient with obesity, CKD and T2DM, some suggestions of ChatGPT were inappropriate or conflicting. For example, he emphasized the priority of lean protein for muscle health and then suggested limiting total protein intake. His responses were generally general, repeatedly emphasizing consultation with a dietitian.
conclusions
The findings highlight several points of agreement and divergence in ChatGPT responses to dietary guidelines. The answers were clear and included practical examples of foods to include or exclude from the diet. Some suggestions from ChatGPT were partially completed. The chatbot failed to provide appropriate guidance in the case of multiple coexisting conditions. While ChatGPT was quite accurate in terms of nutritional advice for NCDs, limitations were evident for more complex scenarios. So while ChatGPT may have potential utility, it cannot replace expert advice.
