Knowledge-Infused LLM-Powered Conversational Health Agent: A Case Study for Diabetes Patients (2402.10153v2)
Abstract: Effective diabetes management is crucial for maintaining health in diabetic patients. LLMs have opened new avenues for diabetes management, facilitating their efficacy. However, current LLM-based approaches are limited by their dependence on general sources and lack of integration with domain-specific knowledge, leading to inaccurate responses. In this paper, we propose a knowledge-infused LLM-powered conversational health agent (CHA) for diabetic patients. We customize and leverage the open-source openCHA framework, enhancing our CHA with external knowledge and analytical capabilities. This integration involves two key components: 1) incorporating the American Diabetes Association dietary guidelines and the Nutritionix information and 2) deploying analytical tools that enable nutritional intake calculation and comparison with the guidelines. We compare the proposed CHA with GPT4. Our evaluation includes 100 diabetes-related questions on daily meal choices and assessing the potential risks associated with the suggested diet. Our findings show that the proposed agent demonstrates superior performance in generating responses to manage essential nutrients.
- J. U. Poulsen et al., “A diabetes management system empowering patients to reach optimised glucose control: from monitor to advisor,” in 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology, pp. 5270–5271, IEEE, 2010.
- L. Mertz, “Automated insulin delivery: taking the guesswork out of diabetes management,” IEEE pulse, vol. 9, no. 1, pp. 8–9, 2018.
- H. A. Klein et al., “Self management of medication and diabetes: Cognitive control,” IEEE Transactions on Systems, Man, and Cybernetics-Part A: Systems and Humans, vol. 34, no. 6, pp. 718–725, 2004.
- G. Fico et al., “Integration of personalized healthcare pathways in an ict platform for diabetes managements: a small-scale exploratory study,” IEEE Journal of Biomedical and Health Informatics, vol. 20, no. 1, pp. 29–38, 2014.
- I. Shalahuddin et al., “Blood sugar levels regulation in diabetes mellitus type 2 patients through diet management,” Jurnal Aisyah : Jurnal Ilmu Kesehatan, 2022.
- W. Russell et al., “Nutritional management of blood glucose levels,” Annals of Nutrition and Metabolism, vol. 63, pp. 1339–1340, 2013.
- G. G. R. Sng et al., “Potential and pitfalls of chatgpt and natural-language artificial intelligence models for diabetes education,” Diabetes Care, vol. 46, no. 5, pp. e103–e105, 2023.
- H. Yang et al., “Exploring the potential of large language models in personalized diabetes treatment strategies,” medRxiv, pp. 2023–06, 2023.
- H. Sun et al., “An ai dietitian for type 2 diabetes mellitus management based on large language and image recognition models: Preclinical concept validation study,” Journal of Medical Internet Research, vol. 25, p. e51300, 2023.
- X. Liu et al., “P-tuning: Prompt tuning can be comparable to fine-tuning across scales and tasks,” in Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pp. 61–68, 2022.
- E. J. Hu et al., “Lora: Low-rank adaptation of large language models,” arXiv preprint arXiv:2106.09685, 2021.
- M. Abbasian et al., “Conversational health agents: A personalized llm-powered agent framework,” arXiv preprint arXiv:2310.02374, 2023.
- Y. Li et al., “Personal llm agents: Insights and survey about the capability, efficiency and security,” arXiv preprint arXiv:2401.05459, 2024.
- U. Neisser, “Perceiving, anticipating, and imagining,” in Perception and Cognition: Issues in the Foundations of Psychology, University of Minnesota Press, Minneapolis, 1978.
- OpenAI, “Chatgpt: Openai’s conversational ai model.” https://openai.com/chatgpt, Accessed: January 2024.
- S. Yao et al., “Tree of thoughts: Deliberate problem solving with large language models,” arXiv preprint arXiv:2305.10601, 2023.
- Syndigo Company, “Nutritionx: The world’s largest verified nutrition database.” https://www.nutritionix.com/.
- “5. Lifestyle Management: Standards of Medical Care in Diabetes-2019,” Diabetes care, vol. 42, pp. S46–S60, 1 2019.
- A. Gray and R. J. Threlkeld, “Nutritional Recommendations for Individuals with Diabetes,” Diabetologia, vol. 54, 10 2019.
- B. E. Millen et al., “2013 American Heart Association/American College of Cardiology Guideline on Lifestyle Management to Reduce Cardiovascular Risk: practice opportunities for registered dietitian nutritionists,” Journal of the Academy of Nutrition and Dietetics, vol. 114, pp. 1723–1729, 11 2014.
- J. K. Snell-Bergeon et al., “Adults with type 1 diabetes eat a high fat, atherogenic diet which is associated with coronary artery calcium,” Diabetologia, vol. 52, p. 801, 5 2009.
- L. Van Horn et al., “The evidence for dietary prevention and treatment of cardiovascular disease,” Journal of the American Dietetic Association, vol. 108, pp. 287–331, 2 2008.
- R. K. Johnson et al., “American heart association nutrition committee of the council on nutrition, physical activity, and metabolism and the council on epidemiology and prevention. dietary sugars intake and cardiovascular health: a scientific statement from the american heart association,” 2009.
- Mahyar Abbasian (9 papers)
- Zhongqi Yang (10 papers)
- Elahe Khatibi (7 papers)
- Pengfei Zhang (261 papers)
- Nitish Nagesh (4 papers)
- Iman Azimi (20 papers)
- Ramesh Jain (33 papers)
- Amir M. Rahmani (48 papers)