Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
119 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Conversational Health Agents: A Personalized LLM-Powered Agent Framework (2310.02374v5)

Published 3 Oct 2023 in cs.CL

Abstract: Conversational Health Agents (CHAs) are interactive systems that provide healthcare services, such as assistance and diagnosis. Current CHAs, especially those utilizing LLMs, primarily focus on conversation aspects. However, they offer limited agent capabilities, specifically lacking multi-step problem-solving, personalized conversations, and multimodal data analysis. Our aim is to overcome these limitations. We propose openCHA, an open-source LLM-powered framework, to empower conversational agents to generate a personalized response for users' healthcare queries. This framework enables developers to integrate external sources including data sources, knowledge bases, and analysis models, into their LLM-based solutions. openCHA includes an orchestrator to plan and execute actions for gathering information from external sources, essential for formulating responses to user inquiries. It facilitates knowledge acquisition, problem-solving capabilities, multilingual and multimodal conversations, and fosters interaction with various AI platforms. We illustrate the framework's proficiency in handling complex healthcare tasks via two demonstrations and four use cases. Moreover, we release openCHA as open source available to the community via GitHub.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (71)
  1. Sallam M. ChatGPT utility in healthcare education, research, and practice: systematic review on the promising perspectives and valid concerns. In: Healthcare. vol. 11. MDPI; 2023. p. 887.
  2. OpenAI. ChatGPT: OpenAI’s Conversational AI Model; 2021. Accessed: 08, 2023. https://openai.com/chatgpt.
  3. MedAlpaca–An Open-Source Collection of Medical Conversational AI Models and Training Data. arXiv preprint arXiv:230408247. 2023.
  4. Towards Generalist Biomedical AI. arXiv preprint arXiv:230714334. 2023.
  5. FeelFit-Design and Evaluation of a Conversational Agent to Enhance Health Awareness. In: ICIS; 2019. .
  6. Survey of conversational agents in health. Expert Systems with Applications. 2019;129:56-67.
  7. Denecke K, May R. Investigating conversational agents in healthcare: Application of a technical-oriented taxonomy. Procedia Computer Science. 2023;219:1289-96.
  8. Conversational agents in health care: scoping review and conceptual analysis. Journal of medical Internet research. 2020;22(8):e17158.
  9. Conversational agents in healthcare: a systematic review. Journal of the American Medical Informatics Association. 2018;25(9):1248-58.
  10. The effectiveness of artificial intelligence conversational agents in health care: systematic review. Journal of medical Internet research. 2020;22(10):e20346.
  11. The role of empathy in health and social care professionals. In: Healthcare. vol. 8. MDPI; 2020. p. 26.
  12. Foundation Metrics: Quantifying Effectiveness of Healthcare Conversations powered by Generative AI. arXiv preprint arXiv:230912444. 2023.
  13. Multichannel Mobile Companions for Personalized Healthcare Opportunities and Challenges. Procedia Computer Science. 2023;220:838-43.
  14. Moore O. How Are Consumers Using Generative AI?; 2023. Accessed: 09, 2023. https://a16z.com/how-are-consumers-using-generative-ai/?fbclid=IwAR3F0G14yP69CijzGZnKF42v8n3nu1a7FgCiO51Ep187a8pZSz3WQtLQhOI.
  15. Plsek PE, Greenhalgh T. The challenge of complexity in health care. Bmj. 2001;323(7313):625-8.
  16. Sturmberg JP, Martin CM. Complexity and health–yesterday’s traditions, tomorrow’s future. J Eval Clin Pract. 2009;15(3):543-8.
  17. Topol EJ. As artificial intelligence goes multimodal, medical applications multiply. American Association for the Advancement of Science; 2023.
  18. BioGPT: generative pre-trained transformer for biomedical text generation and mining. Briefings in Bioinformatics. 2022;23(6):bbac409.
  19. ChatDoctor: A Medical Chat Model Fine-Tuned on a Large Language Model Meta-AI (LLaMA) Using Medical Domain Knowledge. Cureus. 2023;15(6).
  20. A survey of large language models. arXiv preprint arXiv:230318223. 2023.
  21. Randomized Controlled Trials Evaluating AI in Clinical Practice: A Scoping Evaluation. medRxiv. 2023:2023-09.
  22. Biswas S. ChatGPT and the future of medical writing. Radiological Society of North America; 2023.
  23. Aydın Ö, Karaarslan E. OpenAI ChatGPT generated literature review: Digital twin in healthcare. Available at SSRN 4308687. 2022.
  24. The utility of ChatGPT for cancer treatment information. medRxiv. 2023:2023-03.
  25. BioSignal Copilot: Leveraging the power of LLMs in drafting reports for biomedical signals. medRxiv. 2023:2023-06.
  26. BioBERT: a pre-trained biomedical language representation model for biomedical text mining. Bioinformatics. 2020;36(4):1234-40.
  27. Domain-specific language model pretraining for biomedical natural language processing. ACM Transactions on Computing for Healthcare (HEALTH). 2021;3(1):1-23.
  28. Thinking about gpt-3 in-context learning for biomedical ie? think again. arXiv preprint arXiv:220308410. 2022.
  29. Gpt-3 models are poor few-shot learners in the biomedical domain. arXiv preprint arXiv:210902555. 2021.
  30. ELIXR: Towards a general purpose X-ray artificial intelligence system through alignment of large language models and radiology vision encoders. arXiv preprint arXiv:230801317. 2023.
  31. Multimodal LLMs for health grounded in individual-specific data. arXiv preprint arXiv:230709018. 2023.
  32. Hallucinations in large multilingual translation models. arXiv preprint arXiv:230316104. 2023.
  33. Neisser U. Perceiving, anticipating, and imagining. In: Perception and Cognition: Issues in the Foundations of Psychology. University of Minnesota Press, Minneapolis; 1978. .
  34. Google. Google Speech to Text; 2023. Accessed: 10, 2023. https://cloud.google.com/speech-to-text.
  35. Google. Google Translate; 2023. Accessed: 10, 2023. https://py-googletrans.readthedocs.io/en/latest/.
  36. ECG-based heartbeat classification for arrhythmia detection: A survey. Computer methods and programs in biomedicine. 2016;127:144-64.
  37. React: Synergizing reasoning and acting in language models. arXiv preprint arXiv:221003629. 2022.
  38. Plan-and-solve prompting: Improving zero-shot chain-of-thought reasoning by large language models. arXiv preprint arXiv:230504091. 2023.
  39. MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning. arXiv preprint arXiv:220500445. 2022.
  40. LLM-Rec: Personalized Recommendation via Prompting Large Language Models. arXiv preprint arXiv:230715780. 2023.
  41. Optimizing prompts for text-to-image generation. arXiv preprint arXiv:221209611. 2022.
  42. ZotCare: a flexible, personalizable, and affordable mhealth service provider. Frontiers in Digital Health. 2023;5.
  43. Jusoh S. A Survey on Trend, Opportunities and Challenges of mHealth Apps. Int J Interact Mob Technol. 2017;11(6):73-85.
  44. mHealth technologies for chronic diseases and elders: a systematic review. IEEE Journal on Selected Areas in Communications. 2013;31(9):6-18.
  45. ZotCare: A Flexible, Personalizable, and Affordable mHealth Service Provider. Frontiers in Digital Health;5:1253087.
  46. ilumivu. ilumivu; 2023. https://ilumivu.com/ [Accessed at June 2, 2023].
  47. Hiemstra D. Information retrieval models. Information Retrieval: searching in the 21st Century. 2009:1-19.
  48. Turtle HR, Croft WB. A comparison of text retrieval models. The computer journal. 1992;35(3):279-90.
  49. Health information needs, sources, and barriers of primary care patients to achieve patient-centered care: A literature review. Health informatics journal. 2016;22(4):992-1016.
  50. Jain R. Folk computing. Communications of the ACM. 2003;46(4):27-9.
  51. Borovoy RD. Folk computing: Designing technology to support face-to-face community building [Ph.D. thesis]. Massachusetts Institute of Technology; 2002.
  52. Hathaliya JJ, Tanwar S. An exhaustive survey on security and privacy issues in Healthcare 4.0. Computer Communications. 2020;153:311-35.
  53. Price WN, Cohen IG. Privacy in the age of medical big data. Nature medicine. 2019;25(1):37-43.
  54. A survey of privacy preserving data publishing using generalization and suppression. Applied Mathematics & Information Sciences. 2014;8(3):1103.
  55. A survey of cryptographic approaches to securing big-data analytics in the cloud. In: 2014 IEEE High Performance Extreme Computing Conference (HPEC). IEEE; 2014. p. 1-6.
  56. Merkel D. Docker: lightweight linux containers for consistent development and deployment. Linux journal. 2014;2014(239):2.
  57. Docker. Docker Compose; 2023. Accessed: 10, 2023. https://docs.docker.com/engine/reference/commandline/compose/.
  58. Flask. Flask Framework; 2023. Accessed: 10, 2023. https://flask.palletsprojects.com/en/3.0.x/.
  59. Chase H. LangChain; 2022. Available from: https://github.com/hwchase17/langchain.
  60. Langchain. Search Tool; 2023. Accessed: 10, 2023. https://python.langchain.com/docs/integrations/tools/search_tools.
  61. Langchain. OpenAI LLM; 2023. Accessed: 10, 2023. https://python.langchain.com/docs/integrations/llms/openai.
  62. Physiological and Emotional Assessment of College Students Using Wearable and Mobile Devices During the 2020 Covid-19 Lockdown: An Intensive, Longitudinal Dataset. Longitudinal Dataset. 2023.
  63. Samsung. Samsung Gear Watch; 2023. Accessed: 10, 2023. https://www.samsung.com/us/mobile/wearables/smartwatches/gear-sport-blue-sm-r600nzbaxar/.
  64. An energy-efficient semi-supervised approach for on-device photoplethysmogram signal quality assessment. Smart Health. 2023;28:100390.
  65. Ppg signal reconstruction using deep convolutional generative adversarial network. In: 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). IEEE; 2022. p. 3387-91.
  66. Robust ppg peak detection using dilated convolutional neural networks. Sensors. 2022;22(16):6054.
  67. Shaffer F, Ginsberg JP. An overview of heart rate variability metrics and norms. Frontiers in public health. 2017:258.
  68. Impact of COVID-19 Pandemic on Sleep Including HRV and Physical Activity as Mediators: A Causal ML Approach. medRxiv. 2023:2023-06.
  69. Appelhans BM, Luecken LJ. Heart rate variability as an index of regulated emotional responding. Review of general psychology. 2006;10(3):229-40.
  70. Sztajzel J. Heart rate variability: a noninvasive electrocardiographic method to measure the autonomic nervous system. Swiss medical weekly. 2004;134(3536):514-22.
  71. Claude. Claude: A next-generation AI assistant for your tasks, no matter the scale; 2022. Accessed: 09, 2023. https://www.anthropic.com/product.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Mahyar Abbasian (9 papers)
  2. Iman Azimi (20 papers)
  3. Amir M. Rahmani (48 papers)
  4. Ramesh Jain (33 papers)
Citations (50)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now