MedTalk: A Multimodal AI Healthcare Assistant for Intelligent Medicine Information Retrieval
Keywords:
Digital healthcare, Identifying medicines, MedTalk, NLP-based symptom, OCR-based medicine identificationAbstract
The increasing demand for digital healthcare solutions has highlighted the need for intelligent systems capable of providing accurate, real-time drug information. MedTalk is a modular and scalable healthcare AI assistant designed to fetch and deliver structured medical information in response to user queries. Users can input the name of a drug and receive standardized outputs, including name, dosage, description, consumption time, side effects, and warnings. The system integrates with the RapidAPI Medicine API to retrieve reliable drug data and employs FastAPI for a high-performance, asynchronous backend. Its architecture is designed for extensibility, allowing future integration of speech-to-text, image-based medicine identification, LLM-powered knowledge summarization, and multilingual support. MedTalk bridges the gap between complex medical databases and end-users, providing accurate, accessible, and standardized drug information in real-time, thereby enhancing clinical decision-making and patient awareness.
References
A. Baker, Y. Perov, K. Middleton, “A comparison of artificial intelligence and human doctors for the purpose of triage and diagnosis,” Frontiers in Artificial Intelligence, vol. 3, Nov. 2020, doi: https://doi.org/10.3389/frai.2020.543405
J. E. Christopherjames et al., “Natural language processing based human assistive health conversational agent for multi-users,” 2021 Second International Conference on Electronics and Sustainable Communication Systems (ICESC), Coimbatore, India, 2021, pp. 1414–1420, doi: https://doi.org/10.1109/ICESC51422.2021.9532913
Y. Su, C. Zhu, S. Zheng “PathAsst: A generative foundation AI assistant towards artificial general intelligence of pathology,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, no. 5, pp. 5034–5042, Mar. 2024, doi: https://doi.org/10.1609/aaai.v38i5.28308
C. C. Hemasri, M. Vijayalakshmi and V. Jyotheesh, “Redefining medicine: The power of generative AI in modern healthcare,” 2024 5th International Conference on Smart Electronics and Communication (ICOSEC), Trichy, India, 2024, pp. 1293–1298, doi: https://doi.org/10.1109/ICOSEC61587.2024.10722592
C. Xu, S. A. Solomon, and W. Gao, “Artificial intelligence-powered electronic skin,” Nature Machine Intelligence, vol. 5, pp. 1344–1355, Dec. 2023, doi: https://doi.org/10.1038/s42256-023-00760-z
S. Försch, F. Klauschen, P. Hufnagl, and W. Roth, “Artificial intelligence in pathology,” Deutsches Ärzteblatt International, vol. 118, pp. 199–204, 2021, doi: https://doi.org/10.3238/arztebl.m2021.0011
D. Dao, J. Y. C. Teo, W. Wang, and H. D. Nguyen, “LLM-powered multimodal AI conversations for diabetes prevention,” in Proceedings of the 1st ACM Workshop on AI-Powered Q&A Systems for Multimedia, New York, NY, USA, Jun. 2024, pp. 1–6. doi: https://doi.org/10.1145/3643479.3662049
B. S. Garimella, H. S. Garlapati, S. Choul, R. Cherukuri and P. Lanke, “Advancing healthcare accessibility: Development of an AI-driven multimodal chatbot,” 2024 4th International Conference on Intelligent Technologies (CONIT), Bangalore, India, 2024, pp. 1–10, doi: https://doi.org/10.1109/CONIT61985.2024.10626795
A. Bhatt, N. Vaghela, “Med-bot: An AI-powered assistant to provide accurate and reliable medical information,” arXiv preprint, 2024, doi: https://doi.org/10.48550/arXiv.2411.09648
J. Chen, Q. Zhang, “DeepSeek reshaping healthcare in China’s tertiary hospitals,” arXiv preprint, 2025, doi: https://doi.org/10.48550/arXiv.2502.16732
D. B. Olawade, “Enhancing ophthalmic diagnosis and treatment with artificial intelligence,” Medicina, vol. 61, no. 3, Feb. 2025, doi: https://doi.org/10.3390/medicina61030433
B. Tabarsi, A. Basarkar, X. Liu, D. (DK) Xu, and T. Barnes, “MerryQuery: A trustworthy LLM-powered tool providing personalized support for educators and students,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, no. 28, pp. 29700–29702, Apr. 2025, doi: https://doi.org/10.1609/aaai.v39i28.35372
X. Liu, J. Xu, T. Sun, “PsyCounAssist: A full-cycle AI-powered psychological counseling assistant system,” arXiv preprint, 2025, doi: https://doi.org/10.48550/arXiv.2504.16573
G. Huang, X. Chen, and C. Liao, “AI-driven wearable bioelectronics in digital healthcare,” Biosensors, vol. 15, no. 7, Jun. 2025, doi: https://doi.org/10.3390/bios15070410
X. Shen, Z. Wang, J. Kuen, “OIDA-QA: A multimodal benchmark for analyzing the opioid industry documents archive,” arXiv preprint, 2025, doi: https://doi.org/10.48550/arXiv.2511.09914
H. Wang, J. Mao, L. Wang, “Reinforced correlation between vision and language for precise medical AI assistant,” arXiv preprint, 2025, doi: https://doi.org/10.48550/arXiv.2505.03380
