MedAide: Leveraging Large Language Models for On-Premise Medical Assistance on Edge Devices (2403.00830v1)
Abstract: LLMs are revolutionizing various domains with their remarkable NLP abilities. However, deploying LLMs in resource-constrained edge computing and embedded systems presents significant challenges. Another challenge lies in delivering medical assistance in remote areas with limited healthcare facilities and infrastructure. To address this, we introduce MedAide, an on-premise healthcare chatbot. It leverages tiny-LLMs integrated with LangChain, providing efficient edge-based preliminary medical diagnostics and support. MedAide employs model optimizations for minimal memory footprint and latency on embedded edge devices without server infrastructure. The training process is optimized using low-rank adaptation (LoRA). Additionally, the model is trained on diverse medical datasets, employing reinforcement learning from human feedback (RLHF) to enhance its domain-specific capabilities. The system is implemented on various consumer GPUs and Nvidia Jetson development board. MedAide achieves 77\% accuracy in medical consultations and scores 56 in USMLE benchmark, enabling an energy-efficient healthcare assistance platform that alleviates privacy concerns due to edge-based deployment, thereby empowering the community.
- Wayne Xin Zhao et al. A survey of large language models. 3 2023.
- Tom B. Brown et al. Language models are few-shot learners. Advances in Neural Information Processing Systems, 2020-December, 5 2020.
- Sébastien Bubeck et al. Sparks of artificial general intelligence: Early experiments with gpt-4. 3 2023.
- Tirth et al. Dave. Chatgpt in medicine: an overview of its applications, advantages, limitations, future prospects, and ethical considerations. Frontiers in Artificial Intelligence, 6, 2023.
- Katharina Jeblick et al. Chatgpt makes medicine easy to swallow: An exploratory case study on simplified radiology reports. 2022.
- Reconsidering the role of language in medicine. Philosophy, Ethics, and Humanities in Medicine, 13:1–7, 6 2018.
- Mamiko Yoshizu. World bank and who: Half the world lacks access to essential health services, 100 million still pushed into extreme poverty because of health expenses, Nov 2017.
- Margaret E. Kruk et al. Mortality due to low-quality health systems in the universal health coverage era: a systematic analysis of amenable deaths in 137 countries. Lancet (London, England), 392:2203 – 2212, 2018.
- Shukang Yin et al. A survey on multimodal large language models. 2023.
- Daniel Park. Open-llm-leaderboard-report, 2023.
- Stephanie Lin et al. Truthfulqa: Measuring how models mimic human falsehoods, 2022.
- Dan Hendrycks et al. Measuring massive multitask language understanding, 2021.
- Peter Clark et al. Think you have solved question answering? try arc, the ai2 reasoning challenge, 2018.
- Rowan Zellers et al. Hellaswag: Can a machine really finish your sentence?, 2019.
- Hugo Touvron et al. Llama 2: Open foundation and fine-tuned chat models, 2023.
- Margaret Mitchell et al. Bigscience language open-science open-access multilingual (bloom) language model. May 2022.
- Susan Zhang et al. Opt: Open pre-trained transformer language models. 5 2022.
- Harrison Chase. Langchain retrieved from ”https://github.com/langchain-ai/langchain”.
- Jeff et al. Johnson. Billion-scale similarity search with GPUs. IEEE Transactions on Big Data, 7(3):535–547, 2019.
- Ashish Vaswani et al. Attention is all you need. Advances in Neural Information Processing Systems, 2017-December:5999–6009, 6 2017.
- Thomas Wolf et al. Transformers: State-of-the-art natural language processing. In Conference on Empirical Methods in Natural Language Processing, 2019.
- Matthew E. Peters et al. Deep contextualized word representations. ArXiv, abs/1802.05365, 2018.
- Chatdoctor: A medical chat model fine-tuned on a large language model meta-ai (llama) using medical domain knowledge. Cureus, 15(6), 2023.
- Hugo Touvron et al. Llama: Open and efficient foundation language models. 2 2023.
- Renqian Luo et al. Biogpt: generative pre-trained transformer for biomedical text generation and mining. Briefings in Bioinformatics, 23, 11 2022.
- Yanis Labrak et al. Drbert: A robust pre-trained model in french for biomedical and clinical domains, 2023.
- Jacob Devlin et al. Bert: Pre-training of deep bidirectional transformers for language understanding. 1:4171–4186, 10 2018.
- Hongbo Zhang et al. Huatuogpt, towards taming language models to be a doctor. arXiv preprint arXiv:2305.15075, 2023.
- Artificial hallucinations in chatgpt: Implications in scientific writing. Cureus, 15, 02 2023.
- Honglin Xiong et al. Doctorglm: Fine-tuning your chinese doctor is not a herculean task, 2023.
- Zhengxiao et al. Du. Glm: General language model pretraining with autoregressive blank infilling. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, pages 320–335, 2022.
- Tianyu Han et al. Medalpaca – an open-source collection of medical conversational ai models and training data. 4 2023.
- Edward J Hu et al. LoRA: Low-rank adaptation of large language models. In International Conference on Learning Representations, 2022.
Sponsor
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.