Timely and accurate pre-arrival video streaming and analytics are critical for emergency medical services (EMS) to deliver life-saving interventions. Yet, current-generation EMS infrastructure remains constrained by one-to-one video streaming and limited analytics capabilities, leaving dispatchers and EMTs to manually interpret overwhelming, often noisy or redundant information in high-stress environments. We present TeleEMS, a mobile live video analytics system that enables pre-arrival multimodal inference by fusing audio and video into a unified decision-making pipeline before EMTs arrive on scene. TeleEMS comprises two key components: TeleEMS Client and TeleEMS Server. The TeleEMS Client runs across phones, smart glasses, and desktops to support bystanders, EMTs en route, and 911 dispatchers. The TeleEMS Server, deployed at the edge, integrates EMS-Stream, a communication backbone that enables smooth multi-party video streaming. On top of EMSStream, the server hosts three real-time analytics modules: (1) audio-to-symptom analytics via EMSLlama, a domain-specialized LLM for robust symptom extraction and normalization; (2) video-to-vital analytics using state-of-the-art rPPG methods for heart rate estimation; and (3) joint text-vital analytics via PreNet, a multimodal multitask model predicting EMS protocols, medication types, medication quantities, and procedures. Evaluation shows that EMSLlama outperforms GPT-4o (exact-match 0.89 vs. 0.57) and that text-vital fusion improves inference robustness, enabling reliable pre-arrival intervention recommendations. TeleEMS demonstrates the potential of mobile live video analytics to transform EMS operations, bridging the gap between bystanders, dispatchers, and EMTs, and paving the way for next-generation intelligent EMS infrastructure.

Large language models (LLMs) excel at clinical information extraction but their computational demands limit practical deployment. Knowledge distillation--the process of transferring knowledge from larger to smaller models--offers a potential solution. We evaluate the performance of distilled BERT models, which are approximately 1,000 times smaller than modern LLMs, for clinical named entity recognition (NER) tasks. We leveraged state-of-the-art LLMs (Gemini and OpenAI models) and medical ontologies (RxNorm and SNOMED) as teacher labelers for medication, disease, and symptom extraction. We applied our approach to over 3,300 clinical notes spanning five publicly available datasets, comparing distilled BERT models against both their teacher labelers and BERT models fine-tuned on human labels. External validation was conducted using clinical notes from the MedAlign dataset. For disease extraction, F1 scores were 0.82 (teacher model), 0.89 (BioBERT trained on human labels), and 0.84 (BioBERT-distilled). For medication, F1 scores were 0.84 (teacher model), 0.91 (BioBERT-human), and 0.87 (BioBERT-distilled). For symptoms: F1 score of 0.73 (teacher model) and 0.68 (BioBERT-distilled). Distilled BERT models had faster inference (12x, 4x, 8x faster than GPT-4o, o1-mini, and Gemini Flash respectively) and lower costs (85x, 101x, 2x cheaper than GPT-4o, o1-mini, and Gemini Flash respectively). On the external validation dataset, the distilled BERT model achieved F1 scores of 0.883 (medication), 0.726 (disease), and 0.699 (symptom). Distilled BERT models were up to 101x cheaper and 12x faster than state-of-the-art LLMs while achieving similar performance on NER tasks. Distillation offers a computationally efficient and scalable alternative to large LLMs for clinical information extraction.

Large Language Models (LLMs) offer significant potential for clinical symptom extraction, but their deployment in healthcare settings is constrained by privacy concerns, computational limitations, and operational costs. This study investigates the optimization of compact LLMs for cancer toxicity symptom extraction using a novel iterative refinement approach. We employ a student-teacher architecture, utilizing Zephyr-7b-beta and Phi3-mini-128 as student models and GPT-4o as the teacher, to dynamically select between prompt refinement, Retrieval-Augmented Generation (RAG), and fine-tuning strategies. Our experiments on 294 clinical notes covering 12 post-radiotherapy toxicity symptoms demonstrate the effectiveness of this approach. The RAG method proved most efficient, improving average accuracy scores from 0.32 to 0.73 for Zephyr-7b-beta and from 0.40 to 0.87 for Phi3-mini-128 during refinement. In the test set, both models showed an approximate 0.20 increase in accuracy across symptoms. Notably, this improvement was achieved at a cost 45 times lower than GPT-4o for Zephyr and 79 times lower for Phi-3.