# Dual-stage and Lightweight Patient Chart Summarization for Emergency Physicians

arXiv: https://arxiv.org/abs/2510.06263 · HTML: https://mlsanity.com/paper/2510.06263/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 36 references that are in the map.
- First posted on arXiv 5 Oct 2025.

## Builds on (most cited first, 20 of 20)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models](https://mlsanity.com/paper/2305.04091/) (2023)
- [Small Language Models are the Future of Agentic AI](https://mlsanity.com/paper/2506.02153/) (2025)
- [Adapted Large Language Models Can Outperform Medical Experts in Clinical Text Summarization](https://mlsanity.com/paper/2309.07430/) (2023)
- [Mobile Edge Intelligence for Large Language Models: A Contemporary Survey](https://mlsanity.com/paper/2407.18921/) (2024)
- [A Review on Edge Large Language Models: Design, Execution, and Applications](https://mlsanity.com/paper/2410.11845/) (2024)
- [Tiny Titans: Can Smaller Large Language Models Punch Above Their Weight in the Real World for Meeting Summarization?](https://mlsanity.com/paper/2402.00841/) (2024)
- [The Rise of Small Language Models in Healthcare: A Comprehensive Survey](https://mlsanity.com/paper/2504.17119/) (2025)
- [Evaluating Small Language Models for News Summarization: Implications and Factors Influencing Performance](https://mlsanity.com/paper/2502.00641/) (2025)
- [MedAide: Leveraging Large Language Models for On-Premise Medical Assistance on Edge Devices](https://mlsanity.com/paper/2403.00830/) (2024)
- [Benchmarking Deep Learning Models on NVIDIA Jetson Nano for Real-Time Systems: An Empirical Investigation](https://mlsanity.com/paper/2406.17749/) (2024)
- [Development and Validation of the Provider Documentation Summarization Quality Instrument for Large Language Models](https://mlsanity.com/paper/2501.08977/) (2025)
- [Retrieving Evidence from EHRs with LLMs: Possibilities and Challenges](https://mlsanity.com/paper/2309.04550/) (2023)
- [Pushing up to the Limit of Memory Bandwidth and Capacity Utilization for Efficient LLM Decoding on Embedded FPGA](https://mlsanity.com/paper/2502.10659/) (2025)
- [Scaling Up Summarization: Leveraging Large Language Models for Long Text Extractive Summarization](https://mlsanity.com/paper/2408.15801/) (2024)
- [Neural Summarization of Electronic Health Records](https://mlsanity.com/paper/2305.15222/) (2023)
- [Enhanced Electronic Health Records Text Summarization Using Large Language Models](https://mlsanity.com/paper/2410.09628/) (2024)
- [Medicine on the Edge: Comparative Performance Analysis of On-Device LLMs for Clinical Reasoning](https://mlsanity.com/paper/2502.08954/) (2025)

## Abstract (arXiv)

Electronic health records (EHRs) contain extensive unstructured clinical data that can overwhelm emergency physicians trying to identify critical information. We present a two-stage summarization system that runs entirely on embedded devices, enabling offline clinical summarization while preserving patient privacy. In our approach, a dual-device architecture first retrieves relevant patient record sections using the Jetson Nano-R (Retrieve), then generates a structured summary on another Jetson Nano-S (Summarize), communicating via a lightweight socket link. The summarization output is two-fold: (1) a fixed-format list of critical findings, and (2) a context-specific narrative focused on the clinician's query. The retrieval stage uses locally stored EHRs, splits long notes into semantically coherent sections, and searches for the most relevant sections per query. The generation stage uses a locally hosted small language model (SLM) to produce the summary from the retrieved text, operating within the constraints of two NVIDIA Jetson devices. We first benchmarked six open-source SLMs under 7B parameters to identify viable models. We incorporated an LLM-as-Judge evaluation mechanism to assess summary quality in terms of factual accuracy, completeness, and clarity. Preliminary results on MIMIC-IV and de-identified real EHRs demonstrate that our fully offline system can effectively produce useful summaries in under 30 seconds.